Teach the system how to use hashing for UNION. (INTERSECT/EXCEPT will follow,

but seem like a separate patch since most of the remaining work is on the
executor side.)  I took the opportunity to push selection of the grouping
operators for set operations into the parser where it belongs.  Otherwise this
is just a small exercise in making prepunion.c consider both alternatives.

As with the recent DISTINCT patch, this means we can UNION on datatypes that
can hash but not sort, and it means that UNION without ORDER BY is no longer
certain to produce sorted output.

4 files changed, 18 insertions, 9 deletions

diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index 6be25b05f9..b844577c88 100644
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.475 2008/08/05 12:09:30 mha Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.476 2008/08/07 01:11:51 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200808051
+#define CATALOG_VERSION_NO	200808061
 
 #endif
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index f1a1e828fc..65c3698a84 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.370 2008/08/02 21:32:00 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.371 2008/08/07 01:11:51 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -797,7 +797,12 @@ typedef struct SelectStmt
  * top-level Query node containing the leaf SELECTs as subqueries in its
  * range table.  Its setOperations field shows the tree of set operations,
  * with leaf SelectStmt nodes replaced by RangeTblRef nodes, and internal
- * nodes replaced by SetOperationStmt nodes.
+ * nodes replaced by SetOperationStmt nodes.  Information about the output
+ * column types is added, too.  (Note that the child nodes do not necessarily
+ * produce these types directly, but we've checked that their output types
+ * can be coerced to the output column type.)  Also, if it's not UNION ALL,
+ * information about the types' sort/group semantics is provided in the form
+ * of a SortGroupClause list (same representation as, eg, DISTINCT).
  * ----------------------
  */
 typedef struct SetOperationStmt
@@ -812,6 +817,8 @@ typedef struct SetOperationStmt
 	/* Fields derived during parse analysis: */
 	List	   *colTypes;		/* OID list of output column type OIDs */
 	List	   *colTypmods;		/* integer list of output column typmods */
+	List	   *groupClauses;	/* a list of SortGroupClause's */
+	/* groupClauses is NIL if UNION ALL, but must be set otherwise */
 } SetOperationStmt;
 
 
diff --git a/src/include/optimizer/tlist.h b/src/include/optimizer/tlist.h
index 8a8966213b..9899b14c82 100644
--- a/src/include/optimizer/tlist.h
+++ b/src/include/optimizer/tlist.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/tlist.h,v 1.50 2008/08/02 21:32:01 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/tlist.h,v 1.51 2008/08/07 01:11:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -32,6 +32,11 @@ extern Node *get_sortgroupclause_expr(SortGroupClause *sgClause,
 extern List *get_sortgrouplist_exprs(List *sgClauses,
 						List *targetList);
 
+extern Oid *extract_grouping_ops(List *groupClause);
+extern AttrNumber *extract_grouping_cols(List *groupClause, List *tlist);
+extern bool grouping_is_sortable(List *groupClause);
+extern bool grouping_is_hashable(List *groupClause);
+
 extern bool tlist_same_datatypes(List *tlist, List *colTypes, bool junkOK);
 
 #endif   /* TLIST_H */
diff --git a/src/include/parser/parse_clause.h b/src/include/parser/parse_clause.h
index 357a2947cb..ffea3466b5 100644
--- a/src/include/parser/parse_clause.h
+++ b/src/include/parser/parse_clause.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/parser/parse_clause.h,v 1.51 2008/08/02 21:32:01 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/parser/parse_clause.h,v 1.52 2008/08/07 01:11:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -35,9 +35,6 @@ extern List *transformDistinctClause(ParseState *pstate,
 extern List *transformDistinctOnClause(ParseState *pstate, List *distinctlist,
 						List **targetlist, List *sortClause);
 
-extern List *addTargetToGroupList(ParseState *pstate, TargetEntry *tle,
-					 List *grouplist, List *targetlist,
-					 bool requireSortOp, bool resolveUnknown);
 extern Index assignSortGroupRef(TargetEntry *tle, List *tlist);
 extern bool targetIsInSortList(TargetEntry *tle, Oid sortop, List *sortList);