From abc6e54e759f7bd224e687c796aa8c89a6d091fa Mon Sep 17 00:00:00 2001
From: Jim Meyering <address@hidden>
Date: Fri, 18 Dec 2015 15:21:32 -0800
Subject: [PATCH] grep -oP: don't infloop when processing invalid UTF8
 preceding a match

* src/pcresearch.c (Pexecute): When advancing SUBJECT past an
encoding error, don't blindly set P to that new value, since we
will soon compute SEARCH_OFFSET = P - SUBJECT, and mistakenly
making that difference too small would allow us to match some
previously-processed text, resulting in an infinite loop.
* NEWS (Bug fixes): Mention it.
* THANKS.in: Add Christian's name and email address.
* tests/pcre-invalid-utf8-infloop: New file.
* tests/Makefile.am (TESTS): Add it.
Reported by Christian Boltz in http://debbugs.gnu.org/22181
Introduced by commit, v2.21-37-g14f8e48.
---
 NEWS                            |  6 ++++++
 THANKS.in                       |  1 +
 src/pcresearch.c                |  4 +++-
 tests/Makefile.am               |  1 +
 tests/pcre-invalid-utf8-infloop | 26 ++++++++++++++++++++++++++
 5 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100755 tests/pcre-invalid-utf8-infloop

diff --git a/NEWS b/NEWS
index ac632d7..fc5fd3a 100644
--- a/NEWS
+++ b/NEWS
@@ -2,6 +2,12 @@ GNU grep NEWS                                    -*- outline -*-

 * Noteworthy changes in release ?.? (????-??-??) [?]

+** Bug fixes
+
+  grep -oP is no longer susceptible to an infinite loop when processing
+  invalid UTF8 just before a match.
+  [bug introduced in grep-2.22]
+

 * Noteworthy changes in release 2.22 (2015-11-01) [stable]

diff --git a/THANKS.in b/THANKS.in
index b86f772..abd64fd 100644
--- a/THANKS.in
+++ b/THANKS.in
@@ -18,6 +18,7 @@ Ben Elliston                        address@hidden
 Bernd Strieder                      address@hidden
 Bob Proulx                          address@hidden
 Brian Youmans                       address@hidden
+Christian Boltz                     address@hidden
 Christian Groessler                 address@hidden
 Dagobert Michelsen                  address@hidden
 Daisuke GOTO                        address@hidden
diff --git a/src/pcresearch.c b/src/pcresearch.c
index b1f8310..dc68345 100644
--- a/src/pcresearch.c
+++ b/src/pcresearch.c
@@ -289,7 +289,9 @@ Pexecute (char const *buf, size_t size, size_t *match_size,
             break;

           /* Treat the encoding error as data that cannot match.  */
-          p = subject += valid_bytes + 1;
+          subject += valid_bytes + 1;
+          if (p < subject)
+            p = subject;
           bol = false;
         }

diff --git a/tests/Makefile.am b/tests/Makefile.am
index d379821..6ced67c 100644
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -107,6 +107,7 @@ TESTS =						\
   pcre-context					\
   pcre-infloop					\
   pcre-invalid-utf8-input			\
+  pcre-invalid-utf8-infloop			\
   pcre-jitstack					\
   pcre-o					\
   pcre-utf8					\
diff --git a/tests/pcre-invalid-utf8-infloop b/tests/pcre-invalid-utf8-infloop
new file mode 100755
index 0000000..2b696b4
--- /dev/null
+++ b/tests/pcre-invalid-utf8-infloop
@@ -0,0 +1,26 @@
+#! /bin/sh
+# Ensure that grep -oaP doesn't infloop for invalid multi-byte input
+#
+# Copyright (C) 2015 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_timeout_
+require_en_utf8_locale_
+require_compiled_in_MB_support
+LC_ALL=en_US.UTF-8 require_pcre_
+
+fail=0
+
+printf '\201_\0' > in || framework_failure_
+printf '_\n' > exp || framework_failure_
+
+LC_ALL=en_US.UTF-8 timeout 3 grep -aoP _ in > out 2> err || fail=1
+
+compare exp out || fail=1
+compare /dev/null err || fail=1
+
+Exit $fail
-- 
2.6.2