http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out index 8163773..86c5bd7 100644 --- a/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out +++ b/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out @@ -908,46 +908,46 @@ STAGE PLANS: outputColumnNames: _col2, _col4, _col5, _col6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col6 (type: string), _col5 (type: int), _col4 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4 + expressions: _col4 (type: int), _col5 (type: int), _col6 (type: string), _col2 (type: int) + outputColumnNames: _col4, _col5, _col6, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: avg(_col4), stddev_samp(_col4) - keys: _col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int) + aggregations: stddev_samp(_col2), avg(_col2) + keys: _col4 (type: int), _col5 (type: int), _col6 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int) - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col4 (type: struct<count:bigint,sum:double,input:int>), _col5 (type: struct<count:bigint,sum:double,variance:double>) + value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>) Reducer 15 Reduce Operator Tree: Group By Operator - aggregations: avg(VALUE._col0), stddev_samp(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), 4 (type: int) + aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col1, _col2, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: double), _col4 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col5 / _col4) > 1.0)) END (type: boolean) + predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col5 / _col4)) END (type: double) - outputColumnNames: _col1, _col2, _col4, _col5 + expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col4 (type: double), _col5 (type: double) + value expressions: _col3 (type: double), _col4 (type: double) Reducer 2 Reduce Operator Tree: Join Operator @@ -991,46 +991,46 @@ STAGE PLANS: outputColumnNames: _col2, _col4, _col5, _col6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col6 (type: string), _col5 (type: int), _col4 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4 + expressions: _col4 (type: int), _col5 (type: int), _col6 (type: string), _col2 (type: int) + outputColumnNames: _col4, _col5, _col6, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: avg(_col4), stddev_samp(_col4) - keys: _col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int) + aggregations: stddev_samp(_col2), avg(_col2) + keys: _col4 (type: int), _col5 (type: int), _col6 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int) - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col4 (type: struct<count:bigint,sum:double,input:int>), _col5 (type: struct<count:bigint,sum:double,variance:double>) + value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>) Reducer 5 Reduce Operator Tree: Group By Operator - aggregations: avg(VALUE._col0), stddev_samp(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), 3 (type: int) + aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col1, _col2, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: double), _col4 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col5 / _col4) > 1.0)) END (type: boolean) + predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col5 / _col4)) END (type: double) - outputColumnNames: _col1, _col2, _col4, _col5 + expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col4 (type: double), _col5 (type: double) + value expressions: _col3 (type: double), _col4 (type: double) Reducer 6 Reduce Operator Tree: Join Operator @@ -1039,10 +1039,10 @@ STAGE PLANS: keys: 0 _col2 (type: int), _col1 (type: int) 1 _col2 (type: int), _col1 (type: int) - outputColumnNames: _col1, _col2, _col4, _col5, _col7, _col8, _col10, _col11 + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), _col5 (type: double), _col7 (type: int), _col8 (type: int), _col10 (type: double), _col11 (type: double) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: double), _col6 (type: int), _col7 (type: int), _col8 (type: double), _col9 (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -1053,7 +1053,7 @@ STAGE PLANS: Reducer 7 Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 3 (type: int), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 4 (type: int), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out b/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out index a21ea9c..4c4ae03 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out @@ -836,16 +836,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: 1 (type: int), _col1 (type: string) + aggregations: count(key) + keys: key (type: string) mode: final - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 1 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + expressions: 1 (type: int), UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -974,7 +974,7 @@ SELECT 1, key, count(1) FROM T1 GROUP BY 1, key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl3 -POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ] +POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl3.key1 SIMPLE [] POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl3 @@ -1028,22 +1028,22 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), 1 (type: int), _col2 (type: string) - null sort order: aaa - sort order: +++ - Map-reduce partition columns: _col0 (type: string), 1 (type: int), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col3 (type: bigint) + value expressions: _col2 (type: bigint) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1103,12 +1103,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), 1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1184,7 +1184,7 @@ SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] @@ -3074,16 +3074,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3212,7 +3212,7 @@ SELECT key, 1, val, count(1) FROM T2 GROUP BY key, 1, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] @@ -3268,16 +3268,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string), 2 (type: int) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), 2 (type: int), UDFToInteger(_col4) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), 2 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3406,7 +3406,7 @@ SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2 POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl5 -POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.null, ] +POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl5.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl5.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl5.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] @@ -3459,16 +3459,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3657,16 +3657,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: _col0 (type: string), 2 (type: int), _col2 (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out b/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out index d0f5952..e575e97 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out @@ -855,16 +855,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: 1 (type: int), _col1 (type: string) + aggregations: count(key) + keys: key (type: string) mode: final - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 1 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + expressions: 1 (type: int), UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -993,7 +993,7 @@ SELECT 1, key, count(1) FROM T1 GROUP BY 1, key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl3 -POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ] +POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl3.key1 SIMPLE [] POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl3 @@ -1048,22 +1048,22 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), 1 (type: int), _col2 (type: string) - null sort order: aaa - sort order: +++ + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col3 (type: bigint) + value expressions: _col2 (type: bigint) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1123,30 +1123,30 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), 1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: partials - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), 1 (type: int), _col2 (type: string) - null sort order: aaa - sort order: +++ - Map-reduce partition columns: _col0 (type: string), 1 (type: int), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col3 (type: bigint) + value expressions: _col2 (type: bigint) auto parallelism: false Reducer 3 Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), 1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1222,7 +1222,7 @@ SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] @@ -3207,16 +3207,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3345,7 +3345,7 @@ SELECT key, 1, val, count(1) FROM T2 GROUP BY key, 1, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] @@ -3401,16 +3401,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string), 2 (type: int) + aggregations: count(val) + keys: key (type: string), val (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), 2 (type: int), UDFToInteger(_col4) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), 2 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3539,7 +3539,7 @@ SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2 POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl5 -POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.null, ] +POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl5.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl5.key2 SIMPLE [] POSTHOOK: Lineage: outputtbl5.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] @@ -3592,16 +3592,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3790,16 +3790,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: _col0 (type: string), 2 (type: int), _col2 (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join38.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join38.q.out b/ql/src/test/results/clientpositive/spark/join38.q.out index 71d59e2..5177dca 100644 --- a/ql/src/test/results/clientpositive/spark/join38.q.out +++ b/ql/src/test/results/clientpositive/spark/join38.q.out @@ -15,17 +15,17 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmp POSTHOOK: Lineage: tmp.col0 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col10 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col11 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col4 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col5 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col6 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col7 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col8 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.col9 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmp.col1 SIMPLE [] +POSTHOOK: Lineage: tmp.col10 SIMPLE [] +POSTHOOK: Lineage: tmp.col11 SIMPLE [] +POSTHOOK: Lineage: tmp.col2 SIMPLE [] +POSTHOOK: Lineage: tmp.col3 SIMPLE [] +POSTHOOK: Lineage: tmp.col4 SIMPLE [] +POSTHOOK: Lineage: tmp.col5 SIMPLE [] +POSTHOOK: Lineage: tmp.col6 SIMPLE [] +POSTHOOK: Lineage: tmp.col7 SIMPLE [] +POSTHOOK: Lineage: tmp.col8 SIMPLE [] +POSTHOOK: Lineage: tmp.col9 SIMPLE [] PREHOOK: query: select * from tmp PREHOOK: type: QUERY PREHOOK: Input: default@tmp http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join8.q.out b/ql/src/test/results/clientpositive/spark/join8.q.out index 270053c..412a9eb 100644 --- a/ql/src/test/results/clientpositive/spark/join8.q.out +++ b/ql/src/test/results/clientpositive/spark/join8.q.out @@ -161,7 +161,7 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [] POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out index 2c8034f..ee636a0 100644 --- a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out +++ b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select p1.p_name, p2.p_name from part p1 , part p2 PREHOOK: type: QUERY @@ -258,7 +258,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select p1.p_name, p2.p_name, p3.p_name from part p1 , part p2 , part p3 where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out index 0610d13..a9bbe15 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out @@ -192,7 +192,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name PREHOOK: type: QUERY @@ -301,7 +301,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey = 1 and p3.p_name = p2.p_name PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out index 0e748fb..ea5895b 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out @@ -196,7 +196,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name @@ -307,7 +307,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey = 1 and p3.p_name = p2.p_name http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out index 45fba92..303c77f 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out @@ -248,7 +248,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey + p_partkey = p1.p_partkey and p3_name = p2_name PREHOOK: type: QUERY @@ -357,7 +357,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey = 1 and p3_name = p2_name PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out index 9211cb6..641929c 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out @@ -252,7 +252,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey + p1.p_partkey = p1.p_partkey and p3_name = p2_name @@ -363,7 +363,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey = 1 and p3_name = p2_name http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_reorder.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_reorder.q.out b/ql/src/test/results/clientpositive/spark/join_reorder.q.out index df6a36e..cc9f9a5 100644 --- a/ql/src/test/results/clientpositive/spark/join_reorder.q.out +++ b/ql/src/test/results/clientpositive/spark/join_reorder.q.out @@ -98,9 +98,9 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + key expressions: (UDFToDouble(_col0) + 1.0) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + Map-reduce partition columns: (UDFToDouble(_col0) + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 2 @@ -110,7 +110,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + 1 (UDFToDouble(_col0) + 1.0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/join_view.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_view.q.out b/ql/src/test/results/clientpositive/spark/join_view.q.out index 14a28be..9d8f6d7 100644 --- a/ql/src/test/results/clientpositive/spark/join_view.q.out +++ b/ql/src/test/results/clientpositive/spark/join_view.q.out @@ -38,6 +38,7 @@ POSTHOOK: Input: default@invites POSTHOOK: Input: default@invites2 POSTHOOK: Output: database:default POSTHOOK: Output: default@v +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from v where ds='2011-09-01' PREHOOK: type: QUERY POSTHOOK: query: explain select * from v where ds='2011-09-01' @@ -50,7 +51,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -66,9 +67,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: '2011-09-01' (type: string) - sort order: + - Map-reduce partition columns: '2011-09-01' (type: string) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: string) Map 3 @@ -84,9 +83,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: '2011-09-01' (type: string) - sort order: + - Map-reduce partition columns: '2011-09-01' (type: string) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int) Reducer 2 @@ -95,8 +92,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out index 21b7519..cd16787 100644 --- a/ql/src/test/results/clientpositive/spark/pcr.q.out +++ b/ql/src/test/results/clientpositive/spark/pcr.q.out @@ -1547,7 +1547,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: 14 (type: int), KEY.reducesinkkey1 (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2445,19 +2445,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + auto parallelism: false Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-08' (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2710,19 +2714,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string), '2000-04-09' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) + auto parallelism: false Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-09' (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4159,7 +4167,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4344,7 +4352,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/ppd_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/ppd_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out index 1c2b592..f08eb4d 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -148,7 +148,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from ( select a.*,b.d d1,c.d d2 from @@ -271,7 +271,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from ( select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out index 312b3bd..ca6d1f8 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out @@ -43,35 +43,35 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((sqrt(key) <> 13.0) and (key > '10') and (key < '20') and (key > '15') and (key < '25')) (type: boolean) + predicate: ((key > '10') and (key < '20') and (key > '15') and (key < '25') and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '10') and (key < '20') and (key > '15') and (key < '25') and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((sqrt(key) <> 13.0) and (key > '10') and (key < '20') and (key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan @@ -95,7 +95,7 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) @@ -103,7 +103,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col0 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -417,35 +417,35 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((sqrt(key) <> 13.0) and (key > '10') and (key < '20') and (key > '15') and (key < '25')) (type: boolean) + predicate: ((key > '10') and (key < '20') and (key > '15') and (key < '25') and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '10') and (key < '20') and (key > '15') and (key < '25') and (sqrt(key) <> 13.0)) (type: boolean) + predicate: ((sqrt(key) <> 13.0) and (key > '10') and (key < '20') and (key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan @@ -469,7 +469,7 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) @@ -477,7 +477,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col0 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out index ef8c674..e4c3d2b 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out @@ -30,7 +30,7 @@ POSTHOOK: query: create table t4 (id int, key string, value string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@t4 -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from t1 full outer join t2 on t1.id=t2.id join t3 on t2.id=t3.id where t3.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 full outer join t2 on t1.id=t2.id join t3 on t2.id=t3.id where t3.id=20 @@ -128,7 +128,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t2.id=t3.id) where t2.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t2.id=t3.id) where t2.id=20 @@ -222,7 +222,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t1.id=t3.id) where t2.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t1.id=t3.id) where t2.id=20 http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/skewjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/skewjoin.q.out b/ql/src/test/results/clientpositive/spark/skewjoin.q.out index 1475995..6f9e674 100644 --- a/ql/src/test/results/clientpositive/spark/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/spark/skewjoin.q.out @@ -847,9 +847,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) + key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) + Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 @@ -860,7 +860,7 @@ STAGE PLANS: handleSkewJoin: true keys: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) - 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) + 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out index 4b392ba..75422ec 100644 --- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out +++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out @@ -46,8 +46,9 @@ POSTHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwr POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_bucket_3 -Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product -Warning: Shuffle Join JOIN[20][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 6' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[18][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 6' is a cross product +Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5 PREHOOK: type: QUERY @@ -64,7 +65,7 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -129,9 +130,7 @@ STAGE PLANS: 1 Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: @@ -139,8 +138,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), 5 (type: int) @@ -163,9 +162,7 @@ STAGE PLANS: 1 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 @@ -174,8 +171,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[29][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[30][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- explain -- select * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join src c on a.key=c.value @@ -245,8 +243,8 @@ STAGE PLANS: Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 Local Work: Map Reduce Local Work Map 3 @@ -293,8 +291,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 input vertices: 0 Map 1 Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE @@ -318,8 +316,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[29][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[30][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5 PREHOOK: type: QUERY PREHOOK: Input: default@smb_bucket_1 http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out index bbf24fd..71d6e09 100644 --- a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out @@ -77,7 +77,7 @@ SELECT 1, key, count(1) FROM T1 GROUP BY 1, key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -90,7 +90,7 @@ PREHOOK: query: SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -104,7 +104,7 @@ PREHOOK: query: SELECT key, 1, val, 2, count(1) FROM T1 GROUP BY key, 1, val, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -413,7 +413,7 @@ PREHOOK: Input: default@t2 #### A masked pattern was here #### Operator:JOIN_8 Table:default@t1 -Keys:val,key +Keys:key Table:default@t2 Keys:key @@ -439,7 +439,7 @@ Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 -Keys:val,key +Keys:key PREHOOK: query: -- no mapping on functions SELECT * @@ -474,7 +474,7 @@ PREHOOK: Input: default@t2 #### A masked pattern was here #### Operator:JOIN_8 Table:default@t1 -Keys:val,key +Keys:key Table:default@t2 Keys:key @@ -505,7 +505,7 @@ PREHOOK: Input: default@t3 #### A masked pattern was here #### Operator:JOIN_8 Table:default@t1 -Keys:val,key +Keys:key Table:default@t2 Keys:key @@ -518,6 +518,7 @@ Keys:val 13.0 1 17.0 1 46.0 1 +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 4' is a cross product PREHOOK: query: -- join followed by join SELECT * FROM @@ -543,7 +544,7 @@ PREHOOK: Input: default@t3 #### A masked pattern was here #### Operator:JOIN_8 Table:default@t1 -Keys:val,key +Keys:key Table:default@t2 Keys:key http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/spark/union_view.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_view.q.out b/ql/src/test/results/clientpositive/spark/union_view.q.out index 3372afb..7ac641f 100644 --- a/ql/src/test/results/clientpositive/spark/union_view.q.out +++ b/ql/src/test/results/clientpositive/spark/union_view.q.out @@ -541,14 +541,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col1, _col2 + expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int), _col1 (type: string) Map 3 Map Operator Tree: TableScan @@ -563,14 +563,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col1, _col2 + expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int), _col1 (type: string) Map 4 Map Operator Tree: TableScan @@ -585,18 +585,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col1, _col2 + expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int), _col1 (type: string) Reducer 2 Reduce Operator Tree: Select Operator - expressions: 86 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE File Output Operator