Fix LIKE matching with nondeterministic collations and backslashes.

Commit 85b7efa1c added support for LIKE with nondeterministic
collations, but it included a bug in the de-escaping logic for
literal pattern substrings.  That unconditionally skipped all
backslashes, but when it encounters '\\' it should emit the second
backslash as a de-escaped character.  That led to acting as though
the escaped backslash was not there.

Bug: #19474
Reported-by: Bowen Shi <zxwsbg12138@gmail.com>
Author: Nitin Motiani <nitinmotiani@google.com>
Reviewed-by: Zsolt Parragi <zsolt.parragi@percona.com>
Reviewed-by: Ewan Young <kdbase.hack@gmail.com>
Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://postgr.es/m/19474-5b86a95f3d9a7ecb@postgresql.org
Discussion: https://postgr.es/m/CAH5HC94yU+K8Gcdy12M5BS8gwD_SXLSHzc9k5tNk7JDnpBiFMA@mail.gmail.com
Backpatch-through: 18

diff --git a/src/backend/utils/adt/like_match.c b/src/backend/utils/adt/like_match.c
index f5f72b82e215201d1e2bdd2aaee083365ede5c26..ddaf6b1806a651f05fd20d4d28c32e8ba276db7a 100644 (file)
--- a/src/backend/utils/adt/like_match.c
+++ b/src/backend/utils/adt/like_match.c
@@ -257,9 +257,8 @@ MatchText(const char *t, int tlen, const char *p, int plen, pg_locale_t locale)
                                for (const char *c = p; c < p1; c++)
                                {
                                        if (*c == '\\')
-                                               ;
-                                       else
-                                               *(b++) = *c;
+                                               c++;    /* we already checked this isn't the end */
+                                       *(b++) = *c;
                                }
 
                                subpat = buf;

diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
index fb95eee9b7c715325fc324108d691fe175732046..3209964cc440a4706016c417f7c24a5126386c43 100644 (file)
--- a/src/test/regress/expected/collate.icu.utf8.out
+++ b/src/test/regress/expected/collate.icu.utf8.out
@@ -3006,6 +3006,37 @@ SELECT U&'\0061\0308bc' LIKE U&'_\00e4bc' COLLATE ignore_accents;
 -- escape character at end of pattern
 SELECT 'foox' LIKE 'foo\' COLLATE ignore_accents;
 ERROR:  LIKE pattern must not end with escape character
+-- literal backslash with nondeterministic collation (bug #19474)
+SELECT 'back\slash' COLLATE ignore_accents LIKE 'back\slash%' ESCAPE '#';
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT 'aäb' COLLATE ignore_accents LIKE 'a#äb' ESCAPE '#' AS multibyte_escape;
+ multibyte_escape 
+------------------
+ t
+(1 row)
+
+SELECT 'a\äb' COLLATE ignore_accents LIKE 'a\äb%' ESCAPE '#' AS backslash_multibyte;
+ backslash_multibyte 
+---------------------
+ t
+(1 row)
+
+SELECT 'a\b%c' COLLATE ignore_accents LIKE 'a#\b#%%c' ESCAPE '#' AS mixed_escapes;
+ mixed_escapes 
+---------------
+ t
+(1 row)
+
+SELECT 'backslash' COLLATE ignore_accents LIKE 'back\\slash%';
+ ?column? 
+----------
+ f
+(1 row)
+
 -- foreign keys (mixing different nondeterministic collations not allowed)
 CREATE TABLE test10pk (x text COLLATE case_sensitive PRIMARY KEY);
 CREATE TABLE test10fk (x text COLLATE case_insensitive REFERENCES test10pk (x) ON UPDATE CASCADE ON DELETE CASCADE);  -- error

diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
index 954d8ea6cb4c4da82988e6d3bfad404fb0f2db5b..3cee7223f95bf6eec69a01fc198e55c3a9e1bd0f 100644 (file)
--- a/src/test/regress/sql/collate.icu.utf8.sql
+++ b/src/test/regress/sql/collate.icu.utf8.sql
@@ -1083,6 +1083,13 @@ SELECT U&'\0061\0308bc' LIKE U&'_\00e4bc' COLLATE ignore_accents;
 -- escape character at end of pattern
 SELECT 'foox' LIKE 'foo\' COLLATE ignore_accents;
 
+-- literal backslash with nondeterministic collation (bug #19474)
+SELECT 'back\slash' COLLATE ignore_accents LIKE 'back\slash%' ESCAPE '#';
+SELECT 'aäb' COLLATE ignore_accents LIKE 'a#äb' ESCAPE '#' AS multibyte_escape;
+SELECT 'a\äb' COLLATE ignore_accents LIKE 'a\äb%' ESCAPE '#' AS backslash_multibyte;
+SELECT 'a\b%c' COLLATE ignore_accents LIKE 'a#\b#%%c' ESCAPE '#' AS mixed_escapes;
+SELECT 'backslash' COLLATE ignore_accents LIKE 'back\\slash%';
+
 -- foreign keys (mixing different nondeterministic collations not allowed)
 CREATE TABLE test10pk (x text COLLATE case_sensitive PRIMARY KEY);
 CREATE TABLE test10fk (x text COLLATE case_insensitive REFERENCES test10pk (x) ON UPDATE CASCADE ON DELETE CASCADE);  -- error