From 65dc30ced64cd17f3800ff1b73ab1d358e92efd8 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Tue, 24 Aug 2021 16:37:26 -0400 Subject: [PATCH] Fix regexp misbehavior with capturing parens inside "{0}". Regexps like "(.){0}...\1" drew an "invalid backreference number". That's not unreasonable on its face, since the capture group will never be matched if it's iterated zero times. However, other engines such as Perl's don't complain about this, nor do we throw an error for related cases such as "(.)|\1", even though that backref can never succeed either. Also, if the zero-iterations case happens at runtime rather than compile time --- say, "(x)*...\1" when there's no "x" to be found --- that's not an error, we just deem the backref to not match. Making this even less defensible, no error was thrown for nested cases such as "((.)){0}...\2"; and to add insult to injury, those cases could result in assertion failures instead. (It seems that nothing especially bad happened in non-assert builds, though.) Let's just fix it so that no error is thrown and instead the backref is deemed to never match, so that compile-time detection of no iterations behaves the same as run-time detection. Per report from Mark Dilger. This appears to be an aboriginal error in Spencer's library, so back-patch to all supported versions. Pre-v14, it turns out to also be necessary to back-patch one aspect of commits cb76fbd7e/00116dee5, namely to create capture-node subREs with the begin/end states of their subexpressions, not the current lp/rp of the outer parseqatom invocation. Otherwise delsub complains that we're trying to disconnect a state from itself. This is a bit scary but code examination shows that it's safe: in the pre-v14 code, if we want to wrap iteration around the subexpression, the first thing we do is overwrite the atom's begin/end fields with new states. So the bogus values didn't survive long enough to be used for anything, except if no iteration is required, in which case it doesn't matter. Discussion: https://postgr.es/m/A099E4A8-4377-4C64-A98C-3DEDDC075502@enterprisedb.com --- src/backend/regex/regcomp.c | 22 ++++++++++++++----- .../test_regex/expected/test_regex.out | 22 +++++++++++++++++++ .../modules/test_regex/sql/test_regex.sql | 6 +++++ src/test/regress/expected/regex.out | 19 ++++++++++++++++ src/test/regress/sql/regex.sql | 5 +++++ 5 files changed, 69 insertions(+), 5 deletions(-) diff --git a/src/backend/regex/regcomp.c b/src/backend/regex/regcomp.c index ae3a7b6a38..d9840171a3 100644 --- a/src/backend/regex/regcomp.c +++ b/src/backend/regex/regcomp.c @@ -1089,11 +1089,23 @@ parseqatom(struct vars *v, /* annoying special case: {0} or {0,0} cancels everything */ if (m == 0 && n == 0) { - if (atom != NULL) - freesubre(v, atom); - if (atomtype == '(') - v->subs[subno] = NULL; - delsub(v->nfa, lp, rp); + /* + * If we had capturing subexpression(s) within the atom, we don't want + * to destroy them, because it's legal (if useless) to back-ref them + * later. Hence, just unlink the atom from lp/rp and then ignore it. + */ + if (atom != NULL && (atom->flags & CAP)) + { + delsub(v->nfa, lp, atom->begin); + delsub(v->nfa, atom->end, rp); + } + else + { + /* Otherwise, we can clean up any subre infrastructure we made */ + if (atom != NULL) + freesubre(v, atom); + delsub(v->nfa, lp, rp); + } EMPTYARC(lp, rp); return top; } diff --git a/src/test/modules/test_regex/expected/test_regex.out b/src/test/modules/test_regex/expected/test_regex.out index 4886858d66..731ba506d3 100644 --- a/src/test/modules/test_regex/expected/test_regex.out +++ b/src/test/modules/test_regex/expected/test_regex.out @@ -3576,6 +3576,28 @@ select * from test_regex('((.))(\2)', 'xyy', 'oRP'); {yy,NULL,NULL,NULL} (2 rows) +-- expectNomatch 21.39 PQR {(.){0}(\1)} xxx +select * from test_regex('(.){0}(\1)', 'xxx', 'PQR'); + test_regex +-------------------------------------------- + {2,REG_UBACKREF,REG_UBOUNDS,REG_UNONPOSIX} +(1 row) + +-- expectNomatch 21.40 PQR {((.)){0}(\2)} xxx +select * from test_regex('((.)){0}(\2)', 'xxx', 'PQR'); + test_regex +-------------------------------------------- + {3,REG_UBACKREF,REG_UBOUNDS,REG_UNONPOSIX} +(1 row) + +-- expectMatch 21.41 NPQR {((.)){0}(\2){0}} xyz {} {} {} {} +select * from test_regex('((.)){0}(\2){0}', 'xyz', 'NPQR'); + test_regex +------------------------------------------------------------ + {3,REG_UBACKREF,REG_UBOUNDS,REG_UNONPOSIX,REG_UEMPTYMATCH} + {"",NULL,NULL,NULL} +(2 rows) + -- doing 22 "multicharacter collating elements" -- # again ugh -- MCCEs are not implemented in Postgres, so we skip all these tests diff --git a/src/test/modules/test_regex/sql/test_regex.sql b/src/test/modules/test_regex/sql/test_regex.sql index 418527da3d..478fa2c547 100644 --- a/src/test/modules/test_regex/sql/test_regex.sql +++ b/src/test/modules/test_regex/sql/test_regex.sql @@ -1036,6 +1036,12 @@ select * from test_regex('((.))(\2){0}', 'xy', 'RPQ'); select * from test_regex('((.))(\2)', 'xyy', 'RP'); -- expectMatch 21.38 oRP ((.))(\2) xyy yy {} {} {} select * from test_regex('((.))(\2)', 'xyy', 'oRP'); +-- expectNomatch 21.39 PQR {(.){0}(\1)} xxx +select * from test_regex('(.){0}(\1)', 'xxx', 'PQR'); +-- expectNomatch 21.40 PQR {((.)){0}(\2)} xxx +select * from test_regex('((.)){0}(\2)', 'xxx', 'PQR'); +-- expectMatch 21.41 NPQR {((.)){0}(\2){0}} xyz {} {} {} {} +select * from test_regex('((.)){0}(\2){0}', 'xyz', 'NPQR'); -- doing 22 "multicharacter collating elements" -- # again ugh diff --git a/src/test/regress/expected/regex.out b/src/test/regress/expected/regex.out index cbe2cfc3ea..ae0de7307d 100644 --- a/src/test/regress/expected/regex.out +++ b/src/test/regress/expected/regex.out @@ -567,6 +567,25 @@ select 'a' ~ '()+\1'; t (1 row) +-- Test incorrect removal of capture groups within {0} +select 'xxx' ~ '(.){0}(\1)' as f; + f +--- + f +(1 row) + +select 'xxx' ~ '((.)){0}(\2)' as f; + f +--- + f +(1 row) + +select 'xyz' ~ '((.)){0}(\2){0}' as t; + t +--- + t +(1 row) + -- Test ancient oversight in when to apply zaptreesubs select 'abcdef' ~ '^(.)\1|\1.' as f; f diff --git a/src/test/regress/sql/regex.sql b/src/test/regress/sql/regex.sql index c6974a43d1..56217104ce 100644 --- a/src/test/regress/sql/regex.sql +++ b/src/test/regress/sql/regex.sql @@ -135,6 +135,11 @@ select 'a' ~ '.. ()|\1'; select 'a' ~ '()*\1'; select 'a' ~ '()+\1'; +-- Test incorrect removal of capture groups within {0} +select 'xxx' ~ '(.){0}(\1)' as f; +select 'xxx' ~ '((.)){0}(\2)' as f; +select 'xyz' ~ '((.)){0}(\2){0}' as t; + -- Test ancient oversight in when to apply zaptreesubs select 'abcdef' ~ '^(.)\1|\1.' as f; select 'abadef' ~ '^((.)\2|..)\2' as f;