diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java index f6b6447..5c51450 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java @@ -168,7 +168,7 @@ // private final Map columnMap; private int firstOutputColumnIndex; - private enum HiveVectorAdaptorUsageMode { + public enum HiveVectorAdaptorUsageMode { NONE, CHOSEN, ALL; diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java index 2a99274..814fe6c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java @@ -67,6 +67,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorMapJoinOuterFilteredOperator; import org.apache.hadoop.hive.ql.exec.vector.VectorSMBMapJoinOperator; import org.apache.hadoop.hive.ql.exec.vector.VectorizationContext; +import org.apache.hadoop.hive.ql.exec.vector.VectorizationContext.HiveVectorAdaptorUsageMode; import org.apache.hadoop.hive.ql.exec.vector.VectorizationContext.InConstantType; import org.apache.hadoop.hive.ql.exec.vector.VectorizationContextRegion; import org.apache.hadoop.hive.ql.exec.vector.expressions.IdentityExpression; @@ -240,8 +241,16 @@ boolean isSchemaEvolution; + HiveVectorAdaptorUsageMode hiveVectorAdaptorUsageMode; + public Vectorizer() { + /* + * We check UDFs against the supportedGenericUDFs when + * hive.vectorized.adaptor.usage.mode=chosen or none. + * + * We allow all UDFs for hive.vectorized.adaptor.usage.mode=all. + */ supportedGenericUDFs.add(GenericUDFOPPlus.class); supportedGenericUDFs.add(GenericUDFOPMinus.class); supportedGenericUDFs.add(GenericUDFOPMultiply.class); @@ -1394,6 +1403,8 @@ public PhysicalContext resolve(PhysicalContext physicalContext) throws SemanticE HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVE_SCHEMA_EVOLUTION); + hiveVectorAdaptorUsageMode = HiveVectorAdaptorUsageMode.getHiveConfValue(hiveConf); + // create dispatcher and graph walker Dispatcher disp = new VectorizationDispatcher(physicalContext); TaskGraphWalker ogw = new TaskGraphWalker(disp); @@ -1900,13 +1911,17 @@ private boolean validateGenericUdf(ExprNodeGenericFuncDesc genericUDFExpr) { if (VectorizationContext.isCustomUDF(genericUDFExpr)) { return true; } - GenericUDF genericUDF = genericUDFExpr.getGenericUDF(); - if (genericUDF instanceof GenericUDFBridge) { - Class udf = ((GenericUDFBridge) genericUDF).getUdfClass(); - return supportedGenericUDFs.contains(udf); - } else { - return supportedGenericUDFs.contains(genericUDF.getClass()); + if (hiveVectorAdaptorUsageMode == HiveVectorAdaptorUsageMode.NONE || + hiveVectorAdaptorUsageMode == HiveVectorAdaptorUsageMode.CHOSEN) { + GenericUDF genericUDF = genericUDFExpr.getGenericUDF(); + if (genericUDF instanceof GenericUDFBridge) { + Class udf = ((GenericUDFBridge) genericUDF).getUdfClass(); + return supportedGenericUDFs.contains(udf); + } else { + return supportedGenericUDFs.contains(genericUDF.getClass()); + } } + return true; } private boolean validateAggregationIsPrimitive(VectorAggregateExpression vectorAggrExpr) { diff --git ql/src/test/queries/clientpositive/vector_udf1.q ql/src/test/queries/clientpositive/vector_udf1.q index 2fcc69b..6ebe58f 100644 --- ql/src/test/queries/clientpositive/vector_udf1.q +++ ql/src/test/queries/clientpositive/vector_udf1.q @@ -3,9 +3,10 @@ set hive.fetch.task.conversion=none; drop table varchar_udf_1; -create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC; +create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20), + d1 string, d2 string, d3 varchar(10), d4 varchar(10)) STORED AS ORC; insert overwrite table varchar_udf_1 - select key, value, key, value from src where key = '238' limit 1; + select key, value, key, value, '2015-01-14', '2015-01-14', '2017-01-11', '2017-01-11' from src where key = '238' limit 1; -- UDFs with varchar support explain @@ -102,6 +103,58 @@ from varchar_udf_1 limit 1; explain select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1; + +select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1; + +explain +select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1; + +select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1; + +explain +select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1; + +select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1; + +explain +select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1; + +select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1; + +explain +select length(c2), length(c4), length(c2) = length(c4) diff --git ql/src/test/results/clientpositive/llap/vector_join30.q.out ql/src/test/results/clientpositive/llap/vector_join30.q.out index bb6916b..1a1c26a 100644 --- ql/src/test/results/clientpositive/llap/vector_join30.q.out +++ ql/src/test/results/clientpositive/llap/vector_join30.q.out @@ -82,7 +82,7 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) @@ -223,7 +223,7 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) @@ -376,7 +376,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Reducer 4 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) @@ -536,7 +536,7 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) diff --git ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out index 92a4cf7..e5c9cae 100644 --- ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out +++ ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out @@ -144,7 +144,7 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: hash(KEY.reducesinkkey0,KEY.reducesinkkey1,KEY.reducesinkkey2,VALUE._col0,VALUE._col1,VALUE._col2) (type: int) @@ -223,7 +223,7 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: hash(KEY.reducesinkkey0,KEY.reducesinkkey1,KEY.reducesinkkey2,KEY.reducesinkkey3,VALUE._col0,VALUE._col1,VALUE._col2,VALUE._col3) (type: int) diff --git ql/src/test/results/clientpositive/llap/vector_udf1.q.out ql/src/test/results/clientpositive/llap/vector_udf1.q.out index 9450b8f..657e73e 100644 --- ql/src/test/results/clientpositive/llap/vector_udf1.q.out +++ ql/src/test/results/clientpositive/llap/vector_udf1.q.out @@ -2,21 +2,23 @@ PREHOOK: query: drop table varchar_udf_1 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table varchar_udf_1 POSTHOOK: type: DROPTABLE -PREHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC +PREHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20), + d1 string, d2 string, d3 varchar(10), d4 varchar(10)) STORED AS ORC PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@varchar_udf_1 -POSTHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC +POSTHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20), + d1 string, d2 string, d3 varchar(10), d4 varchar(10)) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@varchar_udf_1 PREHOOK: query: insert overwrite table varchar_udf_1 - select key, value, key, value from src where key = '238' limit 1 + select key, value, key, value, '2015-01-14', '2015-01-14', '2017-01-11', '2017-01-11' from src where key = '238' limit 1 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@varchar_udf_1 POSTHOOK: query: insert overwrite table varchar_udf_1 - select key, value, key, value from src where key = '238' limit 1 + select key, value, key, value, '2015-01-14', '2015-01-14', '2017-01-11', '2017-01-11' from src where key = '238' limit 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@varchar_udf_1 @@ -24,6 +26,10 @@ POSTHOOK: Lineage: varchar_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type: POSTHOOK: Lineage: varchar_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: varchar_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: varchar_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: varchar_udf_1.d1 SIMPLE [] +POSTHOOK: Lineage: varchar_udf_1.d2 SIMPLE [] +POSTHOOK: Lineage: varchar_udf_1.d3 EXPRESSION [] +POSTHOOK: Lineage: varchar_udf_1.d4 EXPRESSION [] PREHOOK: query: -- UDFs with varchar support explain select @@ -53,17 +59,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(c1, c2) (type: string), concat(c3, c4) (type: varchar(30)), (concat(c1, c2) = UDFToString(concat(c3, c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -121,17 +127,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: upper(c2) (type: string), upper(c4) (type: varchar(20)), (upper(c2) = UDFToString(upper(c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -189,17 +195,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lower(c2) (type: string), lower(c4) (type: varchar(20)), (lower(c2) = UDFToString(lower(c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -259,22 +265,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ascii(c2) (type: int), ascii(c4) (type: int), (ascii(c2) = ascii(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -327,22 +333,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat_ws('|', c1, c2) (type: string), concat_ws('|', c3, c4) (type: string), (concat_ws('|', c1, c2) = concat_ws('|', c3, c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -395,17 +401,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decode(encode(c2,'US-ASCII'),'US-ASCII') (type: string), decode(encode(c4,'US-ASCII'),'US-ASCII') (type: string), (decode(encode(c2,'US-ASCII'),'US-ASCII') = decode(encode(c4,'US-ASCII'),'US-ASCII')) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,22 +469,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: instr(c2, '_') (type: int), instr(c4, '_') (type: int), (instr(c2, '_') = instr(c4, '_')) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -506,6 +512,278 @@ POSTHOOK: Input: default@varchar_udf_1 4 4 true PREHOOK: query: explain select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: varchar_udf_1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: replace(c1, '_', c2) (type: string), replace(c3, '_', c4) (type: string), (replace(c1, '_', c2) = replace(c3, '_', c4)) (type: boolean) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +POSTHOOK: query: select + replace(c1, '_', c2), + replace(c3, '_', c4), + replace(c1, '_', c2) = replace(c3, '_', c4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +238 238 true +PREHOOK: query: explain +select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: varchar_udf_1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: reverse(c2) (type: string), reverse(c4) (type: string), (reverse(c2) = reverse(c4)) (type: boolean) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +POSTHOOK: query: select + reverse(c2), + reverse(c4), + reverse(c2) = reverse(c4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +832_lav 832_lav true +PREHOOK: query: explain +select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: varchar_udf_1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: next_day(d1, 'TU') (type: string), next_day(d4, 'WE') (type: string), (next_day(d1, 'TU') = next_day(d4, 'WE')) (type: boolean) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +POSTHOOK: query: select + next_day(d1, 'TU'), + next_day(d4, 'WE'), + next_day(d1, 'TU') = next_day(d4, 'WE') +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +2015-01-20 2017-01-18 false +PREHOOK: query: explain +select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: varchar_udf_1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: months_between(d1, d3) (type: double), months_between(d2, d4) (type: double), (months_between(d1, d3) = months_between(d2, d4)) (type: boolean) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +POSTHOOK: query: select + months_between(d1, d3), + months_between(d2, d4), + months_between(d1, d3) = months_between(d2, d4) +from varchar_udf_1 limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@varchar_udf_1 +#### A masked pattern was here #### +-23.90322581 -23.90322581 true +PREHOOK: query: explain +select length(c2), length(c4), length(c2) = length(c4) @@ -531,17 +809,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: length(c2) (type: int), length(c4) (type: int), (length(c2) = length(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -599,7 +877,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 5 (type: int), 5 (type: int), true (type: boolean) outputColumnNames: _col0, _col1, _col2 @@ -667,22 +945,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lpad(c2, 15, ' ') (type: string), lpad(c4, 15, ' ') (type: string), (lpad(c2, 15, ' ') = lpad(c4, 15, ' ')) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -735,17 +1013,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ltrim(c2) (type: string), ltrim(c4) (type: string), (ltrim(c2) = ltrim(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -803,17 +1081,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c2 regexp 'val' (type: boolean), c4 regexp 'val' (type: boolean), (c2 regexp 'val' = c4 regexp 'val') (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -871,17 +1149,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: regexp_extract(c2, 'val_([0-9]+)', 1) (type: string), regexp_extract(c4, 'val_([0-9]+)', 1) (type: string), (regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -939,17 +1217,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: regexp_replace(c2, 'val', 'replaced') (type: string), regexp_replace(c4, 'val', 'replaced') (type: string), (regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1007,22 +1285,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reverse(c2) (type: string), reverse(c4) (type: string), (reverse(c2) = reverse(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -1075,22 +1353,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rpad(c2, 15, ' ') (type: string), rpad(c4, 15, ' ') (type: string), (rpad(c2, 15, ' ') = rpad(c4, 15, ' ')) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Stage: Stage-0 @@ -1143,17 +1421,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rtrim(c2) (type: string), rtrim(c4) (type: string), (rtrim(c2) = rtrim(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1209,7 +1487,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sentences('See spot run. See jane run.') (type: array>), sentences('See spot run. See jane run.') (type: array>) outputColumnNames: _col0, _col1 @@ -1273,17 +1551,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: split(c2, '_') (type: array), split(c4, '_') (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1337,7 +1615,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map), str_to_map('a:1,b:2,c:3',',',':') (type: map) outputColumnNames: _col0, _col1 @@ -1403,17 +1681,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(c2, 1, 3) (type: string), substr(c4, 1, 3) (type: string), (substr(c2, 1, 3) = substr(c4, 1, 3)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1471,17 +1749,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trim(c2) (type: string), trim(c4) (type: string), (trim(c2) = trim(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1542,11 +1820,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c2 (type: string), c4 (type: varchar(20)) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(_col0, 16), compute_stats(_col2, 16) mode: hash @@ -1623,11 +1901,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c2 (type: string), c4 (type: varchar(20)) outputColumnNames: c2, c4 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(c2), min(c4) mode: hash @@ -1704,11 +1982,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_udf_1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c2 (type: string), c4 (type: varchar(20)) outputColumnNames: c2, c4 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(c2), max(c4) mode: hash