diff options
author | Tom Lane | 2025-04-12 16:27:46 +0000 |
---|---|---|
committer | Tom Lane | 2025-04-12 16:28:02 +0000 |
commit | e708ffe79df07fe26801869f391f4c227615dd42 (patch) | |
tree | 62ba53395b0935c9b9bac770c235ec1286bb0988 /contrib | |
parent | a6cab6a78ee58356967a447fa2c6414732856986 (diff) |
Fix GIN's shimTriConsistentFn to not corrupt its input.
Commit 0f21db36d made an assumption that GIN triConsistentFns
would not modify their input entryRes[] arrays. But in fact,
the "shim" triConsistentFn that we use for opclasses that don't
supply their own did exactly that, potentially leading to wrong
answers from a GIN index search. Through bad luck, none of the
test cases that we have for such opclasses exposed the bug.
One response to this could be that the assumption of consistency check
functions not modifying entryRes[] arrays is a bad one, but it still
seems reasonable to me. Notably, shimTriConsistentFn is itself
assuming that with respect to the underlying boolean consistentFn,
so it's sure being self-centered in supposing that it gets to do so.
Fortunately, it's quite simple to fix shimTriConsistentFn to restore
the entry-time state of entryRes[], so let's do that instead.
This issue doesn't affect any core GIN opclasses, since they all
supply their own triConsistentFns. It does affect contrib modules
btree_gin, hstore, and intarray.
Along the way, I (tgl) noticed that shimTriConsistentFn failed to
pick up on a "recheck" flag returned by its first call to the boolean
consistentFn. This may be only a latent problem, since it would be
unlikely for a consistentFn to set recheck for the all-false case
and not any other cases. (Indeed, none of our contrib modules do
that.) Nonetheless, it's formally wrong.
Reported-by: Vinod Sridharan <[email protected]>
Author: Vinod Sridharan <[email protected]>
Reviewed-by: Tom Lane <[email protected]>
Discussion: https://postgr.es/m/CAFMdLD7XzsXfi1+DpTqTgrD8XU0i2C99KuF=5VHLWjx4C1pkcg@mail.gmail.com
Backpatch-through: 13
Diffstat (limited to 'contrib')
-rw-r--r-- | contrib/intarray/expected/_int.out | 42 | ||||
-rw-r--r-- | contrib/intarray/sql/_int.sql | 7 |
2 files changed, 49 insertions, 0 deletions
diff --git a/contrib/intarray/expected/_int.out b/contrib/intarray/expected/_int.out index b39ab82d43d..d0e68d0447f 100644 --- a/contrib/intarray/expected/_int.out +++ b/contrib/intarray/expected/_int.out @@ -492,6 +492,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + SET enable_seqscan = off; -- not all of these would use index by default CREATE INDEX text_idx on test__int using gist ( a gist__int_ops ); SELECT count(*) from test__int WHERE a && '{23,50}'; @@ -566,6 +572,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + INSERT INTO test__int SELECT array(SELECT x FROM generate_series(1, 1001) x); -- should fail ERROR: input array is too big (199 maximum allowed, 1001 current), use gist__intbig_ops opclass instead DROP INDEX text_idx; @@ -648,6 +660,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gist (a gist__intbig_ops(siglen = 0)); ERROR: value 0 out of bounds for option "siglen" @@ -728,6 +746,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gist ( a gist__intbig_ops ); SELECT count(*) from test__int WHERE a && '{23,50}'; @@ -802,6 +826,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gin ( a gin__int_ops ); SELECT count(*) from test__int WHERE a && '{23,50}'; @@ -876,6 +906,12 @@ SELECT count(*) from test__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + DROP INDEX text_idx; -- Repeat the same queries with an extended data set. The data set is the -- same that we used before, except that each element in the array is @@ -968,4 +1004,10 @@ SELECT count(*) from more__int WHERE a @@ '!20 & !21'; 6344 (1 row) +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; + count +------- + 12 +(1 row) + RESET enable_seqscan; diff --git a/contrib/intarray/sql/_int.sql b/contrib/intarray/sql/_int.sql index 2d4ed1c9ae2..5668ab40704 100644 --- a/contrib/intarray/sql/_int.sql +++ b/contrib/intarray/sql/_int.sql @@ -107,6 +107,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; SET enable_seqscan = off; -- not all of these would use index by default @@ -124,6 +125,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; INSERT INTO test__int SELECT array(SELECT x FROM generate_series(1, 1001) x); -- should fail @@ -144,6 +146,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gist (a gist__intbig_ops(siglen = 0)); @@ -162,6 +165,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gist ( a gist__intbig_ops ); @@ -178,6 +182,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; DROP INDEX text_idx; CREATE INDEX text_idx on test__int using gin ( a gin__int_ops ); @@ -194,6 +199,7 @@ SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from test__int WHERE a @@ '20 | !21'; SELECT count(*) from test__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; DROP INDEX text_idx; @@ -229,6 +235,7 @@ SELECT count(*) from more__int WHERE a @> '{20,23}' or a @> '{50,68}'; SELECT count(*) from more__int WHERE a @@ '(20&23)|(50&68)'; SELECT count(*) from more__int WHERE a @@ '20 | !21'; SELECT count(*) from more__int WHERE a @@ '!20 & !21'; +SELECT count(*) from test__int WHERE a @@ '!2733 & (2738 | 254)'; RESET enable_seqscan; |