From de03c11108b087d412943a6bfc304efd62426300 Mon Sep 17 00:00:00 2001 From: Ashutosh Chauhan Date: Wed, 9 Sep 2015 12:02:28 -0700 Subject: [PATCH] HIVE-11678 : Add AggregateProjectMergeRule --- .../rules/HiveAggregateProjectMergeRule.java | 151 ++ .../calcite/rules/HiveRelFieldTrimmer.java | 145 +- .../calcite/translator/PlanModifierForASTConv.java | 4 +- .../hadoop/hive/ql/parse/CalcitePlanner.java | 2 + .../clientpositive/alter_partition_coltype.q.out | 8 +- .../clientpositive/annotate_stats_groupby.q.out | 106 +- .../clientpositive/annotate_stats_groupby2.q.out | 28 +- .../test/results/clientpositive/auto_join18.q.out | 12 +- .../auto_join18_multi_distinct.q.out | 12 +- .../test/results/clientpositive/auto_join27.q.out | 18 +- .../test/results/clientpositive/auto_join32.q.out | 4 +- .../results/clientpositive/binarysortable_1.q.out | 6 +- .../clientpositive/correlationoptimizer2.q.out | 220 +- .../clientpositive/correlationoptimizer6.q.out | 232 +- ql/src/test/results/clientpositive/count.q.out | 14 +- .../test/results/clientpositive/ctas_colname.q.out | 52 +- ql/src/test/results/clientpositive/database.q.out | 2 +- .../results/clientpositive/decimal_precision.q.out | 4 +- .../test/results/clientpositive/decimal_udf.q.out | 30 +- .../results/clientpositive/distinct_stats.q.out | 14 +- .../dynpart_sort_opt_vectorization.q.out | 105 +- .../clientpositive/dynpart_sort_optimization.q.out | 105 +- ...encryption_select_read_only_encrypted_tbl.q.out | 4 +- .../results/clientpositive/explain_logical.q.out | 78 +- .../results/clientpositive/fetch_aggregation.q.out | 4 +- ql/src/test/results/clientpositive/gby_star.q.out | 54 +- ql/src/test/results/clientpositive/groupby12.q.out | 6 +- .../test/results/clientpositive/groupby5_map.q.out | 4 +- .../results/clientpositive/groupby5_map_skew.q.out | 4 +- .../results/clientpositive/groupby_cube1.q.out | 12 +- .../clientpositive/groupby_distinct_samekey.q.out | 6 +- .../clientpositive/groupby_grouping_sets2.q.out | 10 +- .../clientpositive/groupby_grouping_sets3.q.out | 12 +- .../clientpositive/groupby_grouping_sets5.q.out | 8 +- .../clientpositive/groupby_grouping_sets6.q.out | 8 +- .../results/clientpositive/groupby_position.q.out | 36 +- .../clientpositive/groupby_resolution.q.out | 60 +- .../results/clientpositive/groupby_rollup1.q.out | 12 +- .../results/clientpositive/groupby_sort_10.q.out | 8 +- .../results/clientpositive/groupby_sort_11.q.out | 10 +- .../results/clientpositive/groupby_sort_8.q.out | 12 +- ql/src/test/results/clientpositive/having.q.out | 62 +- ql/src/test/results/clientpositive/having2.q.out | 12 +- .../clientpositive/index_auto_mult_tables.q.out | 12 +- .../clientpositive/index_auto_self_join.q.out | 12 +- .../results/clientpositive/index_auto_update.q.out | 6 +- .../index_bitmap_auto_partitioned.q.out | 6 +- .../clientpositive/index_bitmap_compression.q.out | 6 +- .../infer_bucket_sort_dyn_part.q.out | 4 +- .../infer_bucket_sort_map_operators.q.out | 4 +- ql/src/test/results/clientpositive/join18.q.out | 12 +- .../clientpositive/join18_multi_distinct.q.out | 12 +- ql/src/test/results/clientpositive/join31.q.out | 36 +- .../limit_partition_metadataonly.q.out | 4 +- .../results/clientpositive/limit_pushdown.q.out | 36 +- ql/src/test/results/clientpositive/lineage2.q.out | 2 +- ql/src/test/results/clientpositive/lineage3.q.out | 4 +- .../list_bucket_query_multiskew_3.q.out | 2 +- .../results/clientpositive/mapjoin_mapjoin.q.out | 32 +- .../clientpositive/metadata_only_queries.q.out | 4 +- .../results/clientpositive/metadataonly1.q.out | 112 +- .../results/clientpositive/multiMapJoin2.q.out | 226 +- .../clientpositive/nonblock_op_deduplicate.q.out | 8 +- .../test/results/clientpositive/nonmr_fetch.q.out | 14 +- .../clientpositive/partition_multilevels.q.out | 8 +- ql/src/test/results/clientpositive/ppd_gby.q.out | 12 +- ql/src/test/results/clientpositive/ppd_gby2.q.out | 60 +- .../results/clientpositive/ppd_join_filter.q.out | 98 +- .../clientpositive/ql_rewrite_gbtoidx_cbo_1.q.out | 168 +- .../clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out | 94 +- .../reduce_deduplicate_extended.q.out | 32 +- .../clientpositive/selectDistinctStar.q.out | 44 +- .../results/clientpositive/spark/auto_join18.q.out | 10 +- .../spark/auto_join18_multi_distinct.q.out | 12 +- .../results/clientpositive/spark/auto_join27.q.out | 18 +- .../results/clientpositive/spark/auto_join32.q.out | 53 +- .../test/results/clientpositive/spark/count.q.out | 14 +- .../clientpositive/spark/groupby5_map.q.out | 4 +- .../clientpositive/spark/groupby5_map_skew.q.out | 4 +- .../clientpositive/spark/groupby_cube1.q.out | 12 +- .../clientpositive/spark/groupby_position.q.out | 18 +- .../clientpositive/spark/groupby_resolution.q.out | 60 +- .../clientpositive/spark/groupby_rollup1.q.out | 12 +- .../test/results/clientpositive/spark/having.q.out | 62 +- .../spark/infer_bucket_sort_map_operators.q.out | 4 +- .../test/results/clientpositive/spark/join18.q.out | 10 +- .../spark/join18_multi_distinct.q.out | 12 +- .../test/results/clientpositive/spark/join31.q.out | 36 +- .../spark/limit_partition_metadataonly.q.out | 4 +- .../clientpositive/spark/limit_pushdown.q.out | 34 +- .../clientpositive/spark/mapjoin_mapjoin.q.out | 24 +- .../spark/metadata_only_queries.q.out | 4 +- .../clientpositive/spark/ppd_join_filter.q.out | 90 +- .../spark/ql_rewrite_gbtoidx_cbo_1.q.out | 168 +- .../clientpositive/spark/stats_only_null.q.out | 8 +- .../results/clientpositive/spark/subquery_in.q.out | 36 +- .../results/clientpositive/spark/union11.q.out | 42 +- .../results/clientpositive/spark/union14.q.out | 28 +- .../results/clientpositive/spark/union15.q.out | 28 +- .../results/clientpositive/spark/union28.q.out | 4 +- .../results/clientpositive/spark/union30.q.out | 4 +- .../results/clientpositive/spark/union33.q.out | 8 +- .../test/results/clientpositive/spark/union5.q.out | 34 +- .../test/results/clientpositive/spark/union7.q.out | 28 +- .../clientpositive/spark/union_remove_21.q.out | 4 +- .../spark/vector_count_distinct.q.out | 4 +- .../spark/vector_decimal_aggregate.q.out | 12 +- .../clientpositive/spark/vector_distinct_2.q.out | 28 +- .../clientpositive/spark/vector_groupby_3.q.out | 30 +- .../spark/vector_mapjoin_reduce.q.out | 36 +- .../clientpositive/spark/vector_orderby_5.q.out | 6 +- .../clientpositive/spark/vectorization_0.q.out | 16 +- .../clientpositive/spark/vectorization_13.q.out | 32 +- .../clientpositive/spark/vectorization_15.q.out | 16 +- .../clientpositive/spark/vectorization_16.q.out | 16 +- .../clientpositive/spark/vectorization_9.q.out | 16 +- .../spark/vectorization_pushdown.q.out | 4 +- .../spark/vectorization_short_regress.q.out | 74 +- .../spark/vectorized_nested_mapjoin.q.out | 18 +- .../spark/vectorized_timestamp_funcs.q.out | 12 +- .../results/clientpositive/stats_only_null.q.out | 8 +- .../results/clientpositive/stats_ppr_all.q.out | 16 +- .../clientpositive/subq_where_serialization.q.out | 18 +- .../clientpositive/subquery_exists_having.q.out | 48 +- .../test/results/clientpositive/subquery_in.q.out | 36 +- .../clientpositive/subquery_in_having.q.out | 260 +-- .../clientpositive/subquery_notexists.q.out | 18 +- .../clientpositive/subquery_notexists_having.q.out | 26 +- .../results/clientpositive/subquery_notin.q.out | 24 +- .../subquery_notin_having.q.java1.7.out | 50 +- .../clientpositive/subquery_unqualcolumnrefs.q.out | 74 +- .../results/clientpositive/subquery_views.q.out | 8 +- ql/src/test/results/clientpositive/tez/count.q.out | 14 +- .../tez/dynamic_partition_pruning.q.out | 88 +- .../tez/dynpart_sort_opt_vectorization.q.out | 90 +- .../tez/dynpart_sort_optimization.q.out | 89 +- .../results/clientpositive/tez/explainuser_1.q.out | 2319 ++++++++++---------- .../results/clientpositive/tez/explainuser_2.q.out | 782 +++---- .../test/results/clientpositive/tez/having.q.out | 62 +- .../clientpositive/tez/limit_pushdown.q.out | 34 +- .../clientpositive/tez/mapjoin_mapjoin.q.out | 24 +- .../clientpositive/tez/metadata_only_queries.q.out | 4 +- .../results/clientpositive/tez/metadataonly1.q.out | 44 +- ql/src/test/results/clientpositive/tez/mrr.q.out | 94 +- .../clientpositive/tez/selectDistinctStar.q.out | 44 +- .../clientpositive/tez/stats_only_null.q.out | 8 +- .../results/clientpositive/tez/subquery_in.q.out | 36 +- .../test/results/clientpositive/tez/tez_dml.q.out | 6 +- .../test/results/clientpositive/tez/union5.q.out | 44 +- .../test/results/clientpositive/tez/union7.q.out | 28 +- .../clientpositive/tez/unionDistinct_1.q.out | 8 +- .../clientpositive/tez/vector_aggregate_9.q.out | 4 +- .../tez/vector_binary_join_groupby.q.out | 4 +- .../clientpositive/tez/vector_count_distinct.q.out | 4 +- .../tez/vector_decimal_aggregate.q.out | 12 +- .../tez/vector_decimal_precision.q.out | 4 +- .../clientpositive/tez/vector_decimal_udf.q.out | 30 +- .../clientpositive/tez/vector_distinct_2.q.out | 28 +- .../clientpositive/tez/vector_groupby_3.q.out | 30 +- .../clientpositive/tez/vector_groupby_reduce.q.out | 8 +- .../clientpositive/tez/vector_grouping_sets.q.out | 8 +- .../clientpositive/tez/vector_mapjoin_reduce.q.out | 36 +- .../clientpositive/tez/vector_orderby_5.q.out | 6 +- .../clientpositive/tez/vector_outer_join2.q.out | 20 +- .../tez/vector_partition_diff_num_cols.q.out | 20 +- .../tez/vector_partitioned_date_time.q.out | 12 +- .../tez/vector_reduce_groupby_decimal.q.out | 24 +- .../clientpositive/tez/vectorization_0.q.out | 16 +- .../clientpositive/tez/vectorization_13.q.out | 32 +- .../clientpositive/tez/vectorization_15.q.out | 16 +- .../clientpositive/tez/vectorization_16.q.out | 16 +- .../clientpositive/tez/vectorization_9.q.out | 16 +- .../clientpositive/tez/vectorization_limit.q.out | 14 +- .../tez/vectorization_pushdown.q.out | 4 +- .../tez/vectorization_short_regress.q.out | 74 +- .../tez/vectorized_distinct_gby.q.out | 8 +- .../tez/vectorized_dynamic_partition_pruning.q.out | 88 +- .../tez/vectorized_nested_mapjoin.q.out | 18 +- .../clientpositive/tez/vectorized_parquet.q.out | 6 +- .../tez/vectorized_timestamp_funcs.q.out | 12 +- ql/src/test/results/clientpositive/udf8.q.out | 4 +- ql/src/test/results/clientpositive/udf_count.q.out | 16 +- ql/src/test/results/clientpositive/union11.q.out | 70 +- ql/src/test/results/clientpositive/union14.q.out | 32 +- ql/src/test/results/clientpositive/union15.q.out | 38 +- ql/src/test/results/clientpositive/union28.q.out | 8 +- ql/src/test/results/clientpositive/union30.q.out | 8 +- ql/src/test/results/clientpositive/union33.q.out | 8 +- ql/src/test/results/clientpositive/union5.q.out | 48 +- ql/src/test/results/clientpositive/union7.q.out | 32 +- .../results/clientpositive/unionDistinct_1.q.out | 8 +- .../results/clientpositive/union_remove_21.q.out | 8 +- .../clientpositive/vector_aggregate_9.q.out | 4 +- .../vector_aggregate_without_gby.q.out | 4 +- .../vector_binary_join_groupby.q.out | 4 +- .../clientpositive/vector_count_distinct.q.out | 6 +- .../clientpositive/vector_decimal_aggregate.q.out | 12 +- .../clientpositive/vector_decimal_precision.q.out | 4 +- .../clientpositive/vector_decimal_udf.q.out | 30 +- .../results/clientpositive/vector_distinct_2.q.out | 28 +- .../results/clientpositive/vector_groupby_3.q.out | 30 +- .../clientpositive/vector_groupby_reduce.q.out | 8 +- .../clientpositive/vector_grouping_sets.q.out | 8 +- .../clientpositive/vector_left_outer_join.q.out | 8 +- .../clientpositive/vector_mapjoin_reduce.q.out | 36 +- .../results/clientpositive/vector_orderby_5.q.out | 6 +- .../clientpositive/vector_outer_join1.q.out | 8 +- .../clientpositive/vector_outer_join2.q.out | 28 +- .../clientpositive/vector_outer_join3.q.out | 24 +- .../clientpositive/vector_outer_join4.q.out | 8 +- .../clientpositive/vector_outer_join5.q.out | 48 +- .../vector_partition_diff_num_cols.q.out | 20 +- .../vector_partitioned_date_time.q.out | 12 +- .../vector_reduce_groupby_decimal.q.out | 24 +- .../results/clientpositive/vectorization_0.q.out | 16 +- .../results/clientpositive/vectorization_13.q.out | 32 +- .../results/clientpositive/vectorization_15.q.out | 16 +- .../results/clientpositive/vectorization_16.q.out | 16 +- .../results/clientpositive/vectorization_9.q.out | 16 +- .../clientpositive/vectorization_limit.q.out | 16 +- .../clientpositive/vectorization_pushdown.q.out | 4 +- .../vectorization_short_regress.q.out | 74 +- .../clientpositive/vectorized_distinct_gby.q.out | 12 +- .../clientpositive/vectorized_nested_mapjoin.q.out | 26 +- .../clientpositive/vectorized_parquet.q.out | 6 +- .../clientpositive/vectorized_parquet_types.q.out | 6 +- .../vectorized_timestamp_funcs.q.out | 12 +- 227 files changed, 4821 insertions(+), 5020 deletions(-) create mode 100644 ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java new file mode 100644 index 0000000..53f04ee --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java @@ -0,0 +1,151 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to you under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.ql.optimizer.calcite.rules; + +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.plan.RelOptUtil; +import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.AggregateCall; +import org.apache.calcite.rex.RexInputRef; +import org.apache.calcite.rex.RexNode; +import org.apache.calcite.util.ImmutableBitSet; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject; + +import com.google.common.collect.ImmutableList; +import com.google.common.collect.Lists; + +import java.util.HashMap; +import java.util.List; +import java.util.Map; + +/** + * Planner rule that recognizes a {@link HiveAggregate} + * on top of a {@link HiveProject} and if possible + * aggregate through the project or removes the project. + * + *

This is only possible when the grouping expressions and arguments to + * the aggregate functions are field references (i.e. not expressions). + * + *

In some cases, this rule has the effect of trimming: the aggregate will + * use fewer columns than the project did. + */ +public class HiveAggregateProjectMergeRule extends RelOptRule { + public static final HiveAggregateProjectMergeRule INSTANCE = + new HiveAggregateProjectMergeRule(); + + /** Private constructor. */ + private HiveAggregateProjectMergeRule() { + super( + operand(HiveAggregate.class, + operand(HiveProject.class, any()))); + } + + @Override + public void onMatch(RelOptRuleCall call) { + final HiveAggregate aggregate = call.rel(0); + final HiveProject project = call.rel(1); + RelNode x = apply(aggregate, project); + if (x != null) { + call.transformTo(x); + } + } + + public static RelNode apply(HiveAggregate aggregate, + HiveProject project) { + final List newKeys = Lists.newArrayList(); + final Map map = new HashMap<>(); + for (int key : aggregate.getGroupSet()) { + final RexNode rex = project.getProjects().get(key); + if (rex instanceof RexInputRef) { + final int newKey = ((RexInputRef) rex).getIndex(); + newKeys.add(newKey); + map.put(key, newKey); + } else { + // Cannot handle "GROUP BY expression" + return null; + } + } + + final ImmutableBitSet newGroupSet = aggregate.getGroupSet().permute(map); + ImmutableList newGroupingSets = null; + if (aggregate.indicator) { + newGroupingSets = + ImmutableBitSet.ORDERING.immutableSortedCopy( + ImmutableBitSet.permute(aggregate.getGroupSets(), map)); + } + + final ImmutableList.Builder aggCalls = + ImmutableList.builder(); + for (AggregateCall aggregateCall : aggregate.getAggCallList()) { + final ImmutableList.Builder newArgs = ImmutableList.builder(); + for (int arg : aggregateCall.getArgList()) { + final RexNode rex = project.getProjects().get(arg); + if (rex instanceof RexInputRef) { + newArgs.add(((RexInputRef) rex).getIndex()); + } else { + // Cannot handle "AGG(expression)" + return null; + } + } + final int newFilterArg; + if (aggregateCall.filterArg >= 0) { + final RexNode rex = project.getProjects().get(aggregateCall.filterArg); + if (!(rex instanceof RexInputRef)) { + return null; + } + newFilterArg = ((RexInputRef) rex).getIndex(); + } else { + newFilterArg = -1; + } + aggCalls.add(aggregateCall.copy(newArgs.build(), newFilterArg)); + } + + final Aggregate newAggregate = + aggregate.copy(aggregate.getTraitSet(), project.getInput(), + aggregate.indicator, newGroupSet, newGroupingSets, + aggCalls.build()); + + // Add a project if the group set is not in the same order or + // contains duplicates. + RelNode rel = newAggregate; + if (!newKeys.equals(newGroupSet.asList())) { + final List posList = Lists.newArrayList(); + for (int newKey : newKeys) { + posList.add(newGroupSet.indexOf(newKey)); + } + if (aggregate.indicator) { + for (int newKey : newKeys) { + posList.add(aggregate.getGroupCount() + newGroupSet.indexOf(newKey)); + } + } + for (int i = newAggregate.getGroupCount() + + newAggregate.getIndicatorCount(); + i < newAggregate.getRowType().getFieldCount(); i++) { + posList.add(i); + } + rel = RelOptUtil.createProject(HiveProject.DEFAULT_PROJECT_FACTORY, + rel, posList); + } + + return rel; + } +} + +// End AggregateProjectMergeRule.java diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveRelFieldTrimmer.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveRelFieldTrimmer.java index 4144674..a12fa2a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveRelFieldTrimmer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveRelFieldTrimmer.java @@ -24,11 +24,10 @@ import java.util.Set; import org.apache.calcite.plan.RelOptUtil; -import org.apache.calcite.rel.RelCollation; -import org.apache.calcite.rel.RelFieldCollation; import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.AggregateCall; import org.apache.calcite.rel.core.RelFactories; -import org.apache.calcite.rel.metadata.RelMetadataQuery; import org.apache.calcite.rel.type.RelDataType; import org.apache.calcite.rel.type.RelDataTypeField; import org.apache.calcite.rex.RexNode; @@ -37,20 +36,19 @@ import org.apache.calcite.sql.validate.SqlValidator; import org.apache.calcite.sql2rel.RelFieldTrimmer; import org.apache.calcite.util.ImmutableBitSet; -import org.apache.calcite.util.Util; import org.apache.calcite.util.mapping.IntPair; import org.apache.calcite.util.mapping.Mapping; import org.apache.calcite.util.mapping.MappingType; import org.apache.calcite.util.mapping.Mappings; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveMultiJoin; +import com.google.common.base.Function; import com.google.common.collect.ImmutableList; +import com.google.common.collect.Iterables; public class HiveRelFieldTrimmer extends RelFieldTrimmer { - public HiveRelFieldTrimmer(SqlValidator validator) { - super(validator); - } + private final RelFactories.AggregateFactory aggregateFactory; public HiveRelFieldTrimmer(SqlValidator validator, RelFactories.ProjectFactory projectFactory, @@ -62,6 +60,7 @@ public HiveRelFieldTrimmer(SqlValidator validator, RelFactories.SetOpFactory setOpFactory) { super(validator, projectFactory, filterFactory, joinFactory, semiJoinFactory, sortFactory, aggregateFactory, setOpFactory); + this.aggregateFactory = aggregateFactory; } /** @@ -156,27 +155,127 @@ public TrimResult trimFields( return new TrimResult(newJoin, mapping); } - - protected TrimResult trimChild( - RelNode rel, - RelNode input, + /** + * Variant of {@link #trimFields(RelNode, ImmutableBitSet, Set)} for + * {@link org.apache.calcite.rel.logical.LogicalAggregate}. + */ + @Override + public TrimResult trimFields( + Aggregate aggregate, ImmutableBitSet fieldsUsed, Set extraFields) { - Util.discard(rel); - if (input.getClass().getName().endsWith("MedMdrClassExtentRel")) { - // MedMdrJoinRule cannot handle Join of Project of - // MedMdrClassExtentRel, only naked MedMdrClassExtentRel. - // So, disable trimming. - fieldsUsed = ImmutableBitSet.range(input.getRowType().getFieldCount()); + // Fields: + // + // | sys fields | group fields | indicator fields | agg functions | + // + // Two kinds of trimming: + // + // 1. If agg rel has system fields but none of these are used, create an + // agg rel with no system fields. + // + // 2. If aggregate functions are not used, remove them. + // + // But group and indicator fields stay, even if they are not used. + + final RelDataType rowType = aggregate.getRowType(); + + // Compute which input fields are used. + // 1. group fields are always used + final ImmutableBitSet.Builder inputFieldsUsed = + ImmutableBitSet.builder(aggregate.getGroupSet()); + // 2. agg functions + for (AggregateCall aggCall : aggregate.getAggCallList()) { + for (int i : aggCall.getArgList()) { + inputFieldsUsed.set(i); + } + if (aggCall.filterArg >= 0) { + inputFieldsUsed.set(aggCall.filterArg); + } + } + + // Create input with trimmed columns. + final RelNode input = aggregate.getInput(); + final Set inputExtraFields = Collections.emptySet(); + final TrimResult trimResult = + trimChild(aggregate, input, inputFieldsUsed.build(), inputExtraFields); + final RelNode newInput = trimResult.left; + final Mapping inputMapping = trimResult.right; + + // We have to return group keys and (if present) indicators. + // So, pretend that the consumer asked for them. + final int groupCount = aggregate.getGroupSet().cardinality(); + final int indicatorCount = aggregate.getIndicatorCount(); + fieldsUsed = + fieldsUsed.union(ImmutableBitSet.range(groupCount + indicatorCount)); + + // If the input is unchanged, and we need to project all columns, + // there's nothing to do. + if (input == newInput + && fieldsUsed.equals(ImmutableBitSet.range(rowType.getFieldCount()))) { + return new TrimResult( + aggregate, + Mappings.createIdentity(rowType.getFieldCount())); } - final ImmutableList collations = - RelMetadataQuery.collations(input); - for (RelCollation collation : collations) { - for (RelFieldCollation fieldCollation : collation.getFieldCollations()) { - fieldsUsed = fieldsUsed.set(fieldCollation.getFieldIndex()); + + // Which agg calls are used by our consumer? + int j = groupCount + indicatorCount; + int usedAggCallCount = 0; + for (int i = 0; i < aggregate.getAggCallList().size(); i++) { + if (fieldsUsed.get(j++)) { + ++usedAggCallCount; } } - return dispatchTrimFields(input, fieldsUsed, extraFields); + + // Offset due to the number of system fields having changed. + Mapping mapping = + Mappings.create( + MappingType.INVERSE_SURJECTION, + rowType.getFieldCount(), + groupCount + indicatorCount + usedAggCallCount); + + final ImmutableBitSet newGroupSet = + Mappings.apply(inputMapping, aggregate.getGroupSet()); + + final ImmutableList newGroupSets = + ImmutableList.copyOf( + Iterables.transform(aggregate.getGroupSets(), + new Function() { + @Override + public ImmutableBitSet apply(ImmutableBitSet input) { + return Mappings.apply(inputMapping, input); + } + })); + + // Populate mapping of where to find the fields. System, group key and + // indicator fields first. + for (j = 0; j < groupCount + indicatorCount; j++) { + mapping.set(j, j); + } + + // Now create new agg calls, and populate mapping for them. + final List newAggCallList = new ArrayList<>(); + j = groupCount + indicatorCount; + for (AggregateCall aggCall : aggregate.getAggCallList()) { + if (fieldsUsed.get(j)) { + AggregateCall newAggCall = + aggCall.copy(Mappings.apply2(inputMapping, aggCall.getArgList()), + Mappings.apply(inputMapping, aggCall.filterArg)); + if (newAggCall.equals(aggCall)) { + newAggCall = aggCall; // immutable -> canonize to save space + } + mapping.set(j, groupCount + indicatorCount + newAggCallList.size()); + newAggCallList.add(newAggCall); + } + ++j; + } + + RelNode newAggregate = aggregateFactory.createAggregate(newInput, + aggregate.indicator, newGroupSet, newGroupSets, newAggCallList); + + assert newAggregate.getClass() == aggregate.getClass(); + + return new TrimResult(newAggregate, mapping); } + } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java index 67f17c2..16a375c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java @@ -265,8 +265,8 @@ private static boolean validFilterParent(RelNode filterNode, RelNode parent) { // TODO: Verify GB having is not a separate filter (if so we shouldn't // introduce derived table) - if (parent instanceof Filter || parent instanceof Join - || parent instanceof SetOp) { + if (parent instanceof Filter || parent instanceof Join || parent instanceof SetOp || + (parent instanceof Aggregate && filterNode.getInputs().get(0) instanceof Aggregate)) { validParent = false; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 8e992da..36a8358 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -134,6 +134,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveSortLimit; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveUnion; +import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveAggregateProjectMergeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveExpandDistinctAggregatesRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterJoinRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterProjectTransposeRule; @@ -883,6 +884,7 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu hepPgmBldr.addRuleInstance(ProjectRemoveRule.INSTANCE); hepPgmBldr.addRuleInstance(UnionMergeRule.INSTANCE); hepPgmBldr.addRuleInstance(new ProjectMergeRule(false, HiveProject.DEFAULT_PROJECT_FACTORY)); + hepPgmBldr.addRuleInstance(HiveAggregateProjectMergeRule.INSTANCE); hepPgm = hepPgmBldr.build(); HepPlanner hepPlanner = new HepPlanner(hepPgm); diff --git a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out index 9fc3c8d..a42b464 100644 --- a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out +++ b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out @@ -232,8 +232,8 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [$hdt$_0:alter_coltype] - /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=3.0 [alter_coltype] + /alter_coltype/dt=100/ts=6.30 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -411,7 +411,7 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=6.30 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -568,7 +568,7 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=3.0 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out index 82cc0da..1b9ec68 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out @@ -157,11 +157,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: int) + keys: state (type: string), locid (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: PARTIAL @@ -178,22 +178,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 7 Data size: 658 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: int) + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string), _col2 (type: bigint) + mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 658 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: min(_col2) - keys: _col0 (type: string), _col1 (type: bigint) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -255,10 +251,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE @@ -308,10 +304,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int) + keys: state (type: string), locid (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE @@ -361,10 +357,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE @@ -415,10 +411,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE @@ -469,10 +465,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE @@ -523,10 +519,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE @@ -577,10 +573,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE @@ -631,10 +627,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE @@ -689,10 +685,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -742,10 +738,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE @@ -798,10 +794,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), zip (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: state, zip Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: state (type: string), zip (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 344 Basic stats: COMPLETE Column stats: PARTIAL @@ -851,10 +847,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE @@ -905,10 +901,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE @@ -959,10 +955,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE @@ -1013,10 +1009,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE @@ -1067,10 +1063,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE @@ -1121,10 +1117,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE @@ -1175,10 +1171,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: year (type: int) - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE @@ -1228,10 +1224,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out b/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out index 2cb1e84..be3fa1d 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out @@ -91,10 +91,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE @@ -144,10 +144,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 80 Data size: 800 Basic stats: COMPLETE Column stats: NONE @@ -202,10 +202,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE @@ -257,10 +257,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), votes (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: state, votes Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: state (type: string), votes (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: PARTIAL @@ -310,10 +310,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 8256 Basic stats: COMPLETE Column stats: COMPLETE @@ -364,10 +364,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE @@ -417,10 +417,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 80 Data size: 20640 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/auto_join18.q.out b/ql/src/test/results/clientpositive/auto_join18.q.out index 6dc7a63..7fd7dd1 100644 --- a/ql/src/test/results/clientpositive/auto_join18.q.out +++ b/ql/src/test/results/clientpositive/auto_join18.q.out @@ -40,11 +40,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -140,11 +140,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out index cc17ad1..0a9dd76 100644 --- a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out @@ -42,11 +42,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -142,11 +142,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/auto_join27.q.out b/ql/src/test/results/clientpositive/auto_join27.q.out index 16a7f02..9c03c78 100644 --- a/ql/src/test/results/clientpositive/auto_join27.q.out +++ b/ql/src/test/results/clientpositive/auto_join27.q.out @@ -39,20 +39,16 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/auto_join32.q.out b/ql/src/test/results/clientpositive/auto_join32.q.out index f862870..161ab6b 100644 --- a/ql/src/test/results/clientpositive/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/auto_join32.q.out @@ -411,10 +411,10 @@ STAGE PLANS: outputColumnNames: _col1, _col3 Select Operator expressions: _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col3, _col1 Group By Operator aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + keys: _col3 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/binarysortable_1.q.out b/ql/src/test/results/clientpositive/binarysortable_1.q.out index 421fd2e..9ef9221 100644 --- a/ql/src/test/results/clientpositive/binarysortable_1.q.out +++ b/ql/src/test/results/clientpositive/binarysortable_1.q.out @@ -49,11 +49,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/correlationoptimizer2.q.out index c1a20c8..96c7660 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer2.q.out @@ -41,22 +41,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -144,22 +140,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -228,44 +220,36 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE @@ -411,11 +395,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -511,11 +495,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -592,11 +576,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -611,11 +595,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -770,11 +754,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -870,11 +854,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -951,11 +935,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -970,11 +954,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1129,11 +1113,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1229,11 +1213,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1310,11 +1294,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1329,11 +1313,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1489,10 +1473,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1614,10 +1598,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1703,10 +1687,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1720,10 +1704,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -2029,22 +2013,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2144,22 +2124,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/correlationoptimizer6.q.out index 6b003d5..2d72250 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer6.q.out @@ -2650,22 +2650,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2706,22 +2702,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) + Group By Operator + aggregations: sum(_col1), sum(_col3) + keys: _col0 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2803,22 +2795,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2930,44 +2918,36 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -3003,39 +2983,35 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + Group By Operator + aggregations: sum(_col1), sum(_col3) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Mux Operator + Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) @@ -3052,39 +3028,35 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + Group By Operator + aggregations: sum(_col1), sum(_col3) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Mux Operator + Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE Join Operator diff --git a/ql/src/test/results/clientpositive/count.q.out b/ql/src/test/results/clientpositive/count.q.out index e8d0cb3..c744b4f 100644 --- a/ql/src/test/results/clientpositive/count.q.out +++ b/ql/src/test/results/clientpositive/count.q.out @@ -48,11 +48,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) + aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) + keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -171,14 +171,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: a (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + value expressions: d (type: int) Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/ctas_colname.q.out b/ql/src/test/results/clientpositive/ctas_colname.q.out index 232d505..2a70faf 100644 --- a/ql/src/test/results/clientpositive/ctas_colname.q.out +++ b/ql/src/test/results/clientpositive/ctas_colname.q.out @@ -692,11 +692,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1125,22 +1125,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 9.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count(value) + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1256,22 +1252,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 9.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/database.q.out b/ql/src/test/results/clientpositive/database.q.out index 19b0ea2..02eb3d3 100644 --- a/ql/src/test/results/clientpositive/database.q.out +++ b/ql/src/test/results/clientpositive/database.q.out @@ -455,7 +455,7 @@ POSTHOOK: query: INSERT OVERWRITE TABLE temp_tbl2 SELECT COUNT(*) FROM temp_tbl POSTHOOK: type: QUERY POSTHOOK: Input: to_drop_db2@temp_tbl POSTHOOK: Output: to_drop_db2@temp_tbl2 -POSTHOOK: Lineage: temp_tbl2.c EXPRESSION [] +POSTHOOK: Lineage: temp_tbl2.c EXPRESSION [(temp_tbl)temp_tbl.null, ] PREHOOK: query: USE default PREHOOK: type: SWITCHDATABASE PREHOOK: Input: database:default diff --git a/ql/src/test/results/clientpositive/decimal_precision.q.out b/ql/src/test/results/clientpositive/decimal_precision.q.out index 8d67e2a..69a6045 100644 --- a/ql/src/test/results/clientpositive/decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/decimal_precision.q.out @@ -539,10 +539,10 @@ STAGE PLANS: Statistics: Num rows: 23 Data size: 2661 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 23 Data size: 2661 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/decimal_udf.q.out b/ql/src/test/results/clientpositive/decimal_udf.q.out index 338b754..ce1fe3f 100644 --- a/ql/src/test/results/clientpositive/decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/decimal_udf.q.out @@ -1291,11 +1291,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum(key), count(key), avg(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1878,11 +1878,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev(key), variance(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1957,11 +1957,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp(key), var_samp(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -2095,10 +2095,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2154,10 +2154,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2213,10 +2213,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/distinct_stats.q.out b/ql/src/test/results/clientpositive/distinct_stats.q.out index 36049be..164a0a8 100644 --- a/ql/src/test/results/clientpositive/distinct_stats.q.out +++ b/ql/src/test/results/clientpositive/distinct_stats.q.out @@ -43,11 +43,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT b) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -100,10 +100,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: b (type: string) - outputColumnNames: _col0 + outputColumnNames: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: b (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -151,11 +151,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: a (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out index 216a79c..2b5122f 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out @@ -1518,35 +1518,35 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Stage: Stage-0 Move Operator @@ -1572,9 +1572,8 @@ explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si, POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -1586,57 +1585,35 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Stage: Stage-0 Move Operator @@ -1651,7 +1628,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.over1k_part2_orc - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out index 41049bd..4caa587 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out @@ -1420,34 +1420,34 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-0 Move Operator @@ -1473,9 +1473,8 @@ explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b, POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -1487,56 +1486,34 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-0 Move Operator @@ -1551,7 +1528,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.over1k_part2 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_select_read_only_encrypted_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_select_read_only_encrypted_tbl.q.out index 5d4d2af..c57a5ad 100644 --- a/ql/src/test/results/clientpositive/encrypted/encryption_select_read_only_encrypted_tbl.q.out +++ b/ql/src/test/results/clientpositive/encrypted/encryption_select_read_only_encrypted_tbl.q.out @@ -29,11 +29,11 @@ POSTHOOK: Output: default@encrypted_table PREHOOK: query: SELECT count(*) FROM encrypted_table PREHOOK: type: QUERY PREHOOK: Input: default@encrypted_table -#### A masked pattern was here #### +#### A PARTIAL masked pattern was here #### data/warehouse/default/encrypted_table/.hive-staging POSTHOOK: query: SELECT count(*) FROM encrypted_table POSTHOOK: type: QUERY POSTHOOK: Input: default@encrypted_table -#### A masked pattern was here #### +#### A PARTIAL masked pattern was here #### data/warehouse/default/encrypted_table/.hive-staging 500 PREHOOK: query: drop table encrypted_table PURGE PREHOOK: type: DROPTABLE diff --git a/ql/src/test/results/clientpositive/explain_logical.q.out b/ql/src/test/results/clientpositive/explain_logical.q.out index 545034a..8fa0a4c 100644 --- a/ql/src/test/results/clientpositive/explain_logical.q.out +++ b/ql/src/test/results/clientpositive/explain_logical.q.out @@ -804,20 +804,20 @@ $hdt$_0:src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_18) + Filter Operator (FIL_17) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_1) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) + Reduce Output Operator (RS_9) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_13) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 keys: @@ -825,67 +825,63 @@ $hdt$_0:src 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_14) + Select Operator (SEL_13) expressions: _col0 (type: string), _col3 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_15) + Reduce Output Operator (RS_14) key expressions: _col0 (type: string) sort order: + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: string) - Select Operator (SEL_16) + Select Operator (SEL_15) expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_17) + File Output Operator (FS_16) compressed: false Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -$hdt$_1:$hdt$_1:src +$hdt$_1:src TableScan (TS_2) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_19) + Filter Operator (FIL_18) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_3) - expressions: key (type: string), value (type: string) + Group By Operator (GBY_4) + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_5) - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator (RS_5) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_6) - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Group By Operator (GBY_7) - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 + value expressions: _col1 (type: bigint) + Group By Operator (GBY_6) + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_11) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_12) - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Join Operator (JOIN_13) - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Join Operator (JOIN_12) + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/fetch_aggregation.q.out b/ql/src/test/results/clientpositive/fetch_aggregation.q.out index 121d6a4..91f47f8 100644 --- a/ql/src/test/results/clientpositive/fetch_aggregation.q.out +++ b/ql/src/test/results/clientpositive/fetch_aggregation.q.out @@ -17,10 +17,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), sum(_col0), avg(_col0), min(_col0), max(_col0), std(_col0), variance(_col0) + aggregations: count(key), sum(key), avg(key), min(key), max(key), std(key), variance(key) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/gby_star.q.out b/ql/src/test/results/clientpositive/gby_star.q.out index a49f1bf..fb71835 100644 --- a/ql/src/test/results/clientpositive/gby_star.q.out +++ b/ql/src/test/results/clientpositive/gby_star.q.out @@ -17,11 +17,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum(key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -93,22 +93,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: sum(key) + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double) + value expressions: _col2 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -171,22 +167,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: sum(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/groupby12.q.out b/ql/src/test/results/clientpositive/groupby12.q.out index 6eb3e96..b17da54 100644 --- a/ql/src/test/results/clientpositive/groupby12.q.out +++ b/ql/src/test/results/clientpositive/groupby12.q.out @@ -28,12 +28,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/groupby5_map.q.out b/ql/src/test/results/clientpositive/groupby5_map.q.out index ea8ce4a..5fbd3d7 100644 --- a/ql/src/test/results/clientpositive/groupby5_map.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map.q.out @@ -26,10 +26,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out index c0fced7..60b010b 100644 --- a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out @@ -26,10 +26,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_cube1.q.out b/ql/src/test/results/clientpositive/groupby_cube1.q.out index 62e9c54..f5a2d1c 100644 --- a/ql/src/test/results/clientpositive/groupby_cube1.q.out +++ b/ql/src/test/results/clientpositive/groupby_cube1.q.out @@ -206,11 +206,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -389,11 +389,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out index bd92927..b7121d5 100644 --- a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out +++ b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out @@ -115,11 +115,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: int1 (type: int) - outputColumnNames: _col0 + outputColumnNames: int1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: sum(DISTINCT int1) + keys: int1 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out index 6d44f32..6f9237d 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out @@ -36,11 +36,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -143,11 +143,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum(c) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out index 5d1a7a8..d3e6bee 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out @@ -55,11 +55,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col2), count() - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: avg(c), count() + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 288 Basic stats: COMPLETE Column stats: NONE @@ -143,11 +143,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col2), count() - keys: _col0 (type: string), _col1 (type: string) + aggregations: avg(c), count() + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out index bd7c2ff..e022297 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out @@ -42,10 +42,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -159,10 +159,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out index d807d44..1d7b569 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out @@ -42,10 +42,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE @@ -117,10 +117,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_position.q.out b/ql/src/test/results/clientpositive/groupby_position.q.out index 7152101..3472134 100644 --- a/ql/src/test/results/clientpositive/groupby_position.q.out +++ b/ql/src/test/results/clientpositive/groupby_position.q.out @@ -563,20 +563,16 @@ STAGE PLANS: Filter Operator predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) @@ -653,20 +649,16 @@ STAGE PLANS: Filter Operator predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/groupby_resolution.q.out b/ql/src/test/results/clientpositive/groupby_resolution.q.out index 7df53f2..ea40014 100644 --- a/ql/src/test/results/clientpositive/groupby_resolution.q.out +++ b/ql/src/test/results/clientpositive/groupby_resolution.q.out @@ -15,12 +15,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -60,12 +60,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -106,10 +106,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -176,10 +176,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -245,11 +245,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -297,11 +297,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -350,11 +350,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -427,11 +427,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -607,22 +607,18 @@ STAGE PLANS: Filter Operator predicate: (key < '12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/groupby_rollup1.q.out b/ql/src/test/results/clientpositive/groupby_rollup1.q.out index 8e04d86..292e14d 100644 --- a/ql/src/test/results/clientpositive/groupby_rollup1.q.out +++ b/ql/src/test/results/clientpositive/groupby_rollup1.q.out @@ -116,11 +116,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -293,11 +293,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_sort_10.q.out b/ql/src/test/results/clientpositive/groupby_sort_10.q.out index 2fead26..db8899f 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_10.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_10.q.out @@ -41,10 +41,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: final outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE @@ -109,11 +109,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Group By Operator bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_sort_11.q.out b/ql/src/test/results/clientpositive/groupby_sort_11.q.out index adf585d..2d4a44e 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_11.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_11.q.out @@ -41,12 +41,12 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) + aggregations: count(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -435,10 +435,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/groupby_sort_8.q.out b/ql/src/test/results/clientpositive/groupby_sort_8.q.out index ec16eb0..5152385 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_8.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_8.q.out @@ -56,12 +56,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) + aggregations: count(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -122,11 +122,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/having.q.out b/ql/src/test/results/clientpositive/having.q.out index 8682a46..35b2901 100644 --- a/ql/src/test/results/clientpositive/having.q.out +++ b/ql/src/test/results/clientpositive/having.q.out @@ -99,22 +99,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <> 302.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -469,11 +465,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -736,22 +732,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 300.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -930,11 +922,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1192,11 +1184,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/having2.q.out b/ql/src/test/results/clientpositive/having2.q.out index ba601f9..699d8ee 100644 --- a/ql/src/test/results/clientpositive/having2.q.out +++ b/ql/src/test/results/clientpositive/having2.q.out @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: customer_name, customer_balance, order_quantity, discount Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2), count(_col3) - keys: _col0 (type: string) + aggregations: sum(customer_balance), sum(order_quantity), count(discount) + keys: customer_name (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -200,11 +200,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: customer_name, customer_balance, order_quantity, discount Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2), count(_col3) - keys: _col0 (type: string) + aggregations: sum(customer_balance), sum(order_quantity), count(discount) + keys: customer_name (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out b/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out index 7755ed5..2639edf 100644 --- a/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out +++ b/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out @@ -229,10 +229,10 @@ STAGE PLANS: predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -326,10 +326,10 @@ STAGE PLANS: predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/index_auto_self_join.q.out b/ql/src/test/results/clientpositive/index_auto_self_join.q.out index a214845..e8c23dc 100644 --- a/ql/src/test/results/clientpositive/index_auto_self_join.q.out +++ b/ql/src/test/results/clientpositive/index_auto_self_join.q.out @@ -137,10 +137,10 @@ STAGE PLANS: predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -235,10 +235,10 @@ STAGE PLANS: predicate: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/index_auto_update.q.out b/ql/src/test/results/clientpositive/index_auto_update.q.out index 70d0286..11af3f5 100644 --- a/ql/src/test/results/clientpositive/index_auto_update.q.out +++ b/ql/src/test/results/clientpositive/index_auto_update.q.out @@ -109,10 +109,10 @@ STAGE PLANS: alias: temp Select Operator expressions: key (type: string), INPUT__FILE__NAME (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, INPUT__FILE__NAME, BLOCK__OFFSET__INSIDE__FILE Group By Operator - aggregations: collect_set(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: collect_set(BLOCK__OFFSET__INSIDE__FILE) + keys: key (type: string), INPUT__FILE__NAME (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out b/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out index 65b6721..3df629e 100644 --- a/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out +++ b/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out @@ -70,10 +70,10 @@ STAGE PLANS: predicate: ((UDFToDouble(key) = 86.0) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/index_bitmap_compression.q.out b/ql/src/test/results/clientpositive/index_bitmap_compression.q.out index 9673f08..37a2944 100644 --- a/ql/src/test/results/clientpositive/index_bitmap_compression.q.out +++ b/ql/src/test/results/clientpositive/index_bitmap_compression.q.out @@ -44,10 +44,10 @@ STAGE PLANS: predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(_col2) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out index c2f0810..a12dcd5 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out @@ -473,11 +473,11 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out index 6aef463..1294766 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out @@ -81,11 +81,11 @@ STAGE PLANS: Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/join18.q.out b/ql/src/test/results/clientpositive/join18.q.out index c3ab306..6a50604 100644 --- a/ql/src/test/results/clientpositive/join18.q.out +++ b/ql/src/test/results/clientpositive/join18.q.out @@ -43,11 +43,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -113,11 +113,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out index a83102c..dfb0f68 100644 --- a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out @@ -45,11 +45,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -115,11 +115,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/join31.q.out b/ql/src/test/results/clientpositive/join31.q.out index 21aa1de..70ca814 100644 --- a/ql/src/test/results/clientpositive/join31.q.out +++ b/ql/src/test/results/clientpositive/join31.q.out @@ -51,20 +51,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -264,20 +260,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) diff --git a/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out b/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out index 904acfc..dbc5eac 100644 --- a/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out +++ b/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out @@ -550,10 +550,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) - outputColumnNames: _col0 + outputColumnNames: hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: hr (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/limit_pushdown.q.out b/ql/src/test/results/clientpositive/limit_pushdown.q.out index d77bc60..40f6a48 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown.q.out @@ -355,10 +355,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: double) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -438,11 +438,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: tinyint), _col1 (type: double) + aggregations: count(DISTINCT cdouble) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -523,10 +523,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -613,11 +613,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cstring1, cstring2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) + keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -727,11 +727,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(key) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1012,16 +1012,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: key (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/lineage2.q.out b/ql/src/test/results/clientpositive/lineage2.q.out index 549b5f6..4184a83 100644 --- a/ql/src/test/results/clientpositive/lineage2.q.out +++ b/ql/src/test/results/clientpositive/lineage2.q.out @@ -634,7 +634,7 @@ having count(a.c2) > 0 PREHOOK: type: QUERY PREHOOK: Input: default@dest_l2 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"0ae7aa4a0cbd1283210fa79e8a19104a","queryText":"select sum(a.c1) over (partition by a.c1 order by a.id)\nfrom dest_l2 a\nwhere a.c2 != 10\ngroup by a.c1, a.c2, a.id\nhaving count(a.c2) > 0","edges":[{"sources":[1,2,3],"targets":[0],"expression":"(tok_function sum (. (tok_table_or_col $hdt$_0) $f0) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) $f0)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col $hdt$_0) $f2)))) (tok_windowvalues (preceding 2147483647) current)))","edgeType":"PROJECTION"},{"sources":[2],"targets":[0],"expression":"(a.c2 <> 10)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0],"expression":"(count(default.dest_l2.c2) > 0)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"c0"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l2.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"}]} +{"version":"1.0","engine":"mr","hash":"0ae7aa4a0cbd1283210fa79e8a19104a","queryText":"select sum(a.c1) over (partition by a.c1 order by a.id)\nfrom dest_l2 a\nwhere a.c2 != 10\ngroup by a.c1, a.c2, a.id\nhaving count(a.c2) > 0","edges":[{"sources":[1,2,3],"targets":[0],"expression":"(tok_function sum (. (tok_table_or_col $hdt$_0) c1) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) c1)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col $hdt$_0) id)))) (tok_windowvalues (preceding 2147483647) current)))","edgeType":"PROJECTION"},{"sources":[2],"targets":[0],"expression":"(a.c2 <> 10)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0],"expression":"(count(default.dest_l2.c2) > 0)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"c0"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_l2.c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"}]} 1 PREHOOK: query: select sum(a.c1), count(b.c1), b.c2, b.c3 from dest_l2 a join dest_l3 b on (a.id = b.id) diff --git a/ql/src/test/results/clientpositive/lineage3.q.out b/ql/src/test/results/clientpositive/lineage3.q.out index 6fd2aa4..708abee 100644 --- a/ql/src/test/results/clientpositive/lineage3.q.out +++ b/ql/src/test/results/clientpositive/lineage3.q.out @@ -180,7 +180,7 @@ PREHOOK: Input: default@src1 #### A masked pattern was here #### {"version":"1.0","engine":"mr","hash":"8bf193b0658183be94e2428a79d91d10","queryText":"select * from src1 a\nwhere exists\n (select cint from alltypesorc b\n where a.key = b.ctinyint + 300)\nand key > 300","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(a.key) > UDFToDouble(300))","edgeType":"PREDICATE"},{"sources":[2,4],"targets":[0,1],"expression":"(UDFToDouble(a.key) = UDFToDouble((UDFToInteger(b.ctinyint) + 300)))","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"a.key"},{"id":1,"vertexType":"COLUMN","vertexId":"a.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} 311 val_311 -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select key, value from src1 where key not in (select key+18 from src1) order by key PREHOOK: type: QUERY @@ -317,6 +317,6 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@dest_v3 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"40bccc0722002f798d0548b59e369e83","queryText":"select * from dest_v3 limit 2","edges":[{"sources":[3,4,5,6,7],"targets":[0],"expression":"(tok_function sum (. (tok_table_or_col $hdt$_0) $f0) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) $f1)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col $hdt$_0) $f1)))) (tok_windowvalues (preceding 2147483647) current)))","edgeType":"PROJECTION"},{"sources":[6],"targets":[1],"expression":"count(default.alltypesorc.cstring1)","edgeType":"PROJECTION"},{"sources":[5],"targets":[2],"edgeType":"PROJECTION"},{"sources":[8],"targets":[0,1,2],"expression":"(a.cboolean2 = true)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(a.cint = a.cint)","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2],"expression":"(a.cfloat > 0.0)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(count(default.alltypesorc.cint) > 10)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"dest_v3.a"},{"id":1,"vertexType":"COLUMN","vertexId":"dest_v3.x"},{"id":2,"vertexType":"COLUMN","vertexId":"dest_v3.cboolean1"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"}]} +{"version":"1.0","engine":"mr","hash":"40bccc0722002f798d0548b59e369e83","queryText":"select * from dest_v3 limit 2","edges":[{"sources":[3,4,5,6,7],"targets":[0],"expression":"(tok_function sum (. (tok_table_or_col $hdt$_0) ctinyint) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) csmallint)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col $hdt$_0) csmallint)))) (tok_windowvalues (preceding 2147483647) current)))","edgeType":"PROJECTION"},{"sources":[6],"targets":[1],"expression":"count(default.alltypesorc.cstring1)","edgeType":"PROJECTION"},{"sources":[5],"targets":[2],"edgeType":"PROJECTION"},{"sources":[8],"targets":[0,1,2],"expression":"(a.cboolean2 = true)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(a.cint = a.cint)","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2],"expression":"(a.cfloat > 0.0)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(count(default.alltypesorc.cint) > 10)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"dest_v3.a"},{"id":1,"vertexType":"COLUMN","vertexId":"dest_v3.x"},{"id":2,"vertexType":"COLUMN","vertexId":"dest_v3.cboolean1"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"}]} 38 216 false 38 229 true diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out index 753729f..8f1d94e 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out @@ -451,7 +451,7 @@ STAGE PLANS: name: default.fact_daily name: default.fact_daily Truncated Path -> Alias: - /fact_daily/ds=1/hr=1 [$hdt$_0:fact_daily] + /fact_daily/ds=1/hr=1 [fact_daily] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 9775f30..e92f307 100644 --- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -566,11 +566,11 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:src + $hdt$_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:src + $hdt$_1:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -619,11 +619,11 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_2:src + $hdt$_2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_2:src + $hdt$_2:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -651,22 +651,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/metadata_only_queries.q.out index 5907f4a..2dcd437 100644 --- a/ql/src/test/results/clientpositive/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/metadata_only_queries.q.out @@ -431,10 +431,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ts) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/metadataonly1.q.out b/ql/src/test/results/clientpositive/metadataonly1.q.out index 0d758a5..727b2e7 100644 --- a/ql/src/test/results/clientpositive/metadataonly1.q.out +++ b/ql/src/test/results/clientpositive/metadataonly1.q.out @@ -43,10 +43,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -144,10 +144,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -158,7 +158,7 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] Path -> Partition: -mr-10003default.test1{ds=1} Partition @@ -200,7 +200,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -284,11 +284,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT ds) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -299,7 +299,7 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] Path -> Partition: -mr-10003default.test1{ds=1} Partition @@ -341,7 +341,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -425,10 +425,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -482,7 +482,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [$hdt$_0:test1] + /test1/ds=1 [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -604,10 +604,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -618,8 +618,8 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_1:$hdt$_1:a2] - -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_1:$hdt$_1:a2] + -mr-10005default.test1{ds=1} [$hdt$_1:a2] + -mr-10006default.test1{ds=2} [$hdt$_1:a2] Path -> Partition: -mr-10005default.test1{ds=1} Partition @@ -700,8 +700,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_1:$hdt$_1:a2] - -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_1:$hdt$_1:a2] + -mr-10005default.test1{ds=1} [$hdt$_1:a2] + -mr-10006default.test1{ds=2} [$hdt$_1:a2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -862,8 +862,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [$hdt$_0:$hdt$_0:a2] - /test1/ds=2 [$hdt$_0:$hdt$_0:a2] + /test1/ds=1 [$hdt$_0:a2] + /test1/ds=2 [$hdt$_0:a2] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -1053,11 +1053,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1069,9 +1069,9 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10003default.test2{ds=1, hr=1} [test2] + -mr-10004default.test2{ds=1, hr=2} [test2] + -mr-10005default.test2{ds=1, hr=3} [test2] Path -> Partition: -mr-10003default.test2{ds=1, hr=1} Partition @@ -1194,9 +1194,9 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10003default.test2{ds=1, hr=1} [test2] + -mr-10004default.test2{ds=1, hr=2} [test2] + -mr-10005default.test2{ds=1, hr=3} [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1291,11 +1291,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(hr) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1434,9 +1434,9 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - /test2/ds=1/hr=1 [$hdt$_0:test2] - /test2/ds=1/hr=2 [$hdt$_0:test2] - /test2/ds=1/hr=3 [$hdt$_0:test2] + /test2/ds=1/hr=1 [test2] + /test2/ds=1/hr=2 [test2] + /test2/ds=1/hr=3 [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1524,10 +1524,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1538,8 +1538,8 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] - -mr-10004default.test1{ds=2} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] + -mr-10004default.test1{ds=2} [test1] Path -> Partition: -mr-10003default.test1{ds=1} Partition @@ -1620,8 +1620,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] - -mr-10004default.test1{ds=2} [$hdt$_0:test1] + -mr-10003default.test1{ds=1} [test1] + -mr-10004default.test1{ds=2} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1764,11 +1764,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1780,11 +1780,11 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:test2] - -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10003default.test2{ds=01_10_10, hr=01} [test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [test2] + -mr-10005default.test2{ds=1, hr=1} [test2] + -mr-10006default.test2{ds=1, hr=2} [test2] + -mr-10007default.test2{ds=1, hr=3} [test2] Path -> Partition: -mr-10003default.test2{ds=01_10_10, hr=01} Partition @@ -1987,11 +1987,11 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:test2] - -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10003default.test2{ds=01_10_10, hr=01} [test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [test2] + -mr-10005default.test2{ds=1, hr=1} [test2] + -mr-10006default.test2{ds=1, hr=2} [test2] + -mr-10007default.test2{ds=1, hr=3} [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/multiMapJoin2.q.out index 2cbef2e..46b717f 100644 --- a/ql/src/test/results/clientpositive/multiMapJoin2.q.out +++ b/ql/src/test/results/clientpositive/multiMapJoin2.q.out @@ -527,10 +527,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -761,11 +761,11 @@ STAGE PLANS: Stage: Stage-17 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + $hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + $hdt$_0:$hdt$_1:y1 TableScan alias: y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -833,11 +833,11 @@ STAGE PLANS: Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME1 + $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME1 + $INTNAME1 TableScan HashTable Sink Operator keys: @@ -919,11 +919,11 @@ STAGE PLANS: Stage: Stage-16 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME + $INTNAME TableScan HashTable Sink Operator keys: @@ -997,11 +997,11 @@ STAGE PLANS: Stage: Stage-18 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + $hdt$_1:$hdt$_2:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + $hdt$_1:$hdt$_2:y1 TableScan alias: y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1163,14 +1163,14 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + $hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + $hdt$_1:$hdt$_2:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + $hdt$_0:$hdt$_1:y1 TableScan alias: y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1185,7 +1185,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + $hdt$_1:$hdt$_2:y1 TableScan alias: y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1459,20 +1459,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -1492,11 +1488,11 @@ STAGE PLANS: Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME1 + $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME1 + $INTNAME1 TableScan HashTable Sink Operator keys: @@ -1515,22 +1511,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1582,11 +1574,11 @@ STAGE PLANS: Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME + $INTNAME TableScan HashTable Sink Operator keys: @@ -1605,22 +1597,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1648,31 +1636,27 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + $hdt$_0:$hdt$_1:x1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + $hdt$_0:$hdt$_1:x1 TableScan alias: x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1833,11 +1817,11 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + $hdt$_0:$hdt$_1:x1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + $hdt$_0:$hdt$_1:x1 TableScan alias: x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1862,20 +1846,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan alias: x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1924,24 +1904,20 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator keys: KEY._col0 (type: string) mode: mergepartial @@ -1957,24 +1933,20 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2228,11 +2200,11 @@ STAGE PLANS: Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2380,11 +2352,11 @@ STAGE PLANS: Stage: Stage-16 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index feadd5a..9a24ad8 100644 --- a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- This test query is introduced for HIVE-4968. -- First, we do not convert the join to MapJoin. EXPLAIN @@ -140,7 +140,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * @@ -188,7 +188,7 @@ POSTHOOK: Input: default@src1 406 val_406 25 66 val_66 25 98 val_98 25 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- Then, we convert the join to MapJoin. EXPLAIN SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count @@ -296,7 +296,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * diff --git a/ql/src/test/results/clientpositive/nonmr_fetch.q.out b/ql/src/test/results/clientpositive/nonmr_fetch.q.out index a4ce905..9652d7e 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch.q.out @@ -974,11 +974,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1028,10 +1028,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1081,10 +1081,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/partition_multilevels.q.out b/ql/src/test/results/clientpositive/partition_multilevels.q.out index 31862e1..c1c8778 100644 --- a/ql/src/test/results/clientpositive/partition_multilevels.q.out +++ b/ql/src/test/results/clientpositive/partition_multilevels.q.out @@ -991,11 +991,11 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2222' (type: string), level2 (type: string), level3 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: level1, level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: level1 (type: string), level2 (type: string), level3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE @@ -1579,11 +1579,11 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2222' (type: string), level2 (type: string), level3 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: level1, level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: level1 (type: string), level2 (type: string), level3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/ppd_gby.q.out b/ql/src/test/results/clientpositive/ppd_gby.q.out index 87cb907..6f8ee53 100644 --- a/ql/src/test/results/clientpositive/ppd_gby.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby.q.out @@ -33,11 +33,11 @@ STAGE PLANS: Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col0 Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(_col0) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -246,11 +246,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(_col0) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/ppd_gby2.q.out b/ql/src/test/results/clientpositive/ppd_gby2.q.out index bc00149..5fbe70f 100644 --- a/ql/src/test/results/clientpositive/ppd_gby2.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby2.q.out @@ -36,11 +36,11 @@ STAGE PLANS: Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col0 Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(_col0) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -60,22 +60,18 @@ STAGE PLANS: Filter Operator predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) + Group By Operator + aggregations: max(_col0) + keys: _col1 (type: bigint) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -164,11 +160,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(_col0) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -188,22 +184,18 @@ STAGE PLANS: Filter Operator predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) + Group By Operator + aggregations: max(_col0) + keys: _col1 (type: bigint) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/ppd_join_filter.q.out index e99986f..1781fe9 100644 --- a/ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ b/ql/src/test/results/clientpositive/ppd_join_filter.q.out @@ -136,24 +136,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -202,7 +198,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -561,24 +557,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -627,7 +619,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -976,11 +968,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) + aggregations: min(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1040,7 +1032,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1395,24 +1387,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1461,7 +1449,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_1.q.out b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_1.q.out index 7d1aff2..6f00df9 100644 --- a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_1.q.out +++ b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_1.q.out @@ -92,11 +92,11 @@ STAGE PLANS: Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string) - outputColumnNames: _col0 + outputColumnNames: l_shipdate Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: string) + aggregations: count(l_shipdate) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE @@ -253,15 +253,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__lineitem_ix_lineitem_ix_lshipdate_idx__ + alias: default__lineitem_ix_lineitem_ix_lshipdate_idx__ Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) - outputColumnNames: _col0, _count_of_l_shipdate + outputColumnNames: l_shipdate, _count_of_l_shipdate Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_shipdate) - keys: _col0 (type: string) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE @@ -900,15 +900,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: null-subquery1:$hdt$_0-subquery1:$hdt$_0:default__lineitem_ix_lineitem_ix_lshipdate_idx__ + alias: null-subquery1:$hdt$_0-subquery1:default__lineitem_ix_lineitem_ix_lshipdate_idx__ Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) - outputColumnNames: _col0, _count_of_l_shipdate + outputColumnNames: l_shipdate, _count_of_l_shipdate Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_shipdate) - keys: _col0 (type: string) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE @@ -1015,11 +1015,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) + aggregations: count(key) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1063,15 +1063,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1161,11 +1161,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: sum(_count_of_key) @@ -1213,10 +1213,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1261,11 +1261,11 @@ STAGE PLANS: alias: tbl Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: value (type: int), key (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1281,7 +1281,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int) + expressions: _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -1318,10 +1318,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 3 (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1370,10 +1370,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1471,11 +1471,11 @@ STAGE PLANS: alias: tbl Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: value (type: int), key (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1490,17 +1490,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1528,10 +1524,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 1 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1577,10 +1573,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1626,10 +1622,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1675,10 +1671,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1724,10 +1720,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1776,10 +1772,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1828,10 +1824,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 3 (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1878,20 +1874,16 @@ STAGE PLANS: Filter Operator predicate: (value = key) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) + Group By Operator + keys: key (type: int), value (type: int) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) @@ -2033,10 +2025,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -2168,22 +2160,18 @@ STAGE PLANS: Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count(key) + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2260,18 +2248,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__tblpart_tbl_part_index__ + alias: default__tblpart_tbl_part_index__ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -2369,11 +2357,11 @@ STAGE PLANS: Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) + aggregations: count(key) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -2453,15 +2441,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out index 3ee2e0f..667c683 100644 --- a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out +++ b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out @@ -176,11 +176,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ + alias: default__lineitem_ix_lineitem_ix_l_orderkey_idx__ Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), _count_of_l_orderkey (type: bigint) - outputColumnNames: _col0, _count_of_l_orderkey + outputColumnNames: l_orderkey, _count_of_l_orderkey Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_orderkey) @@ -247,11 +247,11 @@ STAGE PLANS: Statistics: Num rows: 1512 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: l_orderkey, l_partkey Statistics: Num rows: 1512 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), count(_col1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count(l_orderkey), count(l_partkey) + keys: l_orderkey (type: int), l_partkey (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1512 Data size: 12099 Basic stats: COMPLETE Column stats: NONE @@ -428,11 +428,11 @@ STAGE PLANS: Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 7 (type: int) - outputColumnNames: _col0 + outputColumnNames: l_orderkey Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) + aggregations: count(l_orderkey) + keys: l_orderkey (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE @@ -1131,11 +1131,11 @@ STAGE PLANS: Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_orderkey Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), sum(_col0) - keys: _col0 (type: int) + aggregations: count(l_orderkey), sum(l_orderkey) + keys: l_orderkey (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE @@ -1223,15 +1223,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ + alias: default__lineitem_ix_lineitem_ix_l_orderkey_idx__ Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), _count_of_l_orderkey (type: bigint) - outputColumnNames: _col0, _count_of_l_orderkey + outputColumnNames: l_orderkey, _count_of_l_orderkey Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_orderkey) - keys: _col0 (type: int) + keys: l_orderkey (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE @@ -1812,11 +1812,11 @@ STAGE PLANS: Statistics: Num rows: 756 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 756 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: bigint) + aggregations: count(_col1) + keys: _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 756 Data size: 3024 Basic stats: COMPLETE Column stats: NONE @@ -1907,18 +1907,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0:$hdt$_0:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ + alias: $hdt$_0:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (l_orderkey < 7) (type: boolean) Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), _count_of_l_orderkey (type: bigint) - outputColumnNames: _col0, _count_of_l_orderkey + outputColumnNames: l_orderkey, _count_of_l_orderkey Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_orderkey) - keys: _col0 (type: int) + keys: l_orderkey (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE @@ -1937,11 +1937,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 4 Data size: 400 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: bigint) + aggregations: count(_col1) + keys: _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 400 Basic stats: COMPLETE Column stats: NONE @@ -3404,18 +3404,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ + alias: $hdt$_0-subquery1:$hdt$_0-subquery1:default__lineitem_ix_lineitem_ix_l_orderkey_idx__ Statistics: Num rows: 26 Data size: 2604 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (l_orderkey < 7) (type: boolean) Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), _count_of_l_orderkey (type: bigint) - outputColumnNames: _col0, _count_of_l_orderkey + outputColumnNames: l_orderkey, _count_of_l_orderkey Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_orderkey) - keys: _col0 (type: int) + keys: l_orderkey (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 801 Basic stats: COMPLETE Column stats: NONE @@ -3495,18 +3495,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: $hdt$_0-subquery2:$hdt$_0-subquery2:$hdt$_0:default__lineitem_ix_lineitem_ix_l_partkey_idx__ + alias: $hdt$_0-subquery2:$hdt$_0-subquery2:default__lineitem_ix_lineitem_ix_l_partkey_idx__ Statistics: Num rows: 100 Data size: 8937 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (l_partkey < 10) (type: boolean) Statistics: Num rows: 33 Data size: 2949 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_partkey (type: int), _count_of_l_partkey (type: bigint) - outputColumnNames: _col0, _count_of_l_partkey + outputColumnNames: l_partkey, _count_of_l_partkey Statistics: Num rows: 33 Data size: 2949 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_partkey) - keys: _col0 (type: int) + keys: l_partkey (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 33 Data size: 2949 Basic stats: COMPLETE Column stats: NONE @@ -3633,20 +3633,16 @@ STAGE PLANS: Filter Operator predicate: (l_orderkey < 7) (type: boolean) Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_orderkey (type: int) + Group By Operator + keys: l_orderkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) @@ -3717,20 +3713,16 @@ STAGE PLANS: Filter Operator predicate: (l_partkey < 10) (type: boolean) Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1008 Data size: 4033 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out index df16ab2..e3ebee7 100644 --- a/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out +++ b/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out @@ -184,11 +184,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string) + aggregations: sum(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -430,10 +430,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -488,10 +488,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2682,12 +2682,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -2914,12 +2914,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -2967,12 +2967,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/selectDistinctStar.q.out b/ql/src/test/results/clientpositive/selectDistinctStar.q.out index abd6795..3f44580 100644 --- a/ql/src/test/results/clientpositive/selectDistinctStar.q.out +++ b/ql/src/test/results/clientpositive/selectDistinctStar.q.out @@ -19,10 +19,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -707,20 +707,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) @@ -2449,10 +2445,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -3133,20 +3129,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/spark/auto_join18.q.out b/ql/src/test/results/clientpositive/spark/auto_join18.q.out index 8607221..349e76d 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join18.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join18.q.out @@ -45,11 +45,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -66,10 +66,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out index df737c2..92c827e 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out @@ -47,11 +47,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -68,11 +68,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/auto_join27.q.out b/ql/src/test/results/clientpositive/spark/auto_join27.q.out index 43313e0..a325533 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join27.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join27.q.out @@ -60,20 +60,16 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan diff --git a/ql/src/test/results/clientpositive/spark/auto_join32.q.out b/ql/src/test/results/clientpositive/spark/auto_join32.q.out index 316792b..679dd79 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join32.q.out @@ -422,7 +422,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -445,20 +446,16 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col1 (type: string) + Group By Operator + keys: _col1 (type: string), _col3 (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator @@ -467,18 +464,32 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: complete + aggregations: count(_col0) + keys: _col1 (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + value expressions: _col1 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/count.q.out b/ql/src/test/results/clientpositive/spark/count.q.out index b2e9ffb..cb9eda5 100644 --- a/ql/src/test/results/clientpositive/spark/count.q.out +++ b/ql/src/test/results/clientpositive/spark/count.q.out @@ -53,11 +53,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) + aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) + keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -188,14 +188,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: a (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + value expressions: d (type: int) Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/spark/groupby5_map.q.out b/ql/src/test/results/clientpositive/spark/groupby5_map.q.out index e775921..add3094 100644 --- a/ql/src/test/results/clientpositive/spark/groupby5_map.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby5_map.q.out @@ -31,10 +31,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out index 5c58934..924ef5d 100644 --- a/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out @@ -31,10 +31,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out b/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out index 25bfbec..8b5a4c0 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out @@ -223,11 +223,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -408,11 +408,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/groupby_position.q.out b/ql/src/test/results/clientpositive/spark/groupby_position.q.out index 088428b..99223b9 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_position.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_position.q.out @@ -588,20 +588,16 @@ STAGE PLANS: Filter Operator predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/spark/groupby_resolution.q.out b/ql/src/test/results/clientpositive/spark/groupby_resolution.q.out index 9d36099..cb2c9bd 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_resolution.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_resolution.q.out @@ -20,12 +20,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: @@ -71,12 +71,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: @@ -123,10 +123,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -189,10 +189,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -254,11 +254,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -312,11 +312,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -371,11 +371,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -444,11 +444,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -620,22 +620,18 @@ STAGE PLANS: Filter Operator predicate: (key < '12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out b/ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out index 0a06c65..ce5998e 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out @@ -127,11 +127,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -306,11 +306,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/having.q.out b/ql/src/test/results/clientpositive/spark/having.q.out index da59af9..ad3ef79 100644 --- a/ql/src/test/results/clientpositive/spark/having.q.out +++ b/ql/src/test/results/clientpositive/spark/having.q.out @@ -110,22 +110,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <> 302.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -486,11 +482,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -759,22 +755,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 300.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -959,11 +951,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1227,11 +1219,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out b/ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out index f39cd57..9b284e7 100644 --- a/ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out +++ b/ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out @@ -79,11 +79,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/join18.q.out b/ql/src/test/results/clientpositive/spark/join18.q.out index c702fdf..e11ecec 100644 --- a/ql/src/test/results/clientpositive/spark/join18.q.out +++ b/ql/src/test/results/clientpositive/spark/join18.q.out @@ -48,11 +48,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -69,10 +69,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out index 18d79d3..5560226 100644 --- a/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out @@ -50,11 +50,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -71,11 +71,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/join31.q.out b/ql/src/test/results/clientpositive/spark/join31.q.out index 108a1ea..469a19f 100644 --- a/ql/src/test/results/clientpositive/spark/join31.q.out +++ b/ql/src/test/results/clientpositive/spark/join31.q.out @@ -49,20 +49,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reducer 5 Local Work: Map Reduce Local Work @@ -92,20 +88,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out b/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out index a34a399..6ca0527 100644 --- a/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out +++ b/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out @@ -553,10 +553,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) - outputColumnNames: _col0 + outputColumnNames: hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: hr (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out index 2dc710c..b0e6c6a 100644 --- a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out @@ -384,10 +384,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: double) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -473,10 +473,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -567,10 +567,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -663,11 +663,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cstring1, cstring2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) + keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -783,11 +783,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(key) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1042,16 +1042,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: key (type: string) Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out index 3b2c80e..549911c 100644 --- a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out @@ -664,22 +664,18 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 diff --git a/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out index 18e1d4e..b2221fc 100644 --- a/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out @@ -448,10 +448,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ts) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out index ed536c2..96defa6 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out @@ -215,24 +215,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -601,24 +597,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -981,11 +973,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) + aggregations: min(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1365,24 +1357,20 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: diff --git a/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx_cbo_1.q.out b/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx_cbo_1.q.out index 02e24c3..878d026 100644 --- a/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx_cbo_1.q.out +++ b/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx_cbo_1.q.out @@ -97,11 +97,11 @@ STAGE PLANS: Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string) - outputColumnNames: _col0 + outputColumnNames: l_shipdate Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: string) + aggregations: count(l_shipdate) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE @@ -264,15 +264,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: $hdt$_0:default__lineitem_ix_lineitem_ix_lshipdate_idx__ + alias: default__lineitem_ix_lineitem_ix_lshipdate_idx__ Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) - outputColumnNames: _col0, _count_of_l_shipdate + outputColumnNames: l_shipdate, _count_of_l_shipdate Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_shipdate) - keys: _col0 (type: string) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE @@ -912,15 +912,15 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: null-subquery1:$hdt$_0-subquery1:$hdt$_0:default__lineitem_ix_lineitem_ix_lshipdate_idx__ + alias: null-subquery1:$hdt$_0-subquery1:default__lineitem_ix_lineitem_ix_lshipdate_idx__ Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) - outputColumnNames: _col0, _count_of_l_shipdate + outputColumnNames: l_shipdate, _count_of_l_shipdate Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_l_shipdate) - keys: _col0 (type: string) + keys: l_shipdate (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE @@ -1004,11 +1004,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) + aggregations: count(key) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1058,15 +1058,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1168,11 +1168,11 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: sum(_count_of_key) @@ -1226,10 +1226,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1280,11 +1280,11 @@ STAGE PLANS: alias: tbl Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: value (type: int), key (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1301,7 +1301,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int) + expressions: _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -1343,10 +1343,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 3 (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1401,10 +1401,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1514,11 +1514,11 @@ STAGE PLANS: alias: tbl Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: value (type: int), key (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1534,17 +1534,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1577,10 +1573,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 1 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1632,10 +1628,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1687,10 +1683,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1742,10 +1738,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1797,10 +1793,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1855,10 +1851,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1913,10 +1909,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 3 (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1969,20 +1965,16 @@ STAGE PLANS: Filter Operator predicate: (value = key) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) + Group By Operator + keys: key (type: int), value (type: int) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator @@ -2142,10 +2134,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: int), _col1 (type: int) + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -2283,22 +2275,18 @@ STAGE PLANS: Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count(key) + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator @@ -2381,18 +2369,18 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: $hdt$_0:default__tblpart_tbl_part_index__ + alias: default__tblpart_tbl_part_index__ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -2496,11 +2484,11 @@ STAGE PLANS: Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: int) + aggregations: count(key) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 17 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -2576,15 +2564,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: $hdt$_0:default__tbl_tbl_key_idx__ + alias: default__tbl_tbl_key_idx__ Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), _count_of_key (type: bigint) - outputColumnNames: _col0, _count_of_key + outputColumnNames: key, _count_of_key Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_count_of_key) - keys: _col0 (type: int) + keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 430 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out index cb0920e..c88e53b 100644 --- a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out @@ -90,10 +90,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -146,10 +146,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/subquery_in.q.out b/ql/src/test/results/clientpositive/spark/subquery_in.q.out index bfcdaa8..b2a1681 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_in.q.out @@ -646,20 +646,16 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator @@ -829,20 +825,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator diff --git a/ql/src/test/results/clientpositive/spark/union11.q.out b/ql/src/test/results/clientpositive/spark/union11.q.out index a6b9367..ab7222e 100644 --- a/ql/src/test/results/clientpositive/spark/union11.q.out +++ b/ql/src/test/results/clientpositive/spark/union11.q.out @@ -36,17 +36,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -54,22 +56,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -78,10 +80,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -92,22 +94,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 7 Reduce Operator Tree: @@ -115,22 +117,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst3' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -155,6 +157,6 @@ POSTHOOK: query: select unionsrc.key, count(1) FROM (select 'tst1' as key, count POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -tst2 1 tst3 1 tst1 1 +tst2 1 diff --git a/ql/src/test/results/clientpositive/spark/union14.q.out b/ql/src/test/results/clientpositive/spark/union14.q.out index 0c9542b..f276d7f 100644 --- a/ql/src/test/results/clientpositive/spark/union14.q.out +++ b/ql/src/test/results/clientpositive/spark/union14.q.out @@ -42,28 +42,30 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Map 3 Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -72,10 +74,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -86,22 +88,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/spark/union15.q.out b/ql/src/test/results/clientpositive/spark/union15.q.out index cb8bc75..fc1eb83 100644 --- a/ql/src/test/results/clientpositive/spark/union15.q.out +++ b/ql/src/test/results/clientpositive/spark/union15.q.out @@ -34,17 +34,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: @@ -60,12 +62,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -73,22 +75,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -97,10 +99,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/union28.q.out b/ql/src/test/results/clientpositive/spark/union28.q.out index 59657cc..7ee06fe 100644 --- a/ql/src/test/results/clientpositive/spark/union28.q.out +++ b/ql/src/test/results/clientpositive/spark/union28.q.out @@ -73,10 +73,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/union30.q.out b/ql/src/test/results/clientpositive/spark/union30.q.out index fd907f9..12eda1d 100644 --- a/ql/src/test/results/clientpositive/spark/union30.q.out +++ b/ql/src/test/results/clientpositive/spark/union30.q.out @@ -87,10 +87,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/union33.q.out b/ql/src/test/results/clientpositive/spark/union33.q.out index 271c377..25e545c 100644 --- a/ql/src/test/results/clientpositive/spark/union33.q.out +++ b/ql/src/test/results/clientpositive/spark/union33.q.out @@ -72,11 +72,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -205,11 +205,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/union5.q.out b/ql/src/test/results/clientpositive/spark/union5.q.out index 06a5d90..af0528a 100644 --- a/ql/src/test/results/clientpositive/spark/union5.q.out +++ b/ql/src/test/results/clientpositive/spark/union5.q.out @@ -31,17 +31,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -49,22 +51,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -73,10 +75,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -87,22 +89,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -123,5 +125,5 @@ POSTHOOK: query: select unionsrc.key, count(1) FROM (select 'tst1' as key, count POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -tst2 1 tst1 1 +tst2 1 diff --git a/ql/src/test/results/clientpositive/spark/union7.q.out b/ql/src/test/results/clientpositive/spark/union7.q.out index 4a81283..181d04c 100644 --- a/ql/src/test/results/clientpositive/spark/union7.q.out +++ b/ql/src/test/results/clientpositive/spark/union7.q.out @@ -30,17 +30,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: @@ -56,12 +58,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -69,22 +71,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -93,10 +95,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/union_remove_21.q.out b/ql/src/test/results/clientpositive/spark/union_remove_21.q.out index 246594f..a4af758 100644 --- a/ql/src/test/results/clientpositive/spark/union_remove_21.q.out +++ b/ql/src/test/results/clientpositive/spark/union_remove_21.q.out @@ -81,10 +81,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out index ee5462d..c8df568 100644 --- a/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out @@ -1258,10 +1258,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ws_order_number Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out index 7e161d1..cb2d56b 100644 --- a/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -159,11 +159,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out index 322270f..52c00f9 100644 --- a/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out @@ -128,34 +128,38 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: t (type: tinyint), s (type: string) + outputColumnNames: t, s Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: tinyint) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out index 3d6a236..2255f72 100644 --- a/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out @@ -128,19 +128,19 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: t (type: tinyint), s (type: string), b (type: bigint) + outputColumnNames: t, s, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col2) - keys: _col0 (type: string), _col1 (type: tinyint) + aggregations: max(b) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized @@ -148,17 +148,21 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out index be39d0d..bbc66fc 100644 --- a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out @@ -65,20 +65,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 4 Local Work: Map Reduce Local Work @@ -270,20 +266,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 4 Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out index 6bbb6b9..3363c8b 100644 --- a/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bo, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: boolean) + aggregations: max(b) + keys: bo (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out index 3ad059c..ba33bfb 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out @@ -133,10 +133,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -439,10 +439,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -745,10 +745,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -998,10 +998,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cbigint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) + aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out index 22be1d7..122e87a 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out @@ -89,19 +89,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized @@ -109,12 +109,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -342,19 +342,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized @@ -362,12 +362,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out index 8013bfe..ec77280 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out @@ -85,19 +85,19 @@ STAGE PLANS: predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) + keys: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + key expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) sort order: +++++++ - Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized @@ -105,12 +105,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_samp(VALUE._col0), min(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_samp(VALUE._col4), stddev_pop(VALUE._col5) - keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: int), KEY._col2 (type: float), KEY._col3 (type: double), KEY._col4 (type: string), KEY._col5 (type: timestamp), KEY._col6 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) + expressions: _col2 (type: float), _col6 (type: boolean), _col3 (type: double), _col4 (type: string), _col0 (type: tinyint), _col1 (type: int), _col5 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col1)) (type: double), _col8 (type: double), (_col3 * 79.553) (type: double), (33.0 % _col2) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col3) (type: double), (- _col0) (type: tinyint), _col11 (type: double), (UDFToFloat(_col1) - _col2) (type: float), (-23 % UDFToInteger(_col0)) (type: int), (- (-26.28 - UDFToDouble(_col1))) (type: double), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out index a42c30a..3326044 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized @@ -82,12 +82,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out index a42c30a..3326044 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized @@ -82,12 +82,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out index eb8914b..59caac7 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out @@ -25,10 +25,10 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out index 3d17aba..7b4f846 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out @@ -156,10 +156,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) + aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -368,10 +368,10 @@ STAGE PLANS: Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) + aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -571,10 +571,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) + aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -753,10 +753,10 @@ STAGE PLANS: Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ctinyint, cbigint, cint, cfloat Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) + aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1882,11 +1882,11 @@ STAGE PLANS: Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: csmallint, cbigint, ctinyint Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() - keys: _col0 (type: smallint) + aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() + keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE @@ -2089,11 +2089,11 @@ STAGE PLANS: Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, cfloat Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) - keys: _col0 (type: double) + aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE @@ -2343,19 +2343,19 @@ STAGE PLANS: predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: cstring1 (type: string), ctimestamp1 (type: timestamp), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) + outputColumnNames: cstring1, ctimestamp1, cint, csmallint, ctinyint, cfloat, cdouble Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) - keys: _col0 (type: timestamp), _col1 (type: string) + aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) + keys: cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: string) + key expressions: _col0 (type: string), _col1 (type: timestamp) sort order: ++ - Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: timestamp) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized @@ -2363,12 +2363,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_pop(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), min(VALUE._col3), var_samp(VALUE._col4), var_pop(VALUE._col5), avg(VALUE._col6), var_samp(VALUE._col7), avg(VALUE._col8), min(VALUE._col9), var_pop(VALUE._col10), stddev_pop(VALUE._col11), sum(VALUE._col12) - keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) + expressions: _col1 (type: timestamp), _col0 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2676,11 +2676,11 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) - keys: _col0 (type: boolean) + aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) + keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE @@ -2915,10 +2915,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: _col0 + outputColumnNames: i Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(i) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3093,10 +3093,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3160,10 +3160,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3227,10 +3227,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3294,10 +3294,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cstring1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3361,10 +3361,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: cboolean1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cboolean1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out index 7ba64b7..316ed63 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out @@ -97,19 +97,15 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: double) + Group By Operator + aggregations: sum(_col1) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + value expressions: _col0 (type: double) Local Work: Map Reduce Local Work Execution mode: vectorized diff --git a/ql/src/test/results/clientpositive/spark/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/spark/vectorized_timestamp_funcs.q.out index 290db0d..ed1ba4b 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_timestamp_funcs.q.out @@ -644,10 +644,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), count(_col0), count() + aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -725,10 +725,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctimestamp1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -815,10 +815,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) + aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/stats_only_null.q.out b/ql/src/test/results/clientpositive/stats_only_null.q.out index 55c5970..bbd32fe 100644 --- a/ql/src/test/results/clientpositive/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/stats_only_null.q.out @@ -85,10 +85,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -135,10 +135,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/stats_ppr_all.q.out b/ql/src/test/results/clientpositive/stats_ppr_all.q.out index 5f6f5d4..7627f7a 100644 --- a/ql/src/test/results/clientpositive/stats_ppr_all.q.out +++ b/ql/src/test/results/clientpositive/stats_ppr_all.q.out @@ -77,10 +77,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 + outputColumnNames: order_amount Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum(order_amount) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -128,10 +128,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 + outputColumnNames: order_amount Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: sum(_col0) + aggregations: sum(order_amount) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL @@ -176,10 +176,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 + outputColumnNames: order_amount Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum(order_amount) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -227,10 +227,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 + outputColumnNames: order_amount Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum(order_amount) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/subq_where_serialization.q.out b/ql/src/test/results/clientpositive/subq_where_serialization.q.out index c0b2a2d..2a60036 100644 --- a/ql/src/test/results/clientpositive/subq_where_serialization.q.out +++ b/ql/src/test/results/clientpositive/subq_where_serialization.q.out @@ -20,20 +20,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) + Group By Operator + keys: key (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) diff --git a/ql/src/test/results/clientpositive/subquery_exists_having.q.out b/ql/src/test/results/clientpositive/subquery_exists_having.q.out index 14819c9..13877fc 100644 --- a/ql/src/test/results/clientpositive/subquery_exists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists_having.q.out @@ -35,22 +35,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -182,22 +178,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/subquery_in.q.out b/ql/src/test/results/clientpositive/subquery_in.q.out index f82c799..f12af57 100644 --- a/ql/src/test/results/clientpositive/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/subquery_in.q.out @@ -632,20 +632,16 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) @@ -886,20 +882,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) diff --git a/ql/src/test/results/clientpositive/subquery_in_having.q.out b/ql/src/test/results/clientpositive/subquery_in_having.q.out index da1da06..deab017 100644 --- a/ql/src/test/results/clientpositive/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_in_having.q.out @@ -73,11 +73,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -146,22 +146,18 @@ STAGE PLANS: Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -287,22 +283,18 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -362,22 +354,18 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -386,14 +374,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col2 + expressions: _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col1, _col2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) + expressions: _col2 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -454,22 +442,18 @@ STAGE PLANS: Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_size (type: int) + Group By Operator + aggregations: avg(p_size) + keys: p_mfgr (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct) + value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0) @@ -526,22 +510,18 @@ STAGE PLANS: Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: max(p_size), min(p_size) + keys: p_mfgr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + value expressions: _col1 (type: int), _col2 (type: int) Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), min(VALUE._col1) @@ -612,44 +592,36 @@ STAGE PLANS: Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_size (type: int) + Group By Operator + aggregations: avg(p_size) + keys: p_mfgr (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct) + value expressions: _col1 (type: struct) TableScan alias: b Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: max(p_size), min(p_size) + keys: p_mfgr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + value expressions: _col1 (type: int), _col2 (type: int) Reduce Operator Tree: Demux Operator Statistics: Num rows: 30 Data size: 3172 Basic stats: COMPLETE Column stats: NONE @@ -905,22 +877,18 @@ STAGE PLANS: Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1005,22 +973,18 @@ STAGE PLANS: Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1244,22 +1208,18 @@ STAGE PLANS: Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + Group By Operator + aggregations: avg(p_size) + keys: p_name (type: string), p_mfgr (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col2) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: struct) + value expressions: _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0) @@ -1267,12 +1227,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Conditional Operator diff --git a/ql/src/test/results/clientpositive/subquery_notexists.q.out b/ql/src/test/results/clientpositive/subquery_notexists.q.out index 81b4137..215d855 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists.q.out @@ -257,20 +257,16 @@ STAGE PLANS: Filter Operator predicate: (value > 'val_2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out index fd09901..637fc62 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out @@ -34,10 +34,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -186,10 +186,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -260,20 +260,16 @@ STAGE PLANS: Filter Operator predicate: (value > 'val_12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/subquery_notin.q.out b/ql/src/test/results/clientpositive/subquery_notin.q.out index fd6d53b..5563794 100644 --- a/ql/src/test/results/clientpositive/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr explain select * @@ -151,7 +151,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from src where src.key not in ( select key from src s1 where s1.key > '2') @@ -285,7 +285,7 @@ POSTHOOK: Input: default@src 199 val_199 199 val_199 2 val_2 -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select p_mfgr, b.p_name, p_size @@ -528,7 +528,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select p_mfgr, b.p_name, p_size from part b where b.p_name not in @@ -567,7 +567,7 @@ Manufacturer#4 almond azure aquamarine papaya violet 12 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join JOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[42][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- agg, non corr explain select p_name, p_size @@ -843,7 +843,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[42][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select p_name, p_size from part where part.p_size not in @@ -890,7 +890,7 @@ almond aquamarine sandy cyan gainsboro 18 almond aquamarine yellow dodger mint 7 almond azure aquamarine papaya violet 12 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join JOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- agg, corr explain select p_mfgr, p_name, p_size @@ -1202,7 +1202,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select p_mfgr, p_name, p_size from part b where b.p_size not in (select min(p_size) @@ -1243,7 +1243,7 @@ Manufacturer#5 almond antique medium spring khaki 6 Manufacturer#5 almond azure blanched chiffon midnight 23 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr, Group By in Parent Query select li.l_partkey, count(*) from lineitem li @@ -1278,7 +1278,7 @@ POSTHOOK: Input: default@lineitem 139636 1 175839 1 182052 1 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- alternate not in syntax select * from src @@ -1442,7 +1442,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@t1_v POSTHOOK: Output: database:default POSTHOOK: Output: default@T2_v -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) @@ -1587,7 +1587,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out index 775f477..9689ae3 100644 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out +++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr -- JAVA_VERSION_SPECIFIC_OUTPUT @@ -39,11 +39,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -188,7 +188,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select b.p_mfgr, min(p_retailprice) @@ -229,11 +229,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -332,11 +332,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -404,11 +404,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -445,7 +445,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr @@ -470,7 +470,7 @@ POSTHOOK: Input: default@part #### A masked pattern was here #### Manufacturer#1 1173.15 Manufacturer#2 1690.68 -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product +Warning: Shuffle Join JOIN[35][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- agg, non corr explain select b.p_mfgr, min(p_retailprice) @@ -513,11 +513,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -613,11 +613,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -659,11 +659,11 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE @@ -733,7 +733,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product +Warning: Shuffle Join JOIN[35][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product PREHOOK: query: select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 76d7503..908ad39 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -549,20 +549,16 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) @@ -658,22 +654,18 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -733,22 +725,18 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -757,14 +745,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col2 + expressions: _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col1, _col2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) + expressions: _col2 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -785,7 +773,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select p_mfgr, b.p_name, p_size diff --git a/ql/src/test/results/clientpositive/subquery_views.q.out b/ql/src/test/results/clientpositive/subquery_views.q.out index c59d86e..cfa7339 100644 --- a/ql/src/test/results/clientpositive/subquery_views.q.out +++ b/ql/src/test/results/clientpositive/subquery_views.q.out @@ -69,8 +69,8 @@ POSTHOOK: type: CREATEVIEW POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@cv2 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[52][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product PREHOOK: query: explain select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') @@ -378,8 +378,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[52][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product PREHOOK: query: select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/tez/count.q.out b/ql/src/test/results/clientpositive/tez/count.q.out index a5e6082..b474f05 100644 --- a/ql/src/test/results/clientpositive/tez/count.q.out +++ b/ql/src/test/results/clientpositive/tez/count.q.out @@ -53,11 +53,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) + aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) + keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -188,14 +188,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: a (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + value expressions: d (type: int) Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out index cd2de52..e11f3e5 100644 --- a/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out @@ -59,10 +59,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -1773,7 +1773,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -1812,10 +1812,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1875,7 +1875,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2739,10 +2739,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2757,10 +2757,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2936,10 +2936,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2954,10 +2954,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3121,20 +3121,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 10 Map Operator Tree: TableScan @@ -3142,10 +3138,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3159,20 +3155,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3180,10 +3172,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4133,7 +4125,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -4188,10 +4180,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4233,7 +4225,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -4824,10 +4816,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4842,10 +4834,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out index 4451046..63e6ade 100644 --- a/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out +++ b/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out @@ -1591,36 +1591,36 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Execution mode: vectorized Stage: Stage-2 @@ -1659,7 +1659,6 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1670,49 +1669,36 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Execution mode: vectorized - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Execution mode: vectorized Stage: Stage-2 diff --git a/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out index cb001b9..b76b4f9 100644 --- a/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out @@ -1496,35 +1496,35 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-2 Dependency Collection @@ -1562,7 +1562,6 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1573,47 +1572,35 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-2 Dependency Collection diff --git a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out index 36f1099..7d9d99e 100644 --- a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out @@ -398,28 +398,28 @@ Stage-0 compressed:false Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -464,28 +464,28 @@ Stage-0 keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -525,152 +525,149 @@ Stage-0 sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Group By Operator [GBY_41] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_40] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_39] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_41] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_40] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_39] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_37] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_36] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_38] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_37] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_55] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_34] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_30] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_53] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_29] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_28] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_36] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_55] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_34] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_30] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_53] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_29] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_27] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_28] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_54] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_25] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_20] - | | outputColumnNames:["_col0","_col1"] - | | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] - | key expressions:_col3 (type: double), _col2 (type: bigint) - | sort order:-+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [SEL_18] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_17] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_16] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_15] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_13] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_52] - | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) - | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_11] - | alias:cbo_t2 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] - key expressions:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_7] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_27] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_54] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_20] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col3 (type: double), _col2 (type: bigint) + | sort order:-+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int) + | Select Operator [SEL_17] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_16] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_14] + | aggregations:["sum(c_int)"] + | keys:key (type: string), c_int (type: int), c_float (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_52] + | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_11] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_4] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_2] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_3] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_51] predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE @@ -711,143 +708,146 @@ Stage-0 sort order:+- Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint), _col2 (type: bigint) - Group By Operator [GBY_40] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_39] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_38] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_40] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_39] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_34] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_37] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_34] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_53] - | condition map:[{"":"Left Outer Join0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_29] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_28] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_30] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_27] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_48] + predicate:((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_53] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_31] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_29] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_28] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_30] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_27] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_52] - | condition map:[{"":"Left Outer Join0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: bigint), _col1 (type: int) - | sort order:+- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_49] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_24] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_26] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_52] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: bigint), _col1 (type: int) + | sort order:+- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_49] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_19] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Group By Operator [GBY_18] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_50] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_50] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY @@ -867,129 +867,132 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_36] + File Output Operator [FS_35] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_34] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_33] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_32] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_34] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_33] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_30] - outputColumnNames:["_col0","_col1"] + value expressions:_col2 (type: bigint) + Group By Operator [GBY_31] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_29] - predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Select Operator [SEL_30] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_41] - | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col4","_col6"] - | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_24] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_23] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_25] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: bigint), _col0 (type: string) - | sort order:+- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_39] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_26] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_29] + predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_40] + | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_23] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: bigint), _col0 (type: string) + | sort order:+- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_38] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_26] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_19] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Group By Operator [GBY_18] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_40] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_39] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int PREHOOK: type: QUERY @@ -1011,150 +1014,153 @@ Stage-0 limit:-1 Stage-1 Reducer 6 - File Output Operator [FS_43] + File Output Operator [FS_42] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_42] + Select Operator [SEL_41] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_41] + Reduce Output Operator [RS_40] key expressions:_col0 (type: int) sort order:+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint), _col2 (type: bigint) - Group By Operator [GBY_39] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_38] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_37] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_38] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_33] - outputColumnNames:["_col0","_col1"] + value expressions:_col2 (type: bigint) + Group By Operator [GBY_36] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_45] - predicate:(((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 + _col4) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Select Operator [SEL_33] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_48] - | condition map:[{"":"Outer Join 0 to 1"},{"":"Outer Join 0 to 2"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col4","_col6"] - | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_30] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_27] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_26] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_28] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: double) - | sort order:- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_46] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_29] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_24] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col3 (type: double), _col2 (type: bigint) - sort order:-+ - Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col0 (type: string), _col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_44] + predicate:(((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 + _col4) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_47] + | condition map:[{"":"Outer Join 0 to 1"},{"":"Outer Join 0 to 2"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_30] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_27] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_26] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_28] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: double) + | sort order:- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_45] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col3 (type: double), _col2 (type: bigint) + sort order:-+ Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_19] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col0 (type: string), _col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + value expressions:_col3 (type: bigint) + Group By Operator [GBY_18] + aggregations:["sum(_col2)"] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_46] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY @@ -1174,141 +1180,144 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_41] + File Output Operator [FS_40] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_39] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_38] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_37] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_38] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_35] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_36] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_35] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_51] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_32] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_28] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_49] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_27] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_30] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_26] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_34] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_50] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_32] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_28] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_48] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_27] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_30] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_25] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_50] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_21] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_47] - | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_19] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_25] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_49] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_46] + | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_18] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_16] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_17] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_12] + Group By Operator [GBY_15] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Select Operator [SEL_12] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_10] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_47] + predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_10] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc PREHOOK: type: QUERY @@ -1324,27 +1333,28 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_8] + File Output Operator [FS_7] compressed:false Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] + Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_3] - aggregations:["count(1)"] + Group By Operator [GBY_2] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] + outputColumnNames:["key"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src @@ -1375,93 +1385,93 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_29] + File Output Operator [FS_26] compressed:false Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_28] + Select Operator [SEL_25] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_24] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_6] + | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_5] + | Group By Operator [GBY_4] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_4] + | Reduce Output Operator [RS_3] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_3] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_2] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] - | outputColumnNames:["_col0"] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [CONTAINS] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_24] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] + | Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_13] + | Group By Operator [GBY_11] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_11] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_9] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] - | outputColumnNames:["_col0"] + | Select Operator [SEL_8] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [CONTAINS] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_24] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_21] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_20] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_21] - aggregations:["count(_col0)"] + Group By Operator [GBY_18] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_19] - outputColumnNames:["_col0"] + Select Operator [SEL_17] + outputColumnNames:["key"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_18] + TableScan [TS_16] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE @@ -1491,125 +1501,125 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_34] + File Output Operator [FS_31] compressed:false Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_33] + Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] + Reduce Output Operator [RS_29] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_30] + Group By Operator [GBY_27] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_26] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: bigint) - | Group By Operator [GBY_28] + | Group By Operator [GBY_25] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_6] + | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_5] + | Group By Operator [GBY_4] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_4] + | Reduce Output Operator [RS_3] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_3] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_2] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] - | outputColumnNames:["_col0"] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [CONTAINS] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_26] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: bigint) - | Group By Operator [GBY_28] + | Group By Operator [GBY_25] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] + | Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_13] + | Group By Operator [GBY_11] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_11] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_9] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] - | outputColumnNames:["_col0"] + | Select Operator [SEL_8] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [CONTAINS] - Reduce Output Operator [RS_29] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_28] + Group By Operator [GBY_25] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_21] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_20] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_21] - aggregations:["count(_col0)"] + Group By Operator [GBY_18] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_19] - outputColumnNames:["_col0"] + Select Operator [SEL_17] + outputColumnNames:["key"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_18] + TableScan [TS_16] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE @@ -2122,28 +2132,28 @@ Stage-0 sort order:+ Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col2 (type: bigint) - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -2201,28 +2211,28 @@ Stage-0 keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -2385,164 +2395,161 @@ Stage-0 sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Group By Operator [GBY_43] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_42] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_41] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_43] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_42] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_41] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_39] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_38] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_40] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_39] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_60] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_36] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_32] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_58] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_31] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_34] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_30] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_38] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_60] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_36] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_32] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_58] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_31] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_34] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_29] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_30] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_59] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Filter Operator [FIL_56] - | predicate:_col0 is not null (type: boolean) - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Limit [LIM_22] - | Number of rows:5 - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_21] - | | outputColumnNames:["_col0","_col1"] - | | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_20] - | key expressions:_col3 (type: double), _col2 (type: bigint) - | sort order:-+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [SEL_19] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_18] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_16] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_57] - | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) - | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_12] - | alias:cbo_t2 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Filter Operator [FIL_54] - predicate:_col0 is not null (type: boolean) + Filter Operator [FIL_29] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_59] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Filter Operator [FIL_56] + | predicate:_col0 is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Limit [LIM_22] + | Number of rows:5 + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_21] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col3 (type: double), _col2 (type: bigint) + | sort order:-+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int) + | Select Operator [SEL_18] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_17] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_16] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_15] + | aggregations:["sum(c_int)"] + | keys:key (type: string), c_int (type: int), c_float (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_57] + | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Limit [LIM_10] - Number of rows:5 + value expressions:_col1 (type: int), _col2 (type: bigint) + Filter Operator [FIL_54] + predicate:_col0 is not null (type: boolean) Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] - key expressions:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_7] - outputColumnNames:["_col0","_col1","_col2"] + Limit [LIM_10] + Number of rows:5 + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_4] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_2] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_3] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_55] predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE @@ -2786,34 +2793,34 @@ Stage-0 | Filter Operator [FIL_60] | predicate:(((_col1 + 1) >= 0) and ((_col1 > 0) or (UDFToDouble(_col0) >= 0.0))) (type: boolean) | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] + | Select Operator [SEL_8] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_61] - | predicate:(((UDFToDouble(_col2) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col2) >= 1.0) or (_col3 >= 1))) (type: boolean) + | predicate:(((UDFToDouble(_col0) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col0) >= 1.0) or (_col3 >= 1))) (type: boolean) | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_65] - | outputColumnNames:["_col1","_col2","_col3"] + | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] + | Group By Operator [GBY_7] | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) | sort order:+++ | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] + | outputColumnNames:["_col0","_col2","_col3"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_62] | predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) @@ -2839,28 +2846,28 @@ Stage-0 key expressions:_col1 (type: double), _col0 (type: string) sort order:-+ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_25] + Group By Operator [GBY_24] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_24] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_23] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_22] + aggregations:["sum(_col2)"] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_19] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_63] predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) @@ -2928,27 +2935,27 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_14] + Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_11] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_10] outputColumnNames:["_col0"] Statistics:Num rows: 200 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | Statistics:Num rows: 200 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -2998,23 +3005,23 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_15] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_17] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 193 Data size: 51917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_11] + | Reduce Output Operator [RS_10] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -3027,37 +3034,34 @@ Stage-0 | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_10] + Select Operator [SEL_9] outputColumnNames:["_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_9] + Group By Operator [GBY_8] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_7] - keys:_col0 (type: string), _col1 (type: string) + Group By Operator [GBY_6] + keys:key (type: string), value (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_5] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_18] + predicate:(value > 'val_2') (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_19] - predicate:(value > 'val_2') (type: boolean) - Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_3] - alias:b - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo b @@ -3088,58 +3092,58 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_15] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_17] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col1 (type: string), _col0 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_10] + | Select Operator [SEL_9] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_19] + | Filter Operator [FIL_18] | predicate:(value > 'val_12') (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] key expressions:_col1 (type: string), _col0 (type: string) Map-reduce partition columns:_col1 (type: string), _col0 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] + Group By Operator [GBY_5] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] + Reduce Output Operator [RS_4] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_4] - keys:_col0 (type: string), _col1 (type: string) + Group By Operator [GBY_3] + keys:key (type: string), value (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] - outputColumnNames:["_col0","_col1"] + outputColumnNames:["key","value"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:b @@ -3382,32 +3386,32 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_28] + File Output Operator [FS_27] compressed:false Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_27] + Select Operator [SEL_26] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_38] + Merge Join Operator [MERGEJOIN_37] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: int) - | Merge Join Operator [MERGEJOIN_37] + | Merge Join Operator [MERGEJOIN_36] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_18] + | | Reduce Output Operator [RS_17] | | key expressions:_col0 (type: int) | | Map-reduce partition columns:_col0 (type: int) | | sort order:+ @@ -3416,60 +3420,57 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_34] + | | Filter Operator [FIL_33] | | predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:lineitem | | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 4 [SIMPLE_EDGE] - | Reduce Output Operator [RS_20] + | Reduce Output Operator [RS_19] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_16] + | Group By Operator [GBY_15] | keys:_col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_35] + | Filter Operator [FIL_34] | predicate:(((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:lineitem | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] + Reduce Output Operator [RS_24] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_13] + Group By Operator [GBY_12] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] - keys:_col0 (type: int) + Group By Operator [GBY_10] + keys:l_partkey (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - outputColumnNames:["_col0"] + Filter Operator [FIL_35] + predicate:l_partkey is not null (type: boolean) Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_36] - predicate:l_partkey is not null (type: boolean) - Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_8] - alias:lineitem - Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_8] + alias:lineitem + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, value, count(*) from src_cbo b @@ -3496,23 +3497,23 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_38] + File Output Operator [FS_37] compressed:false Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Merge Join Operator [MERGEJOIN_51] + Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col2 (type: bigint)","1":"_col0 (type: bigint)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_33] + | Reduce Output Operator [RS_32] | key expressions:_col2 (type: bigint) | Map-reduce partition columns:_col2 (type: bigint) | sort order:+ | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) - | Filter Operator [FIL_44] + | Filter Operator [FIL_43] | predicate:_col2 is not null (type: boolean) | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_20] @@ -3532,7 +3533,7 @@ Stage-0 | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE - | Merge Join Operator [MERGEJOIN_50] + | Merge Join Operator [MERGEJOIN_49] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] @@ -3547,7 +3548,7 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_45] + | | Filter Operator [FIL_44] | | predicate:(key > '8') (type: boolean) | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] @@ -3566,57 +3567,54 @@ Stage-0 | Select Operator [SEL_9] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_46] + | Filter Operator [FIL_45] | predicate:(key > '8') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_7] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_35] + Reduce Output Operator [RS_34] key expressions:_col0 (type: bigint) Map-reduce partition columns:_col0 (type: bigint) sort order:+ Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_31] + Group By Operator [GBY_30] keys:_col0 (type: bigint) outputColumnNames:["_col0"] Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_29] + Select Operator [SEL_28] outputColumnNames:["_col0"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] + Filter Operator [FIL_46] predicate:_col1 is not null (type: boolean) Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_49] + Select Operator [SEL_48] outputColumnNames:["_col1"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_28] + Group By Operator [GBY_27] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_26] + Group By Operator [GBY_25] aggregations:["count()"] - keys:_col0 (type: string) + keys:key (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] - outputColumnNames:["_col0"] + Filter Operator [FIL_47] + predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:(key > '9') (type: boolean) - Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_22] - alias:b - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_22] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, avg(p_size) from part @@ -3642,78 +3640,78 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_22] + File Output Operator [FS_21] compressed:false Statistics:Num rows: 3 Data size: 681 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 3 Data size: 681 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_16] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col2 (type: double) - | Group By Operator [GBY_6] - | | aggregations:["avg(VALUE._col0)"] - | | keys:KEY._col0 (type: string), KEY._col1 (type: string) - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_5] - | key expressions:_col0 (type: string), _col1 (type: string) - | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) - | sort order:++ - | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col2 (type: struct) - | Group By Operator [GBY_4] - | aggregations:["avg(_col2)"] - | keys:_col0 (type: string), _col1 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] + | Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_5] + | | aggregations:["avg(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] + | value expressions:_col2 (type: struct) + | Group By Operator [GBY_3] + | aggregations:["avg(p_size)"] + | keys:p_name (type: string), p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] | predicate:p_name is not null (type: boolean) | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:part | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_18] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_15] + Group By Operator [GBY_14] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] outputColumnNames:["_col0"] Statistics:Num rows: 13 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_25] predicate:first_value_window_0 is not null (type: boolean) Statistics:Num rows: 13 Data size: 6383 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator [PTF_11] + PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"name:":"windowingtablefunction","order by:":"_col5","partition by:":"_col2"}] Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_10] + Select Operator [SEL_9] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_8] key expressions:p_mfgr (type: string), p_size (type: int) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_name (type: string) - TableScan [TS_8] + TableScan [TS_7] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE @@ -3744,59 +3742,59 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_29] + File Output Operator [FS_28] compressed:false Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_28] + Select Operator [SEL_27] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_32] + Filter Operator [FIL_31] predicate:_col3 is null (type: boolean) Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_37] + Merge Join Operator [MERGEJOIN_36] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 605 Data size: 107690 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_17] + | Select Operator [SEL_16] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_35] + | Filter Operator [FIL_34] | predicate:(key > '2') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_15] + | TableScan [TS_14] | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) - Merge Join Operator [MERGEJOIN_36] + Merge Join Operator [MERGEJOIN_35] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] + | Reduce Output Operator [RS_18] | sort order: | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) @@ -3807,30 +3805,30 @@ Stage-0 | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_33] + Filter Operator [FIL_32] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] + Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_10] + Reduce Output Operator [RS_9] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_9] + Group By Operator [GBY_8] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] + Filter Operator [FIL_33] predicate:((key > '2') and key is null) (type: boolean) Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3865,50 +3863,50 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_27] + File Output Operator [FS_26] compressed:false Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_30] + Filter Operator [FIL_29] predicate:_col4 is null (type: boolean) Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_35] + Merge Join Operator [MERGEJOIN_34] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_17] + | Select Operator [SEL_16] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_33] + | Filter Operator [FIL_32] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_15] + | TableScan [TS_14] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: int) - Merge Join Operator [MERGEJOIN_34] + Merge Join Operator [MERGEJOIN_33] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] + | Reduce Output Operator [RS_18] | sort order: | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) @@ -3919,30 +3917,30 @@ Stage-0 | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_31] + Filter Operator [FIL_30] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] + Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_10] + Reduce Output Operator [RS_9] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_9] + Group By Operator [GBY_8] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_32] + Filter Operator [FIL_31] predicate:((p_size < 10) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3979,39 +3977,39 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_39] + File Output Operator [FS_38] compressed:false Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_38] + Select Operator [SEL_37] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_36] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: int) - Merge Join Operator [MERGEJOIN_49] + Merge Join Operator [MERGEJOIN_48] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] + | Reduce Output Operator [RS_30] | sort order: | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int) - | Filter Operator [FIL_42] + | Filter Operator [FIL_41] | predicate:_col2 is null (type: boolean) | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE - | Merge Join Operator [MERGEJOIN_48] + | Merge Join Operator [MERGEJOIN_47] | | condition map:[{"":"Left Outer Join0 to 1"}] | | keys:{"0":"UDFToDouble(_col1) (type: double)","1":"_col0 (type: double)"} | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_28] + | | Reduce Output Operator [RS_27] | | key expressions:UDFToDouble(_col1) (type: double) | | Map-reduce partition columns:UDFToDouble(_col1) (type: double) | | sort order:+ @@ -4024,73 +4022,67 @@ Stage-0 | | alias:part | | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_28] | key expressions:_col0 (type: double) | Map-reduce partition columns:_col0 (type: double) | sort order:+ | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_9] + | Group By Operator [GBY_8] | | aggregations:["avg(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_8] + | Reduce Output Operator [RS_7] | sort order: | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | value expressions:_col0 (type: struct) - | Group By Operator [GBY_7] - | aggregations:["avg(_col0)"] + | Group By Operator [GBY_6] + | aggregations:["avg(p_size)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - | Select Operator [SEL_5] - | outputColumnNames:["_col0"] + | Filter Operator [FIL_43] + | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_44] - | predicate:(p_size < 10) (type: boolean) - | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_3] - | alias:part - | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:part + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] + Reduce Output Operator [RS_31] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_23] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_45] + Filter Operator [FIL_44] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_22] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_18] + Select Operator [SEL_16] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_46] + Filter Operator [FIL_45] predicate:_col0 is null (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_17] + Group By Operator [GBY_15] | aggregations:["avg(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_16] + Reduce Output Operator [RS_14] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col0 (type: struct) - Group By Operator [GBY_15] - aggregations:["avg(_col0)"] + Group By Operator [GBY_13] + aggregations:["avg(p_size)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_13] - outputColumnNames:["_col0"] + Filter Operator [FIL_46] + predicate:(p_size < 10) (type: boolean) Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] - predicate:(p_size < 10) (type: boolean) - Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_11] - alias:part - Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_10] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select b.p_mfgr, min(p_retailprice) from part b @@ -4128,152 +4120,149 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_44] + File Output Operator [FS_40] compressed:false Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_43] + Select Operator [SEL_39] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_42] + Reduce Output Operator [RS_38] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: double) - Select Operator [SEL_41] + Select Operator [SEL_37] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_47] + Filter Operator [FIL_43] predicate:_col3 is null (type: boolean) Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_53] + Merge Join Operator [MERGEJOIN_49] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: double)","1":"_col0 (type: string), _col1 (type: double)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: NONE |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_38] + | Reduce Output Operator [RS_34] | key expressions:_col0 (type: string), _col1 (type: double) | Map-reduce partition columns:_col0 (type: string), _col1 (type: double) | sort order:++ | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_32] + | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_50] + | Filter Operator [FIL_46] | predicate:((_col2 - _col1) > 600.0) (type: boolean) | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_30] + | Group By Operator [GBY_26] | | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_25] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double), _col2 (type: double) - | Group By Operator [GBY_28] - | aggregations:["min(_col1)","max(_col1)"] - | keys:_col0 (type: string) + | Group By Operator [GBY_24] + | aggregations:["min(p_retailprice)","max(p_retailprice)"] + | keys:p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_26] - | outputColumnNames:["_col0","_col1"] + | TableScan [TS_22] + | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_25] - | alias:b - | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_33] key expressions:_col0 (type: string), _col1 (type: double) Map-reduce partition columns:_col0 (type: string), _col1 (type: double) sort order:++ Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_52] + Merge Join Operator [MERGEJOIN_48] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_34] + | Reduce Output Operator [RS_30] | sort order: | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: double) - | Group By Operator [GBY_6] + | Group By Operator [GBY_5] | | aggregations:["min(VALUE._col0)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_5] + | Reduce Output Operator [RS_4] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double) - | Group By Operator [GBY_4] - | aggregations:["min(_col1)"] - | keys:_col0 (type: string) + | Group By Operator [GBY_3] + | aggregations:["min(p_retailprice)"] + | keys:p_mfgr (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1"] + | outputColumnNames:["p_mfgr","p_retailprice"] | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_35] + Reduce Output Operator [RS_31] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_22] + Select Operator [SEL_19] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_48] + Filter Operator [FIL_44] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] + Group By Operator [GBY_18] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_19] + Group By Operator [GBY_16] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Select Operator [SEL_13] Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_49] + Filter Operator [FIL_45] predicate:((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean) Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_13] + Group By Operator [GBY_11] | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_10] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: double), _col2 (type: double) - Group By Operator [GBY_11] - aggregations:["min(_col1)","max(_col1)"] - keys:_col0 (type: string) + Group By Operator [GBY_9] + aggregations:["min(p_retailprice)","max(p_retailprice)"] + keys:p_mfgr (type: string) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - outputColumnNames:["_col0","_col1"] + Select Operator [SEL_8] + outputColumnNames:["p_mfgr","p_retailprice"] Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_8] + TableScan [TS_7] alias:b Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE @@ -4864,29 +4853,29 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_7] + File Output Operator [FS_6] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] + Reduce Output Operator [RS_3] key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions:_col5 (type: bigint) - Group By Operator [GBY_3] - aggregations:["count(DISTINCT _col1)","count(DISTINCT _col2)","sum(_col3)"] - keys:_col0 (type: int), _col1 (type: int), _col2 (type: int) + Group By Operator [GBY_2] + aggregations:["count(DISTINCT b)","count(DISTINCT c)","sum(d)"] + keys:a (type: int), b (type: int), c (type: int) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2","_col3"] + outputColumnNames:["a","b","c","d"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd @@ -4906,24 +4895,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_6] + File Output Operator [FS_5] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_4] + Group By Operator [GBY_3] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_3] - key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) - Map-reduce partition columns:_col0 (type: int) + Reduce Output Operator [RS_2] + key expressions:a (type: int), b (type: int), c (type: int) + Map-reduce partition columns:a (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: int) + value expressions:d (type: int) Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2","_col3"] + outputColumnNames:["a","b","c","d"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd @@ -8013,32 +8002,32 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_8] + File Output Operator [FS_7] compressed:true Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_6] + Group By Operator [GBY_5] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] + Reduce Output Operator [RS_4] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_4] + Group By Operator [GBY_3] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_3] - key expressions:_col0 (type: string), _col1 (type: string) + Reduce Output Operator [RS_2] + key expressions:key (type: string), value (type: string) Map-reduce partition columns:rand() (type: double) sort order:++ Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1"] + outputColumnNames:["key","value"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src diff --git a/ql/src/test/results/clientpositive/tez/explainuser_2.q.out b/ql/src/test/results/clientpositive/tez/explainuser_2.q.out index 8156789..57fcc3c 100644 --- a/ql/src/test/results/clientpositive/tez/explainuser_2.q.out +++ b/ql/src/test/results/clientpositive/tez/explainuser_2.q.out @@ -335,245 +335,248 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_68] compressed:false Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Limit [LIM_68] + Limit [LIM_67] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_66] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_64] - | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] - | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] - | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] - key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) - Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] - aggregations:["count(_col3)","count(_col4)","count(_col5)"] - keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Select Operator [SEL_64] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_63] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_62] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_60] + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_61] + aggregations:["count(_col13)","count(_col21)","count(_col3)"] + keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_111] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col1 (type: string), _col3 (type: string)","1":"_col15 (type: string), _col17 (type: string)"} - | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] - | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_58] - | key expressions:_col15 (type: string), _col17 (type: string) - | Map-reduce partition columns:_col15 (type: string), _col17 (type: string) - | sort order:++ - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) - | Select Operator [SEL_49] - | outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_110] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"0":"_col4 (type: string), _col6 (type: string)","1":"_col2 (type: string), _col4 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] - | | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | |<-Reducer 10 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_45] - | | key expressions:_col4 (type: string), _col6 (type: string) - | | Map-reduce partition columns:_col4 (type: string), _col6 (type: string) - | | sort order:++ - | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string) - | | Merge Join Operator [MERGEJOIN_108] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col3 (type: string)","1":"_col1 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 14 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_42] - | | | key expressions:_col1 (type: string) - | | | Map-reduce partition columns:_col1 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | Select Operator [SEL_16] - | | | outputColumnNames:["_col1"] - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_102] - | | | predicate:((key = 'src1key') and value is not null) (type: boolean) - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_14] - | | | alias:src1 - | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | |<-Reducer 9 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_40] - | | key expressions:_col3 (type: string) - | | Map-reduce partition columns:_col3 (type: string) - | | sort order:+ - | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_107] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 13 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_37] - | | | key expressions:_col0 (type: string) - | | | Map-reduce partition columns:_col0 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | Select Operator [SEL_13] - | | | outputColumnNames:["_col0"] - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_101] - | | | predicate:((value = 'd1value') and key is not null) (type: boolean) - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_11] - | | | alias:d1 - | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | |<-Reducer 8 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_35] - | | key expressions:_col2 (type: string) - | | Map-reduce partition columns:_col2 (type: string) - | | sort order:+ - | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_106] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col1 (type: string)","1":"_col3 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 12 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_32] - | | | key expressions:_col3 (type: string) - | | | Map-reduce partition columns:_col3 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) - | | | Select Operator [SEL_10] - | | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_100] - | | | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_8] - | | | alias:ss - | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 7 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_30] - | | key expressions:_col1 (type: string) - | | Map-reduce partition columns:_col1 (type: string) - | | sort order:+ - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_7] - | | outputColumnNames:["_col1"] - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_99] - | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_5] - | | alias:srcpart - | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - | |<-Reducer 16 [SIMPLE_EDGE] - | Reduce Output Operator [RS_47] - | key expressions:_col2 (type: string), _col4 (type: string) - | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col3 (type: string), _col5 (type: string) - | Merge Join Operator [MERGEJOIN_109] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 15 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_24] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - | | Select Operator [SEL_19] - | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] - | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_17] - | | alias:sr - | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | |<-Map 17 [SIMPLE_EDGE] - | Reduce Output Operator [RS_26] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_22] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_20] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_56] - key expressions:_col1 (type: string), _col3 (type: string) - Map-reduce partition columns:_col1 (type: string), _col3 (type: string) - sort order:++ - Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - value expressions:_col2 (type: string) - Merge Join Operator [MERGEJOIN_105] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col3"] - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_51] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) - | Select Operator [SEL_1] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_97] - | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_0] - | alias:cs - | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_53] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_4] - outputColumnNames:["_col0"] + Select Operator [SEL_60] + outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: string), _col3 (type: string)","1":"_col15 (type: string), _col17 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_58] + | key expressions:_col15 (type: string), _col17 (type: string) + | Map-reduce partition columns:_col15 (type: string), _col17 (type: string) + | sort order:++ + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) + | Select Operator [SEL_49] + | outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | Merge Join Operator [MERGEJOIN_109] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col4 (type: string), _col6 (type: string)","1":"_col2 (type: string), _col4 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] + | | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 10 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_45] + | | key expressions:_col4 (type: string), _col6 (type: string) + | | Map-reduce partition columns:_col4 (type: string), _col6 (type: string) + | | sort order:++ + | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string) + | | Merge Join Operator [MERGEJOIN_107] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col3 (type: string)","1":"_col1 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 14 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_42] + | | | key expressions:_col1 (type: string) + | | | Map-reduce partition columns:_col1 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | Select Operator [SEL_16] + | | | outputColumnNames:["_col1"] + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_101] + | | | predicate:((key = 'src1key') and value is not null) (type: boolean) + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_14] + | | | alias:src1 + | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | | |<-Reducer 9 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_40] + | | key expressions:_col3 (type: string) + | | Map-reduce partition columns:_col3 (type: string) + | | sort order:+ + | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col4 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_106] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 13 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_37] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | Select Operator [SEL_13] + | | | outputColumnNames:["_col0"] + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_100] + | | | predicate:((value = 'd1value') and key is not null) (type: boolean) + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_11] + | | | alias:d1 + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Reducer 8 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_35] + | | key expressions:_col2 (type: string) + | | Map-reduce partition columns:_col2 (type: string) + | | sort order:+ + | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_105] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col1 (type: string)","1":"_col3 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_32] + | | | key expressions:_col3 (type: string) + | | | Map-reduce partition columns:_col3 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + | | | Select Operator [SEL_10] + | | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_99] + | | | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_8] + | | | alias:ss + | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 7 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_30] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_7] + | | outputColumnNames:["_col1"] + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_98] + | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_5] + | | alias:srcpart + | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 16 [SIMPLE_EDGE] + | Reduce Output Operator [RS_47] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Merge Join Operator [MERGEJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 15 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_19] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_102] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_17] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Map 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_26] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_22] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_20] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_56] + key expressions:_col1 (type: string), _col3 (type: string) + Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + sort order:++ + Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: string) + Merge Join Operator [MERGEJOIN_104] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3"] + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_51] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_96] + | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:cs + | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_53] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_98] - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + Select Operator [SEL_4] + outputColumnNames:["_col0"] Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_2] - alias:d1 - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_97] + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:d1 + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value @@ -1522,199 +1525,202 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_68] compressed:false Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Limit [LIM_68] + Limit [LIM_67] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_66] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_64] - | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] - | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] - | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE - |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] - key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) - Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] - aggregations:["count(_col3)","count(_col4)","count(_col5)"] - keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Select Operator [SEL_64] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_63] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_62] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_60] + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_61] + aggregations:["count(_col13)","count(_col21)","count(_col3)"] + keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_111] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 3":"_col15 (type: string), _col17 (type: string)"} - | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] - | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - |<-Map 2 [BROADCAST_EDGE] - | Reduce Output Operator [RS_56] - | key expressions:_col1 (type: string), _col3 (type: string) - | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col2 (type: string) - | Map Join Operator [MAPJOIN_105] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} - | | outputColumnNames:["_col1","_col2","_col3"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 1 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_51] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) - | | Select Operator [SEL_1] - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_97] - | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_0] - | | alias:cs - | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_4] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_98] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_2] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_49] - outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] - Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_110] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col4 (type: string), _col6 (type: string)","Map 10":"_col2 (type: string), _col4 (type: string)"} - | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - |<-Map 10 [BROADCAST_EDGE] - | Reduce Output Operator [RS_47] - | key expressions:_col2 (type: string), _col4 (type: string) - | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col3 (type: string), _col5 (type: string) - | Map Join Operator [MAPJOIN_109] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"Map 9":"_col0 (type: string)","Map 10":"_col0 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 9 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_24] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - | | Select Operator [SEL_19] - | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] - | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_17] - | | alias:sr - | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_22] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_20] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_108] + Select Operator [SEL_60] + outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 3":"_col15 (type: string), _col17 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_56] + | key expressions:_col1 (type: string), _col3 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col2 (type: string) + | Map Join Operator [MAPJOIN_104] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_51] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_96] + | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_0] + | | alias:cs + | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_97] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_49] + outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_109] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col3 (type: string)","Map 8":"_col1 (type: string)"} - | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - |<-Map 8 [BROADCAST_EDGE] - | Reduce Output Operator [RS_42] - | key expressions:_col1 (type: string) - | Map-reduce partition columns:_col1 (type: string) - | sort order:+ - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_16] - | outputColumnNames:["_col1"] - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_102] - | predicate:((key = 'src1key') and value is not null) (type: boolean) - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_14] - | alias:src1 - | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | keys:{"Map 3":"_col4 (type: string), _col6 (type: string)","Map 10":"_col2 (type: string), _col4 (type: string)"} + | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [BROADCAST_EDGE] + | Reduce Output Operator [RS_47] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Map Join Operator [MAPJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 9":"_col0 (type: string)","Map 10":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 9 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_19] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_102] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_17] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_22] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_20] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_107] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col2 (type: string)","Map 7":"_col0 (type: string)"} + | keys:{"Map 3":"_col3 (type: string)","Map 8":"_col1 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - |<-Map 7 [BROADCAST_EDGE] - | Reduce Output Operator [RS_37] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) + | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [BROADCAST_EDGE] + | Reduce Output Operator [RS_42] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) | sort order:+ - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_13] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_16] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_101] - | predicate:((value = 'd1value') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_11] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | predicate:((key = 'src1key') and value is not null) (type: boolean) + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_14] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_106] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col1 (type: string)","Map 6":"_col3 (type: string)"} + | keys:{"Map 3":"_col2 (type: string)","Map 7":"_col0 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - |<-Map 6 [BROADCAST_EDGE] - | Reduce Output Operator [RS_32] - | key expressions:_col3 (type: string) - | Map-reduce partition columns:_col3 (type: string) + | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [BROADCAST_EDGE] + | Reduce Output Operator [RS_37] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) | sort order:+ - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) - | Select Operator [SEL_10] - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_13] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_100] - | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_8] - | alias:ss - | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_7] - outputColumnNames:["_col1"] - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_99] - predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + | predicate:((value = 'd1value') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_11] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_105] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col1 (type: string)","Map 6":"_col3 (type: string)"} + | outputColumnNames:["_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [BROADCAST_EDGE] + | Reduce Output Operator [RS_32] + | key expressions:_col3 (type: string) + | Map-reduce partition columns:_col3 (type: string) + | sort order:+ + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + | Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_99] + | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:ss + | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_7] + outputColumnNames:["_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_5] - alias:srcpart - Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_98] + predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_5] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value diff --git a/ql/src/test/results/clientpositive/tez/having.q.out b/ql/src/test/results/clientpositive/tez/having.q.out index 80f02de..31de85a 100644 --- a/ql/src/test/results/clientpositive/tez/having.q.out +++ b/ql/src/test/results/clientpositive/tez/having.q.out @@ -110,22 +110,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <> 302.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -486,11 +482,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -759,22 +755,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 300.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -959,11 +951,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1227,11 +1219,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out index 01ccae7..14d57e3 100644 --- a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out @@ -384,10 +384,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: double) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -473,10 +473,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -567,10 +567,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -663,11 +663,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cstring1, cstring2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) + keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -783,11 +783,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(key) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1042,16 +1042,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: key (type: string) Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out index 23df010..0bf689b 100644 --- a/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out @@ -617,22 +617,18 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Map 3 Map Operator Tree: TableScan diff --git a/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out index aaea52e..f43440e 100644 --- a/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out @@ -448,10 +448,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ts) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/metadataonly1.q.out b/ql/src/test/results/clientpositive/tez/metadataonly1.q.out index 927b686..b55cb7e 100644 --- a/ql/src/test/results/clientpositive/tez/metadataonly1.q.out +++ b/ql/src/test/results/clientpositive/tez/metadataonly1.q.out @@ -48,10 +48,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -155,10 +155,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -301,11 +301,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT ds) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -448,10 +448,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -736,10 +736,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1017,11 +1017,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1261,11 +1261,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(hr) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1500,10 +1500,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1746,11 +1746,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/mrr.q.out b/ql/src/test/results/clientpositive/tez/mrr.q.out index efbd02d..faace21 100644 --- a/ql/src/test/results/clientpositive/tez/mrr.q.out +++ b/ql/src/test/results/clientpositive/tez/mrr.q.out @@ -27,11 +27,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1304,22 +1304,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Map 6 Map Operator Tree: TableScan @@ -1328,22 +1324,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Map 9 Map Operator Tree: TableScan @@ -1352,22 +1344,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 10 Reduce Operator Tree: Group By Operator @@ -1692,22 +1680,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Map 3 Map Operator Tree: TableScan diff --git a/ql/src/test/results/clientpositive/tez/selectDistinctStar.q.out b/ql/src/test/results/clientpositive/tez/selectDistinctStar.q.out index 0a091da..22ac115 100644 --- a/ql/src/test/results/clientpositive/tez/selectDistinctStar.q.out +++ b/ql/src/test/results/clientpositive/tez/selectDistinctStar.q.out @@ -24,10 +24,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -718,20 +718,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator @@ -2474,10 +2470,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -3164,20 +3160,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/tez/stats_only_null.q.out b/ql/src/test/results/clientpositive/tez/stats_only_null.q.out index eabda89..0412052 100644 --- a/ql/src/test/results/clientpositive/tez/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/tez/stats_only_null.q.out @@ -90,10 +90,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -146,10 +146,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/subquery_in.q.out b/ql/src/test/results/clientpositive/tez/subquery_in.q.out index 2b1237b..add2c52 100644 --- a/ql/src/test/results/clientpositive/tez/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/tez/subquery_in.q.out @@ -646,20 +646,16 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -829,20 +825,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator diff --git a/ql/src/test/results/clientpositive/tez/tez_dml.q.out b/ql/src/test/results/clientpositive/tez/tez_dml.q.out index ae85292..728eb6b 100644 --- a/ql/src/test/results/clientpositive/tez/tez_dml.q.out +++ b/ql/src/test/results/clientpositive/tez/tez_dml.q.out @@ -30,11 +30,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: string) + aggregations: count(value) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/union5.q.out b/ql/src/test/results/clientpositive/tez/union5.q.out index 327195c..9939b7d 100644 --- a/ql/src/test/results/clientpositive/tez/union5.q.out +++ b/ql/src/test/results/clientpositive/tez/union5.q.out @@ -31,33 +31,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -65,22 +69,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 4 Reduce Operator Tree: @@ -89,10 +93,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -103,22 +107,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Union 3 Vertex: Union 3 diff --git a/ql/src/test/results/clientpositive/tez/union7.q.out b/ql/src/test/results/clientpositive/tez/union7.q.out index c5ece62..7a02993 100644 --- a/ql/src/test/results/clientpositive/tez/union7.q.out +++ b/ql/src/test/results/clientpositive/tez/union7.q.out @@ -31,17 +31,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: @@ -57,12 +59,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -70,22 +72,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 4 Reduce Operator Tree: @@ -94,10 +96,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out index cab3a28..bcae2fc 100644 --- a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out @@ -14059,11 +14059,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -14202,11 +14202,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/tez/vector_aggregate_9.q.out index 382380e..d6a8517 100644 --- a/ql/src/test/results/clientpositive/tez/vector_aggregate_9.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_aggregate_9.q.out @@ -125,10 +125,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dc (type: decimal(38,18)) - outputColumnNames: _col0 + outputColumnNames: dc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), sum(_col0), avg(_col0) + aggregations: min(dc), max(dc), sum(dc), avg(dc) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out index 8dcd40d..ebc0466 100644 --- a/ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out @@ -221,11 +221,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bin (type: binary) - outputColumnNames: _col0 + outputColumnNames: bin Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: binary) + keys: bin (type: binary) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out index 95863a3..f46bcd9 100644 --- a/ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out @@ -1258,10 +1258,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ws_order_number Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out index 2e9c232..13e047b 100644 --- a/ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -159,11 +159,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_decimal_precision.q.out b/ql/src/test/results/clientpositive/tez/vector_decimal_precision.q.out index 4e1b654..8b6614e 100644 --- a/ql/src/test/results/clientpositive/tez/vector_decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_decimal_precision.q.out @@ -567,10 +567,10 @@ STAGE PLANS: Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_decimal_udf.q.out b/ql/src/test/results/clientpositive/tez/vector_decimal_udf.q.out index 13f0de2..dc929d3 100644 --- a/ql/src/test/results/clientpositive/tez/vector_decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_decimal_udf.q.out @@ -1639,11 +1639,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum(key), count(key), avg(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2317,11 +2317,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev(key), variance(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2403,11 +2403,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp(key), var_samp(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2554,10 +2554,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2621,10 +2621,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2688,10 +2688,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out index 1671ddf..6c31294 100644 --- a/ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out @@ -128,34 +128,38 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: t (type: tinyint), s (type: string) + outputColumnNames: t, s Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: tinyint) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out index 9b9dcdd..6aa39f1 100644 --- a/ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out @@ -128,19 +128,19 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: t (type: tinyint), s (type: string), b (type: bigint) + outputColumnNames: t, s, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col2) - keys: _col0 (type: string), _col1 (type: tinyint) + aggregations: max(b) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized @@ -148,17 +148,21 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out index ba2fb77..814ee39 100644 --- a/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out @@ -245,10 +245,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -369,10 +369,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/tez/vector_grouping_sets.q.out index 688d2ac..6d39d02 100644 --- a/ql/src/test/results/clientpositive/tez/vector_grouping_sets.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_grouping_sets.q.out @@ -126,10 +126,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE @@ -207,10 +207,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out index e7fec82..d33b0ed 100644 --- a/ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out @@ -109,20 +109,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 4 Reduce Operator Tree: Group By Operator @@ -252,20 +248,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reducer 4 Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out index af15925..3712b16 100644 --- a/ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bo, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: boolean) + aggregations: max(b) + keys: bo (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/tez/vector_outer_join2.q.out index f9159eb..2315cb9 100644 --- a/ql/src/test/results/clientpositive/tez/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_outer_join2.q.out @@ -227,19 +227,15 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 24 Data size: 5361 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 24 Data size: 5361 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col0) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count(), sum(_col1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map 3 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/tez/vector_partition_diff_num_cols.q.out b/ql/src/test/results/clientpositive/tez/vector_partition_diff_num_cols.q.out index 65b2ff1..c9ceeb4 100644 --- a/ql/src/test/results/clientpositive/tez/vector_partition_diff_num_cols.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_partition_diff_num_cols.q.out @@ -100,10 +100,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -226,10 +226,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -353,10 +353,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -461,10 +461,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -575,10 +575,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out index 4b45ac1..70d415d 100644 --- a/ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out @@ -379,11 +379,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -1159,11 +1159,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1963,11 +1963,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: fl_time Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: timestamp) + keys: fl_time (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out index 528c2cb..14aa777 100644 --- a/ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out @@ -44,22 +44,18 @@ STAGE PLANS: Filter Operator predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2, _col3 + Group By Operator + aggregations: min(cdecimal1) + keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - sort order: ++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(20,10)) + value expressions: _col4 (type: decimal(20,10)) Execution mode: vectorized Reducer 2 Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out index 18e042d..4580fe0 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out @@ -133,10 +133,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -439,10 +439,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -745,10 +745,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -998,10 +998,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cbigint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) + aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorization_13.q.out b/ql/src/test/results/clientpositive/tez/vectorization_13.q.out index 6214640..d153dd9 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_13.q.out @@ -89,19 +89,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized @@ -109,12 +109,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -342,19 +342,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized @@ -362,12 +362,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/tez/vectorization_15.q.out b/ql/src/test/results/clientpositive/tez/vectorization_15.q.out index 1858cb0..c134c0b 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_15.q.out @@ -85,19 +85,19 @@ STAGE PLANS: predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) + keys: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + key expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) sort order: +++++++ - Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized @@ -105,12 +105,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_samp(VALUE._col0), min(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_samp(VALUE._col4), stddev_pop(VALUE._col5) - keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: int), KEY._col2 (type: float), KEY._col3 (type: double), KEY._col4 (type: string), KEY._col5 (type: timestamp), KEY._col6 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) + expressions: _col2 (type: float), _col6 (type: boolean), _col3 (type: double), _col4 (type: string), _col0 (type: tinyint), _col1 (type: int), _col5 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col1)) (type: double), _col8 (type: double), (_col3 * 79.553) (type: double), (33.0 % _col2) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col3) (type: double), (- _col0) (type: tinyint), _col11 (type: double), (UDFToFloat(_col1) - _col2) (type: float), (-23 % UDFToInteger(_col0)) (type: int), (- (-26.28 - UDFToDouble(_col1))) (type: double), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/tez/vectorization_16.q.out b/ql/src/test/results/clientpositive/tez/vectorization_16.q.out index bfed7d1..1b39796 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_16.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized @@ -82,12 +82,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/tez/vectorization_9.q.out b/ql/src/test/results/clientpositive/tez/vectorization_9.q.out index bfed7d1..1b39796 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_9.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized @@ -82,12 +82,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out b/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out index 1c5b51f..33f7ed9 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out @@ -251,10 +251,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -342,10 +342,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -469,11 +469,11 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, ctinyint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum(ctinyint) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out index e203bfd..c9c301e 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out @@ -25,10 +25,10 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out index 59b457a..99171f2 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out @@ -156,10 +156,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) + aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -368,10 +368,10 @@ STAGE PLANS: Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) + aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -571,10 +571,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) + aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -753,10 +753,10 @@ STAGE PLANS: Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ctinyint, cbigint, cint, cfloat Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) + aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1882,11 +1882,11 @@ STAGE PLANS: Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: csmallint, cbigint, ctinyint Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() - keys: _col0 (type: smallint) + aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() + keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE @@ -2089,11 +2089,11 @@ STAGE PLANS: Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, cfloat Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) - keys: _col0 (type: double) + aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE @@ -2343,19 +2343,19 @@ STAGE PLANS: predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: cstring1 (type: string), ctimestamp1 (type: timestamp), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) + outputColumnNames: cstring1, ctimestamp1, cint, csmallint, ctinyint, cfloat, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) - keys: _col0 (type: timestamp), _col1 (type: string) + aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) + keys: cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: string) + key expressions: _col0 (type: string), _col1 (type: timestamp) sort order: ++ - Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: timestamp) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized @@ -2363,12 +2363,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_pop(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), min(VALUE._col3), var_samp(VALUE._col4), var_pop(VALUE._col5), avg(VALUE._col6), var_samp(VALUE._col7), avg(VALUE._col8), min(VALUE._col9), var_pop(VALUE._col10), stddev_pop(VALUE._col11), sum(VALUE._col12) - keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) + expressions: _col1 (type: timestamp), _col0 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2676,11 +2676,11 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) - keys: _col0 (type: boolean) + aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) + keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE @@ -2915,10 +2915,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: _col0 + outputColumnNames: i Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(i) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3093,10 +3093,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3160,10 +3160,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3227,10 +3227,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3294,10 +3294,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cstring1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3361,10 +3361,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: cboolean1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cboolean1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out index 23798e0..468802c 100644 --- a/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out @@ -38,10 +38,10 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: a (type: int) mode: final outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -109,10 +109,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: cint (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out index b253508..f0ddc5b 100644 --- a/ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out @@ -59,10 +59,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -1793,7 +1793,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -1832,10 +1832,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1897,7 +1897,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2773,10 +2773,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2791,10 +2791,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2973,10 +2973,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2991,10 +2991,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3161,20 +3161,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 10 Map Operator Tree: TableScan @@ -3182,10 +3178,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3199,20 +3195,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3220,10 +3212,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4186,7 +4178,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -4241,10 +4233,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4288,7 +4280,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -4889,10 +4881,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4907,10 +4899,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out index 01a36e5..74be17b 100644 --- a/ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out @@ -75,19 +75,15 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col1 (type: double) + Group By Operator + aggregations: sum(_col1) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + value expressions: _col0 (type: double) Execution mode: vectorized Map 4 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out b/ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out index 8118139..966f131 100644 --- a/ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out @@ -135,11 +135,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: ctinyint, cint, csmallint, cstring1, cfloat, cdouble Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) - keys: _col0 (type: tinyint) + aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out index b285a4f..cb47605 100644 --- a/ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out @@ -644,10 +644,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), count(_col0), count() + aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -725,10 +725,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctimestamp1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -815,10 +815,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) + aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/udf8.q.out b/ql/src/test/results/clientpositive/udf8.q.out index 8276ba9..1f43e23 100644 --- a/ql/src/test/results/clientpositive/udf8.q.out +++ b/ql/src/test/results/clientpositive/udf8.q.out @@ -43,10 +43,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: string) - outputColumnNames: _col0 + outputColumnNames: c1 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0), count(_col0) + aggregations: avg(c1), sum(c1), count(c1) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/udf_count.q.out b/ql/src/test/results/clientpositive/udf_count.q.out index c9a596f..430893d 100644 --- a/ql/src/test/results/clientpositive/udf_count.q.out +++ b/ql/src/test/results/clientpositive/udf_count.q.out @@ -29,10 +29,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -86,11 +86,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -144,11 +144,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0, _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT key, value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/union11.q.out b/ql/src/test/results/clientpositive/union11.q.out index 0d0b8fa..55d593d 100644 --- a/ql/src/test/results/clientpositive/union11.q.out +++ b/ql/src/test/results/clientpositive/union11.q.out @@ -31,28 +31,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -65,48 +67,48 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -114,10 +116,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -128,28 +130,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -162,28 +166,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst3' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union14.q.out b/ql/src/test/results/clientpositive/union14.q.out index 7a7e938..eabdaa8 100644 --- a/ql/src/test/results/clientpositive/union14.q.out +++ b/ql/src/test/results/clientpositive/union14.q.out @@ -27,28 +27,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -67,33 +69,33 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -101,10 +103,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union15.q.out b/ql/src/test/results/clientpositive/union15.q.out index 148f25f..be7f966 100644 --- a/ql/src/test/results/clientpositive/union15.q.out +++ b/ql/src/test/results/clientpositive/union15.q.out @@ -29,28 +29,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -63,18 +65,18 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan alias: s2 @@ -84,18 +86,18 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan alias: s2 @@ -105,18 +107,18 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -124,10 +126,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union28.q.out b/ql/src/test/results/clientpositive/union28.q.out index 38f8ee6..c3789d0 100644 --- a/ql/src/test/results/clientpositive/union28.q.out +++ b/ql/src/test/results/clientpositive/union28.q.out @@ -53,10 +53,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -193,10 +193,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/union30.q.out b/ql/src/test/results/clientpositive/union30.q.out index 894ed49..26a27c8 100644 --- a/ql/src/test/results/clientpositive/union30.q.out +++ b/ql/src/test/results/clientpositive/union30.q.out @@ -67,10 +67,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -228,10 +228,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/union33.q.out b/ql/src/test/results/clientpositive/union33.q.out index 308cd8b..17e0844 100644 --- a/ql/src/test/results/clientpositive/union33.q.out +++ b/ql/src/test/results/clientpositive/union33.q.out @@ -53,11 +53,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -268,11 +268,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/union5.q.out b/ql/src/test/results/clientpositive/union5.q.out index 75389f8..f57c60a 100644 --- a/ql/src/test/results/clientpositive/union5.q.out +++ b/ql/src/test/results/clientpositive/union5.q.out @@ -26,28 +26,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -60,33 +62,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -94,10 +96,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,28 +110,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union7.q.out b/ql/src/test/results/clientpositive/union7.q.out index 592f073..162fe36 100644 --- a/ql/src/test/results/clientpositive/union7.q.out +++ b/ql/src/test/results/clientpositive/union7.q.out @@ -25,28 +25,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -59,18 +61,18 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan alias: s2 @@ -80,18 +82,18 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -99,10 +101,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/unionDistinct_1.q.out index 8d74fbe..81c46da 100644 --- a/ql/src/test/results/clientpositive/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/unionDistinct_1.q.out @@ -15008,11 +15008,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -15172,11 +15172,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/union_remove_21.q.out b/ql/src/test/results/clientpositive/union_remove_21.q.out index 4743d8d..c956940 100644 --- a/ql/src/test/results/clientpositive/union_remove_21.q.out +++ b/ql/src/test/results/clientpositive/union_remove_21.q.out @@ -76,10 +76,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -121,10 +121,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out index f81816c..72dc004 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out @@ -120,10 +120,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dc (type: decimal(38,18)) - outputColumnNames: _col0 + outputColumnNames: dc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), sum(_col0), avg(_col0) + aggregations: min(dc), max(dc), sum(dc), avg(dc) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out index 1175cb8..cd4e4cc 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out @@ -53,10 +53,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt (type: int), greg_dt (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: dt, greg_dt Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), max(_col1) + aggregations: max(dt), max(greg_dt) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out index c3e4d52..7da8ae0 100644 --- a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out +++ b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out @@ -213,11 +213,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bin (type: binary) - outputColumnNames: _col0 + outputColumnNames: bin Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: binary) + keys: bin (type: binary) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/vector_count_distinct.q.out index b87b2c7..0d491b3 100644 --- a/ql/src/test/results/clientpositive/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/vector_count_distinct.q.out @@ -1252,11 +1252,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ws_order_number Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: count(DISTINCT ws_order_number) + keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out index 02c1c83..cf975d1 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out @@ -49,11 +49,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -147,11 +147,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out index 16f2e3f..f2aaf8d 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out @@ -562,10 +562,10 @@ STAGE PLANS: Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_decimal_udf.q.out b/ql/src/test/results/clientpositive/vector_decimal_udf.q.out index 91a585c..cfd2a55 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_udf.q.out @@ -1574,11 +1574,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum(key), count(key), avg(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2239,11 +2239,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev(key), variance(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2319,11 +2319,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp(key), var_samp(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2458,10 +2458,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2518,10 +2518,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2578,10 +2578,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/vector_distinct_2.q.out index 4153155..6b552be 100644 --- a/ql/src/test/results/clientpositive/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/vector_distinct_2.q.out @@ -123,33 +123,37 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: t (type: tinyint), s (type: string) + outputColumnNames: t, s Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: tinyint) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/vector_groupby_3.q.out index af7cb58..ffe42a7 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_3.q.out @@ -123,36 +123,40 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: t (type: tinyint), s (type: string), b (type: bigint) + outputColumnNames: t, s, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col2) - keys: _col0 (type: string), _col1 (type: tinyint) + aggregations: max(b) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out index edcb0b3..331ba4f 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out @@ -240,10 +240,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -357,10 +357,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out index 69d6187..32e95c0 100644 --- a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out +++ b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out @@ -121,10 +121,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE @@ -196,10 +196,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out index 2f986c2..2f8efd5 100644 --- a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out @@ -25,14 +25,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -44,7 +44,7 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out index fdd7ea8..ee74fbe 100644 --- a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out @@ -44,20 +44,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) @@ -315,20 +311,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) diff --git a/ql/src/test/results/clientpositive/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/vector_orderby_5.q.out index 45ccc62..a3be243 100644 --- a/ql/src/test/results/clientpositive/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/vector_orderby_5.q.out @@ -121,11 +121,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bo, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: boolean) + aggregations: max(b) + keys: bo (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_outer_join1.q.out b/ql/src/test/results/clientpositive/vector_outer_join1.q.out index 8e8f7fa..fd86093 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join1.q.out @@ -489,14 +489,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE @@ -508,7 +508,7 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/vector_outer_join2.q.out index c649883..236fa18 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join2.q.out @@ -193,14 +193,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE @@ -212,7 +212,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE @@ -251,19 +251,15 @@ STAGE PLANS: 1 _col0 (type: bigint) outputColumnNames: _col1 Statistics: Num rows: 24 Data size: 5060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 24 Data size: 5060 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col0) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count(), sum(_col1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + value expressions: _col0 (type: bigint), _col1 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized diff --git a/ql/src/test/results/clientpositive/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/vector_outer_join3.q.out index 502f2d3..821a642 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join3.q.out @@ -193,14 +193,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE @@ -212,7 +212,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE @@ -334,14 +334,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE @@ -353,7 +353,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE @@ -475,14 +475,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE @@ -494,7 +494,7 @@ STAGE PLANS: keys: 0 _col3 (type: string), _col1 (type: bigint) 1 _col1 (type: string), _col0 (type: bigint) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_outer_join4.q.out b/ql/src/test/results/clientpositive/vector_outer_join4.q.out index 50ae497..fad7685 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join4.q.out @@ -859,14 +859,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + $hdt$_1:c Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + $hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + $hdt$_1:c TableScan alias: c Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE @@ -878,7 +878,7 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + $hdt$_2:c TableScan alias: c Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_outer_join5.q.out b/ql/src/test/results/clientpositive/vector_outer_join5.q.out index bbe8ba1..2cb80b6 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join5.q.out @@ -85,11 +85,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:st + $hdt$_1:st Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:st + $hdt$_1:st TableScan alias: st Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -193,11 +193,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -307,11 +307,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -421,11 +421,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -539,14 +539,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:s + $hdt$_2:s Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -558,7 +558,7 @@ STAGE PLANS: keys: 0 UDFToLong(_col1) (type: bigint) 1 (_col0 pmod UDFToLong(8)) (type: bigint) - $hdt$_0:$hdt$_2:s + $hdt$_2:s TableScan alias: s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE @@ -732,11 +732,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:st + $hdt$_1:st Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:st + $hdt$_1:st TableScan alias: st Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -840,11 +840,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -954,11 +954,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -1068,11 +1068,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -1186,14 +1186,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:s + $hdt$_2:s Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + $hdt$_1:sm TableScan alias: sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE @@ -1205,7 +1205,7 @@ STAGE PLANS: keys: 0 UDFToLong(_col1) (type: bigint) 1 (_col0 pmod UDFToLong(8)) (type: bigint) - $hdt$_0:$hdt$_2:s + $hdt$_2:s TableScan alias: s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out b/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out index 0437ff6..f483614 100644 --- a/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out +++ b/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out @@ -95,10 +95,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -214,10 +214,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -334,10 +334,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -435,10 +435,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -542,10 +542,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out index 83e7f19..a2762a3 100644 --- a/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out @@ -376,11 +376,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -1153,11 +1153,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1954,11 +1954,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: fl_time Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: timestamp) + keys: fl_time (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out index b38add3..77dc175 100644 --- a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out @@ -39,22 +39,18 @@ STAGE PLANS: Filter Operator predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2, _col3 + Group By Operator + aggregations: min(cdecimal1) + keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - sort order: ++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(20,10)) + value expressions: _col4 (type: decimal(20,10)) Execution mode: vectorized Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/vectorization_0.q.out b/ql/src/test/results/clientpositive/vectorization_0.q.out index 89163cd..3671055 100644 --- a/ql/src/test/results/clientpositive/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/vectorization_0.q.out @@ -130,10 +130,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -443,10 +443,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -756,10 +756,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1014,10 +1014,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cbigint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) + aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index 95cb09a..38966d1 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -84,31 +84,31 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -340,31 +340,31 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out index da0e8e0..be06613 100644 --- a/ql/src/test/results/clientpositive/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/vectorization_15.q.out @@ -80,31 +80,31 @@ STAGE PLANS: predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) + keys: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + key expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) sort order: +++++++ - Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: stddev_samp(VALUE._col0), min(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_samp(VALUE._col4), stddev_pop(VALUE._col5) - keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: int), KEY._col2 (type: float), KEY._col3 (type: double), KEY._col4 (type: string), KEY._col5 (type: timestamp), KEY._col6 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) + expressions: _col2 (type: float), _col6 (type: boolean), _col3 (type: double), _col4 (type: string), _col0 (type: tinyint), _col1 (type: int), _col5 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col1)) (type: double), _col8 (type: double), (_col3 * 79.553) (type: double), (33.0 % _col2) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col3) (type: double), (- _col0) (type: tinyint), _col11 (type: double), (UDFToFloat(_col1) - _col2) (type: float), (-23 % UDFToInteger(_col0)) (type: int), (- (-26.28 - UDFToDouble(_col1))) (type: double), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index 6ae3b4e..6ee9957 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.q.out @@ -57,31 +57,31 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index 6ae3b4e..6ee9957 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -57,31 +57,31 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out index 7691a4d..9ff888c 100644 --- a/ql/src/test/results/clientpositive/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -250,10 +250,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -334,11 +334,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: tinyint), _col1 (type: double) + aggregations: count(DISTINCT cdouble) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -452,11 +452,11 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, ctinyint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum(ctinyint) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out index 7205376..3aff6a3 100644 --- a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -20,10 +20,10 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out index 728f628..570e649 100644 --- a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -151,10 +151,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) + aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -357,10 +357,10 @@ STAGE PLANS: Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) + aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -554,10 +554,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) + aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -730,10 +730,10 @@ STAGE PLANS: Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ctinyint, cbigint, cint, cfloat Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) + aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1825,11 +1825,11 @@ STAGE PLANS: Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: csmallint, cbigint, ctinyint Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() - keys: _col0 (type: smallint) + aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() + keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE @@ -2035,11 +2035,11 @@ STAGE PLANS: Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, cfloat Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) - keys: _col0 (type: double) + aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE @@ -2292,31 +2292,31 @@ STAGE PLANS: predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: cstring1 (type: string), ctimestamp1 (type: timestamp), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) + outputColumnNames: cstring1, ctimestamp1, cint, csmallint, ctinyint, cfloat, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) - keys: _col0 (type: timestamp), _col1 (type: string) + aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) + keys: cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: string) + key expressions: _col0 (type: string), _col1 (type: timestamp) sort order: ++ - Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: timestamp) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: stddev_pop(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), min(VALUE._col3), var_samp(VALUE._col4), var_pop(VALUE._col5), avg(VALUE._col6), var_samp(VALUE._col7), avg(VALUE._col8), min(VALUE._col9), var_pop(VALUE._col10), stddev_pop(VALUE._col11), sum(VALUE._col12) - keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) + expressions: _col1 (type: timestamp), _col0 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2628,11 +2628,11 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) - keys: _col0 (type: boolean) + aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) + keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE @@ -2863,10 +2863,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: _col0 + outputColumnNames: i Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(i) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3027,10 +3027,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3087,10 +3087,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3147,10 +3147,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3207,10 +3207,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cstring1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3267,10 +3267,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: cboolean1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cboolean1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out index 2e041a3..b5c667f 100644 --- a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out @@ -33,12 +33,12 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0), count(DISTINCT _col0) + aggregations: sum(DISTINCT a), count(DISTINCT a) bucketGroup: true - keys: _col0 (type: int) + keys: a (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -93,11 +93,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), avg(DISTINCT _col0), std(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: sum(DISTINCT cint), count(DISTINCT cint), avg(DISTINCT cint), std(DISTINCT cint) + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out index 82e90da..6a9532e 100644 --- a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out @@ -15,14 +15,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:v1 + $hdt$_0:$hdt$_0:v1 Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:v1 + $hdt$_1:v1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:v1 + $hdt$_0:$hdt$_0:v1 TableScan alias: v1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -37,7 +37,7 @@ STAGE PLANS: keys: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) - $hdt$_0:$hdt$_1:v1 + $hdt$_1:v1 TableScan alias: v1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -86,19 +86,15 @@ STAGE PLANS: 1 _col0 (type: smallint) outputColumnNames: _col1 Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: double) + Group By Operator + aggregations: sum(_col1) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + value expressions: _col0 (type: double) Local Work: Map Reduce Local Work Execution mode: vectorized diff --git a/ql/src/test/results/clientpositive/vectorized_parquet.q.out b/ql/src/test/results/clientpositive/vectorized_parquet.q.out index 7b2dc6d..50e210c 100644 --- a/ql/src/test/results/clientpositive/vectorized_parquet.q.out +++ b/ql/src/test/results/clientpositive/vectorized_parquet.q.out @@ -146,11 +146,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: ctinyint, cint, csmallint, cstring1, cfloat, cdouble Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) - keys: _col0 (type: tinyint) + aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out index 8d1bddc..a3bd8aa 100644 --- a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out +++ b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out @@ -291,11 +291,11 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double), cdecimal (type: decimal(4,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: ctinyint, cint, csmallint, cstring1, cfloat, cdouble, cdecimal Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5), max(_col6) - keys: _col0 (type: tinyint) + aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble), max(cdecimal) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out index f66903b..830eb92 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out @@ -611,10 +611,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), count(_col0), count() + aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -685,10 +685,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctimestamp1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -768,10 +768,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) + aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -- 1.7.12.4 (Apple Git-37)