>From 0e8fda0d880cccd0e1997a905eb9a7910f957245 Mon Sep 17 00:00:00 2001
From: Paul Eggert <address@hidden>
Date: Fri, 3 Jul 2015 18:23:59 -0700
Subject: [PATCH 1/6] grep: -z '.' now consistently matches newline

Problem reported by Balazs Kezes in: http://bugs.gnu.org/20974
* NEWS: Document this.
* tests/utf8-bracket: New file, to test for this bug.
* src/grep.c (Gcompile, Ecompile): Also specify RE_DOT_NEWLINE.
* tests/Makefile.am (TESTS): Add it.
---
 NEWS               |  4 ++++
 src/grep.c         |  7 ++++---
 tests/Makefile.am  |  1 +
 tests/utf8-bracket | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 3 deletions(-)
 create mode 100755 tests/utf8-bracket

diff --git a/NEWS b/NEWS
index bbbe893..88ed0f4 100644
--- a/NEWS
+++ b/NEWS
@@ -12,6 +12,10 @@ GNU grep NEWS                                    -*- outline -*-
   grep no longer reads from uninitialized memory or from beyond the end
   of the heap-allocated input buffer.  This fix addressed CVE-2015-1345.
 
+  With -z, '.' in a pattern now consistently matches newline.
+  Previously, it sometimes matched newline, and sometimes did not.
+  [bug introduced in grep-2.4]
+
   When the JIT stack is exhausted, grep -P now grows the stack rather
   than reporting an internal PCRE error.
 
diff --git a/src/grep.c b/src/grep.c
index 778dbcb..ed54dc2 100644
--- a/src/grep.c
+++ b/src/grep.c
@@ -1861,15 +1861,16 @@ if any error occurs and -q is not given, the exit status is 2.\n"));
 static void
 Gcompile (char const *pattern, size_t size)
 {
-  GEAcompile (pattern, size, RE_SYNTAX_GREP | RE_NO_EMPTY_RANGES);
+  GEAcompile (pattern, size,
+              RE_SYNTAX_GREP | RE_DOT_NEWLINE | RE_NO_EMPTY_RANGES);
 }
 
 static void
 Ecompile (char const *pattern, size_t size)
 {
   GEAcompile (pattern, size,
-              (RE_SYNTAX_POSIX_EGREP | RE_NO_EMPTY_RANGES
-               | RE_UNMATCHED_RIGHT_PAREN_ORD));
+              (RE_SYNTAX_POSIX_EGREP | RE_DOT_NEWLINE
+               | RE_NO_EMPTY_RANGES | RE_UNMATCHED_RIGHT_PAREN_ORD));
 }
 
 static void
diff --git a/tests/Makefile.am b/tests/Makefile.am
index 7bceac7..629d322 100644
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -120,6 +120,7 @@ TESTS =						\
   two-files					\
   unibyte-bracket-expr				\
   unibyte-negated-circumflex			\
+  utf8-bracket					\
   warn-char-classes				\
   word-delim-multibyte				\
   word-multi-file				\
diff --git a/tests/utf8-bracket b/tests/utf8-bracket
new file mode 100755
index 0000000..f5c4a60
--- /dev/null
+++ b/tests/utf8-bracket
@@ -0,0 +1,34 @@
+#!/bin/sh
+# Check bracket expressions in a UTF-8 locale.
+
+# Copyright 2015 Free Software Foundation, Inc.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+. "${srcdir=.}/init.sh"; path_prepend_ ../src
+require_en_utf8_locale_
+
+printf '1\n2\n' >in || framework_failure_
+
+fail=0
+
+for locale in C en_US.UTF-8; do
+  for pattern in '1.2' '[12].2' '[1-2].2'; do
+    for suffix in '' '\(\)\1'; do
+      LC_ALL=$locale grep --null-data --quiet "$pattern$suffix" in || fail=1
+    done
+  done
+done
+
+Exit $fail
-- 
2.1.0