diff --git a/src/backend/regex/regcomp.c b/src/backend/regex/regcomp.c index 91078dcd80..fba44625d7 100644 --- a/src/backend/regex/regcomp.c +++ b/src/backend/regex/regcomp.c @@ -958,7 +958,7 @@ parseqatom(struct vars *v, if (cap) { v->subs[subno] = atom; - t = subre(v, '(', atom->flags | CAP, lp, rp); + t = subre(v, '(', atom->flags | CAP, s, s2); NOERR(); t->subno = subno; t->left = atom; @@ -1041,11 +1041,23 @@ 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; } diff --git a/src/test/regress/expected/regex.out b/src/test/regress/expected/regex.out index fccd91566c..f842d5724c 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 762b3ae69b..758de44d2f 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;