HIVE-11152 : Swapping join inputs in ASTConverter (Jesus Camacho Rodr…

…iguez via John Pullokkaran)

ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTConverter.java

@@ -31,6 +31,7 @@
 import org.apache.calcite.rel.core.AggregateCall;
 import org.apache.calcite.rel.core.Filter;
 import org.apache.calcite.rel.core.Join;
+import org.apache.calcite.rel.core.JoinRelType;
 import org.apache.calcite.rel.core.Project;
 import org.apache.calcite.rel.core.SemiJoin;
 import org.apache.calcite.rel.core.Sort;
@@ -285,9 +286,24 @@ private QueryBlockInfo convertSource(RelNode r) throws CalciteSemanticException
       s = new Schema(left.schema, right.schema);
       ASTNode cond = join.getCondition().accept(new RexVisitor(s));
       boolean semiJoin = join instanceof SemiJoin;
-      ast = ASTBuilder.join(left.ast, right.ast, join.getJoinType(), cond, semiJoin);
-      if (semiJoin)
+      if (join.getRight() instanceof Join) {
+        // Invert join inputs; this is done because otherwise the SemanticAnalyzer
+        // methods to merge joins will not kick in
+        JoinRelType type;
+        if (join.getJoinType() == JoinRelType.LEFT) {
+          type = JoinRelType.RIGHT;
+        } else if (join.getJoinType() == JoinRelType.RIGHT) {
+          type = JoinRelType.LEFT;
+        } else {
+          type = join.getJoinType();
+        }
+        ast = ASTBuilder.join(right.ast, left.ast, type, cond, semiJoin);
+      } else {
+        ast = ASTBuilder.join(left.ast, right.ast, join.getJoinType(), cond, semiJoin);
+      }
+      if (semiJoin) {
         s = left.schema;
+      }
     } else if (r instanceof Union) {
       RelNode leftInput = ((Union) r).getInput(0);
       RelNode rightInput = ((Union) r).getInput(1);

ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java

@@ -242,7 +242,15 @@ private static boolean validJoinParent(RelNode joinNode, RelNode parent) {
     boolean validParent = true;
 
     if (parent instanceof Join) {
-      if (((Join) parent).getRight() == joinNode) {
+      // In Hive AST, right child of join cannot be another join,
+      // thus we need to introduce a project on top of it.
+      // But we only need the additional project if the left child
+      // is another join too; if it is not, ASTConverter will swap
+      // the join inputs, leaving the join operator on the left.
+      // This will help triggering multijoin recognition methods that
+      // are embedded in SemanticAnalyzer.
+      if (((Join) parent).getRight() == joinNode &&
+            (((Join) parent).getLeft() instanceof Join) ) {
         validParent = false;
       }
     } else if (parent instanceof SetOp) {
@@ -255,7 +263,7 @@ private static boolean validJoinParent(RelNode joinNode, RelNode parent) {
   private static boolean validFilterParent(RelNode filterNode, RelNode parent) {
     boolean validParent = true;
 
-    // TOODO: Verify GB having is not a seperate filter (if so we shouldn't
+    // TODO: Verify GB having is not a separate filter (if so we shouldn't
     // introduce derived table)
     if (parent instanceof Filter || parent instanceof Join
         || parent instanceof SetOp) {

ql/src/test/results/clientpositive/auto_join13.q.out

@@ -21,18 +21,18 @@ JOIN
 ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-7 is a root stage
-  Stage-2 depends on stages: Stage-7
-  Stage-0 depends on stages: Stage-2
+  Stage-8 is a root stage
+  Stage-3 depends on stages: Stage-8
+  Stage-0 depends on stages: Stage-3
 
 STAGE PLANS:
-  Stage: Stage-7
+  Stage: Stage-8
     Map Reduce Local Work
       Alias -> Map Local Tables:
         $hdt$_0:$hdt$_0:src 
           Fetch Operator
             limit: -1
-        $hdt$_0:$hdt$_1:$hdt$_1:src 
+        $hdt$_0:$hdt$_1:src 
           Fetch Operator
             limit: -1
       Alias -> Map Local Operator Tree:
@@ -49,9 +49,9 @@ STAGE PLANS:
                 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
-                    0 UDFToDouble(_col0) (type: double)
-                    1 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
-        $hdt$_0:$hdt$_1:$hdt$_1:src 
+                    0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+                    1 UDFToDouble(_col0) (type: double)
+        $hdt$_0:$hdt$_1:src 
           TableScan
             alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -67,7 +67,7 @@ STAGE PLANS:
                     0 _col0 (type: string)
                     1 _col0 (type: string)
 
-  Stage: Stage-2
+  Stage: Stage-3
     Map Reduce
       Map Operator Tree:
           TableScan
@@ -95,12 +95,12 @@ STAGE PLANS:
                       condition map:
                            Inner Join 0 to 1
                       keys:
-                        0 UDFToDouble(_col0) (type: double)
-                        1 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
-                      outputColumnNames: _col2, _col3
+                        0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+                        1 UDFToDouble(_col0) (type: double)
+                      outputColumnNames: _col1, _col2
                       Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
-                        expressions: hash(_col3,_col2) (type: int)
+                        expressions: hash(_col2,_col1) (type: int)
                         outputColumnNames: _col0
                         Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
                         Group By Operator