diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java index 2a0c469..6f0308d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java @@ -253,7 +253,8 @@ private static void getNestedColsFromExprNodeDesc( if (childDesc instanceof ExprNodeGenericFuncDesc) { ExprNodeGenericFuncDesc funcDesc = (ExprNodeGenericFuncDesc) childDesc; if (funcDesc.getGenericUDF() instanceof GenericUDFIndex) { - getNestedColsFromExprNodeDesc(funcDesc, pathToRoot, paths); + paths.clear(); + getNestedColsFromExprNodeDesc(funcDesc, null, paths); return; } } diff --git ql/src/test/queries/clientpositive/nested_column_pruning.q ql/src/test/queries/clientpositive/nested_column_pruning.q index 35de3ed..427bec1 100644 --- ql/src/test/queries/clientpositive/nested_column_pruning.q +++ ql/src/test/queries/clientpositive/nested_column_pruning.q @@ -12,14 +12,19 @@ CREATE TABLE nested_tbl_1 ( s1 struct, f6: int>, s2 struct, f11: map>>, s3 struct>>, - s4 map> + s4 map>, + s5 struct>>>, + s6 map>>>> ) STORED AS PARQUET; INSERT INTO TABLE nested_tbl_1 SELECT 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)) + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) FROM dummy; DROP TABLE IF EXISTS nested_tbl_2; @@ -29,7 +34,10 @@ INSERT INTO TABLE nested_tbl_2 SELECT 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)) + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) FROM dummy; -- Testing only select statements @@ -145,3 +153,21 @@ GROUP BY s4['key1'].f15; SELECT count(s1.f6), s4['key1'].f15 FROM nested_tbl_1 GROUP BY s4['key1'].f15; + +EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19; + +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19; + +EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22; + +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22; diff --git ql/src/test/results/clientpositive/nested_column_pruning.q.out ql/src/test/results/clientpositive/nested_column_pruning.q.out index da2908c..2fe9967 100644 --- ql/src/test/results/clientpositive/nested_column_pruning.q.out +++ ql/src/test/results/clientpositive/nested_column_pruning.q.out @@ -28,7 +28,9 @@ PREHOOK: query: CREATE TABLE nested_tbl_1 ( s1 struct, f6: int>, s2 struct, f11: map>>, s3 struct>>, - s4 map> + s4 map>, + s5 struct>>>, + s6 map>>>> ) STORED AS PARQUET PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -38,7 +40,9 @@ POSTHOOK: query: CREATE TABLE nested_tbl_1 ( s1 struct, f6: int>, s2 struct, f11: map>>, s3 struct>>, - s4 map> + s4 map>, + s5 struct>>>, + s6 map>>>> ) STORED AS PARQUET POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default @@ -47,7 +51,10 @@ PREHOOK: query: INSERT INTO TABLE nested_tbl_1 SELECT 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)) + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) FROM dummy PREHOOK: type: QUERY PREHOOK: Input: default@dummy @@ -56,7 +63,10 @@ POSTHOOK: query: INSERT INTO TABLE nested_tbl_1 SELECT 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)) + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) FROM dummy POSTHOOK: type: QUERY POSTHOOK: Input: default@dummy @@ -66,6 +76,8 @@ POSTHOOK: Lineage: nested_tbl_1.s1 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_1.s2 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_1.s3 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_1.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1.s6 EXPRESSION [] PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_2 PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_2 @@ -82,7 +94,10 @@ PREHOOK: query: INSERT INTO TABLE nested_tbl_2 SELECT 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)) + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) FROM dummy PREHOOK: type: QUERY PREHOOK: Input: default@dummy @@ -91,7 +106,10 @@ POSTHOOK: query: INSERT INTO TABLE nested_tbl_2 SELECT 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)) + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) FROM dummy POSTHOOK: type: QUERY POSTHOOK: Input: default@dummy @@ -101,6 +119,8 @@ POSTHOOK: Lineage: nested_tbl_2.s1 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_2.s2 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_2.s3 EXPRESSION [] POSTHOOK: Lineage: nested_tbl_2.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2.s6 EXPRESSION [] PREHOOK: query: -- Testing only select statements EXPLAIN SELECT a FROM nested_tbl_1 @@ -119,14 +139,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: nested_tbl_1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -162,14 +182,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -205,14 +225,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f1, s1.f2 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean), s1.f2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -250,14 +270,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -295,14 +315,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3.f5 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -340,14 +360,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3.f4, s2.f8.f9 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -387,17 +407,17 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f2, s1.f1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f1 = false) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -433,17 +453,17 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f3.f4 = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -479,17 +499,17 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f2, s2.f8 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2.f8 (type: struct,f11:map>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -533,32 +553,32 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s2.f8.f10 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3 (type: struct>>) outputColumnNames: s3 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator - outputColumnNames: _col3, _col8 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int) - outputColumnNames: _col8 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator - outputColumnNames: _col8, _col9 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int), _col9 (type: struct) + expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -566,20 +586,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator - outputColumnNames: _col8, _col9 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int), _col9 (type: struct) + expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -587,29 +607,29 @@ STAGE PLANS: Select Operator expressions: s2.f8.f10 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator - outputColumnNames: _col3, _col8 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int) - outputColumnNames: _col8 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator - outputColumnNames: _col8, _col9 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int), _col9 (type: struct) + expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -617,20 +637,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator - outputColumnNames: _col8, _col9 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: int), _col9 (type: struct) + expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -675,14 +695,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s2.f8.f10, s1.f3.f4 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -722,22 +742,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -745,10 +765,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -784,22 +804,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -807,10 +827,10 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -847,22 +867,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -870,7 +890,7 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -885,16 +905,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -939,32 +959,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s2.f8.f9 = false) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -974,14 +994,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1030,32 +1050,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s2.f8.f9 = true) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1065,14 +1085,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1165,22 +1185,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s3.f12, s1.f6 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 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: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1188,14 +1208,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1241,22 +1261,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 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: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1264,14 +1284,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1296,3 +1316,155 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@nested_tbl_1 #### A masked pattern was here #### 1 1 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: nested_tbl_1 + Pruned Column Paths: s5.f16, s1.f6 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 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: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 7 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1 +#### A masked pattern was here #### +1 14 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: nested_tbl_1 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 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: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 7 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1 +#### A masked pattern was here #### +1 1