grep/backport-pcre-use-UCP-in-UTF-mode.patch
gaoruoshu ee5ef74a98 grep:pcre use UCP in UTF mode
(cherry picked from commit fba0aecf8a7b94b77225555e041113846d85aad2)
2023-04-25 09:27:16 +08:00

110 lines
3.8 KiB
Diff

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: [PATCH] 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.
Reference:https://git.savannah.gnu.org/cgit/grep.git/commit?id=5e3b760f65f13856e5717e5b9d935f5b4a615be3
Conflict:delete NEWS and change src/pcresearch.c
---
THANKS.in | 2 ++
src/pcresearch.c | 2 +-
tests/Makefile.am | 1 +
tests/pcre-utf8-w | 28 ++++++++++++++++++++++++++++
4 files changed, 32 insertions(+), 1 deletion(-)
create mode 100755 tests/pcre-utf8-w
diff --git a/THANKS.in b/THANKS.in
index 9872bfa..d0d6f92 100644
--- a/THANKS.in
+++ b/THANKS.in
@@ -35,6 +35,7 @@ Gerald Stoller gerald_stoller@hotmail.com
Grant McDorman grant@isgtec.com
Greg Boyd gboyd.ccsf@gmail.com
Greg Louis glouis@dynamicro.on.ca
+Gro-Tsen https://twitter.com/gro_tsen
Guglielmo 'bond' Bondioni g.bondioni@libero.it
H. Merijn Brand h.m.brand@hccnet.nl
Harald Hanche-Olsen hanche@math.ntnu.no
@@ -50,6 +51,7 @@ Joel N. Weber II devnull@gnu.org
John Hughes john@nitelite.calvacom.fr
Jorge Stolfi stolfi@dcc.unicamp.br
Karl Heuer kwzh@gnu.org
+Karl Petterson karl.pettersson@klpn.se
Kaveh R. Ghazi ghazi@caip.rutgers.edu
Kazuro Furukawa furukawa@apricot.kek.jp
Keith Bostic bostic@bsdi.com
diff --git a/src/pcresearch.c b/src/pcresearch.c
index a107f4d..45b67ee 100644
--- a/src/pcresearch.c
+++ b/src/pcresearch.c
@@ -141,7 +141,7 @@ Pcompile (char *pattern, size_t size, reg_syntax_t ignored, bool exact)
{
if (! localeinfo.using_utf8)
die (EXIT_TROUBLE, 0, _("-P supports only unibyte and UTF-8 locales"));
- flags |= PCRE_UTF8;
+ flags |= (PCRE_UTF8 | PCRE_UCP);
}
/* FIXME: Remove this restriction. */
diff --git a/tests/Makefile.am b/tests/Makefile.am
index e0b0503..a47cf5c 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 0000000..4cd7db6
--- /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
--
2.33.0