HIVE-29646: Enable semijoin reduction and map-join conversion on external tables with accurate statistics

iceberg/iceberg-handler/src/test/results/positive/delete_iceberg_copy_on_write_partitioned.q.out

@@ -1679,7 +1679,7 @@ STAGE PLANS:
     Stats Work
       Basic Stats Work:
 
-Warning: Shuffle Join MERGEJOIN[180][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[217][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
 PREHOOK: query: delete from tbl_ice where a in (select t1.a from tbl_ice t1 join tbl_standard_other t2 on t1.a = t2.a)
 PREHOOK: type: QUERY
 PREHOOK: Input: default@tbl_ice

iceberg/iceberg-handler/src/test/results/positive/delete_iceberg_copy_on_write_unpartitioned.q.out

@@ -1388,7 +1388,7 @@ POSTHOOK: Input: _dummy_database@_dummy_table
 POSTHOOK: Output: default@tbl_standard_other
 POSTHOOK: Lineage: tbl_standard_other.a SCRIPT []
 POSTHOOK: Lineage: tbl_standard_other.b SCRIPT []
-Warning: Shuffle Join MERGEJOIN[178][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[215][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
 PREHOOK: query: explain delete from tbl_ice where a in (select t1.a from tbl_ice t1 join tbl_standard_other t2 on t1.a = t2.a)
 PREHOOK: type: QUERY
 PREHOOK: Input: default@tbl_ice
@@ -1410,16 +1410,16 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 10 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
-        Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
-        Reducer 12 <- Reducer 8 (CUSTOM_SIMPLE_EDGE)
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 12 (XPROD_EDGE), Reducer 2 (XPROD_EDGE)
-        Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
+        Reducer 10 <- Reducer 8 (SIMPLE_EDGE)
+        Reducer 11 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+        Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 9 (XPROD_EDGE)
+        Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
         Reducer 6 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
         Reducer 7 <- Reducer 6 (SIMPLE_EDGE), Union 5 (CONTAINS)
         Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE)
-        Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
+        Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -1501,6 +1501,25 @@ STAGE PLANS:
                         Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
             Execution mode: vectorized
         Reducer 10 
+            Execution mode: vectorized
+            Reduce Operator Tree:
+              Group By Operator
+                keys: KEY._col0 (type: int)
+                mode: mergepartial
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), true (type: boolean)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: int)
+                    null sort order: z
+                    sort order: +
+                    Map-reduce partition columns: _col0 (type: int)
+                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col1 (type: boolean)
+        Reducer 11 
             Reduce Operator Tree:
               Merge Join Operator
                 condition map:
@@ -1516,7 +1535,7 @@ STAGE PLANS:
                   sort order: +
                   Map-reduce partition columns: _col1 (type: string)
                   Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-        Reducer 11 
+        Reducer 12 
             Execution mode: vectorized
             Reduce Operator Tree:
               Select Operator
@@ -1562,19 +1581,6 @@ STAGE PLANS:
                           sort order: +
                           Map-reduce partition columns: _col0 (type: string)
                           Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-        Reducer 12 
-            Execution mode: vectorized
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: count(VALUE._col0), count(VALUE._col1)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  null sort order: 
-                  sort order: 
-                  Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col0 (type: bigint), _col1 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
               Merge Join Operator
@@ -1708,6 +1714,17 @@ STAGE PLANS:
                   1 _col0 (type: int)
                 outputColumnNames: _col1
                 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  aggregations: count(), count(_col1)
+                  minReductionHashAggr: 0.99
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    null sort order: 
+                    sort order: 
+                    Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: bigint), _col1 (type: bigint)
                 Group By Operator
                   keys: _col1 (type: int)
                   minReductionHashAggr: 0.99
@@ -1736,17 +1753,6 @@ STAGE PLANS:
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
                       Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                Group By Operator
-                  aggregations: count(), count(_col1)
-                  minReductionHashAggr: 0.99
-                  mode: hash
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    null sort order: 
-                    sort order: 
-                    Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: _col0 (type: bigint), _col1 (type: bigint)
                 Select Operator
                   expressions: _col1 (type: int)
                   outputColumnNames: _col0
@@ -1767,21 +1773,15 @@ STAGE PLANS:
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                keys: KEY._col0 (type: int)
+                aggregations: count(VALUE._col0), count(VALUE._col1)
                 mode: mergepartial
-                outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: int), true (type: boolean)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: int)
-                    null sort order: z
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: int)
-                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: _col1 (type: boolean)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+                Reduce Output Operator
+                  null sort order: 
+                  sort order: 
+                  Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+                  value expressions: _col0 (type: bigint), _col1 (type: bigint)
         Union 5 
             Vertex: Union 5
 
@@ -1802,7 +1802,7 @@ STAGE PLANS:
     Stats Work
       Basic Stats Work:
 
-Warning: Shuffle Join MERGEJOIN[178][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[215][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
 PREHOOK: query: delete from tbl_ice where a in (select t1.a from tbl_ice t1 join tbl_standard_other t2 on t1.a = t2.a)
 PREHOOK: type: QUERY
 PREHOOK: Input: default@tbl_ice