From d26e084ed00cde21d917cd4dc52f2ab1467fdc19 Mon Sep 17 00:00:00 2001 From: spoondla Date: Wed, 11 Feb 2026 16:06:56 -0800 Subject: [PATCH] Fix REFRESH MATERIALIZED VIEW CONCURRENTLY to detect NULL containing duplicates. 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. 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 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 81a55a33ef2..6aaf7a68c20 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)))); -- 2.39.5 (Apple Git-154)