Code coverage for most pg_mblen* calls.

A security patch changed them today, so close the coverage gap now.
Test that buffer overrun is avoided when pg_mblen*() requires more
than the number of bytes remaining.

This does not cover the calls in dict_thesaurus.c or in dict_synonym.c.
That code is straightforward.  To change that code's input, one must
have access to modify installed OS files, so low-privilege users are not
a threat.  Testing this would likewise require changing installed
share/postgresql/tsearch_data, which was enough of an obstacle to not
bother.

Security: CVE-2026-2006
Backpatch-through: 14
Co-authored-by: Thomas Munro <thomas.munro@gmail.com>
Co-authored-by: Noah Misch <noah@leadboat.com>
Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi>

6 files changed, 72 insertions, 1 deletions

diff --git a/contrib/pg_trgm/Makefile b/contrib/pg_trgm/Makefile
index 1fbdc9ec1ef..c1756993ec7 100644
--- a/contrib/pg_trgm/Makefile
+++ b/contrib/pg_trgm/Makefile
@@ -14,7 +14,7 @@ DATA = pg_trgm--1.5--1.6.sql pg_trgm--1.4--1.5.sql pg_trgm--1.3--1.4.sql \
 	pg_trgm--1.0--1.1.sql
 PGFILEDESC = "pg_trgm - trigram matching"
 
-REGRESS = pg_trgm pg_word_trgm pg_strict_word_trgm
+REGRESS = pg_trgm pg_utf8_trgm pg_word_trgm pg_strict_word_trgm
 
 ifdef USE_PGXS
 PG_CONFIG = pg_config
diff --git a/contrib/pg_trgm/data/trgm_utf8.data b/contrib/pg_trgm/data/trgm_utf8.data
new file mode 100644
index 00000000000..713856e76a6
--- /dev/null
+++ b/contrib/pg_trgm/data/trgm_utf8.data
@@ -0,0 +1,50 @@
+Mathematics
+数学
+गणित
+Matemáticas
+رياضيات
+Mathématiques
+গণিত
+Matemática
+Математика
+ریاضی
+Matematika
+Mathematik
+数学
+Mathematics
+गणित
+గణితం
+Matematik
+கணிதம்
+數學
+Toán học
+Matematika
+数学
+수학
+ریاضی
+Lissafi
+Hisabati
+Matematika
+Matematica
+ریاضی
+ಗಣಿತ
+ગણિત
+คณิตศาสตร์
+ሂሳብ
+गणित
+ਗਣਿਤ
+數學
+数学
+Iṣiro
+數學
+သင်္ချာ
+Herrega
+رياضي
+गणित
+Математика
+Matematyka
+ഗണിതം
+Matematika
+رياضي
+Matematika
+Matematică
diff --git a/contrib/pg_trgm/expected/pg_utf8_trgm.out b/contrib/pg_trgm/expected/pg_utf8_trgm.out
new file mode 100644
index 00000000000..0768e7d6a83
--- /dev/null
+++ b/contrib/pg_trgm/expected/pg_utf8_trgm.out
@@ -0,0 +1,8 @@
+SELECT getdatabaseencoding() <> 'UTF8' AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+-- Index 50 translations of the word "Mathematics"
+CREATE TEMP TABLE mb (s text);
+\copy mb from 'data/trgm_utf8.data'
+CREATE INDEX ON mb USING gist(s gist_trgm_ops);
diff --git a/contrib/pg_trgm/expected/pg_utf8_trgm_1.out b/contrib/pg_trgm/expected/pg_utf8_trgm_1.out
new file mode 100644
index 00000000000..8505c4fa552
--- /dev/null
+++ b/contrib/pg_trgm/expected/pg_utf8_trgm_1.out
@@ -0,0 +1,3 @@
+SELECT getdatabaseencoding() <> 'UTF8' AS skip_test \gset
+\if :skip_test
+\quit
diff --git a/contrib/pg_trgm/meson.build b/contrib/pg_trgm/meson.build
index 093ac18400c..bd3a34f2557 100644
--- a/contrib/pg_trgm/meson.build
+++ b/contrib/pg_trgm/meson.build
@@ -39,6 +39,7 @@ tests += {
   'regress': {
     'sql': [
       'pg_trgm',
+      'pg_utf8_trgm',
       'pg_word_trgm',
       'pg_strict_word_trgm',
     ],
diff --git a/contrib/pg_trgm/sql/pg_utf8_trgm.sql b/contrib/pg_trgm/sql/pg_utf8_trgm.sql
new file mode 100644
index 00000000000..0dd962ced83
--- /dev/null
+++ b/contrib/pg_trgm/sql/pg_utf8_trgm.sql
@@ -0,0 +1,9 @@
+SELECT getdatabaseencoding() <> 'UTF8' AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+
+-- Index 50 translations of the word "Mathematics"
+CREATE TEMP TABLE mb (s text);
+\copy mb from 'data/trgm_utf8.data'
+CREATE INDEX ON mb USING gist(s gist_trgm_ops);