Add support for MERGE SQL command

MERGE performs actions that modify rows in the target table using a
source table or query. MERGE provides a single SQL statement that can
conditionally INSERT/UPDATE/DELETE rows -- a task that would otherwise
require multiple PL statements.  For example,

MERGE INTO target AS t
USING source AS s
ON t.tid = s.sid
WHEN MATCHED AND t.balance > s.delta THEN
  UPDATE SET balance = t.balance - s.delta
WHEN MATCHED THEN
  DELETE
WHEN NOT MATCHED AND s.delta > 0 THEN
  INSERT VALUES (s.sid, s.delta)
WHEN NOT MATCHED THEN
  DO NOTHING;

MERGE works with regular tables, partitioned tables and inheritance
hierarchies, including column and row security enforcement, as well as
support for row and statement triggers and transition tables therein.

MERGE is optimized for OLTP and is parameterizable, though also useful
for large scale ETL/ELT. MERGE is not intended to be used in preference
to existing single SQL commands for INSERT, UPDATE or DELETE since there
is some overhead.  MERGE can be used from PL/pgSQL.

MERGE does not support targetting updatable views or foreign tables, and
RETURNING clauses are not allowed either.  These limitations are likely
fixable with sufficient effort.  Rewrite rules are also not supported,
but it's not clear that we'd want to support them.

Author: Pavan Deolasee <pavan.deolasee@gmail.com>
Author: Álvaro Herrera <alvherre@alvh.no-ip.org>
Author: Amit Langote <amitlangote09@gmail.com>
Author: Simon Riggs <simon.riggs@enterprisedb.com>
Reviewed-by: Peter Eisentraut <peter.eisentraut@enterprisedb.com>
Reviewed-by: Andres Freund <andres@anarazel.de> (earlier versions)
Reviewed-by: Peter Geoghegan <pg@bowt.ie> (earlier versions)
Reviewed-by: Robert Haas <robertmhaas@gmail.com> (earlier versions)
Reviewed-by: Japin Li <japinli@hotmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Tomas Vondra <tomas.vondra@enterprisedb.com>
Reviewed-by: Zhihong Yu <zyu@yugabyte.com>
Discussion: https://postgr.es/m/CANP8+jKitBSrB7oTgT9CY2i1ObfOt36z0XMraQc+Xrz8QB0nXA@mail.gmail.com
Discussion: https://postgr.es/m/CAH2-WzkJdBuxj9PO=2QaO9-3h3xGbQPZ34kJH=HukRekwM-GZg@mail.gmail.com
Discussion: https://postgr.es/m/20201231134736.GA25392@alvherre.pgsql

3 files changed, 23 insertions, 11 deletions

diff --git a/src/backend/optimizer/util/appendinfo.c b/src/backend/optimizer/util/appendinfo.c
index 2f06fa743c2..9d4bb470270 100644
--- a/src/backend/optimizer/util/appendinfo.c
+++ b/src/backend/optimizer/util/appendinfo.c
@@ -774,8 +774,8 @@ add_row_identity_var(PlannerInfo *root, Var *orig_var,
 	Assert(orig_var->varlevelsup == 0);
 
 	/*
-	 * If we're doing non-inherited UPDATE/DELETE, there's little need for
-	 * ROWID_VAR shenanigans.  Just shove the presented Var into the
+	 * If we're doing non-inherited UPDATE/DELETE/MERGE, there's little need
+	 * for ROWID_VAR shenanigans.  Just shove the presented Var into the
 	 * processed_tlist, and we're done.
 	 */
 	if (rtindex == root->parse->resultRelation)
@@ -862,14 +862,16 @@ add_row_identity_columns(PlannerInfo *root, Index rtindex,
 	char		relkind = target_relation->rd_rel->relkind;
 	Var		   *var;
 
-	Assert(commandType == CMD_UPDATE || commandType == CMD_DELETE);
+	Assert(commandType == CMD_UPDATE || commandType == CMD_DELETE || commandType == CMD_MERGE);
 
-	if (relkind == RELKIND_RELATION ||
+	if (commandType == CMD_MERGE ||
+		relkind == RELKIND_RELATION ||
 		relkind == RELKIND_MATVIEW ||
 		relkind == RELKIND_PARTITIONED_TABLE)
 	{
 		/*
-		 * Emit CTID so that executor can find the row to update or delete.
+		 * Emit CTID so that executor can find the row to merge, update or
+		 * delete.
 		 */
 		var = makeVar(rtindex,
 					  SelfItemPointerAttributeNumber,
@@ -942,8 +944,11 @@ distribute_row_identity_vars(PlannerInfo *root)
 	RelOptInfo *target_rel;
 	ListCell   *lc;
 
-	/* There's nothing to do if this isn't an inherited UPDATE/DELETE. */
-	if (parse->commandType != CMD_UPDATE && parse->commandType != CMD_DELETE)
+	/*
+	 * There's nothing to do if this isn't an inherited UPDATE/DELETE/MERGE.
+	 */
+	if (parse->commandType != CMD_UPDATE && parse->commandType != CMD_DELETE &&
+		parse->commandType != CMD_MERGE)
 	{
 		Assert(root->row_identity_vars == NIL);
 		return;
diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c
index 5c32c96b71c..99df76b6b71 100644
--- a/src/backend/optimizer/util/pathnode.c
+++ b/src/backend/optimizer/util/pathnode.c
@@ -3620,6 +3620,7 @@ create_lockrows_path(PlannerInfo *root, RelOptInfo *rel,
  * 'rowMarks' is a list of PlanRowMarks (non-locking only)
  * 'onconflict' is the ON CONFLICT clause, or NULL
  * 'epqParam' is the ID of Param for EvalPlanQual re-eval
+ * 'mergeActionLists' is a list of lists of MERGE actions (one per rel)
  */
 ModifyTablePath *
 create_modifytable_path(PlannerInfo *root, RelOptInfo *rel,
@@ -3631,13 +3632,14 @@ create_modifytable_path(PlannerInfo *root, RelOptInfo *rel,
 						List *updateColnosLists,
 						List *withCheckOptionLists, List *returningLists,
 						List *rowMarks, OnConflictExpr *onconflict,
-						int epqParam)
+						List *mergeActionLists, int epqParam)
 {
 	ModifyTablePath *pathnode = makeNode(ModifyTablePath);
 
-	Assert(operation == CMD_UPDATE ?
-		   list_length(resultRelations) == list_length(updateColnosLists) :
-		   updateColnosLists == NIL);
+	Assert(operation == CMD_MERGE ||
+		   (operation == CMD_UPDATE ?
+			list_length(resultRelations) == list_length(updateColnosLists) :
+			updateColnosLists == NIL));
 	Assert(withCheckOptionLists == NIL ||
 		   list_length(resultRelations) == list_length(withCheckOptionLists));
 	Assert(returningLists == NIL ||
@@ -3697,6 +3699,7 @@ create_modifytable_path(PlannerInfo *root, RelOptInfo *rel,
 	pathnode->rowMarks = rowMarks;
 	pathnode->onconflict = onconflict;
 	pathnode->epqParam = epqParam;
+	pathnode->mergeActionLists = mergeActionLists;
 
 	return pathnode;
 }
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index a5002ad8955..df97b799174 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -2167,6 +2167,10 @@ has_row_triggers(PlannerInfo *root, Index rti, CmdType event)
 				 trigDesc->trig_delete_before_row))
 				result = true;
 			break;
+			/* There is no separate event for MERGE, only INSERT/UPDATE/DELETE */
+		case CMD_MERGE:
+			result = false;
+			break;
 		default:
 			elog(ERROR, "unrecognized CmdType: %d", (int) event);
 			break;