You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2016/08/20 01:38:29 UTC
[2/3] hive git commit: HIVE-14503: Remove explicit order by in qfiles
for union tests (Prasanth Jayachandran reviewed by Siddharth Seth, Hari)
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_2.q.out b/ql/src/test/results/clientpositive/spark/union_remove_2.q.out
index 4667e70..755ff3f 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_2.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_2.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -13,7 +14,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -217,11 +219,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_20.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_20.q.out b/ql/src/test/results/clientpositive/spark/union_remove_20.q.out
index b7682a9..bec77a8 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_20.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_20.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select and a file sink
-- However, the order of the columns in the select list is different. So, union cannot
-- be removed.
@@ -13,7 +14,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select and a file sink
-- However, the order of the columns in the select list is different. So, union cannot
-- be removed.
@@ -200,11 +202,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_21.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_21.q.out b/ql/src/test/results/clientpositive/spark/union_remove_21.q.out
index c9bcf36..f5a1caa 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_21.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_21.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select and a file sink
-- However, all the columns are not selected. So, union cannot
-- be removed.
@@ -13,7 +14,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select and a file sink
-- However, all the columns are not selected. So, union cannot
-- be removed.
@@ -186,11 +188,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_22.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_22.q.out b/ql/src/test/results/clientpositive/spark/union_remove_22.q.out
index 90caa89..c762002 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_22.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_22.q.out
@@ -347,11 +347,11 @@ POSTHOOK: Output: default@outputtbl1
POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ]
POSTHOOK: Lineage: outputtbl1.values2 EXPRESSION [(inputtbl1)inputtbl1.null, ]
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_23.q.out b/ql/src/test/results/clientpositive/spark/union_remove_23.q.out
index 3d51af5..b351893 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_23.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_23.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely. One of the sub-queries
@@ -13,7 +14,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely. One of the sub-queries
@@ -253,11 +255,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_24.q.out b/ql/src/test/results/clientpositive/spark/union_remove_24.q.out
index 94f71ac..c66691e 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_24.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_24.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -11,7 +12,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -196,11 +198,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_25.q.out b/ql/src/test/results/clientpositive/spark/union_remove_25.q.out
index eb95cad..ba9d4d1 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_25.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_25.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -12,7 +13,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -212,12 +214,12 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
PREHOOK: Input: default@outputtbl1@ds=2004
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
POSTHOOK: Input: default@outputtbl1@ds=2004
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_3.q.out b/ql/src/test/results/clientpositive/spark/union_remove_3.q.out
index 66675ce..7692443 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_3.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_3.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->remove->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->remove->filesink optimization
-- Union of 3 subqueries is performed (all of which are map-only queries)
-- followed by select star and a file sink.
-- There is no need for any optimization, since the whole query can be processed in
@@ -13,7 +14,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->remove->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->remove->filesink optimization
-- Union of 3 subqueries is performed (all of which are map-only queries)
-- followed by select star and a file sink.
-- There is no need for any optimization, since the whole query can be processed in
@@ -207,11 +209,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_4.q.out b/ql/src/test/results/clientpositive/spark/union_remove_4.q.out
index 1bf917a..3ab62c8 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_4.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_4.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -12,7 +13,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -240,11 +242,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_5.q.out b/ql/src/test/results/clientpositive/spark/union_remove_5.q.out
index aabb6c4..9a9caf6 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_5.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_5.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -14,7 +15,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -269,11 +271,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_6.q.out b/ql/src/test/results/clientpositive/spark/union_remove_6.q.out
index d677d1b..1bdeb09 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_6.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_6.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 subqueries is performed (all of which are mapred queries)
-- followed by select star and a file sink in 2 output tables.
-- The optimiaztion does not take affect since it is a multi-table insert.
@@ -9,7 +10,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 subqueries is performed (all of which are mapred queries)
-- followed by select star and a file sink in 2 output tables.
-- The optimiaztion does not take affect since it is a multi-table insert.
@@ -191,11 +193,11 @@ POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(n
POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ]
POSTHOOK: Lineage: outputtbl2.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: outputtbl2.values EXPRESSION [(inputtbl1)inputtbl1.null, ]
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
@@ -209,11 +211,11 @@ POSTHOOK: Input: default@outputtbl1
7 1
8 2
8 2
-PREHOOK: query: select * from outputTbl2 order by key, `values`
+PREHOOK: query: select * from outputTbl2
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl2
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl2 order by key, `values`
+POSTHOOK: query: select * from outputTbl2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl2
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out b/ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out
index dac8247..10de07d 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out
@@ -203,11 +203,11 @@ POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(n
POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ]
POSTHOOK: Lineage: outputtbl2.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: outputtbl2.values EXPRESSION [(inputtbl1)inputtbl1.null, ]
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
@@ -221,11 +221,11 @@ POSTHOOK: Input: default@outputtbl1
7 1
8 2
8 2
-PREHOOK: query: select * from outputTbl2 order by key, `values`
+PREHOOK: query: select * from outputTbl2
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl2
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl2 order by key, `values`
+POSTHOOK: query: select * from outputTbl2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl2
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_7.q.out b/ql/src/test/results/clientpositive/spark/union_remove_7.q.out
index 6af69e0..585b61e 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_7.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_7.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -14,7 +15,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 map-reduce subqueries is performed followed by select star and a file sink
-- There is no need to write the temporary results of the sub-queries, and then read them
-- again to process the union. The union can be removed completely.
@@ -194,11 +196,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_8.q.out b/ql/src/test/results/clientpositive/spark/union_remove_8.q.out
index f19afad..17079a1 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_8.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_8.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -15,7 +16,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 3 subqueries is performed (exactly one of which requires a map-reduce job)
-- followed by select star and a file sink.
-- There is no need to write the temporary results of the sub-queries, and then read them
@@ -221,11 +223,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_remove_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_remove_9.q.out b/ql/src/test/results/clientpositive/spark/union_remove_9.q.out
index 2e2abf9..0b46bd7 100644
--- a/ql/src/test/results/clientpositive/spark/union_remove_9.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_remove_9.q.out
@@ -1,4 +1,5 @@
-PREHOOK: query: -- This is to test the union->selectstar->filesink optimization
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 subqueries is performed (one of which contains a union and is map-only),
-- and the other one is a map-reduce query followed by select star and a file sink.
-- There is no need for the outer union.
@@ -14,7 +15,8 @@ create table inputTbl1(key string, val string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@inputTbl1
-POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- This is to test the union->selectstar->filesink optimization
-- Union of 2 subqueries is performed (one of which contains a union and is map-only),
-- and the other one is a map-reduce query followed by select star and a file sink.
-- There is no need for the outer union.
@@ -277,11 +279,11 @@ Bucket Columns: []
Sort Columns: []
Storage Desc Params:
serialization.format 1
-PREHOOK: query: select * from outputTbl1 order by key, `values`
+PREHOOK: query: select * from outputTbl1
PREHOOK: type: QUERY
PREHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
-POSTHOOK: query: select * from outputTbl1 order by key, `values`
+POSTHOOK: query: select * from outputTbl1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@outputtbl1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/spark/union_script.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_script.q.out b/ql/src/test/results/clientpositive/spark/union_script.q.out
index e044f63..44ea01b 100644
--- a/ql/src/test/results/clientpositive/spark/union_script.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_script.q.out
@@ -1,10 +1,12 @@
-PREHOOK: query: select * from (
- select transform(key) using 'cat' as cola from src)s order by cola
+PREHOOK: query: -- SORT_QUERY_RESULTS
+select * from (
+ select transform(key) using 'cat' as cola from src)s
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
-POSTHOOK: query: select * from (
- select transform(key) using 'cat' as cola from src)s order by cola
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+select * from (
+ select transform(key) using 'cat' as cola from src)s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
@@ -511,14 +513,14 @@ POSTHOOK: Input: default@src
PREHOOK: query: select * from (
select transform(key) using 'cat' as cola from src
union all
- select transform(key) using 'cat' as cola from src) s order by cola
+ select transform(key) using 'cat' as cola from src) s
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
POSTHOOK: query: select * from (
select transform(key) using 'cat' as cola from src
union all
- select transform(key) using 'cat' as cola from src) s order by cola
+ select transform(key) using 'cat' as cola from src) s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/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 892cc6f..a5970c0 100644
--- a/ql/src/test/results/clientpositive/spark/union_view.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_view.q.out
@@ -406,8 +406,6 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (SORT, 1), Map 3 (SORT, 1), Map 4 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -424,15 +422,17 @@ 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: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 3
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Map 2
Map Operator Tree:
TableScan
alias: src_union_2
@@ -446,15 +446,17 @@ 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: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 4
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Map 3
Map Operator Tree:
TableScan
alias: src_union_3
@@ -468,27 +470,16 @@ 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: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 2
- Reduce Operator Tree:
- Select Operator
- expressions: 86 (type: int), VALUE._col0 (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
- compressed: false
- Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -501,9 +492,9 @@ STAGE PLANS:
86 val_86 2
86 val_86 3
86 val_86 3
-86 val_86 1
86 val_86 2
86 val_86 2
+86 val_86 1
86 val_86 3
86 val_86 3
STAGE DEPENDENCIES:
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out
index dd78248..2c8e57f 100644
--- a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out
+++ b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out
@@ -7174,7 +7174,6 @@ from (
from src
UNION DISTINCT
select key as key2, value as value2 from src) s
-order by s.key2, s.value2
PREHOOK: type: QUERY
POSTHOOK: query: -- union23.q
@@ -7185,7 +7184,6 @@ from (
from src
UNION DISTINCT
select key as key2, value as value2 from src) s
-order by s.key2, s.value2
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -7197,9 +7195,8 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Map 1 <- Union 2 (CONTAINS)
- Map 5 <- Union 2 (CONTAINS)
+ Map 4 <- Union 2 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -7228,7 +7225,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -7254,16 +7251,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 4
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
@@ -7286,7 +7273,6 @@ from (
from src
UNION DISTINCT
select key as key2, value as value2 from src) s
-order by s.key2, s.value2
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
@@ -7296,7 +7282,6 @@ from (
from src
UNION DISTINCT
select key as key2, value as value2 from src) s
-order by s.key2, s.value2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
@@ -12823,7 +12808,6 @@ SELECT * FROM
(SELECT CAST(key AS DOUBLE) AS key FROM t1
UNION DISTINCT
SELECT CAST(key AS BIGINT) AS key FROM t2) a
-ORDER BY key
PREHOOK: type: QUERY
POSTHOOK: query: -- Test simple union with double
EXPLAIN
@@ -12831,7 +12815,6 @@ SELECT * FROM
(SELECT CAST(key AS DOUBLE) AS key FROM t1
UNION DISTINCT
SELECT CAST(key AS BIGINT) AS key FROM t2) a
-ORDER BY key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -12843,9 +12826,8 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Map 1 <- Union 2 (CONTAINS)
- Map 5 <- Union 2 (CONTAINS)
+ Map 4 <- Union 2 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -12867,7 +12849,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: double)
Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: t2
@@ -12893,16 +12875,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reducer 4
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double)
- outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
@@ -13992,7 +13964,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
POSTHOOK: query: -- When we convert the Join of sub1 and sub0 into a MapJoin,
-- we can use a single MR job to evaluate this entire query.
@@ -14001,7 +13973,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -14012,12 +13984,11 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS)
- Map 6 <- Union 7 (CONTAINS)
- Map 9 <- Union 7 (CONTAINS)
+ Map 1 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS)
+ Map 5 <- Union 6 (CONTAINS)
+ Map 8 <- Union 6 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
- Reducer 8 <- Union 2 (CONTAINS), Union 7 (SIMPLE_EDGE)
+ Reducer 7 <- Union 2 (CONTAINS), Union 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -14040,7 +14011,7 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1
input vertices:
- 1 Map 5
+ 1 Map 4
Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Group By Operator
@@ -14053,7 +14024,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: src10_2
@@ -14070,7 +14041,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: src10_3
@@ -14089,7 +14060,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Map 9
+ Map 8
Map Operator Tree:
TableScan
alias: src10_4
@@ -14115,17 +14086,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 4
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
@@ -14133,7 +14093,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 8
+ Reducer 7
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
@@ -14152,8 +14112,8 @@ STAGE PLANS:
Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE
Union 2
Vertex: Union 2
- Union 7
- Vertex: Union 7
+ Union 6
+ Vertex: Union 6
Stage: Stage-0
Fetch Operator
@@ -14165,7 +14125,7 @@ PREHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
PREHOOK: Input: default@src10_1
PREHOOK: Input: default@src10_2
@@ -14176,7 +14136,7 @@ POSTHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src10_1
POSTHOOK: Input: default@src10_2
@@ -14202,7 +14162,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
POSTHOOK: query: -- When we do not convert the Join of sub1 and sub0 into a MapJoin,
-- we need to use two MR jobs to evaluate this query.
@@ -14213,7 +14173,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -14224,12 +14184,11 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 10 <- Union 8 (CONTAINS)
- Map 7 <- Union 8 (CONTAINS)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Map 6 <- Union 7 (CONTAINS)
+ Map 9 <- Union 7 (CONTAINS)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS)
Reducer 4 <- Union 3 (SIMPLE_EDGE)
- Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
- Reducer 9 <- Union 3 (CONTAINS), Union 8 (SIMPLE_EDGE)
+ Reducer 8 <- Union 3 (CONTAINS), Union 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -14250,26 +14209,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Map 10
- Map Operator Tree:
- TableScan
- alias: src10_4
- Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: src10_2
@@ -14286,7 +14226,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Map 7
+ Map 6
Map Operator Tree:
TableScan
alias: src10_3
@@ -14305,6 +14245,25 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: src10_4
+ Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Merge Join Operator
@@ -14332,17 +14291,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 5
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE
@@ -14350,7 +14298,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 9
+ Reducer 8
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
@@ -14369,8 +14317,8 @@ STAGE PLANS:
Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE
Union 3
Vertex: Union 3
- Union 8
- Vertex: Union 8
+ Union 7
+ Vertex: Union 7
Stage: Stage-0
Fetch Operator
@@ -14382,7 +14330,7 @@ PREHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
PREHOOK: Input: default@src10_1
PREHOOK: Input: default@src10_2
@@ -14393,7 +14341,7 @@ POSTHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION DISTINCT
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION DISTINCT SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src10_1
POSTHOOK: Input: default@src10_2
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/tez/union_type_chk.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/union_type_chk.q.out b/ql/src/test/results/clientpositive/tez/union_type_chk.q.out
index 12f060b..1eb0182 100644
--- a/ql/src/test/results/clientpositive/tez/union_type_chk.q.out
+++ b/ql/src/test/results/clientpositive/tez/union_type_chk.q.out
@@ -1,28 +1,30 @@
-PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u order by y
+PREHOOK: query: -- SORT_QUERY_RESULTS
+select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
-POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u order by y
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
+0.4999999900000002
+0.4999999900000002
4.999999900000002E-9
4.999999900000002E-9
4.999999900000002E-9
4.999999900000002E-9
-0.4999999900000002
-0.4999999900000002
-PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u order by y
+PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
-POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u order by y
+POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
-NULL
-NULL
0.25
0.25
0.25
0.25
+NULL
+NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/union32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union32.q.out b/ql/src/test/results/clientpositive/union32.q.out
index f61a313..136a1c3 100644
--- a/ql/src/test/results/clientpositive/union32.q.out
+++ b/ql/src/test/results/clientpositive/union32.q.out
@@ -38,7 +38,6 @@ SELECT * FROM
(SELECT CAST(key AS DOUBLE) AS key FROM t1
UNION ALL
SELECT CAST(key AS BIGINT) AS key FROM t2) a
-ORDER BY key
PREHOOK: type: QUERY
POSTHOOK: query: -- Test simple union with double
EXPLAIN
@@ -46,7 +45,6 @@ SELECT * FROM
(SELECT CAST(key AS DOUBLE) AS key FROM t1
UNION ALL
SELECT CAST(key AS BIGINT) AS key FROM t2) a
-ORDER BY key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -65,10 +63,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TableScan
alias: t2
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
@@ -78,22 +79,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double)
- outputColumnNames: _col0
- Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/union34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union34.q.out b/ql/src/test/results/clientpositive/union34.q.out
index 06f75e7..8d7846c 100644
--- a/ql/src/test/results/clientpositive/union34.q.out
+++ b/ql/src/test/results/clientpositive/union34.q.out
@@ -1,8 +1,10 @@
-PREHOOK: query: create table src10_1 (key string, value string)
+PREHOOK: query: -- SORT_QUERY_RESULTS
+create table src10_1 (key string, value string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@src10_1
-POSTHOOK: query: create table src10_1 (key string, value string)
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+create table src10_1 (key string, value string)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@src10_1
@@ -67,7 +69,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
POSTHOOK: query: -- When we convert the Join of sub1 and sub0 into a MapJoin,
-- we can use a single MR job to evaluate this entire query.
@@ -76,7 +78,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-7 is a root stage
@@ -119,11 +121,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TableScan
alias: src10_4
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
@@ -133,11 +137,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TableScan
alias: src10_2
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
@@ -158,25 +164,15 @@ STAGE PLANS:
Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Local Work:
Map Reduce Local Work
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -188,7 +184,7 @@ PREHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
PREHOOK: Input: default@src10_1
PREHOOK: Input: default@src10_2
@@ -199,7 +195,7 @@ POSTHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src10_1
POSTHOOK: Input: default@src10_2
@@ -245,7 +241,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
POSTHOOK: query: -- When we do not convert the Join of sub1 and sub0 into a MapJoin,
-- we need to use two MR jobs to evaluate this query.
@@ -256,7 +252,7 @@ SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -320,11 +316,13 @@ STAGE PLANS:
TableScan
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TableScan
alias: src10_3
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
@@ -334,11 +332,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TableScan
alias: src10_4
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
@@ -348,23 +348,13 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Union
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
+ File Output Operator
+ compressed: false
Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -376,7 +366,7 @@ PREHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
PREHOOK: type: QUERY
PREHOOK: Input: default@src10_1
PREHOOK: Input: default@src10_2
@@ -387,7 +377,7 @@ POSTHOOK: query: SELECT * FROM (
SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key)
UNION ALL
SELECT key,value FROM (SELECT * FROM (SELECT * FROM src10_3) sub2 UNION ALL SELECT * FROM src10_4 ) alias0
-) alias1 order by key
+) alias1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src10_1
POSTHOOK: Input: default@src10_2
http://git-wip-us.apache.org/repos/asf/hive/blob/d14673a0/ql/src/test/results/clientpositive/union36.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union36.q.out b/ql/src/test/results/clientpositive/union36.q.out
index 12f060b..1eb0182 100644
--- a/ql/src/test/results/clientpositive/union36.q.out
+++ b/ql/src/test/results/clientpositive/union36.q.out
@@ -1,28 +1,30 @@
-PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u order by y
+PREHOOK: query: -- SORT_QUERY_RESULTS
+select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
-POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u order by y
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select '100000000' x from (select * from src limit 2) s3)u
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
+0.4999999900000002
+0.4999999900000002
4.999999900000002E-9
4.999999900000002E-9
4.999999900000002E-9
4.999999900000002E-9
-0.4999999900000002
-0.4999999900000002
-PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u order by y
+PREHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u
PREHOOK: type: QUERY
PREHOOK: Input: default@src
#### A masked pattern was here ####
-POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u order by y
+POSTHOOK: query: select (x/sum(x) over()) as y from(select cast(1 as decimal(10,0)) as x from (select * from src limit 2)s1 union all select cast(1 as decimal(10,0)) x from (select * from src limit 2) s2 union all select cast (null as string) x from (select * from src limit 2) s3)u
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
-NULL
-NULL
0.25
0.25
0.25
0.25
+NULL
+NULL