From dd37acb30b637c306f2ae7f041c164e892e92a22 Mon Sep 17 00:00:00 2001 From: Laurenz Albe Date: Sat, 13 Sep 2025 09:59:47 +0200 Subject: [PATCH v2 1/2] Amend recent fix for SIMILAR TO regex conversion Commit e3ffc3e91d fixed the translation of character classes in SIMILAR TO regular expressions. Unfortunately the fix broke a corner case: if there is an escape character right after the opening bracket, (for example in "[\q]") a closing bracket right after the escape sequence would not be seen as closing the character class. There were two more oversights: a backslash or a nested opening bracket right at the beginning of a character class should remove the special meaning from any following caret or closing bracket. Author: Laurenz Albe Reported-By: Dominique Devienne Reported-By: Stephan Springl Discussion: https://postgr.es/m/41a37137-f8bb-8fc5-2948-31b528f166dc%40bfw-online.de Discussion: https://postgr.es/m/CAFCRh-8NwJd0jq6P%3DR3qhHyqU7hw0BTor3W0SvUcii24et%2BzAw%40mail.gmail.com Backpatch-through: 13 --- src/backend/utils/adt/regexp.c | 14 ++++++++++++++ src/test/regress/expected/strings.out | 9 +++++++++ src/test/regress/sql/strings.sql | 3 +++ 3 files changed, 26 insertions(+) diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c index 6e2864cbbda..b62d67a5a98 100644 --- a/src/backend/utils/adt/regexp.c +++ b/src/backend/utils/adt/regexp.c @@ -948,6 +948,12 @@ similar_escape_internal(text *pat_text, text *esc_text) */ *r++ = '\\'; *r++ = pchar; + /* + * If we encounter an escaped character in a character class, + * we are no longer at the beginning. + */ + if (charclass_depth > 0) + charclass_start = 3; } afterescape = false; } @@ -959,7 +965,11 @@ similar_escape_internal(text *pat_text, text *esc_text) else if (charclass_depth > 0) { if (pchar == '\\') + { *r++ = '\\'; + /* we are no longer at the beginning of a character class */ + charclass_start = 3; + } *r++ = pchar; /* @@ -971,7 +981,11 @@ similar_escape_internal(text *pat_text, text *esc_text) if (pchar == ']' && charclass_start > 2) charclass_depth--; else if (pchar == '[') + { charclass_depth++; + /* we are no longer at the beginning of a character class */ + charclass_start = 3; + } /* * If there is a caret right after the opening bracket, it negates diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out index ba302da51e7..2d6cb02ad60 100644 --- a/src/test/regress/expected/strings.out +++ b/src/test/regress/expected/strings.out @@ -693,6 +693,15 @@ EXPLAIN (COSTS OFF) SELECT * FROM TEXT_TBL WHERE f1 SIMILAR TO '[^^]^'; Filter: (f1 ~ '^(?:[^^]\^)$'::text) (2 rows) +-- Closing square bracket after an escape sequence at the beginning of +-- a character closes the character class +EXPLAIN (COSTS OFF) SELECT * FROM TEXT_TBL WHERE f1 SIMILAR TO '[|a]%' ESCAPE '|'; + QUERY PLAN +--------------------------------------- + Seq Scan on text_tbl + Filter: (f1 ~ '^(?:[\a].*)$'::text) +(2 rows) + -- Test backslash escapes in regexp_replace's replacement string SELECT regexp_replace('1112223333', E'(\\d{3})(\\d{3})(\\d{4})', E'(\\1) \\2-\\3'); regexp_replace diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql index b94004cc08c..5ed421d6205 100644 --- a/src/test/regress/sql/strings.sql +++ b/src/test/regress/sql/strings.sql @@ -218,6 +218,9 @@ EXPLAIN (COSTS OFF) SELECT * FROM TEXT_TBL WHERE f1 SIMILAR TO '[]%][^]%][^%]%'; -- Closing square bracket effective after two carets at the beginning -- of character class. EXPLAIN (COSTS OFF) SELECT * FROM TEXT_TBL WHERE f1 SIMILAR TO '[^^]^'; +-- Closing square bracket after an escape sequence at the beginning of +-- a character closes the character class +EXPLAIN (COSTS OFF) SELECT * FROM TEXT_TBL WHERE f1 SIMILAR TO '[|a]%' ESCAPE '|'; -- Test backslash escapes in regexp_replace's replacement string SELECT regexp_replace('1112223333', E'(\\d{3})(\\d{3})(\\d{4})', E'(\\1) \\2-\\3'); -- 2.51.0