HIVE-11712: Duplicate groupby keys cause ClassCastException (Jimmy, reviewed by Xuefu)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/bb4f5e70 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/bb4f5e70 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/bb4f5e70 Branch: refs/heads/llap Commit: bb4f5e702b11720ca54e43ba4a6c3aff099b0f4c Parents: c40382d Author: Jimmy Xiang <jxi...@cloudera.com> Authored: Tue Sep 1 11:48:36 2015 -0700 Committer: Jimmy Xiang <jxi...@cloudera.com> Committed: Thu Sep 3 09:57:23 2015 -0700 ---------------------------------------------------------------------- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 4 + .../queries/clientpositive/groupby1_map_nomap.q | 2 + ql/src/test/queries/clientpositive/groupby6.q | 2 + .../clientpositive/groupby_grouping_id2.q | 2 + .../clientpositive/groupby_ppr_multi_distinct.q | 2 + ql/src/test/queries/clientpositive/having2.q | 27 + .../clientpositive/groupby1_map_nomap.q.out | 8 +- .../test/results/clientpositive/groupby6.q.out | 8 +- .../clientpositive/groupby_duplicate_key.q.out | 16 +- .../clientpositive/groupby_grouping_id2.q.out | 28 +- .../groupby_ppr_multi_distinct.q.out | 8 +- .../test/results/clientpositive/having2.q.out | 353 ++++++++++++ .../spark/groupby1_map_nomap.q.out | 564 ++++++++++--------- .../results/clientpositive/spark/groupby6.q.out | 20 +- .../spark/groupby_grouping_id2.q.out | 38 +- .../spark/groupby_ppr_multi_distinct.q.out | 16 +- 16 files changed, 761 insertions(+), 337 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index b809a23..778c7b2 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -4620,6 +4620,10 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { ExprNodeDesc grpByExprNode = genExprNodeDesc(grpbyExpr, groupByInputRowResolver); + if (ExprNodeDescUtils.indexOf(grpByExprNode, groupByKeys) >= 0) { + // Skip duplicated grouping keys + continue; + } groupByKeys.add(grpByExprNode); String field = getColumnInternalName(i); outputColumnNames.add(field); http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/queries/clientpositive/groupby1_map_nomap.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/groupby1_map_nomap.q b/ql/src/test/queries/clientpositive/groupby1_map_nomap.q index eb09a9c..b22a61e 100644 --- a/ql/src/test/queries/clientpositive/groupby1_map_nomap.q +++ b/ql/src/test/queries/clientpositive/groupby1_map_nomap.q @@ -2,6 +2,8 @@ set hive.map.aggr=true; set hive.groupby.skewindata=false; set hive.groupby.mapaggr.checkinterval=20; +-- SORT_QUERY_RESULTS + CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE; EXPLAIN http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/queries/clientpositive/groupby6.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/groupby6.q b/ql/src/test/queries/clientpositive/groupby6.q index 3a3cc58..17597cb 100755 --- a/ql/src/test/queries/clientpositive/groupby6.q +++ b/ql/src/test/queries/clientpositive/groupby6.q @@ -1,6 +1,8 @@ set hive.map.aggr=false; set hive.groupby.skewindata=true; +-- SORT_QUERY_RESULTS + CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE; EXPLAIN http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/queries/clientpositive/groupby_grouping_id2.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/groupby_grouping_id2.q b/ql/src/test/queries/clientpositive/groupby_grouping_id2.q index f451f17..5c05aad 100644 --- a/ql/src/test/queries/clientpositive/groupby_grouping_id2.q +++ b/ql/src/test/queries/clientpositive/groupby_grouping_id2.q @@ -4,6 +4,8 @@ LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt' INTO TABLE T1; set hive.groupby.skewindata = true; +-- SORT_QUERY_RESULTS + SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP; SELECT GROUPING__ID, count(*) http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/queries/clientpositive/groupby_ppr_multi_distinct.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/groupby_ppr_multi_distinct.q b/ql/src/test/queries/clientpositive/groupby_ppr_multi_distinct.q index 20c73bd..1249853 100644 --- a/ql/src/test/queries/clientpositive/groupby_ppr_multi_distinct.q +++ b/ql/src/test/queries/clientpositive/groupby_ppr_multi_distinct.q @@ -1,6 +1,8 @@ set hive.map.aggr=false; set hive.groupby.skewindata=false; +-- SORT_QUERY_RESULTS + CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE; EXPLAIN EXTENDED http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/queries/clientpositive/having2.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/having2.q b/ql/src/test/queries/clientpositive/having2.q index 282b2c0..83ae1e1 100644 --- a/ql/src/test/queries/clientpositive/having2.q +++ b/ql/src/test/queries/clientpositive/having2.q @@ -63,3 +63,30 @@ SELECT customer_name, SUM(customer_balance), SUM(order_quantity) FROM default.te (SUM(customer_balance) <= 4074689.000000041) AND (COUNT(s1.discount) <= 822) ); + +explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +); + +explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name, s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +); + +explain +SELECT distinct s1.customer_name as x, s1.customer_name as y +FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +); http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out index cc985a5..7cdf240 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/groupby6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby6.q.out b/ql/src/test/results/clientpositive/groupby6.q.out index b790224..d8cb2ac 100644 --- a/ql/src/test/results/clientpositive/groupby6.q.out +++ b/ql/src/test/results/clientpositive/groupby6.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out index 2f2a6e6..fc95f41 100644 --- a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out +++ b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out @@ -21,14 +21,14 @@ STAGE PLANS: outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), '' (type: string), '' (type: string) + keys: key (type: string), '' (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -99,14 +99,14 @@ STAGE PLANS: outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), 'X' (type: string), 'X' (type: string) + keys: key (type: string), 'X' (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out index 4a0a9d2..544a7ae 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out @@ -14,25 +14,29 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t1 -PREHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +PREHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +POSTHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -NULL NULL 0 6 +1 1 3 1 1 NULL 1 2 1 NULL 3 1 -1 1 3 1 -2 NULL 1 1 2 2 3 1 +2 NULL 1 1 +3 3 3 1 3 NULL 1 2 3 NULL 3 1 -3 3 3 1 -4 NULL 1 1 4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 PREHOOK: query: SELECT GROUPING__ID, count(*) FROM ( @@ -129,17 +133,17 @@ POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -NULL NULL 0 6 +1 1 3 1 1 NULL 1 2 1 NULL 3 1 -1 1 3 1 -2 NULL 1 1 2 2 3 1 +2 NULL 1 1 +3 3 3 1 3 NULL 1 2 3 NULL 3 1 -3 3 3 1 -4 NULL 1 1 4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 PREHOOK: query: SELECT GROUPING__ID, count(*) FROM ( http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out index c50abde..6eb3f66 100644 --- a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/having2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/having2.q.out b/ql/src/test/results/clientpositive/having2.q.out index aafd3b6..ba601f9 100644 --- a/ql/src/test/results/clientpositive/having2.q.out +++ b/ql/src/test/results/clientpositive/having2.q.out @@ -242,3 +242,356 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: s1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: customer_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: customer_name (type: string) + sort order: + + Map-reduce partition columns: customer_name (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: discount (type: double), customer_balance (type: double) + TableScan + alias: s2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 customer_name (type: string) + 1 key (type: string) + outputColumnNames: _col6, _col18, _col21, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col21 (type: double), _col6 (type: double), _col54 (type: string) + outputColumnNames: _col18, _col21, _col6, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col21), avg(_col6), count(_col54) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), avg(VALUE._col1), count(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col1 <= 4074689.000000041) and (_col2 <= 822.0)) and (_col3 > 4)) (type: boolean) + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name, s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT s1.customer_name FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +GROUP BY s1.customer_name, s1.customer_name +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: s1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: customer_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: customer_name (type: string) + sort order: + + Map-reduce partition columns: customer_name (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: discount (type: double), customer_balance (type: double) + TableScan + alias: s2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 customer_name (type: string) + 1 key (type: string) + outputColumnNames: _col6, _col18, _col21, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col21 (type: double), _col6 (type: double), _col54 (type: string) + outputColumnNames: _col18, _col21, _col6, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col21), avg(_col6), count(_col54) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), avg(VALUE._col1), count(VALUE._col2) + keys: KEY._col0 (type: string), KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: bigint) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col2 <= 4074689.000000041) and (_col3 <= 822.0)) and (_col4 > 4)) (type: boolean) + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +SELECT distinct s1.customer_name as x, s1.customer_name as y +FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT distinct s1.customer_name as x, s1.customer_name as y +FROM default.testv1_staples s1 join default.src s2 on s1.customer_name = s2.key +HAVING ( +(SUM(s1.customer_balance) <= 4074689.000000041) +AND (AVG(s1.discount) <= 822) +AND (COUNT(s2.value) > 4) +) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: s1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: customer_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: customer_name (type: string) + sort order: + + Map-reduce partition columns: customer_name (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: discount (type: double), customer_balance (type: double) + TableScan + alias: s2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 customer_name (type: string) + 1 key (type: string) + outputColumnNames: _col6, _col18, _col21, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col21 (type: double), _col6 (type: double), _col54 (type: string) + outputColumnNames: _col18, _col21, _col6, _col54 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col21), avg(_col6), count(_col54) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), avg(VALUE._col1), count(VALUE._col2) + keys: KEY._col0 (type: string), KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: bigint) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col2 <= 4074689.000000041) and (_col3 <= 822.0)) and (_col4 > 4)) (type: boolean) + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/spark/groupby1_map_nomap.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby1_map_nomap.q.out b/ql/src/test/results/clientpositive/spark/groupby1_map_nomap.q.out index 8fd9661..0799ff5 100644 --- a/ql/src/test/results/clientpositive/spark/groupby1_map_nomap.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby1_map_nomap.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key INT, value DOUBLE) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 @@ -97,312 +101,312 @@ POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### -273 819.0 -275 275.0 -419 419.0 -118 236.0 -202 202.0 -282 564.0 -82 82.0 +0 0.0 +10 10.0 +100 200.0 +103 206.0 +104 208.0 +105 105.0 +11 11.0 +111 111.0 +113 226.0 +114 114.0 116 116.0 -345 345.0 -332 332.0 -19 19.0 -42 84.0 -459 918.0 -190 190.0 -257 257.0 +118 236.0 +119 357.0 +12 24.0 +120 240.0 +125 250.0 +126 126.0 +128 384.0 +129 258.0 +131 131.0 +133 133.0 134 268.0 -165 330.0 +136 136.0 +137 274.0 138 552.0 -222 222.0 +143 143.0 +145 145.0 +146 292.0 +149 298.0 +15 30.0 +150 150.0 +152 304.0 +153 153.0 +155 155.0 +156 156.0 +157 157.0 +158 158.0 +160 160.0 +162 162.0 163 163.0 -219 438.0 -411 411.0 -305 305.0 -479 479.0 -28 28.0 -318 954.0 -244 244.0 +164 328.0 +165 330.0 +166 166.0 +167 501.0 +168 168.0 +169 676.0 +17 17.0 +170 170.0 +172 344.0 +174 348.0 +175 350.0 +176 352.0 +177 177.0 +178 178.0 +179 358.0 +18 36.0 +180 180.0 +181 181.0 +183 183.0 +186 186.0 +187 561.0 +189 189.0 +19 19.0 +190 190.0 +191 382.0 +192 192.0 +193 579.0 +194 194.0 +195 390.0 +196 196.0 +197 394.0 +199 597.0 +2 2.0 +20 20.0 +200 400.0 +201 201.0 +202 202.0 +203 406.0 +205 410.0 +207 414.0 208 624.0 -136 136.0 -24 48.0 -239 478.0 -84 168.0 -11 11.0 -367 734.0 -288 576.0 -150 150.0 -402 402.0 -466 1398.0 +209 418.0 +213 426.0 +214 214.0 +216 432.0 +217 434.0 +218 218.0 +219 438.0 +221 442.0 +222 222.0 +223 446.0 224 448.0 +226 226.0 +228 228.0 +229 458.0 +230 1150.0 +233 466.0 +235 235.0 237 474.0 -105 105.0 -484 484.0 -20 20.0 -400 400.0 -97 194.0 -280 560.0 -255 510.0 -103 206.0 +238 476.0 +239 478.0 +24 48.0 +241 241.0 242 484.0 -323 323.0 -309 618.0 -365 365.0 -178 178.0 +244 244.0 +247 247.0 +248 248.0 +249 249.0 +252 252.0 +255 510.0 +256 512.0 +257 257.0 +258 258.0 26 52.0 -404 808.0 -196 196.0 -448 448.0 -462 924.0 -389 389.0 -338 338.0 -167 501.0 -493 493.0 -33 33.0 -152 304.0 -477 477.0 -431 1293.0 -316 948.0 -125 250.0 -444 444.0 -457 457.0 -446 446.0 -310 310.0 -129 258.0 -183 183.0 -392 392.0 +260 260.0 +262 262.0 +263 263.0 +265 530.0 +266 266.0 +27 27.0 +272 544.0 +273 819.0 +274 274.0 +275 275.0 277 1108.0 -4 4.0 -80 80.0 -228 228.0 -145 145.0 -356 356.0 +278 556.0 +28 28.0 +280 560.0 +281 562.0 +282 564.0 +283 283.0 284 284.0 -455 455.0 -53 53.0 -149 298.0 -424 848.0 -37 74.0 +285 285.0 286 286.0 -327 981.0 -170 170.0 -187 561.0 -86 86.0 +287 287.0 +288 576.0 +289 289.0 291 291.0 -233 466.0 -439 878.0 -266 266.0 -2 2.0 -396 1188.0 +292 292.0 +296 296.0 +298 894.0 +30 30.0 +302 302.0 +305 305.0 +306 306.0 +307 614.0 +308 308.0 +309 618.0 +310 310.0 +311 933.0 +315 315.0 +316 948.0 +317 634.0 +318 954.0 +321 642.0 +322 644.0 +323 323.0 +325 650.0 +327 981.0 +33 33.0 +331 662.0 +332 332.0 +333 666.0 +335 335.0 336 336.0 -226 226.0 -176 352.0 -66 66.0 -497 497.0 -172 344.0 -491 491.0 -44 44.0 -200 400.0 -235 235.0 -77 77.0 -260 260.0 -406 1624.0 -460 460.0 -495 495.0 -143 143.0 -189 189.0 -453 453.0 -64 64.0 -158 158.0 +338 338.0 +339 339.0 +34 34.0 341 341.0 -475 475.0 -8 8.0 -394 394.0 -57 57.0 -169 676.0 -15 30.0 +342 684.0 +344 688.0 +345 345.0 +348 1740.0 35 105.0 -174 348.0 -325 650.0 -0 0.0 -248 248.0 -468 1872.0 -435 435.0 -51 102.0 -321 642.0 -413 826.0 +351 351.0 +353 706.0 +356 356.0 +360 360.0 +362 362.0 +364 364.0 +365 365.0 +366 366.0 +367 734.0 +368 368.0 369 1107.0 -480 1440.0 -156 156.0 -192 192.0 -213 426.0 +37 74.0 +373 373.0 374 374.0 -437 437.0 -17 17.0 -181 181.0 -482 482.0 -307 614.0 -194 194.0 -217 434.0 -95 190.0 -114 114.0 -262 262.0 +375 375.0 +377 377.0 378 378.0 -417 1251.0 -281 562.0 -180 180.0 -467 467.0 -201 201.0 -432 432.0 -238 476.0 -96 96.0 +379 379.0 +382 764.0 +384 1152.0 386 386.0 -283 283.0 -168 168.0 -209 418.0 -463 926.0 -377 377.0 -317 634.0 -252 252.0 -104 208.0 -373 373.0 -131 131.0 -494 494.0 -230 1150.0 -83 166.0 -191 382.0 -41 41.0 -193 579.0 -436 436.0 -496 496.0 -166 166.0 -229 458.0 -298 894.0 -133 133.0 -333 666.0 -65 65.0 -292 292.0 -364 364.0 -472 472.0 -274 274.0 -47 47.0 -401 2005.0 -67 134.0 -5 15.0 -18 36.0 -27 27.0 -344 688.0 -409 1227.0 -256 512.0 -85 85.0 -72 144.0 -54 54.0 +389 389.0 +392 392.0 393 393.0 -160 160.0 -438 1314.0 -263 263.0 -351 351.0 -207 414.0 -449 449.0 -111 111.0 -128 384.0 -289 289.0 -399 798.0 -489 1956.0 -205 410.0 -177 177.0 -119 357.0 -331 662.0 -348 1740.0 -478 956.0 -76 152.0 -458 916.0 -382 764.0 -157 157.0 -315 315.0 -469 2345.0 -302 302.0 +394 394.0 395 790.0 -384 1152.0 -162 162.0 -113 226.0 -98 196.0 -221 442.0 -203 406.0 -199 597.0 -454 1362.0 -218 218.0 -241 241.0 -272 544.0 -120 240.0 +396 1188.0 +397 794.0 +399 798.0 +4 4.0 +400 400.0 +401 2005.0 +402 402.0 403 1209.0 -366 366.0 -249 249.0 +404 808.0 +406 1624.0 +407 407.0 +409 1227.0 +41 41.0 +411 411.0 +413 826.0 +414 828.0 +417 1251.0 +418 418.0 +419 419.0 +42 84.0 421 421.0 -214 214.0 -92 92.0 -487 487.0 -258 258.0 +424 848.0 +427 427.0 429 858.0 -265 530.0 -175 350.0 -34 34.0 -368 368.0 -69 69.0 -414 828.0 -30 30.0 -492 984.0 -9 9.0 -296 296.0 -311 933.0 -247 247.0 -164 328.0 -306 306.0 -153 153.0 -339 339.0 -322 644.0 -10 10.0 +43 43.0 430 1290.0 -155 155.0 +431 1293.0 +432 432.0 +435 435.0 +436 436.0 +437 437.0 +438 1314.0 +439 878.0 +44 44.0 +443 443.0 +444 444.0 +446 446.0 +448 448.0 +449 449.0 452 452.0 -179 358.0 +453 453.0 +454 1362.0 +455 455.0 +457 457.0 +458 916.0 +459 918.0 +460 460.0 +462 924.0 +463 926.0 +466 1398.0 +467 467.0 +468 1872.0 +469 2345.0 +47 47.0 +470 470.0 +472 472.0 +475 475.0 +477 477.0 +478 956.0 +479 479.0 +480 1440.0 +481 481.0 +482 482.0 +483 483.0 +484 484.0 485 485.0 +487 487.0 +489 1956.0 490 490.0 -443 443.0 -379 379.0 -186 186.0 -100 200.0 -137 274.0 -483 483.0 -90 270.0 -481 481.0 -287 287.0 -146 292.0 -216 432.0 -342 684.0 -470 470.0 -362 362.0 -375 375.0 -407 407.0 -397 794.0 -58 116.0 +491 491.0 +492 984.0 +493 493.0 +494 494.0 +495 495.0 +496 496.0 +497 497.0 498 1494.0 -87 87.0 -195 390.0 -197 394.0 -78 78.0 -278 556.0 -12 24.0 -335 335.0 -360 360.0 -308 308.0 -223 446.0 -418 418.0 -43 43.0 -353 706.0 -74 74.0 -427 427.0 +5 15.0 +51 102.0 +53 53.0 +54 54.0 +57 57.0 +58 116.0 +64 64.0 +65 65.0 +66 66.0 +67 134.0 +69 69.0 70 210.0 -285 285.0 -126 126.0 +72 144.0 +74 74.0 +76 152.0 +77 77.0 +78 78.0 +8 8.0 +80 80.0 +82 82.0 +83 166.0 +84 168.0 +85 85.0 +86 86.0 +87 87.0 +9 9.0 +90 270.0 +92 92.0 +95 190.0 +96 96.0 +97 194.0 +98 196.0 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/spark/groupby6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby6.q.out b/ql/src/test/results/clientpositive/spark/groupby6.q.out index c3caccd..bb9b315 100644 --- a/ql/src/test/results/clientpositive/spark/groupby6.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby6.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 @@ -101,13 +105,13 @@ POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### -4 -8 -6 0 +1 2 -7 +3 +4 5 +6 +7 +8 9 -3 -1 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out index 9a5c832..544a7ae 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out @@ -14,25 +14,29 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t1 -PREHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +PREHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +POSTHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -NULL NULL 0 6 1 1 3 1 -2 NULL 1 1 -2 2 3 1 -3 3 3 1 -4 NULL 1 1 1 NULL 1 2 1 NULL 3 1 +2 2 3 1 +2 NULL 1 1 +3 3 3 1 3 NULL 1 2 3 NULL 3 1 4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 PREHOOK: query: SELECT GROUPING__ID, count(*) FROM ( @@ -52,8 +56,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### 0 1 -3 6 1 4 +3 6 PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 JOIN (SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 @@ -129,17 +133,17 @@ POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -1 NULL 3 1 +1 1 3 1 1 NULL 1 2 -NULL NULL 0 6 -4 5 3 1 -3 NULL 3 1 -3 NULL 1 2 -4 NULL 1 1 -2 NULL 1 1 +1 NULL 3 1 2 2 3 1 -1 1 3 1 +2 NULL 1 1 3 3 3 1 +3 NULL 1 2 +3 NULL 3 1 +4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 PREHOOK: query: SELECT GROUPING__ID, count(*) FROM ( @@ -159,8 +163,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### 0 1 -3 6 1 4 +3 6 PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 JOIN (SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 http://git-wip-us.apache.org/repos/asf/hive/blob/bb4f5e70/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out index 01ea4ea..ef1cba2 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 @@ -335,12 +339,12 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### 0 1 00.0 0 1 -2 69 251142.0 15780 69 -4 74 4105526.0 30965 74 -6 5 6796.0 331 5 -8 8 81524.0 595 8 1 71 132828.0 10044 71 +2 69 251142.0 15780 69 3 62 364008.0 20119 62 +4 74 4105526.0 30965 74 5 6 5794.0 278 6 +6 5 6796.0 331 5 7 6 71470.0 447 6 +8 8 81524.0 595 8 9 7 92094.0 577 7
