add q test

apache · Oct 14, 2024 · 99042b8 · 99042b8
1 parent cd816a0
commit 99042b8
Show file tree

Hide file tree

Showing 4 changed files with 274 additions and 41 deletions.
diff --git a/ql/src/test/queries/clientpositive/distributeby.q b/ql/src/test/queries/clientpositive/distributeby.q
@@ -1,5 +1,3 @@
-set hive.vectorized.execution.enabled=false;
-
 create table t1 (a string, b int);
 
 insert into t1 values ('2014-03-14 10:10:12', 10);
@@ -19,9 +17,6 @@ explain
 select * from t1 distribute by a, b sort by a;
 
 -- cluster by
-explain ast
-select * from t1 cluster by a, b;
-
 explain cbo
 select * from t1 cluster by a, b;
 

diff --git a/ql/src/test/queries/clientpositive/distributeby_cboret.q b/ql/src/test/queries/clientpositive/distributeby_cboret.q
@@ -0,0 +1,26 @@
+set hive.cbo.returnpath.hiveop=true;
+
+create table t1 (a string, b int);
+
+insert into t1 values ('2014-03-14 10:10:12', 10);
+
+-- distribute by
+explain cbo
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a;
+explain
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a;
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a;
+
+-- distribute by and sort by
+explain cbo
+select * from t1 distribute by a, b sort by a;
+
+explain
+select * from t1 distribute by a, b sort by a;
+
+-- cluster by
+explain cbo
+select * from t1 cluster by a, b;
+
+explain
+select * from t1 cluster by a, b;
diff --git a/ql/src/test/results/clientpositive/llap/distributeby.q.out b/ql/src/test/results/clientpositive/llap/distributeby.q.out
@@ -73,10 +73,10 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: string), _col1 (type: int)
-            Execution mode: llap
+            Execution mode: vectorized, llap
             LLAP IO: all inputs
         Reducer 2 
-            Execution mode: llap
+            Execution mode: vectorized, llap
             Reduce Operator Tree:
               Select Operator
                 expressions: VALUE._col0 (type: string), VALUE._col1 (type: int)
@@ -158,10 +158,10 @@ STAGE PLANS:
                       Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
                       Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
                       value expressions: _col1 (type: int)
-            Execution mode: llap
+            Execution mode: vectorized, llap
             LLAP IO: all inputs
         Reducer 2 
-            Execution mode: llap
+            Execution mode: vectorized, llap
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: int)
@@ -181,36 +181,6 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-PREHOOK: query: explain ast
-select * from t1 cluster by a, b
-PREHOOK: type: QUERY
-PREHOOK: Input: default@t1
-#### A masked pattern was here ####
-POSTHOOK: query: explain ast
-select * from t1 cluster by a, b
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@t1
-#### A masked pattern was here ####
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
-   TOK_FROM
-      TOK_TABREF
-         TOK_TABNAME
-            t1
-   TOK_INSERT
-      TOK_DESTINATION
-         TOK_DIR
-            TOK_TMP_FILE
-      TOK_SELECT
-         TOK_SELEXPR
-            TOK_ALLCOLREF
-      TOK_CLUSTERBY
-         TOK_TABLE_OR_COL
-            a
-         TOK_TABLE_OR_COL
-            b
-
 PREHOOK: query: explain cbo
 select * from t1 cluster by a, b
 PREHOOK: type: QUERY
@@ -263,10 +233,10 @@ STAGE PLANS:
                       sort order: ++
                       Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
                       Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
-            Execution mode: llap
+            Execution mode: vectorized, llap
             LLAP IO: all inputs
         Reducer 2 
-            Execution mode: llap
+            Execution mode: vectorized, llap
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)

diff --git a/ql/src/test/results/clientpositive/llap/distributeby_cboret.q.out b/ql/src/test/results/clientpositive/llap/distributeby_cboret.q.out
@@ -0,0 +1,242 @@
+PREHOOK: query: create table t1 (a string, b int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@t1
+POSTHOOK: query: create table t1 (a string, b int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@t1
+PREHOOK: query: insert into t1 values ('2014-03-14 10:10:12', 10)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@t1
+POSTHOOK: query: insert into t1 values ('2014-03-14 10:10:12', 10)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@t1
+POSTHOOK: Lineage: t1.a SCRIPT []
+POSTHOOK: Lineage: t1.b SCRIPT []
+PREHOOK: query: explain cbo
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain
+select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: t1
+                  filterExpr: CAST( a AS DATE) BETWEEN DATE'2014-03-13' AND DATE'2014-03-14' (type: boolean)
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  Filter Operator
+                    predicate: CAST( a AS DATE) BETWEEN DATE'2014-03-13' AND DATE'2014-03-14' (type: boolean)
+                    Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: a (type: string), b (type: int)
+                      outputColumnNames: a, b
+                      Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                      Reduce Output Operator
+                        null sort order: 
+                        sort order: 
+                        Map-reduce partition columns: a (type: string)
+                        Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                        value expressions: a (type: string), b (type: int)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+        Reducer 2 
+            Execution mode: vectorized, llap
+            Reduce Operator Tree:
+              Select Operator
+                expressions: VALUE.a (type: string), VALUE.b (type: int)
+                outputColumnNames: a, b
+                Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t1 where a between date_add('2014-03-14', -1) and '2014-03-14' distribute by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+2014-03-14 10:10:12	10
+PREHOOK: query: explain cbo
+select * from t1 distribute by a, b sort by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo
+select * from t1 distribute by a, b sort by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select * from t1 distribute by a, b sort by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain
+select * from t1 distribute by a, b sort by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: t1
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  Select Operator
+                    expressions: a (type: string), b (type: int)
+                    outputColumnNames: a, b
+                    Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: a (type: string)
+                      null sort order: z
+                      sort order: +
+                      Map-reduce partition columns: a (type: string), b (type: int)
+                      Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                      value expressions: b (type: int)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+        Reducer 2 
+            Execution mode: vectorized, llap
+            Reduce Operator Tree:
+              Select Operator
+                expressions: KEY.reducesinkkey0 (type: string), VALUE.b (type: int)
+                outputColumnNames: a, b
+                Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: explain cbo
+select * from t1 cluster by a, b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo
+select * from t1 cluster by a, b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select * from t1 cluster by a, b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain
+select * from t1 cluster by a, b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: t1
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  Select Operator
+                    expressions: a (type: string), b (type: int)
+                    outputColumnNames: a, b
+                    Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: a (type: string), b (type: int)
+                      null sort order: aa
+                      sort order: ++
+                      Map-reduce partition columns: a (type: string), b (type: int)
+                      Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+        Reducer 2 
+            Execution mode: vectorized, llap
+            Reduce Operator Tree:
+              Select Operator
+                expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
+                outputColumnNames: a, b
+                Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+