From 6d36aee5b718524f718436d0973822bc2cb30bdd Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Tue, 8 Jul 2014 14:03:19 -0400 Subject: Don't assume a subquery's output is unique if there's a SRF in its tlist. While the x output of "select x from t group by x" can be presumed unique, this does not hold for "select x, generate_series(1,10) from t group by x", because we may expand the set-returning function after the grouping step. (Perhaps that should be re-thought; but considering all the other oddities involved with SRFs in targetlists, it seems unlikely we'll change it.) Put a check in query_is_distinct_for() so it's not fooled by such cases. Back-patch to all supported branches. David Rowley --- src/backend/optimizer/util/pathnode.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'src/backend/optimizer/util/pathnode.c') diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c index 0652a2d3598..2c1c46434d5 100644 --- a/src/backend/optimizer/util/pathnode.c +++ b/src/backend/optimizer/util/pathnode.c @@ -1473,6 +1473,17 @@ query_is_distinct_for(Query *query, List *colnos, List *opids) Assert(list_length(colnos) == list_length(opids)); + /* + * A set-returning function in the query's targetlist can result in + * returning duplicate rows, if the SRF is evaluated after the + * de-duplication step; so we play it safe and say "no" if there are any + * SRFs. (We could be certain that it's okay if SRFs appear only in the + * specified columns, since those must be evaluated before de-duplication; + * but it doesn't presently seem worth the complication to check that.) + */ + if (expression_returns_set((Node *) query->targetList)) + return false; + /* * DISTINCT (including DISTINCT ON) guarantees uniqueness if all the * columns in the DISTINCT clause appear in colnos and operator semantics -- cgit v1.2.3