From 9397c74fce88eef17dd00a7c7b889d0495f45b51 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= <carenas@gmail.com>
Date: Thu, 20 Apr 2023 18:37:20 -0700
Subject: [PATCH] pcre: work around a PCRE2_MATCH_INVALID_UTF bug

PCRE2 has a bug when using PCRE2_MATCH_INVALID_UTF: it would
sometimes fail to match patterns using perl negative classes
like \W and \D.

* NEWS (Bug fixes): Mention it.
* src/pcre2search.c: restric impact of the bug
Do not use the problematic flag with broken versions of PCRE2.
Generate locale tables only for single-byte locales.
* tests/Makefile.am (TESTS): Add the file name
* tests/pcre-utf8-bug224: New file, to test for this.
---
 NEWS                   |  5 +++++
 src/pcresearch.c       | 22 ++++++++++++++--------
 tests/Makefile.am      |  1 +
 tests/pcre-utf8-bug224 | 31 +++++++++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 8 deletions(-)
 create mode 100755 tests/pcre-utf8-bug224

diff --git a/NEWS b/NEWS
index c15764c..97a913c 100644
--- a/NEWS
+++ b/NEWS
@@ -15,6 +15,11 @@ GNU grep NEWS                                    -*- outline -*-
   when running on 32-bit x86 and ARM hosts using glibc 2.34+.
   [bug introduced in grep 3.9]

+  grep no longer fails to match patterns using negated perl
+  classes like \D or \W when linked with PCRE2 10.34 or newer.
+  [bug introduced in grep 3.8]
+
+
 ** Changes in behavior

   grep --version now prints a line describing the version of PCRE2 it uses.
diff --git a/src/pcresearch.c b/src/pcresearch.c
index e867f49..68ec6de 100644
--- a/src/pcresearch.c
+++ b/src/pcresearch.c
@@ -58,6 +58,9 @@ struct pcre_comp
   /* Table, indexed by ! (flag & PCRE2_NOTBOL), of whether the empty
      string matches when that flag is used.  */
   int empty_match[2];
+
+  /* Flags */
+  unsigned binary_safe:1;
 };

 /* Memory allocation functions for PCRE.  */
@@ -130,16 +133,11 @@ jit_exec (struct pcre_comp *pc, char const *subject, idx_t search_bytes,
     }
 }

-/* Return true if E is an error code for bad UTF-8, and if pcre2_match
-   could return E because PCRE lacks PCRE2_MATCH_INVALID_UTF.  */
+/* Return true if E is an error code for bad UTF-8 */
 static bool
 bad_utf8_from_pcre2 (int e)
 {
-#ifdef PCRE2_MATCH_INVALID_UTF
-  return false;
-#else
   return PCRE2_ERROR_UTF8_ERR21 <= e && e <= PCRE2_ERROR_UTF8_ERR1;
-#endif
 }

 /* Compile the -P style PATTERN, containing SIZE bytes that are
@@ -157,6 +155,7 @@ Pcompile (char *pattern, idx_t size, reg_syntax_t ignored, bool exact)
     = pcre2_general_context_create (private_malloc, private_free, NULL);
   pcre2_compile_context *ccontext = pcre2_compile_context_create (gcontext);

+  pc->binary_safe = false;
   if (localeinfo.multibyte)
     {
       uint32_t unicode;
@@ -181,8 +180,13 @@ Pcompile (char *pattern, idx_t size, reg_syntax_t ignored, bool exact)
       flags |= PCRE2_NEVER_BACKSLASH_C;
 #endif
 #ifdef PCRE2_MATCH_INVALID_UTF
+      /* workaround PCRE2 bug
+         https://github.com/PCRE2Project/pcre2/issues/224 */
+#if 10 < PCRE2_MAJOR || (PCRE2_MAJOR == 10 && 42 < PCRE2_MINOR)
+      pc->binary_safe = true;
       /* Consider invalid UTF-8 as a barrier, instead of error.  */
       flags |= PCRE2_MATCH_INVALID_UTF;
+#endif
 #endif
     }

@@ -226,7 +230,9 @@ Pcompile (char *pattern, idx_t size, reg_syntax_t ignored, bool exact)
       size = re_size;
     }

-  pcre2_set_character_tables (ccontext, pcre2_maketables (gcontext));
+  if (!localeinfo.multibyte)
+    pcre2_set_character_tables (ccontext, pcre2_maketables (gcontext));
+
   pc->cre = pcre2_compile ((PCRE2_SPTR) pattern, size, flags,
                            &ec, &e, ccontext);
   if (!pc->cre)
@@ -313,7 +319,7 @@ Pexecute (void *vcp, char const *buf, idx_t size, idx_t *match_size,

           e = jit_exec (pc, subject, line_end - subject,
                         search_offset, options);
-          if (!bad_utf8_from_pcre2 (e))
+          if (pc->binary_safe || !bad_utf8_from_pcre2 (e))
             break;

           idx_t valid_bytes = pcre2_get_startchar (pc->data);
diff --git a/tests/Makefile.am b/tests/Makefile.am
index 7718f24..9b4422e 100644
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -155,6 +155,7 @@ TESTS =						\
   pcre-jitstack					\
   pcre-o					\
   pcre-utf8					\
+  pcre-utf8-bug224				\
   pcre-utf8-w					\
   pcre-w					\
   pcre-wx-backref				\
diff --git a/tests/pcre-utf8-bug224 b/tests/pcre-utf8-bug224
new file mode 100755
index 0000000..e7e0dcd
--- /dev/null
+++ b/tests/pcre-utf8-bug224
@@ -0,0 +1,31 @@
+#!/bin/sh
+# Ensure negated perl classes match multibyte characters in UTF mode
+#
+# 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_
+
+echo . | grep -qP '(*UTF).' 2>/dev/null \
+  || skip_ 'PCRE unicode support is compiled out'
+
+fail=0
+
+# 'ñ' (U+00F1)
+printf '\302\221\n' > in || framework_failure_
+grep -P '\D' in > out || fail=1
+compare in out || fail=1
+
+# “𝄞” (U+1D11E)
+printf '\360\235\204\236\n' > in || framework_failure_
+grep -P '\W' in > out || fail=1
+compare in out || fail=1
+
+Exit $fail
-- 
2.40.0.363.g9c6990cca2