Fix incorrect non-strict join recheck in MERGE WHEN NOT MATCHED BY SOURCE.

If a MERGE command contains WHEN NOT MATCHED BY SOURCE actions, the
merge join condition is used by the executor to distinguish MATCHED
from NOT MATCHED BY SOURCE cases. However, this qual is executed using
the output from the join subplan node, which nulls the output from the
source relation in the not matched case, and so the result may be
incorrect if the join condition is "non-strict" -- for example,
something like "src.col IS NOT DISTINCT FROM tgt.col".

Fix this by enhancing the join recheck condition with an additional
"src IS NOT NULL" check, so that it does the right thing when
evaluated using the output from the join subplan.

Noted by Tom Lane while investigating bug #18634 from Alexander
Lakhin.

Back-patch to v17, where WHEN NOT MATCHED BY SOURCE support was added
to MERGE.

Discussion: https://postgr.es/m/18634-db5299c937877f2b%40postgresql.org

diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c
index a70404558ff488f01229fdfa167e1b9c7b9cd327..ca15994fdc732974a8db89c938e4b54db6a57009 100644 (file)
--- a/src/backend/optimizer/prep/prepjointree.c
+++ b/src/backend/optimizer/prep/prepjointree.c
@@ -158,6 +158,9 @@ transform_MERGE_to_join(Query *parse)
    int         joinrti;
    List       *vars;
    RangeTblRef *rtr;
+   FromExpr   *target;
+   Node       *source;
+   int         sourcerti;
 
    if (parse->commandType != CMD_MERGE)
        return;
@@ -226,13 +229,36 @@ transform_MERGE_to_join(Query *parse)
     * parse->jointree->quals are restrictions on the target relation (if the
     * target relation is an auto-updatable view).
     */
+   /* target rel, with any quals */
    rtr = makeNode(RangeTblRef);
    rtr->rtindex = parse->mergeTargetRelation;
+   target = makeFromExpr(list_make1(rtr), parse->jointree->quals);
+
+   /* source rel (expect exactly one -- see transformMergeStmt()) */
+   Assert(list_length(parse->jointree->fromlist) == 1);
+   source = linitial(parse->jointree->fromlist);
+
+   /*
+    * index of source rel (expect either a RangeTblRef or a JoinExpr -- see
+    * transformFromClauseItem()).
+    */
+   if (IsA(source, RangeTblRef))
+       sourcerti = ((RangeTblRef *) source)->rtindex;
+   else if (IsA(source, JoinExpr))
+       sourcerti = ((JoinExpr *) source)->rtindex;
+   else
+   {
+       elog(ERROR, "unrecognized source node type: %d",
+            (int) nodeTag(source));
+       sourcerti = 0;          /* keep compiler quiet */
+   }
+
+   /* Join the source and target */
    joinexpr = makeNode(JoinExpr);
    joinexpr->jointype = jointype;
    joinexpr->isNatural = false;
-   joinexpr->larg = (Node *) makeFromExpr(list_make1(rtr), parse->jointree->quals);
-   joinexpr->rarg = linitial(parse->jointree->fromlist);   /* source rel */
+   joinexpr->larg = (Node *) target;
+   joinexpr->rarg = source;
    joinexpr->usingClause = NIL;
    joinexpr->join_using_alias = NULL;
    joinexpr->quals = parse->mergeJoinCondition;
@@ -261,9 +287,39 @@ transform_MERGE_to_join(Query *parse)
     * use the join condition to distinguish between MATCHED and NOT MATCHED
     * BY SOURCE cases.  Otherwise, it's no longer needed, and we set it to
     * NULL, saving cycles during planning and execution.
-    */
-   if (!have_action[MERGE_WHEN_NOT_MATCHED_BY_SOURCE])
-       parse->mergeJoinCondition = NULL;
+    *
+    * We need to be careful though: the executor evaluates this condition
+    * using the output of the join subplan node, which nulls the output from
+    * the source relation when the join condition doesn't match.  That risks
+    * producing incorrect results when rechecking using a "non-strict" join
+    * condition, such as "src.col IS NOT DISTINCT FROM tgt.col".  To guard
+    * against that, we add an additional "src IS NOT NULL" check to the join
+    * condition, so that it does the right thing when performing a recheck
+    * based on the output of the join subplan.
+    */
+   if (have_action[MERGE_WHEN_NOT_MATCHED_BY_SOURCE])
+   {
+       Var        *var;
+       NullTest   *ntest;
+
+       /* source wholerow Var (nullable by the new join) */
+       var = makeWholeRowVar(rt_fetch(sourcerti, parse->rtable),
+                             sourcerti, 0, false);
+       var->varnullingrels = bms_make_singleton(joinrti);
+
+       /* "src IS NOT NULL" check */
+       ntest = makeNode(NullTest);
+       ntest->arg = (Expr *) var;
+       ntest->nulltesttype = IS_NOT_NULL;
+       ntest->argisrow = false;
+       ntest->location = -1;
+
+       /* combine it with the original join condition */
+       parse->mergeJoinCondition =
+           (Node *) make_and_qual((Node *) ntest, parse->mergeJoinCondition);
+   }
+   else
+       parse->mergeJoinCondition = NULL;   /* join condition not needed */
 }
 
 /*

diff --git a/src/test/regress/expected/merge.out b/src/test/regress/expected/merge.out
index 3d33259e8ffbb50aa5d210354e4b7210e2ddce23..0e59bae1a7fe7a564c71b5eb8974e36cdd74247c 100644 (file)
--- a/src/test/regress/expected/merge.out
+++ b/src/test/regress/expected/merge.out
@@ -2689,6 +2689,28 @@ DETAIL:  drop cascades to table measurement_y2006m02
 drop cascades to table measurement_y2006m03
 drop cascades to table measurement_y2007m01
 DROP FUNCTION measurement_insert_trigger();
+--
+-- test non-strict join clause
+--
+CREATE TABLE src (a int, b text);
+INSERT INTO src VALUES (1, 'src row');
+CREATE TABLE tgt (a int, b text);
+INSERT INTO tgt VALUES (NULL, 'tgt row');
+MERGE INTO tgt USING src ON tgt.a IS NOT DISTINCT FROM src.a
+  WHEN MATCHED THEN UPDATE SET a = src.a, b = src.b
+  WHEN NOT MATCHED BY SOURCE THEN DELETE
+  RETURNING merge_action(), src.*, tgt.*;
+ merge_action | a | b | a |    b    
+--------------+---+---+---+---------
+ DELETE       |   |   |   | tgt row
+(1 row)
+
+SELECT * FROM tgt;
+ a | b 
+---+---
+(0 rows)
+
+DROP TABLE src, tgt;
 -- prepare
 RESET SESSION AUTHORIZATION;
 -- try a system catalog

diff --git a/src/test/regress/sql/merge.sql b/src/test/regress/sql/merge.sql
index 92163ec9fe0d5e8cc7178dd8b9148b1c21d36e69..2a7753c65b08564120047c627991774458c1fc63 100644 (file)
--- a/src/test/regress/sql/merge.sql
+++ b/src/test/regress/sql/merge.sql
@@ -1710,6 +1710,24 @@ SELECT * FROM new_measurement ORDER BY city_id, logdate;
 DROP TABLE measurement, new_measurement CASCADE;
 DROP FUNCTION measurement_insert_trigger();
 
+--
+-- test non-strict join clause
+--
+CREATE TABLE src (a int, b text);
+INSERT INTO src VALUES (1, 'src row');
+
+CREATE TABLE tgt (a int, b text);
+INSERT INTO tgt VALUES (NULL, 'tgt row');
+
+MERGE INTO tgt USING src ON tgt.a IS NOT DISTINCT FROM src.a
+  WHEN MATCHED THEN UPDATE SET a = src.a, b = src.b
+  WHEN NOT MATCHED BY SOURCE THEN DELETE
+  RETURNING merge_action(), src.*, tgt.*;
+
+SELECT * FROM tgt;
+
+DROP TABLE src, tgt;
+
 -- prepare
 
 RESET SESSION AUTHORIZATION;