diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeDescUtils.java ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeDescUtils.java index 0223038..2383af5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeDescUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeDescUtils.java @@ -109,9 +109,17 @@ public static boolean containsPredicate(ExprNodeDesc source, ExprNodeDesc predic * bind two predicates by AND op */ public static ExprNodeGenericFuncDesc mergePredicates(ExprNodeDesc prev, ExprNodeDesc next) { - List children = new ArrayList(2); - children.add(prev); - children.add(next); + final List children = new ArrayList(2); + if (FunctionRegistry.isOpAnd(prev)) { + children.addAll(prev.getChildren()); + } else { + children.add(prev); + } + if (FunctionRegistry.isOpAnd(next)) { + children.addAll(next.getChildren()); + } else { + children.add(next); + } return new ExprNodeGenericFuncDesc(TypeInfoFactory.booleanTypeInfo, FunctionRegistry.getGenericUDFForAnd(), children); } diff --git ql/src/test/results/clientpositive/auto_join_reordering_values.q.out ql/src/test/results/clientpositive/auto_join_reordering_values.q.out index 59aa738..5f75c9a 100644 --- ql/src/test/results/clientpositive/auto_join_reordering_values.q.out +++ ql/src/test/results/clientpositive/auto_join_reordering_values.q.out @@ -184,7 +184,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((date is not null and dealid is not null) and cityid is not null) and userid is not null) (type: boolean) + predicate: (date is not null and dealid is not null and cityid is not null and userid is not null) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dealid (type: int), date (type: string), cityid (type: int), userid (type: int) diff --git ql/src/test/results/clientpositive/cbo_const.q.out ql/src/test/results/clientpositive/cbo_const.q.out index d6682ca..4b603af 100644 --- ql/src/test/results/clientpositive/cbo_const.q.out +++ ql/src/test/results/clientpositive/cbo_const.q.out @@ -294,7 +294,7 @@ STAGE PLANS: alias: z Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((ds = '2008-04-08') and (UDFToDouble(hr) = 14.0)) and value is not null) (type: boolean) + predicate: ((ds = '2008-04-08') and (UDFToDouble(hr) = 14.0) and value is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) diff --git ql/src/test/results/clientpositive/correlationoptimizer13.q.out ql/src/test/results/clientpositive/correlationoptimizer13.q.out index 048f63b..58bd0ad 100644 --- ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -162,7 +162,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((c2 > 100) and c3 is not null) and (c1 < 120)) (type: boolean) + predicate: ((c2 > 100) and c3 is not null and (c1 < 120)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c3 (type: string), c1 (type: int) diff --git ql/src/test/results/clientpositive/correlationoptimizer9.q.out ql/src/test/results/clientpositive/correlationoptimizer9.q.out index b687616..09ed370 100644 --- ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -464,7 +464,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((c2 > 100) and c3 is not null) and (c1 < 120)) (type: boolean) + predicate: ((c2 > 100) and c3 is not null and (c1 < 120)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c3 (type: string) @@ -579,7 +579,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((c2 > 100) and c3 is not null) and (c1 < 120)) (type: boolean) + predicate: ((c2 > 100) and c3 is not null and (c1 < 120)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c3 (type: string) diff --git ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index a8be151..f85cf26 100644 --- ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -926,7 +926,7 @@ STAGE PLANS: alias: inventory Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int) @@ -1025,7 +1025,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((d_year = 1999) and d_date_sk is not null) and (d_moy = 3)) (type: boolean) + predicate: ((d_year = 1999) and d_date_sk is not null and (d_moy = 3)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -1163,7 +1163,7 @@ STAGE PLANS: alias: inventory Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int) @@ -1262,7 +1262,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((d_year = 1999) and d_date_sk is not null) and (d_moy = 4)) (type: boolean) + predicate: ((d_year = 1999) and d_date_sk is not null and (d_moy = 4)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: d_date_sk (type: int) diff --git ql/src/test/results/clientpositive/filter_cond_pushdown.q.out ql/src/test/results/clientpositive/filter_cond_pushdown.q.out index 1c3a5ab..c2216a4 100644 --- ql/src/test/results/clientpositive/filter_cond_pushdown.q.out +++ ql/src/test/results/clientpositive/filter_cond_pushdown.q.out @@ -37,7 +37,7 @@ STAGE PLANS: alias: f Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (value <> '')) and key is not null) (type: boolean) + predicate: (value is not null and (value <> '') and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -163,7 +163,7 @@ STAGE PLANS: alias: f Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (value <> '')) and key is not null) (type: boolean) + predicate: (value is not null and (value <> '') and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -419,7 +419,7 @@ STAGE PLANS: alias: f Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key is not null and ((value = '2008-04-10') or (value = '2008-04-08'))) and value is not null) and (value <> '')) (type: boolean) + predicate: (key is not null and ((value = '2008-04-10') or (value = '2008-04-08')) and value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/filter_join_breaktask.q.out ql/src/test/results/clientpositive/filter_join_breaktask.q.out index c17b48a..b041e77 100644 --- ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -168,7 +168,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key is not null and value is not null) and (value <> '')) (type: boolean) + predicate: (key is not null and value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/input_testxpath4.q.out ql/src/test/results/clientpositive/input_testxpath4.q.out index 74607a4..4fd8294 100644 --- ql/src/test/results/clientpositive/input_testxpath4.q.out +++ ql/src/test/results/clientpositive/input_testxpath4.q.out @@ -96,7 +96,7 @@ STAGE PLANS: alias: src_thrift Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((mstringstring['key_9'] is not null and lintstring.myint is not null) and lintstring is not null) (type: boolean) + predicate: (mstringstring['key_9'] is not null and lintstring.myint is not null and lintstring is not null) (type: boolean) Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: mstringstring['key_9'] (type: string), lintstring.myint (type: array) diff --git ql/src/test/results/clientpositive/join19.q.out ql/src/test/results/clientpositive/join19.q.out index b1b9dfe..31e368e 100644 --- ql/src/test/results/clientpositive/join19.q.out +++ ql/src/test/results/clientpositive/join19.q.out @@ -136,7 +136,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation')) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string) @@ -167,7 +167,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) @@ -211,7 +211,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author')) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string) @@ -226,7 +226,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null) and object is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) diff --git ql/src/test/results/clientpositive/join42.q.out ql/src/test/results/clientpositive/join42.q.out index 4f9e2a9..27102aa 100644 --- ql/src/test/results/clientpositive/join42.q.out +++ ql/src/test/results/clientpositive/join42.q.out @@ -135,7 +135,7 @@ STAGE PLANS: alias: la Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((aid is not null and pi_id is not null) and (loan_id = 4436)) (type: boolean) + predicate: (aid is not null and pi_id is not null and (loan_id = 4436)) (type: boolean) Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: aid (type: int), pi_id (type: int) diff --git ql/src/test/results/clientpositive/join_grp_diff_keys.q.out ql/src/test/results/clientpositive/join_grp_diff_keys.q.out index b24bcba..0929fbb 100644 --- ql/src/test/results/clientpositive/join_grp_diff_keys.q.out +++ ql/src/test/results/clientpositive/join_grp_diff_keys.q.out @@ -59,7 +59,7 @@ STAGE PLANS: alias: foo Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((id is not null and line_id is not null) and (orders <> 'blah')) (type: boolean) + predicate: (id is not null and line_id is not null and (orders <> 'blah')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: id (type: int), line_id (type: int) diff --git ql/src/test/results/clientpositive/join_reorder2.q.out ql/src/test/results/clientpositive/join_reorder2.q.out index e06be2d..9756342 100644 --- ql/src/test/results/clientpositive/join_reorder2.q.out +++ ql/src/test/results/clientpositive/join_reorder2.q.out @@ -208,7 +208,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean) + predicate: (key is not null and val is not null and (key + 1) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) diff --git ql/src/test/results/clientpositive/join_reorder3.q.out ql/src/test/results/clientpositive/join_reorder3.q.out index ff08758..04a60d1 100644 --- ql/src/test/results/clientpositive/join_reorder3.q.out +++ ql/src/test/results/clientpositive/join_reorder3.q.out @@ -208,7 +208,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean) + predicate: (key is not null and val is not null and (key + 1) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) diff --git ql/src/test/results/clientpositive/multiMapJoin1.q.out ql/src/test/results/clientpositive/multiMapJoin1.q.out index e2efec0..9a7d991 100644 --- ql/src/test/results/clientpositive/multiMapJoin1.q.out +++ ql/src/test/results/clientpositive/multiMapJoin1.q.out @@ -863,7 +863,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -1372,7 +1372,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -1424,7 +1424,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -1729,7 +1729,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -2023,7 +2023,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -2375,7 +2375,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -2884,7 +2884,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) @@ -2936,7 +2936,7 @@ STAGE PLANS: alias: bigtbl Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key1 is not null and value is not null) and key2 is not null) (type: boolean) + predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean) Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), key2 (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out index 90032fe..d82b2ed 100644 --- ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out +++ ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out @@ -460,7 +460,7 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + predicate: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 262 Data size: 77718 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: tinyint), s (type: string) @@ -500,10 +500,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + filterExpr: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + predicate: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 262 Data size: 77718 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: tinyint), s (type: string) @@ -591,7 +591,7 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + predicate: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 131 Data size: 38859 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), s (type: string) @@ -644,10 +644,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + filterExpr: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + predicate: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 131 Data size: 38859 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), s (type: string) @@ -768,7 +768,7 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 5 Data size: 1483 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -834,10 +834,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 5 Data size: 1483 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -972,7 +972,7 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -1068,10 +1068,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + filterExpr: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) diff --git ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out index 7c5be6d..d157f98 100644 --- ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out +++ ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out @@ -448,7 +448,7 @@ STAGE PLANS: alias: tbl_pred Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + predicate: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 262 Data size: 2882 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: tinyint), s (type: string) @@ -488,10 +488,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + filterExpr: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((t = -1) and s is not null) and (s like 'bob%')) (type: boolean) + predicate: ((t = -1) and s is not null and (s like 'bob%')) (type: boolean) Statistics: Num rows: 262 Data size: 2882 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: tinyint), s (type: string) @@ -579,7 +579,7 @@ STAGE PLANS: alias: tbl_pred Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + predicate: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 131 Data size: 1441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), s (type: string) @@ -632,10 +632,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + filterExpr: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((s is not null and (s like 'bob%')) and (not (t) IN (-1, -2, -3))) and t BETWEEN 25 AND 30) (type: boolean) + predicate: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) Statistics: Num rows: 131 Data size: 1441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), s (type: string) @@ -756,7 +756,7 @@ STAGE PLANS: alias: tbl_pred Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 5 Data size: 55 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -822,10 +822,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (t > 0)) and si BETWEEN 300 AND 400) and (not (s like '%car%'))) (type: boolean) + predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) Statistics: Num rows: 5 Data size: 55 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -1005,7 +1005,7 @@ STAGE PLANS: alias: tbl_pred Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -1101,10 +1101,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + filterExpr: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((t > 10) and (t <> 101)) and (d >= 10.0)) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: ((t > 10) and (t <> 101) and (d >= 10.0) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -1212,10 +1212,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: ((((((((((((f < 123.2) and (f > 1.92)) and (f >= 9.99)) and f BETWEEN 1.92 AND 123.2) and (i < 67627)) and (i > 60627)) and (i >= 60626)) and i BETWEEN 60626 AND 67627) and (b < 4294967861)) and (b > 4294967261)) and (b >= 4294967260)) and b BETWEEN 4294967261 AND 4294967861) (type: boolean) + filterExpr: ((f < 123.2) and (f > 1.92) and (f >= 9.99) and f BETWEEN 1.92 AND 123.2 and (i < 67627) and (i > 60627) and (i >= 60626) and i BETWEEN 60626 AND 67627 and (b < 4294967861) and (b > 4294967261) and (b >= 4294967260) and b BETWEEN 4294967261 AND 4294967861) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((((((f < 123.2) and (f > 1.92)) and (f >= 9.99)) and f BETWEEN 1.92 AND 123.2) and (i < 67627)) and (i > 60627)) and (i >= 60626)) and i BETWEEN 60626 AND 67627) and (b < 4294967861)) and (b > 4294967261)) and (b >= 4294967260)) and b BETWEEN 4294967261 AND 4294967861) (type: boolean) + predicate: ((f < 123.2) and (f > 1.92) and (f >= 9.99) and f BETWEEN 1.92 AND 123.2 and (i < 67627) and (i > 60627) and (i >= 60626) and i BETWEEN 60626 AND 67627 and (b < 4294967861) and (b > 4294967261) and (b >= 4294967260) and b BETWEEN 4294967261 AND 4294967861) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f (type: float), i (type: int), b (type: bigint) diff --git ql/src/test/results/clientpositive/ppd_join2.q.out ql/src/test/results/clientpositive/ppd_join2.q.out index 955f4ad..8d08740 100644 --- ql/src/test/results/clientpositive/ppd_join2.q.out +++ ql/src/test/results/clientpositive/ppd_join2.q.out @@ -39,7 +39,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key <> '302') and (key < '400')) and (key <> '305')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) + predicate: ((key <> '302') and (key < '400') and (key <> '305') and value is not null and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -55,7 +55,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key <> '302')) and (key < '400')) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -97,7 +97,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((key <> '306') and value is not null and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) @@ -1723,7 +1723,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key <> '302') and (key < '400')) and (key <> '305')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) + predicate: ((key <> '302') and (key < '400') and (key <> '305') and value is not null and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1739,7 +1739,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key <> '302')) and (key < '400')) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1781,7 +1781,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((key <> '306') and value is not null and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) diff --git ql/src/test/results/clientpositive/ppd_vc.q.out ql/src/test/results/clientpositive/ppd_vc.q.out index 5165826..fd7a15f 100644 --- ql/src/test/results/clientpositive/ppd_vc.q.out +++ ql/src/test/results/clientpositive/ppd_vc.q.out @@ -83,7 +83,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -129,7 +129,7 @@ STAGE PLANS: ds 2008-04-08 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -175,7 +175,7 @@ STAGE PLANS: ds 2008-04-09 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -221,7 +221,7 @@ STAGE PLANS: ds 2008-04-09 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -434,7 +434,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((BLOCK__OFFSET__INSIDE__FILE < 100) and (BLOCK__OFFSET__INSIDE__FILE < 50)) and key is not null) (type: boolean) + predicate: ((BLOCK__OFFSET__INSIDE__FILE < 100) and (BLOCK__OFFSET__INSIDE__FILE < 50) and key is not null) (type: boolean) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) @@ -457,7 +457,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -477,7 +477,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -504,7 +504,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -550,7 +550,7 @@ STAGE PLANS: ds 2008-04-08 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -596,7 +596,7 @@ STAGE PLANS: ds 2008-04-09 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -642,7 +642,7 @@ STAGE PLANS: ds 2008-04-09 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' diff --git ql/src/test/results/clientpositive/sample8.q.out ql/src/test/results/clientpositive/sample8.q.out index ae51b36..356efc0 100644 --- ql/src/test/results/clientpositive/sample8.q.out +++ ql/src/test/results/clientpositive/sample8.q.out @@ -98,7 +98,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: true - predicate: (((((hash(key) & 2147483647) % 10) = 0) and value is not null) and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) + predicate: ((((hash(key) & 2147483647) % 10) = 0) and value is not null and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -113,7 +113,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: true - predicate: (((((hash(key) & 2147483647) % 1) = 0) and value is not null) and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) + predicate: ((((hash(key) & 2147483647) % 1) = 0) and value is not null and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -134,7 +134,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -180,7 +180,7 @@ STAGE PLANS: ds 2008-04-08 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -226,7 +226,7 @@ STAGE PLANS: ds 2008-04-09 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -272,7 +272,7 @@ STAGE PLANS: ds 2008-04-09 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' diff --git ql/src/test/results/clientpositive/semijoin.q.out ql/src/test/results/clientpositive/semijoin.q.out index 11b1891..f8f72cd 100644 --- ql/src/test/results/clientpositive/semijoin.q.out +++ ql/src/test/results/clientpositive/semijoin.q.out @@ -762,7 +762,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 84 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/semijoin2.q.out ql/src/test/results/clientpositive/semijoin2.q.out index e7d7271..d98f2dc 100644 --- ql/src/test/results/clientpositive/semijoin2.q.out +++ ql/src/test/results/clientpositive/semijoin2.q.out @@ -62,7 +62,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((bigint_col_22 is not null and decimal1709_col_26 is not null) and tinyint_col_8 is not null) and timestamp_col_10 is not null) (type: boolean) + predicate: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) @@ -74,7 +74,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null) and tinyint_col_33 is not null) and UDFToInteger(smallint_col_38) is not null) (type: boolean) + predicate: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) diff --git ql/src/test/results/clientpositive/semijoin4.q.out ql/src/test/results/clientpositive/semijoin4.q.out index 77f2615..ccb7d64 100644 --- ql/src/test/results/clientpositive/semijoin4.q.out +++ ql/src/test/results/clientpositive/semijoin4.q.out @@ -69,7 +69,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((decimal1309_col_65 is not null and bigint_col_13 is not null) and UDFToInteger(tinyint_col_46) is not null) and (UDFToInteger(tinyint_col_46) = -92)) (type: boolean) + predicate: (decimal1309_col_65 is not null and bigint_col_13 is not null and UDFToInteger(tinyint_col_46) is not null and (UDFToInteger(tinyint_col_46) = -92)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: bigint_col_13 (type: bigint), smallint_col_24 (type: smallint), double_col_60 (type: double), decimal1309_col_65 (type: decimal(13,9)) @@ -85,7 +85,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((tinyint_col_18 is not null and decimal2709_col_9 is not null) and UDFToInteger(tinyint_col_21) is not null) and (UDFToInteger(tinyint_col_21) = -92)) (type: boolean) + predicate: (tinyint_col_18 is not null and decimal2709_col_9 is not null and UDFToInteger(tinyint_col_21) is not null and (UDFToInteger(tinyint_col_21) = -92)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: decimal2709_col_9 (type: decimal(27,9)), tinyint_col_18 (type: tinyint) diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out index f9043d3..85b8028 100644 --- ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out +++ ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out @@ -106,7 +106,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key = '2')) (type: boolean) + predicate: (key is not null and val is not null and (key = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -136,7 +136,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (not (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt12.q.out ql/src/test/results/clientpositive/skewjoinopt12.q.out index 6c38b97..e2d1e5e 100644 --- ql/src/test/results/clientpositive/skewjoinopt12.q.out +++ ql/src/test/results/clientpositive/skewjoinopt12.q.out @@ -62,7 +62,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -77,7 +77,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -135,7 +135,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -150,7 +150,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt14.q.out ql/src/test/results/clientpositive/skewjoinopt14.q.out index a8536de..c238f1e 100644 --- ql/src/test/results/clientpositive/skewjoinopt14.q.out +++ ql/src/test/results/clientpositive/skewjoinopt14.q.out @@ -92,7 +92,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key = '2')) (type: boolean) + predicate: (key is not null and val is not null and (key = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -197,7 +197,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (not (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt16.q.out ql/src/test/results/clientpositive/skewjoinopt16.q.out index 15b3e62..59ed9b9 100644 --- ql/src/test/results/clientpositive/skewjoinopt16.q.out +++ ql/src/test/results/clientpositive/skewjoinopt16.q.out @@ -62,7 +62,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -77,7 +77,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -135,7 +135,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -150,7 +150,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt17.q.out ql/src/test/results/clientpositive/skewjoinopt17.q.out index a48d245..8a3a1b1 100644 --- ql/src/test/results/clientpositive/skewjoinopt17.q.out +++ ql/src/test/results/clientpositive/skewjoinopt17.q.out @@ -286,7 +286,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -301,7 +301,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -359,7 +359,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -374,7 +374,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt2.q.out ql/src/test/results/clientpositive/skewjoinopt2.q.out index d37237f..bb2bff5 100644 --- ql/src/test/results/clientpositive/skewjoinopt2.q.out +++ ql/src/test/results/clientpositive/skewjoinopt2.q.out @@ -70,7 +70,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -85,7 +85,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -143,7 +143,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -158,7 +158,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -388,7 +388,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -403,7 +403,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -485,7 +485,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -500,7 +500,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/smb_mapjoin_10.q.out ql/src/test/results/clientpositive/smb_mapjoin_10.q.out index 5a3a619..da42f21 100644 --- ql/src/test/results/clientpositive/smb_mapjoin_10.q.out +++ ql/src/test/results/clientpositive/smb_mapjoin_10.q.out @@ -84,7 +84,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean) + predicate: (userid is not null and pageid is not null and postid is not null and type is not null) (type: boolean) Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/smb_mapjoin_14.q.out ql/src/test/results/clientpositive/smb_mapjoin_14.q.out index 701145b..8635921 100644 --- ql/src/test/results/clientpositive/smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/smb_mapjoin_14.q.out @@ -590,7 +590,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) + predicate: ((key < 8) and (key < 6)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) diff --git ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out index 9450084..0bf34b4 100644 --- ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out +++ ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out @@ -74,7 +74,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) + predicate: (value is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out index 6d11948..6a47a94 100644 --- ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out +++ ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out @@ -74,7 +74,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) + predicate: (value is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out index d814b9d..f63b132 100644 --- ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out +++ ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out @@ -78,7 +78,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) + predicate: (value is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -92,7 +92,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) + predicate: (value is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out index 2eb3289..0b15321 100644 --- ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out +++ ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out @@ -195,7 +195,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean) + predicate: (value2 is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 2095 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -209,7 +209,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 10218 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean) + predicate: (value2 is not null and (key < 10)) (type: boolean) Statistics: Num rows: 166 Data size: 3392 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out index 8bf5977..290cc86 100644 --- ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out @@ -189,7 +189,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((date is not null and dealid is not null) and cityid is not null) and userid is not null) (type: boolean) + predicate: (date is not null and dealid is not null and cityid is not null and userid is not null) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dealid (type: int), date (type: string), cityid (type: int), userid (type: int) diff --git ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out index 66cd5cc..00af148 100644 --- ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out +++ ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out @@ -139,7 +139,7 @@ STAGE PLANS: alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: ((l_shipmode = 'AIR') and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) diff --git ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out index 8639871..e21404e 100644 --- ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out @@ -731,7 +731,7 @@ STAGE PLANS: alias: inventory Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int) @@ -749,7 +749,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((d_year = 1999) and d_date_sk is not null) and (d_moy = 3)) (type: boolean) + predicate: ((d_year = 1999) and d_date_sk is not null and (d_moy = 3)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -766,7 +766,7 @@ STAGE PLANS: alias: inventory Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int) @@ -819,7 +819,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((d_year = 1999) and d_date_sk is not null) and (d_moy = 4)) (type: boolean) + predicate: ((d_year = 1999) and d_date_sk is not null and (d_moy = 4)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: d_date_sk (type: int) diff --git ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out index fa5a5c6..68e2cd2 100644 --- ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out +++ ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out @@ -225,7 +225,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key is not null and value is not null) and (value <> '')) (type: boolean) + predicate: (key is not null and value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/spark/index_bitmap3.q.out ql/src/test/results/clientpositive/spark/index_bitmap3.q.out index 2c4aeb5..cf43011 100644 --- ql/src/test/results/clientpositive/spark/index_bitmap3.q.out +++ ql/src/test/results/clientpositive/spark/index_bitmap3.q.out @@ -110,45 +110,45 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 4 (PARTITION-LEVEL SORT, 4) - Reducer 3 <- Reducer 2 (GROUP, 4) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: default__src_src1_index__ - Statistics: Num rows: 500 Data size: 46311 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 56811 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) = 0.0) and _bucketname is not null) and _offset is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 0.0) and _bucketname is not null and _offset is not null) (type: boolean) + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _bucketname (type: string), _offset (type: bigint), _bitmaps (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: array) Map 4 Map Operator Tree: TableScan alias: default__src_src2_index__ - Statistics: Num rows: 500 Data size: 48311 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 58811 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value = 'val_0') and _bucketname is not null) and _offset is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + predicate: ((value = 'val_0') and _bucketname is not null and _offset is not null) (type: boolean) + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _bucketname (type: string), _offset (type: bigint), _bitmaps (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: array) Reducer 2 Reduce Operator Tree: @@ -159,25 +159,25 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: bigint) 1 _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col5 - Statistics: Num rows: 275 Data size: 25470 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 31245 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not EWAH_BITMAP_EMPTY(EWAH_BITMAP_AND(_col2,_col5))) (type: boolean) - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: collect_set(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 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: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: array) Reducer 3 Reduce Operator Tree: @@ -186,10 +186,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 69 Data size: 6390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 7839 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 69 Data size: 6390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 7839 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 ql/src/test/results/clientpositive/spark/index_bitmap_auto.q.out ql/src/test/results/clientpositive/spark/index_bitmap_auto.q.out index c499c43..324d996 100644 --- ql/src/test/results/clientpositive/spark/index_bitmap_auto.q.out +++ ql/src/test/results/clientpositive/spark/index_bitmap_auto.q.out @@ -129,45 +129,45 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 4 (PARTITION-LEVEL SORT, 4) - Reducer 3 <- Reducer 2 (GROUP, 4) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: default__src_src1_index__ - Statistics: Num rows: 500 Data size: 46311 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 56811 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) = 0.0) and _bucketname is not null) and _offset is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 0.0) and _bucketname is not null and _offset is not null) (type: boolean) + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _bucketname (type: string), _offset (type: bigint), _bitmaps (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 250 Data size: 23155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28405 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: array) Map 4 Map Operator Tree: TableScan alias: default__src_src2_index__ - Statistics: Num rows: 500 Data size: 48311 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 58811 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value = 'val_0') and _bucketname is not null) and _offset is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + predicate: ((value = 'val_0') and _bucketname is not null and _offset is not null) (type: boolean) + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _bucketname (type: string), _offset (type: bigint), _bitmaps (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 250 Data size: 24155 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29405 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: array) Reducer 2 Reduce Operator Tree: @@ -178,25 +178,25 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: bigint) 1 _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col5 - Statistics: Num rows: 275 Data size: 25470 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 31245 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not EWAH_BITMAP_EMPTY(EWAH_BITMAP_AND(_col2,_col5))) (type: boolean) - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: collect_set(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 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: 138 Data size: 12781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 15679 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: array) Reducer 3 Reduce Operator Tree: @@ -205,10 +205,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 69 Data size: 6390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 7839 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 69 Data size: 6390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 7839 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 ql/src/test/results/clientpositive/spark/join19.q.out ql/src/test/results/clientpositive/spark/join19.q.out index 5de045b..34b8790 100644 --- ql/src/test/results/clientpositive/spark/join19.q.out +++ ql/src/test/results/clientpositive/spark/join19.q.out @@ -141,7 +141,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation')) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string) @@ -176,7 +176,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) @@ -194,7 +194,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author')) and subject is not null) (type: boolean) + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string) @@ -211,7 +211,7 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null) and object is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) diff --git ql/src/test/results/clientpositive/spark/join_reorder2.q.out ql/src/test/results/clientpositive/spark/join_reorder2.q.out index ede4047..9bc3e12 100644 --- ql/src/test/results/clientpositive/spark/join_reorder2.q.out +++ ql/src/test/results/clientpositive/spark/join_reorder2.q.out @@ -225,7 +225,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean) + predicate: (key is not null and val is not null and (key + 1) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/join_reorder3.q.out ql/src/test/results/clientpositive/spark/join_reorder3.q.out index f54ec6a..da8e7a1 100644 --- ql/src/test/results/clientpositive/spark/join_reorder3.q.out +++ ql/src/test/results/clientpositive/spark/join_reorder3.q.out @@ -225,7 +225,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean) + predicate: (key is not null and val is not null and (key + 1) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/ppd_join2.q.out ql/src/test/results/clientpositive/spark/ppd_join2.q.out index f7721fb..8049c79 100644 --- ql/src/test/results/clientpositive/spark/ppd_join2.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((key <> '306') and value is not null and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) @@ -61,7 +61,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key <> '302') and (key < '400')) and (key <> '305')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) + predicate: ((key <> '302') and (key < '400') and (key <> '305') and value is not null and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -79,7 +79,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key <> '302')) and (key < '400')) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1728,7 +1728,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((key <> '306') and value is not null and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) @@ -1745,7 +1745,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key <> '302') and (key < '400')) and (key <> '305')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) + predicate: ((key <> '302') and (key < '400') and (key <> '305') and value is not null and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1763,7 +1763,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key <> '302')) and (key < '400')) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/sample8.q.out ql/src/test/results/clientpositive/spark/sample8.q.out index ae5aec0..898c580 100644 --- ql/src/test/results/clientpositive/spark/sample8.q.out +++ ql/src/test/results/clientpositive/spark/sample8.q.out @@ -103,7 +103,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: true - predicate: (((((hash(key) & 2147483647) % 10) = 0) and value is not null) and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) + predicate: ((((hash(key) & 2147483647) % 10) = 0) and value is not null and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -124,7 +124,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -171,7 +171,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: true - predicate: (((((hash(key) & 2147483647) % 1) = 0) and value is not null) and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) + predicate: ((((hash(key) & 2147483647) % 1) = 0) and value is not null and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -192,7 +192,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -238,7 +238,7 @@ STAGE PLANS: ds 2008-04-08 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -284,7 +284,7 @@ STAGE PLANS: ds 2008-04-09 hr 11 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' @@ -330,7 +330,7 @@ STAGE PLANS: ds 2008-04-09 hr 12 properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 columns key,value columns.comments 'default','default' diff --git ql/src/test/results/clientpositive/spark/semijoin.q.out ql/src/test/results/clientpositive/spark/semijoin.q.out index 36153d6..73049d7 100644 --- ql/src/test/results/clientpositive/spark/semijoin.q.out +++ ql/src/test/results/clientpositive/spark/semijoin.q.out @@ -755,7 +755,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 84 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out index 9a15385..abe794c 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out @@ -66,7 +66,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -83,7 +83,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -100,7 +100,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -117,7 +117,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out index ef36afd..bfe24de 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out @@ -97,7 +97,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (key = '2')) (type: boolean) + predicate: (key is not null and val is not null and (key = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -151,7 +151,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (not (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out index f520b77..a0b6500 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out @@ -66,7 +66,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -83,7 +83,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -100,7 +100,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -117,7 +117,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out index 53dba3f..27f9464 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out @@ -273,7 +273,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -290,7 +290,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) + predicate: (key is not null and val is not null and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -307,7 +307,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -324,7 +324,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) + predicate: (key is not null and val is not null and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out index e618832..22dd420 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out @@ -74,7 +74,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -91,7 +91,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -108,7 +108,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -125,7 +125,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -359,7 +359,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -376,7 +376,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) + predicate: (key is not null and val is not null and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -393,7 +393,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -410,7 +410,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) + predicate: (key is not null and val is not null and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out index 567c9b4..b543c59 100644 --- ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out +++ ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out @@ -87,7 +87,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean) + predicate: (userid is not null and pageid is not null and postid is not null and type is not null) (type: boolean) Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: diff --git ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out index d8c5e70..e570e1b 100644 --- ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out @@ -636,7 +636,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) + predicate: ((key < 8) and (key < 6)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) diff --git ql/src/test/results/clientpositive/spark/sort_merge_join_desc_2.q.out ql/src/test/results/clientpositive/spark/sort_merge_join_desc_2.q.out index 6f83401..72fccc4 100644 --- ql/src/test/results/clientpositive/spark/sort_merge_join_desc_2.q.out +++ ql/src/test/results/clientpositive/spark/sort_merge_join_desc_2.q.out @@ -79,15 +79,15 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) - Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -104,17 +104,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - 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 - 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 diff --git ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out index d705d9a..7be0a38 100644 --- ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out +++ ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out @@ -79,15 +79,15 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) - Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -104,17 +104,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - 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 - 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 diff --git ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out index 0a70e59..f0885f1 100644 --- ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out +++ ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out @@ -76,8 +76,8 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -97,8 +97,8 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -107,7 +107,7 @@ STAGE PLANS: 1 key (type: string), value (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -126,17 +126,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - 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 - 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 diff --git ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out index 4614d9c..09f1dea 100644 --- ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out +++ ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out @@ -149,17 +149,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - 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 - 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 @@ -208,8 +204,8 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 517 Basic stats: COMPLETE Column stats: NONE + predicate: (value2 is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 2095 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 key (type: string), value2 (type: string) @@ -229,8 +225,8 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 10218 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 837 Basic stats: COMPLETE Column stats: NONE + predicate: (value2 is not null and (key < 10)) (type: boolean) + Statistics: Num rows: 166 Data size: 3392 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -239,7 +235,7 @@ STAGE PLANS: 1 key (type: string), value2 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 45 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 3731 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -258,17 +254,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - 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 - 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 diff --git ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning.q.out index a628aae..16aa452 100644 --- ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning.q.out @@ -62,10 +62,10 @@ 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 @@ -213,16 +213,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Stage: Stage-1 Spark @@ -237,11 +241,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -251,19 +259,23 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -336,11 +348,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -350,19 +366,23 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -457,39 +477,47 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Map 8 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -504,12 +532,16 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: hr (type: string) + 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 + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -519,39 +551,47 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: string) - sort order: + - Map-reduce partition columns: hr (type: string) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 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: 5 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: @@ -559,8 +599,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -640,12 +680,16 @@ STAGE PLANS: alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: hr (type: string) + 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 + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -655,39 +699,47 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: string) - sort order: + - Map-reduce partition columns: hr (type: string) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 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: 5 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: @@ -695,8 +747,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -782,48 +834,56 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Map 6 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -837,33 +897,41 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -936,33 +1004,41 @@ STAGE PLANS: alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1053,16 +1129,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Stage: Stage-1 Spark @@ -1077,11 +1157,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -1091,19 +1175,23 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1176,11 +1264,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -1190,19 +1282,23 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1282,25 +1378,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToDouble(hr) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -1313,39 +1413,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(hr) (type: double) + key expressions: UDFToDouble(_col0) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(hr) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1413,25 +1518,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Select Operator + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: (hr * 2) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: (UDFToDouble(hr) * 2.0) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -1444,39 +1553,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (hr * 2) (type: double) + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) sort order: + - Map-reduce partition columns: (hr * 2) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: double) - sort order: + - Map-reduce partition columns: hr (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 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: 7 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1546,39 +1660,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(hr) (type: double) + key expressions: UDFToDouble(_col0) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(hr) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1648,39 +1767,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (hr * 2) (type: double) + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) sort order: + - Map-reduce partition columns: (hr * 2) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: double) - sort order: + - Map-reduce partition columns: hr (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 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: 7 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1761,25 +1885,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToString(hr) (type: string) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: UDFToString(_col0) (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToString((hr * 2)) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -1792,39 +1920,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((hr * 2)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((hr * 2)) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToString((hr * 2)) (type: string) + key expressions: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) sort order: + - Map-reduce partition columns: UDFToString((hr * 2)) (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString(hr) (type: string) - sort order: + - Map-reduce partition columns: UDFToString(hr) (type: string) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToString(_col0) (type: string) + sort order: + + Map-reduce partition columns: UDFToString(_col0) (type: string) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToString((hr * 2)) (type: string) - 1 UDFToString(hr) (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + 1 UDFToString(_col0) (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1887,7 +2020,6 @@ 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 JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work '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 @@ -1895,15 +2027,64 @@ POSTHOOK: 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' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark + Edges: + Reducer 7 <- Map 6 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (ds = '2008-04-08') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '2008-04-08' (type: string) + outputColumnNames: ds + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reducer 7 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Stage: Stage-1 Spark Edges: Reducer 5 <- Map 4 (GROUP, 2) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2) Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: @@ -1911,13 +2092,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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 4 Map Operator Tree: TableScan @@ -1926,10 +2111,10 @@ 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 @@ -1944,9 +2129,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 - 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1977,11 +2162,11 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator + 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 - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 Fetch Operator @@ -1989,18 +2174,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work '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 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: 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' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -2016,7 +2204,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join JOIN[4][tables = [srcpart, srcpart_date_hour]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.date = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2040,23 +2228,31 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((date = '2008-04-08') and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((date = '2008-04-08') and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col2 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -2065,10 +2261,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col3, _col7, _col9 + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 = _col7) or (_col3 = _col9)) (type: boolean) + predicate: ((_col0 = _col2) or (_col1 = _col4)) (type: boolean) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -2102,7 +2298,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [srcpart, srcpart_date_hour]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.date = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2142,48 +2338,56 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Map 6 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Stage: Stage-1 Spark @@ -2197,49 +2401,51 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) - outputColumnNames: _col2, _col3, _col7, _col9 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 = _col7) and (_col3 = _col9)) (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator @@ -2287,62 +2493,101 @@ POSTHOOK: query: -- left join EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.date = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map 4 + Map 5 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + 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) + outputColumnNames: _col0 + 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 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator @@ -2391,16 +2636,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 4 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 4 Stage: Stage-1 Spark @@ -2418,29 +2667,37 @@ STAGE PLANS: Filter Operator predicate: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 Reducer 2 Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2479,10 +2736,43 @@ POSTHOOK: query: -- full outer EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.date = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Stage: Stage-1 Spark Edges: @@ -2495,46 +2785,51 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: - Outer Join 0 to 1 + Right Outer Join0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator @@ -2587,39 +2882,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 - Map 8 - Map Operator Tree: - TableScan - alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '11' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Stage: Stage-1 Spark @@ -2633,13 +2909,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr = 11) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -2649,33 +2928,39 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '11' (type: string) - sort order: + - Map-reduce partition columns: '11' (type: string) + Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '11' (type: string) + sort order: + + Map-reduce partition columns: '11' (type: string) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '11' (type: string) @@ -2688,8 +2973,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2763,16 +3048,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + filterExpr: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + predicate: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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: 0 Basic stats: PARTIAL Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -2782,33 +3071,39 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 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: 21 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr = 13) (type: boolean) + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr = 13) (type: boolean) + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '13' (type: string) - sort order: + - Map-reduce partition columns: '13' (type: string) + Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '13' (type: string) + sort order: + + Map-reduce partition columns: '13' (type: string) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: '13' (type: string) @@ -2821,8 +3116,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() @@ -2895,10 +3190,10 @@ 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 @@ -2913,10 +3208,10 @@ 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 @@ -3014,10 +3309,10 @@ 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 @@ -3032,10 +3327,10 @@ 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 @@ -3163,10 +3458,10 @@ 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 @@ -3181,10 +3476,10 @@ 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 @@ -3282,10 +3577,10 @@ 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 @@ -3300,10 +3595,10 @@ 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 @@ -3436,10 +3731,10 @@ 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 @@ -3454,10 +3749,10 @@ 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 @@ -3586,10 +3881,9 @@ STAGE PLANS: Spark Edges: Reducer 2 <- Map 1 (GROUP, 2) - Reducer 5 <- Map 1 (GROUP, 2) Reducer 7 <- Map 6 (GROUP, 1) Reducer 9 <- Map 8 (GROUP, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -3598,20 +3892,16 @@ 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 6 Map Operator Tree: TableScan @@ -3619,10 +3909,10 @@ 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 @@ -3637,10 +3927,10 @@ 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 @@ -3677,18 +3967,6 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 5 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 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 Reducer 7 Reduce Operator Tree: Group By Operator @@ -3781,24 +4059,28 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Local Work: Map Reduce Local Work @@ -3812,26 +4094,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 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) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -3914,53 +4200,61 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Local Work: Map Reduce Local Work Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col3 (type: string) - 1 hr (type: string) Select Operator expressions: hr (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Local Work: Map Reduce Local Work @@ -3975,34 +4269,38 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 input vertices: - 1 Map 4 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -4080,43 +4378,47 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Local Work: Map Reduce Local Work @@ -4131,24 +4433,28 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -4227,24 +4533,28 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Local Work: Map Reduce Local Work @@ -4260,24 +4570,28 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -4327,29 +4641,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) Select Operator - expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Spark HashTable Sink Operator + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToDouble(hr) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Local Work: Map Reduce Local Work @@ -4363,20 +4681,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4446,29 +4765,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) Select Operator expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Spark HashTable Sink Operator + keys: + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Select Operator + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: (hr * 2) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: (UDFToDouble(hr) * 2.0) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Local Work: Map Reduce Local Work @@ -4482,20 +4805,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4560,7 +4884,6 @@ 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 'Stage-1:MAPRED' 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 @@ -4587,10 +4910,10 @@ 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 @@ -4608,12 +4931,24 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Stage: Stage-1 Spark @@ -4625,19 +4960,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col0 (type: string) + 1 _col0 (type: string) input vertices: 1 Reducer 4 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4670,18 +5007,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Stage-1:MAPRED' 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 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: 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' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -4717,11 +5057,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Local Work: Map Reduce Local Work @@ -4735,31 +5097,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -4811,16 +5172,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 3 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 3 Stage: Stage-3 Spark @@ -4831,10 +5196,14 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -4853,24 +5222,28 @@ STAGE PLANS: Filter Operator predicate: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -4901,15 +5274,46 @@ POSTHOOK: query: -- full outer EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.date = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + + Stage: Stage-3 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -4917,46 +5321,56 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map 4 + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 3 <- Map 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 2 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Outer Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) 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 - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work Reducer 3 Reduce Operator Tree: Group By Operator @@ -5005,53 +5419,45 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Local Work: Map Reduce Local Work Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 '11' (type: string) - 1 '11' (type: string) Select Operator - expressions: '11' (type: string) - outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark HashTable Sink Operator + keys: + 0 '11' (type: string) + 1 '11' (type: string) Local Work: Map Reduce Local Work @@ -5065,35 +5471,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr = 11) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 '11' (type: string) - 1 '11' (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) input vertices: - 1 Map 4 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 1 Map 3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 '11' (type: string) + 1 '11' (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -5157,15 +5566,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + filterExpr: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + predicate: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -5182,19 +5595,23 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 0 Map 1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Spark HashTable Sink Operator + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 '13' (type: string) - 1 '13' (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 '13' (type: string) + 1 '13' (type: string) Local Work: Map Reduce Local Work @@ -5208,29 +5625,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr = 13) (type: boolean) + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr = 13) (type: boolean) + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 '13' (type: string) - 1 '13' (type: string) - input vertices: - 0 Map 2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 '13' (type: string) + 1 '13' (type: string) + input vertices: + 0 Map 2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 4 @@ -5288,10 +5707,10 @@ 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 @@ -5306,10 +5725,10 @@ 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 @@ -5407,10 +5826,10 @@ 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 @@ -5425,10 +5844,10 @@ 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 ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out index 9cab06c..c8f6cd7 100644 --- ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out @@ -58,10 +58,10 @@ 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 @@ -71,6 +71,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -89,7 +90,6 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart_date - Execution mode: vectorized Stage: Stage-0 Move Operator @@ -210,16 +210,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Execution mode: vectorized Stage: Stage-1 @@ -235,11 +239,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -249,11 +257,15 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -261,8 +273,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -274,6 +286,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -287,7 +300,6 @@ STAGE PLANS: 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 Fetch Operator @@ -336,11 +348,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -350,11 +366,15 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -362,8 +382,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -375,6 +395,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -388,7 +409,6 @@ STAGE PLANS: 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 Fetch Operator @@ -459,40 +479,49 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Execution mode: vectorized Map 8 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -507,12 +536,16 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: hr (type: string) + 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 + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -522,40 +555,49 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: string) - sort order: + - Map-reduce partition columns: hr (type: string) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 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: 172 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: @@ -563,8 +605,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -576,6 +618,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -589,7 +632,6 @@ STAGE PLANS: 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 Fetch Operator @@ -645,12 +687,16 @@ STAGE PLANS: alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: hr (type: string) + 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 + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -660,40 +706,49 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: string) - sort order: + - Map-reduce partition columns: hr (type: string) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 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: 172 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: @@ -701,8 +756,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -714,6 +769,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -727,7 +783,6 @@ STAGE PLANS: 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 Fetch Operator @@ -789,48 +844,58 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -844,33 +909,42 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -882,6 +956,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -895,7 +970,6 @@ STAGE PLANS: 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 Fetch Operator @@ -944,33 +1018,42 @@ STAGE PLANS: alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -982,6 +1065,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -995,7 +1079,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1062,16 +1145,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Execution mode: vectorized Stage: Stage-1 @@ -1087,11 +1174,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -1101,11 +1192,15 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1113,8 +1208,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1126,6 +1221,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1139,7 +1235,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1188,11 +1283,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan @@ -1202,20 +1301,24 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1227,6 +1330,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1240,7 +1344,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1296,25 +1399,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToDouble(hr) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -1327,39 +1435,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(hr) (type: double) + key expressions: UDFToDouble(_col0) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(hr) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1370,6 +1484,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1383,7 +1498,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1428,25 +1542,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Select Operator + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: (hr * 2) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: (UDFToDouble(hr) * 2.0) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -1459,39 +1578,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (hr * 2) (type: double) + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) sort order: + - Map-reduce partition columns: (hr * 2) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: double) - sort order: + - Map-reduce partition columns: hr (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 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: 94 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1502,6 +1627,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1515,7 +1641,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1562,39 +1687,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(hr) (type: double) + key expressions: UDFToDouble(_col0) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(hr) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1605,6 +1736,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1618,7 +1750,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1665,39 +1796,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (hr * 2) (type: double) + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) sort order: + - Map-reduce partition columns: (hr * 2) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: hr (type: double) - sort order: + - Map-reduce partition columns: hr (type: double) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 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: 94 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1708,6 +1845,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1721,7 +1859,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1779,25 +1916,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToString(hr) (type: string) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: UDFToString(_col0) (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToString((hr * 2)) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -1810,39 +1952,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((hr * 2)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((hr * 2)) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToString((hr * 2)) (type: string) + key expressions: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) sort order: + - Map-reduce partition columns: UDFToString((hr * 2)) (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString(hr) (type: string) - sort order: + - Map-reduce partition columns: UDFToString(hr) (type: string) + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToString(_col0) (type: string) + sort order: + + Map-reduce partition columns: UDFToString(_col0) (type: string) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToString((hr * 2)) (type: string) - 1 UDFToString(hr) (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + 1 UDFToString(_col0) (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1853,6 +2001,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1866,7 +2015,6 @@ STAGE PLANS: 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 Fetch Operator @@ -1906,7 +2054,6 @@ 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 JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work '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 @@ -1914,15 +2061,65 @@ POSTHOOK: 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' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark + Edges: + Reducer 7 <- Map 6 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (ds = '2008-04-08') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '2008-04-08' (type: string) + outputColumnNames: ds + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reducer 7 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Stage: Stage-1 Spark Edges: Reducer 5 <- Map 4 (GROUP, 2) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2) Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: @@ -1930,13 +2127,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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 4 Map Operator Tree: TableScan @@ -1945,10 +2146,10 @@ 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 @@ -1963,9 +2164,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 - 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1976,6 +2177,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1989,20 +2191,19 @@ STAGE PLANS: 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 Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator + 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 - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Stage: Stage-0 Fetch Operator @@ -2010,18 +2211,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work '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 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: 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' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -2037,7 +2241,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join JOIN[4][tables = [srcpart, srcpart_date_hour]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2061,23 +2265,32 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((date = '2008-04-08') and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((date = '2008-04-08') and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col2 (type: string) + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator @@ -2086,10 +2299,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col3, _col7, _col9 + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 = _col7) or (_col3 = _col9)) (type: boolean) + predicate: ((_col0 = _col2) or (_col1 = _col4)) (type: boolean) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -2103,6 +2316,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2116,7 +2330,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2124,7 +2337,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [srcpart, srcpart_date_hour]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2164,48 +2377,58 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Stage: Stage-1 Spark @@ -2219,50 +2442,54 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: ds (type: string), hr (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) - outputColumnNames: _col2, _col3, _col7, _col9 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 = _col7) and (_col3 = _col9)) (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2276,7 +2503,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2310,10 +2536,44 @@ POSTHOOK: query: -- left join EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + Stage: Stage-1 Spark Edges: @@ -2325,49 +2585,56 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2381,7 +2648,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2416,16 +2682,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 4 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 4 Execution mode: vectorized Stage: Stage-1 @@ -2444,30 +2714,38 @@ STAGE PLANS: Filter Operator predicate: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 Reducer 2 Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2479,6 +2757,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2492,7 +2771,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2507,10 +2785,44 @@ POSTHOOK: query: -- full outer EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + Stage: Stage-1 Spark Edges: @@ -2523,48 +2835,54 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 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 4 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: - Outer Join 0 to 1 + Right Outer Join0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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 - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2578,7 +2896,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2617,40 +2934,21 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '11' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 Stage: Stage-1 Spark @@ -2664,13 +2962,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr = 11) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -2680,34 +2981,41 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '11' (type: string) - sort order: + - Map-reduce partition columns: '11' (type: string) + Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '11' (type: string) + sort order: + + Map-reduce partition columns: '11' (type: string) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '11' (type: string) @@ -2720,8 +3028,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2733,6 +3041,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2746,7 +3055,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2796,16 +3104,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + filterExpr: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + predicate: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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: 0 Basic stats: PARTIAL Column stats: NONE + Execution mode: vectorized Map 5 Map Operator Tree: TableScan @@ -2815,34 +3128,41 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 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: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr = 13) (type: boolean) + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr = 13) (type: boolean) + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '13' (type: string) - sort order: + - Map-reduce partition columns: '13' (type: string) + Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '13' (type: string) + sort order: + + Map-reduce partition columns: '13' (type: string) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: '13' (type: string) @@ -2855,8 +3175,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() @@ -2868,6 +3188,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2881,7 +3202,6 @@ STAGE PLANS: 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 Fetch Operator @@ -2930,10 +3250,10 @@ 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 @@ -2948,10 +3268,10 @@ 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 @@ -2960,6 +3280,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 11 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -2989,6 +3310,7 @@ STAGE PLANS: target column name: ds target work: Map 1 Reducer 9 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3049,10 +3371,10 @@ 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 @@ -3067,10 +3389,10 @@ 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 @@ -3097,6 +3419,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3110,8 +3433,8 @@ STAGE PLANS: 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 Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3132,6 +3455,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reducer 7 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3199,10 +3523,10 @@ 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 @@ -3217,10 +3541,10 @@ 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 @@ -3229,6 +3553,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 11 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3258,6 +3583,7 @@ STAGE PLANS: target column name: ds target work: Map 1 Reducer 9 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3318,10 +3644,10 @@ 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 @@ -3336,10 +3662,10 @@ 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 @@ -3368,6 +3694,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -3381,8 +3708,8 @@ STAGE PLANS: 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 Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3403,6 +3730,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reducer 7 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3473,10 +3801,10 @@ 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 @@ -3491,10 +3819,10 @@ 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 @@ -3503,6 +3831,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 11 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3532,6 +3861,7 @@ STAGE PLANS: target column name: ds target work: Map 1 Reducer 13 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3561,6 +3891,7 @@ STAGE PLANS: target column name: ds target work: Map 1 Reducer 15 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3590,6 +3921,7 @@ STAGE PLANS: target column name: ds target work: Map 4 Reducer 17 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3635,20 +3967,16 @@ 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 6 Map Operator Tree: TableScan @@ -3656,10 +3984,10 @@ 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 @@ -3674,10 +4002,10 @@ 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 @@ -3686,6 +4014,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -3697,7 +4026,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Reducer 3 Reduce Operator Tree: Join Operator @@ -3716,6 +4044,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -3727,8 +4056,8 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Reducer 7 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3749,6 +4078,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reducer 9 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3820,27 +4150,31 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Stage: Stage-1 Spark @@ -3854,27 +4188,32 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3888,7 +4227,6 @@ STAGE PLANS: 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 Fetch Operator @@ -3955,54 +4293,63 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col3 (type: string) - 1 hr (type: string) Select Operator expressions: hr (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4017,37 +4364,42 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 hr (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 input vertices: - 1 Map 4 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4061,7 +4413,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4123,43 +4474,48 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4174,27 +4530,32 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string), hr (type: string) - 1 ds (type: string), hr (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4208,7 +4569,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4271,27 +4631,31 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Stage: Stage-1 Spark @@ -4305,27 +4669,32 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4339,7 +4708,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4373,29 +4741,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) Select Operator - expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Spark HashTable Sink Operator + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToDouble(hr) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4409,20 +4782,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(hr) (type: double) - 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4435,6 +4809,7 @@ STAGE PLANS: Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4448,7 +4823,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4493,29 +4867,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (hr is not null and (hour = 11)) (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr is not null and (hour = 11)) (type: boolean) + predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) Select Operator expressions: hr (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Spark HashTable Sink Operator + keys: + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) + Select Operator + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: (hr * 2) + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: (UDFToDouble(hr) * 2.0) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4529,20 +4908,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr * 2) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (hr * 2) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (hr * 2) (type: double) - 1 hr (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4555,6 +4935,7 @@ STAGE PLANS: Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4568,7 +4949,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4608,7 +4988,6 @@ 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 'Stage-1:MAPRED' 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 @@ -4635,10 +5014,10 @@ 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 @@ -4648,6 +5027,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reducer 4 + Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4656,13 +5036,24 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - Execution mode: vectorized + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 Stage: Stage-1 Spark @@ -4674,19 +5065,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col0 (type: string) + 1 _col0 (type: string) input vertices: 1 Reducer 4 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -4699,6 +5092,7 @@ STAGE PLANS: Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4712,7 +5106,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4720,18 +5113,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Stage-1:MAPRED' 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 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: 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' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -4767,14 +5163,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Filter Operator + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Stage: Stage-1 Spark @@ -4786,34 +5204,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4827,7 +5245,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4863,16 +5280,20 @@ STAGE PLANS: expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 3 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 3 Execution mode: vectorized Stage: Stage-3 @@ -4884,10 +5305,14 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -4906,28 +5331,33 @@ STAGE PLANS: Filter Operator predicate: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4941,7 +5371,6 @@ STAGE PLANS: 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 Fetch Operator @@ -4956,15 +5385,47 @@ POSTHOOK: query: -- full outer EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + + Stage: Stage-3 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -4972,48 +5433,59 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map 4 + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 3 <- Map 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 2 Map Operator Tree: TableScan alias: srcpart_date + filterExpr: (date = '2008-04-08') (type: boolean) Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE - value expressions: date (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Outer Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - outputColumnNames: _col8 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col8 = '2008-04-08') (type: boolean) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash + Filter Operator + predicate: (date = '2008-04-08') (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) 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 - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + value expressions: _col0 (type: bigint) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -5027,7 +5499,6 @@ STAGE PLANS: 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 Fetch Operator @@ -5062,54 +5533,47 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((hr is not null and (hour = 11)) and (hr = 11)) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 '11' (type: string) - 1 '11' (type: string) Select Operator - expressions: '11' (type: string) - outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Spark HashTable Sink Operator + keys: + 0 '11' (type: string) + 1 '11' (type: string) + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -5123,38 +5587,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr = 11) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 '11' (type: string) - 1 '11' (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) input vertices: - 1 Map 4 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 1 Map 3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 '11' (type: string) + 1 '11' (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -5168,7 +5636,6 @@ STAGE PLANS: 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 Fetch Operator @@ -5216,15 +5683,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + filterExpr: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((ds is not null and hr is not null) and (hr = 13)) (type: boolean) + predicate: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string) - 1 ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Execution mode: vectorized Local Work: Map Reduce Local Work @@ -5241,22 +5713,26 @@ STAGE PLANS: Filter Operator predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 ds (type: string) - 1 ds (type: string) - input vertices: - 0 Map 1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Spark HashTable Sink Operator + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 '13' (type: string) - 1 '13' (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 '13' (type: string) + 1 '13' (type: string) + Execution mode: vectorized Local Work: Map Reduce Local Work - Execution mode: vectorized Stage: Stage-1 Spark @@ -5268,32 +5744,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: (hr = 13) (type: boolean) + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (hr = 13) (type: boolean) + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 '13' (type: string) - 1 '13' (type: string) - input vertices: - 0 Map 2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 '13' (type: string) + 1 '13' (type: string) + input vertices: + 0 Map 2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -5307,7 +5787,6 @@ STAGE PLANS: 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 Fetch Operator @@ -5349,10 +5828,10 @@ 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 @@ -5367,10 +5846,10 @@ 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 @@ -5379,6 +5858,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 11 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -5408,6 +5888,7 @@ STAGE PLANS: target column name: ds target work: Map 1 Reducer 9 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -5468,10 +5949,10 @@ 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 @@ -5486,10 +5967,10 @@ 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 @@ -5518,6 +5999,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -5531,8 +6013,8 @@ STAGE PLANS: 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 Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -5553,6 +6035,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reducer 7 + Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -5652,43 +6135,47 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and UDFToDouble(hr) is not null) and (hour = 11)) and ((date = '2008-04-08') or (date = '2008-04-09'))) (type: boolean) + filterExpr: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and UDFToDouble(hr) is not null) and (hour = 11)) and ((date = '2008-04-08') or (date = '2008-04-09'))) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 ds (type: string), UDFToDouble(hr) (type: double) - 1 ds (type: string), UDFToDouble(hr) (type: double) + predicate: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: ds - target work: Map 1 - Select Operator - expressions: UDFToDouble(hr) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Select Operator + expressions: UDFToDouble(_col2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Spark Partition Pruning Sink Operator - partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - target column name: hr - target work: Map 1 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 Local Work: Map Reduce Local Work @@ -5702,20 +6189,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_orc - filterExpr: UDFToDouble(hr) is not null (type: boolean) Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 ds (type: string), UDFToDouble(hr) (type: double) - 1 ds (type: string), UDFToDouble(hr) (type: double) + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 103400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git ql/src/test/results/clientpositive/spark/subquery_in.q.out ql/src/test/results/clientpositive/spark/subquery_in.q.out index dc9109c..1bc0824 100644 --- ql/src/test/results/clientpositive/spark/subquery_in.q.out +++ ql/src/test/results/clientpositive/spark/subquery_in.q.out @@ -785,7 +785,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) diff --git ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out index 010bb0c..6475d90 100644 --- ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out @@ -100,7 +100,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) @@ -202,7 +202,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: ((l_shipmode = 'AIR') and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) @@ -262,7 +262,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) diff --git ql/src/test/results/clientpositive/subquery_in.q.out ql/src/test/results/clientpositive/subquery_in.q.out index 0bbefc2..6463bf1 100644 --- ql/src/test/results/clientpositive/subquery_in.q.out +++ ql/src/test/results/clientpositive/subquery_in.q.out @@ -790,7 +790,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) diff --git ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out index 7995873..67104e4 100644 --- ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out @@ -1041,10 +1041,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -1179,10 +1179,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2420,10 +2420,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -4281,10 +4281,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5697,10 +5697,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and ((date = '2008-04-08') or (date = '2008-04-09'))) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and ((date = '2008-04-08') or (date = '2008-04-09'))) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) diff --git ql/src/test/results/clientpositive/tez/explainuser_1.q.out ql/src/test/results/clientpositive/tez/explainuser_1.q.out index 120894d..f4f4d9f 100644 --- ql/src/test/results/clientpositive/tez/explainuser_1.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_1.q.out @@ -429,7 +429,7 @@ Stage-0 Group By Operator [GBY_14] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_49] (rows=3 width=93) - predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_11] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 3 [SIMPLE_EDGE] @@ -449,7 +449,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_48] (rows=3 width=93) - predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -528,7 +528,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_44] (rows=1 width=93) - 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) + 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) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 9 [SIMPLE_EDGE] @@ -544,7 +544,7 @@ Stage-0 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_45] (rows=1 width=93) - 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) + 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) TableScan [TS_11] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -606,7 +606,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_34] (rows=1 width=93) - 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)) + 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)) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 7 [SIMPLE_EDGE] @@ -622,7 +622,7 @@ Stage-0 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_35] (rows=1 width=93) - 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)) + 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)) TableScan [TS_11] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -692,7 +692,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_39] (rows=1 width=93) - 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)) + 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)) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 9 [SIMPLE_EDGE] @@ -712,7 +712,7 @@ Stage-0 Group By Operator [GBY_14] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_40] (rows=1 width=93) - 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)) + 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)) TableScan [TS_11] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -781,7 +781,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_39] (rows=1 width=93) - 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) + 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) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 7 [SIMPLE_EDGE] @@ -797,7 +797,7 @@ Stage-0 Group By Operator [GBY_11] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_40] (rows=1 width=93) - 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) + 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) TableScan [TS_8] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1229,7 +1229,7 @@ Stage-0 Select Operator [SEL_2] (rows=5 width=74) Output:["_col0","_col1","_col2"] Filter Operator [FIL_24] (rows=5 width=74) - predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 4 [SIMPLE_EDGE] @@ -1238,7 +1238,7 @@ Stage-0 Select Operator [SEL_5] (rows=5 width=71) Output:["_col0","_col1"] Filter Operator [FIL_25] (rows=5 width=74) - predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_3] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1585,7 +1585,7 @@ Stage-0 Select Operator [SEL_2] (rows=6 width=77) Output:["_col0","_col1"] Filter Operator [FIL_15] (rows=6 width=77) - predicate:((key is not null and ((c_int + 1) = 2)) and ((c_int > 0) or (c_float >= 0.0))) + predicate:(key is not null and ((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 3 [SIMPLE_EDGE] @@ -1625,7 +1625,7 @@ Stage-0 Select Operator [SEL_2] (rows=5 width=74) Output:["_col0","_col1","_col2"] Filter Operator [FIL_25] (rows=5 width=74) - predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 3 [SIMPLE_EDGE] @@ -1636,7 +1636,7 @@ Stage-0 Select Operator [SEL_5] (rows=5 width=68) Output:["_col0"] Filter Operator [FIL_26] (rows=5 width=74) - predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0)) and key is not null) TableScan [TS_3] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 4 [SIMPLE_EDGE] @@ -1717,7 +1717,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_48] (rows=1 width=93) - 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 (((c_int + 1) + 1) >= 0)) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0))) and (UDFToDouble(key) > 0.0)) + 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 (((c_int + 1) + 1) >= 0) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0)) and (UDFToDouble(key) > 0.0)) TableScan [TS_0] (rows=20 width=83) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 9 [SIMPLE_EDGE] @@ -1739,7 +1739,7 @@ Stage-0 Group By Operator [GBY_15] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_49] (rows=1 width=93) - 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)) + 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)) TableScan [TS_12] (rows=20 width=83) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -2133,7 +2133,7 @@ Stage-0 Select Operator [SEL_2] (rows=16 width=16) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_28] (rows=16 width=16) - predicate:((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) + predicate:(l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) TableScan [TS_0] (rows=100 width=16) default@lineitem,lineitem,Tbl:COMPLETE,Col:COMPLETE,Output:["l_orderkey","l_partkey","l_suppkey","l_linenumber"] <-Map 4 [SIMPLE_EDGE] @@ -2144,7 +2144,7 @@ Stage-0 Select Operator [SEL_5] (rows=14 width=4) Output:["_col0"] Filter Operator [FIL_29] (rows=14 width=96) - predicate:(((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) + predicate:((l_shipmode = 'AIR') and l_orderkey is not null and (l_linenumber = 1)) TableScan [TS_3] (rows=100 width=96) default@lineitem,lineitem,Tbl:COMPLETE,Col:COMPLETE,Output:["l_orderkey","l_linenumber","l_shipmode"] <-Reducer 6 [SIMPLE_EDGE] diff --git ql/src/test/results/clientpositive/tez/explainuser_2.q.out ql/src/test/results/clientpositive/tez/explainuser_2.q.out index d8eb6c8..651b66b 100644 --- ql/src/test/results/clientpositive/tez/explainuser_2.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_2.q.out @@ -367,7 +367,7 @@ Stage-0 Select Operator [SEL_11] (rows=42 width=34) Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_86] (rows=42 width=34) - predicate:((((((v3 = 'ssv3') and k2 is not null) and k3 is not null) and k1 is not null) and v1 is not null) and v2 is not null) + predicate:((v3 = 'ssv3') and k2 is not null and k3 is not null and k1 is not null and v1 is not null and v2 is not null) TableScan [TS_9] (rows=85 width=34) default@ss,ss,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] <-Map 7 [SIMPLE_EDGE] @@ -390,7 +390,7 @@ Stage-0 Select Operator [SEL_20] (rows=42 width=34) Output:["_col0","_col2","_col3","_col4","_col5"] Filter Operator [FIL_89] (rows=42 width=34) - predicate:((((((v1 = 'srv1') and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) and k1 is not null) + predicate:((v1 = 'srv1') and k2 is not null and k3 is not null and v2 is not null and v3 is not null and k1 is not null) TableScan [TS_18] (rows=85 width=34) default@sr,sr,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] <-Map 17 [SIMPLE_EDGE] @@ -413,7 +413,7 @@ Stage-0 Select Operator [SEL_2] (rows=170 width=34) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_83] (rows=170 width=34) - predicate:((v2 is not null and v3 is not null) and k1 is not null) + predicate:(v2 is not null and v3 is not null and k1 is not null) TableScan [TS_0] (rows=170 width=34) default@cs,cs,Tbl:COMPLETE,Col:NONE,Output:["k1","v2","k3","v3"] <-Map 6 [SIMPLE_EDGE] @@ -1066,7 +1066,7 @@ Stage-0 <-Select Operator [SEL_2] (rows=170 width=34) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_83] (rows=170 width=34) - predicate:((v2 is not null and v3 is not null) and k1 is not null) + predicate:(v2 is not null and v3 is not null and k1 is not null) TableScan [TS_0] (rows=170 width=34) default@cs,cs,Tbl:COMPLETE,Col:NONE,Output:["k1","v2","k3","v3"] <-Select Operator [SEL_40] (rows=1464 width=10) @@ -1084,7 +1084,7 @@ Stage-0 Select Operator [SEL_20] (rows=42 width=34) Output:["_col0","_col2","_col3","_col4","_col5"] Filter Operator [FIL_89] (rows=42 width=34) - predicate:((((((v1 = 'srv1') and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) and k1 is not null) + predicate:((v1 = 'srv1') and k2 is not null and k3 is not null and v2 is not null and v3 is not null and k1 is not null) TableScan [TS_18] (rows=85 width=34) default@sr,sr,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] <-Select Operator [SEL_23] (rows=250 width=10) @@ -1123,7 +1123,7 @@ Stage-0 Select Operator [SEL_11] (rows=42 width=34) Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_86] (rows=42 width=34) - predicate:((((((v3 = 'ssv3') and k2 is not null) and k3 is not null) and k1 is not null) and v1 is not null) and v2 is not null) + predicate:((v3 = 'ssv3') and k2 is not null and k3 is not null and k1 is not null and v1 is not null and v2 is not null) TableScan [TS_9] (rows=85 width=34) default@ss,ss,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] <-Select Operator [SEL_8] (rows=1000 width=10) diff --git ql/src/test/results/clientpositive/tez/explainuser_4.q.out ql/src/test/results/clientpositive/tez/explainuser_4.q.out index 3a3e17d..fa9b46c 100644 --- ql/src/test/results/clientpositive/tez/explainuser_4.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_4.q.out @@ -49,7 +49,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] Filter Operator [FIL_16] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] @@ -130,7 +130,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0"] Filter Operator [FIL_18] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] @@ -210,7 +210,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0"] Filter Operator [FIL_20] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] @@ -281,7 +281,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] Filter Operator [FIL_16] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] <-Map 1 [CUSTOM_SIMPLE_EDGE] @@ -362,7 +362,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0"] Filter Operator [FIL_18] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] <-Map 1 [CUSTOM_SIMPLE_EDGE] @@ -442,7 +442,7 @@ Stage-0 Select Operator [SEL_5] (rows=6144 width=215) Output:["_col0"] Filter Operator [FIL_20] (rows=6144 width=215) - predicate:((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) + predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) TableScan [TS_3] (rows=12288 width=215) default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] <-Map 1 [CUSTOM_SIMPLE_EDGE] diff --git ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out index f2a7aef..2094071 100644 --- ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out +++ ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out @@ -226,7 +226,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key is not null and value is not null) and (value <> '')) (type: boolean) + predicate: (key is not null and value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out index d397855..afb3ea6 100644 --- ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out +++ ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out @@ -1104,7 +1104,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key is not null and value is not null) and (value < 'zzzzzzzzzz')) and (key < 'zzzzzzzz')) (type: boolean) + predicate: ((value < 'zzzzzzzzzz') and (key < 'zzzzzzzz')) (type: boolean) Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -1160,7 +1160,7 @@ STAGE PLANS: alias: y1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and (value < 'zzzzzzzz')) and (key < 'zzzzzzzz')) (type: boolean) + predicate: ((value < 'zzzzzzzz') and (key < 'zzzzzzzz')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -1173,7 +1173,7 @@ STAGE PLANS: alias: z2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key < 'zzzzzzzzzz')) and (value < 'zzzzzzzzzz')) (type: boolean) + predicate: ((key < 'zzzzzzzzzz') and (value < 'zzzzzzzzzz')) (type: boolean) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) @@ -1288,7 +1288,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key is not null and value is not null) and (value < 'zzzzzzzzzz')) and (key < 'zzzzzzzz')) (type: boolean) + predicate: ((value < 'zzzzzzzzzz') and (key < 'zzzzzzzz')) (type: boolean) Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -1346,7 +1346,7 @@ STAGE PLANS: alias: y1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key is not null and (value < 'zzzzzzzz')) and (key < 'zzzzzzzz')) (type: boolean) + predicate: ((value < 'zzzzzzzz') and (key < 'zzzzzzzz')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -1359,7 +1359,7 @@ STAGE PLANS: alias: z2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key < 'zzzzzzzzzz')) and (value < 'zzzzzzzzzz')) (type: boolean) + predicate: ((key < 'zzzzzzzzzz') and (value < 'zzzzzzzzzz')) (type: boolean) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) diff --git ql/src/test/results/clientpositive/tez/subquery_in.q.out ql/src/test/results/clientpositive/tez/subquery_in.q.out index 2c04009..1aa0a19 100644 --- ql/src/test/results/clientpositive/tez/subquery_in.q.out +++ ql/src/test/results/clientpositive/tez/subquery_in.q.out @@ -790,7 +790,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) diff --git ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_1.q.out ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_1.q.out index 7352d8e..17b19be 100644 --- ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_1.q.out +++ ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_1.q.out @@ -52,7 +52,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -177,7 +177,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -300,7 +300,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -446,7 +446,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -574,7 +574,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -700,7 +700,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) diff --git ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_1.q.out ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_1.q.out index d532d6b..b19b9f7 100644 --- ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_1.q.out +++ ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_1.q.out @@ -52,7 +52,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -177,7 +177,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -300,7 +300,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -447,7 +447,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -579,7 +579,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -709,7 +709,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cint is not null and cbigint is not null) and cint BETWEEN 1000000 AND 3000000) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) diff --git ql/src/test/results/clientpositive/tez/vector_decimal_cast.q.out ql/src/test/results/clientpositive/tez/vector_decimal_cast.q.out index 35b7e87..16d9929 100644 --- ql/src/test/results/clientpositive/tez/vector_decimal_cast.q.out +++ ql/src/test/results/clientpositive/tez/vector_decimal_cast.q.out @@ -13,7 +13,7 @@ STAGE PLANS: TableScan alias: alltypesorc Filter Operator - predicate: (((cdouble is not null and cint is not null) and cboolean1 is not null) and ctimestamp1 is not null) (type: boolean) + predicate: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean) Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 diff --git ql/src/test/results/clientpositive/tez/vector_decimal_expressions.q.out ql/src/test/results/clientpositive/tez/vector_decimal_expressions.q.out index 432543b..bee918f 100644 --- ql/src/test/results/clientpositive/tez/vector_decimal_expressions.q.out +++ ql/src/test/results/clientpositive/tez/vector_decimal_expressions.q.out @@ -38,7 +38,7 @@ STAGE PLANS: alias: decimal_test Statistics: Num rows: 12288 Data size: 2128368 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cdecimal1 > 0) and (cdecimal1 < 12345.5678)) and (cdecimal2 <> 0)) and (cdecimal2 > 1000)) and cdouble is not null) (type: boolean) + predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) Statistics: Num rows: 455 Data size: 78809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((UDFToDouble(cdecimal1) + 2.34) / UDFToDouble(cdecimal2)) (type: double), (UDFToDouble(cdecimal1) * (UDFToDouble(cdecimal2) / 3.4)) (type: double), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), UDFToString(cdecimal2) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) diff --git ql/src/test/results/clientpositive/tez/vector_leftsemi_mapjoin.q.out ql/src/test/results/clientpositive/tez/vector_leftsemi_mapjoin.q.out index 9c79c1a..1bb0afb 100644 --- ql/src/test/results/clientpositive/tez/vector_leftsemi_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vector_leftsemi_mapjoin.q.out @@ -734,7 +734,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -2992,7 +2992,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -5273,7 +5273,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -7598,7 +7598,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -9928,7 +9928,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -12253,7 +12253,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out index 2db5c7c..d3f03bb 100644 --- ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out @@ -40,7 +40,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) @@ -196,7 +196,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) @@ -241,7 +241,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: ((l_shipmode = 'AIR') and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) diff --git ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out index 13735e6..ef2fd3d 100644 --- ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out @@ -819,10 +819,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -959,10 +959,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2220,10 +2220,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3990,10 +3990,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5432,10 +5432,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((ds is not null and hr is not null) and ((date = '2008-04-08') or (date = '2008-04-09'))) and (UDFToDouble(hour) = 11.0)) (type: boolean) + filterExpr: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ds is not null and hr is not null) and ((date = '2008-04-08') or (date = '2008-04-09'))) and (UDFToDouble(hour) = 11.0)) (type: boolean) + predicate: (ds is not null and hr is not null and ((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) (type: boolean) Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) diff --git ql/src/test/results/clientpositive/vector_decimal_cast.q.out ql/src/test/results/clientpositive/vector_decimal_cast.q.out index 05ba0f4..41bd393 100644 --- ql/src/test/results/clientpositive/vector_decimal_cast.q.out +++ ql/src/test/results/clientpositive/vector_decimal_cast.q.out @@ -14,7 +14,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cdouble is not null and cint is not null) and cboolean1 is not null) and ctimestamp1 is not null) (type: boolean) + predicate: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) diff --git ql/src/test/results/clientpositive/vector_decimal_expressions.q.out ql/src/test/results/clientpositive/vector_decimal_expressions.q.out index 9bc8ae0..cfc790b 100644 --- ql/src/test/results/clientpositive/vector_decimal_expressions.q.out +++ ql/src/test/results/clientpositive/vector_decimal_expressions.q.out @@ -32,7 +32,7 @@ STAGE PLANS: alias: decimal_test Statistics: Num rows: 12288 Data size: 2128368 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cdecimal1 > 0) and (cdecimal1 < 12345.5678)) and (cdecimal2 <> 0)) and (cdecimal2 > 1000)) and cdouble is not null) (type: boolean) + predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) Statistics: Num rows: 455 Data size: 78809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((UDFToDouble(cdecimal1) + 2.34) / UDFToDouble(cdecimal2)) (type: double), (UDFToDouble(cdecimal1) * (UDFToDouble(cdecimal2) / 3.4)) (type: double), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), UDFToString(cdecimal2) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) diff --git ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out index 581ce66..077e0bc 100644 --- ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out +++ ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out @@ -727,7 +727,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -2961,7 +2961,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -5201,7 +5201,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -7453,7 +7453,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -9705,7 +9705,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -11957,7 +11957,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out index e8cd48a..1acbac7 100644 --- ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out @@ -222,7 +222,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) @@ -466,7 +466,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: ((l_shipmode = 'AIR') and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) @@ -489,7 +489,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (l_partkey is not null and l_orderkey is not null and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int)