From 5e3b760f65f13856e5717e5b9d935f5b4a615be3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= <carenas@gmail.com>
Date: Fri, 6 Jan 2023 19:34:56 -0800
Subject: pcre: use UCP in UTF mode

This fixes a serious bug affecting word-boundary and word-constituent regular
expressions when the desired match involves non-ASCII UTF8 characters.
* src/pcresearch.c: Set PCRE2_UCP together with PCRE2_UTF
* tests/pcre-utf8-w: New file.
* tests/Makefile.am (TESTS): Add it.
* NEWS (Bug fixes): Mention this.
* THANKS.in: Add Gro-Tsen and Karl Petterson.
Reported by Gro-Tsen https://twitter.com/gro_tsen/status/1610972356972875777
via Karl Pettersson in https://github.com/PCRE2Project/pcre2/issues/185
This bug was present from grep-2.5, when --perl-regexp (-P) support was added.
---
 tests/Makefile.am |  1 +
 tests/pcre-utf8-w | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100755 tests/pcre-utf8-w

(limited to 'tests')

diff --git a/tests/Makefile.am b/tests/Makefile.am
index e0b0503c..a47cf5c0 100644
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -147,6 +147,7 @@ TESTS =						\
   pcre-jitstack					\
   pcre-o					\
   pcre-utf8					\
+  pcre-utf8-w					\
   pcre-w					\
   pcre-wx-backref				\
   pcre-z					\
diff --git a/tests/pcre-utf8-w b/tests/pcre-utf8-w
new file mode 100755
index 00000000..4cd7db69
--- /dev/null
+++ b/tests/pcre-utf8-w
@@ -0,0 +1,28 @@
+#!/bin/sh
+# Ensure non-ASCII UTF-8 characters are correctly identified as word-consituent
+#
+# Copyright (C) 2023 Free Software Foundation, Inc.
+#
+# Copying and distribution of this file, with or without modification,
+# are permitted in any medium without royalty provided the copyright
+# notice and this notice are preserved.
+
+. "${srcdir=.}/init.sh"; path_prepend_ ../src
+require_en_utf8_locale_
+LC_ALL=en_US.UTF-8
+export LC_ALL
+require_pcre_
+
+fail=0
+
+echo 'Perú'> in || framework_failure_
+
+echo 'ú' > exp || framework_failure_
+grep -Po '.\b' in > out || fail=1
+compare exp out || fail=1
+
+echo 'rú' > exp || framework_failure_
+grep -Po 'r\w' in > out || fail=1
+compare exp out || fail=1
+
+Exit $fail
-- 
cgit v1.2.1