0003-Fix-REFRESH-MATERIALIZED-VIEW-CONCURRENTLY-to-detect_bug1.patch

From a74bf7261d82f84b27396221e60cec440045dad5 Mon Sep 17 00:00:00 2001
From: spoondla <s_poondla@apple.com>
Date: Mon, 2 Mar 2026 11:22:11 -0800
Subject: [PATCH v3] Fix REFRESH MATERIALIZED VIEW CONCURRENTLY to detect
 duplicate rows with NULLs

REFRESH MATERIALIZED VIEW CONCURRENTLY doesn't throw expected error as REFRESH MATERIALIZED VIEW
Issue:
REFRESH MATERIALIZED VIEW CONCURRENTLY was incorrectly skipping duplicate
detection for rows containing any NULL values. This would cause the refresh
to silently succeed while leaving the materialized view with stale data,
rather than properly reporting duplicate row errors.

The bug occurred because the duplicate check used "WHERE newdata.* IS NOT NULL"
which returns false if any column contains NULL. When duplicates existed in
rows with NULLs (e.g., two rows of ('test', NULL)), the check was skipped
entirely. The subsequent FULL OUTER JOIN would then match both duplicate rows
to the same old row, producing an empty diff, causing no updates to be applied.

Fix:
The fix removes the "IS NOT NULL" preconditions from the duplicate detection
query. The query now correctly checks all rows using the record equality
operator (*=), which treats NULL as equal to NULL. This matches the same
equality semantics used by the FULL OUTER JOIN in the diff query, ensuring
consistent duplicate detection.

Added a regression test covering the case of duplicate rows that contain
NULL values.

Note:
The non-concurrent REFRESH was unaffected since it rebuilds indexes from
scratch, which properly detects duplicates during index creation.
---
 src/backend/commands/matview.c        | 20 +++++++++++---------
 src/test/regress/expected/matview.out | 16 +++++++++++++++-
 src/test/regress/sql/matview.sql      | 10 ++++++++++
 3 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 81a55a33ef2..e90b10972ef 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -635,11 +635,13 @@ refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
 
 	/*
-	 * We need to ensure that there are not duplicate rows without NULLs in
-	 * the new data set before we can count on the "diff" results.  Check for
-	 * that in a way that allows showing the first duplicated row found.  Even
-	 * after we pass this test, a unique index on the materialized view may
-	 * find a duplicate key problem.
+	 * We need to ensure that there are not duplicate rows in the new data set
+	 * before we can count on the "diff" results.  Check for that in a way
+	 * that allows showing the first duplicated row found.  We check for
+	 * duplicates using the record equality operator (*=), which treats NULLs
+	 * as equal to each other --- the same semantics used by the FULL OUTER
+	 * JOIN in the diff query below.  Even after we pass this test, a unique
+	 * index on the materialized view may find a duplicate key problem.
 	 *
 	 * Note: here and below, we use "tablename.*::tablerowtype" as a hack to
 	 * keep ".*" from being expanded into multiple columns in a SELECT list.
@@ -648,9 +650,9 @@ refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 	resetStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
 					 "SELECT newdata.*::%s FROM %s newdata "
-					 "WHERE newdata.* IS NOT NULL AND EXISTS "
-					 "(SELECT 1 FROM %s newdata2 WHERE newdata2.* IS NOT NULL "
-					 "AND newdata2.* OPERATOR(pg_catalog.*=) newdata.* "
+					 "WHERE EXISTS "
+					 "(SELECT 1 FROM %s newdata2 "
+					 "WHERE newdata2.* OPERATOR(pg_catalog.*=) newdata.* "
 					 "AND newdata2.ctid OPERATOR(pg_catalog.<>) "
 					 "newdata.ctid)",
 					 tempname, tempname, tempname);
@@ -667,7 +669,7 @@ refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 		 */
 		ereport(ERROR,
 				(errcode(ERRCODE_CARDINALITY_VIOLATION),
-				 errmsg("new data for materialized view \"%s\" contains duplicate rows without any null columns",
+				 errmsg("new data for materialized view \"%s\" contains duplicate rows",
 						RelationGetRelationName(matviewRel)),
 				 errdetail("Row: %s",
 						   SPI_getvalue(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 1))));
diff --git a/src/test/regress/expected/matview.out b/src/test/regress/expected/matview.out
index 0355720dfc6..3f66ada1b6b 100644
--- a/src/test/regress/expected/matview.out
+++ b/src/test/regress/expected/matview.out
@@ -396,10 +396,24 @@ REFRESH MATERIALIZED VIEW mvtest_mv;
 ERROR:  could not create unique index "mvtest_mv_a_idx"
 DETAIL:  Key (a)=(1) is duplicated.
 REFRESH MATERIALIZED VIEW CONCURRENTLY mvtest_mv;
-ERROR:  new data for materialized view "mvtest_mv" contains duplicate rows without any null columns
+ERROR:  new data for materialized view "mvtest_mv" contains duplicate rows
 DETAIL:  Row: (1,10)
 DROP TABLE mvtest_foo CASCADE;
 NOTICE:  drop cascades to materialized view mvtest_mv
+-- test that duplicate rows containing NULLs are also detected (bug fix)
+CREATE TABLE mvtest_foo(a text, b text);
+INSERT INTO mvtest_foo VALUES('test', NULL);
+CREATE MATERIALIZED VIEW mvtest_mv AS SELECT * FROM mvtest_foo;
+CREATE UNIQUE INDEX ON mvtest_mv(a);
+INSERT INTO mvtest_foo VALUES('test', NULL);
+REFRESH MATERIALIZED VIEW mvtest_mv;
+ERROR:  could not create unique index "mvtest_mv_a_idx"
+DETAIL:  Key (a)=(test) is duplicated.
+REFRESH MATERIALIZED VIEW CONCURRENTLY mvtest_mv;
+ERROR:  new data for materialized view "mvtest_mv" contains duplicate rows
+DETAIL:  Row: (test,)
+DROP TABLE mvtest_foo CASCADE;
+NOTICE:  drop cascades to materialized view mvtest_mv
 -- make sure that all columns covered by unique indexes works
 CREATE TABLE mvtest_foo(a, b, c) AS VALUES(1, 2, 3);
 CREATE MATERIALIZED VIEW mvtest_mv AS SELECT * FROM mvtest_foo;
diff --git a/src/test/regress/sql/matview.sql b/src/test/regress/sql/matview.sql
index 934426b9ae8..d14a5b95384 100644
--- a/src/test/regress/sql/matview.sql
+++ b/src/test/regress/sql/matview.sql
@@ -135,6 +135,16 @@ REFRESH MATERIALIZED VIEW mvtest_mv;
 REFRESH MATERIALIZED VIEW CONCURRENTLY mvtest_mv;
 DROP TABLE mvtest_foo CASCADE;
 
+-- test that duplicate rows containing NULLs are also detected (bug fix)
+CREATE TABLE mvtest_foo(a text, b text);
+INSERT INTO mvtest_foo VALUES('test', NULL);
+CREATE MATERIALIZED VIEW mvtest_mv AS SELECT * FROM mvtest_foo;
+CREATE UNIQUE INDEX ON mvtest_mv(a);
+INSERT INTO mvtest_foo VALUES('test', NULL);
+REFRESH MATERIALIZED VIEW mvtest_mv;
+REFRESH MATERIALIZED VIEW CONCURRENTLY mvtest_mv;
+DROP TABLE mvtest_foo CASCADE;
+
 -- make sure that all columns covered by unique indexes works
 CREATE TABLE mvtest_foo(a, b, c) AS VALUES(1, 2, 3);
 CREATE MATERIALIZED VIEW mvtest_mv AS SELECT * FROM mvtest_foo;
-- 
2.39.5 (Apple Git-154)