grep branch, master, updated. v2.15-19-g9311cf9

[Jim Meyering]

This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "grep".

The branch, master has been updated
       via  9311cf9c4f1e6a97c2e01e4a86f8f937c8010a01 (commit)
      from  fb4d5a856f322187f8dc00f3d50381f39531f43e (commit)

Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.

- Log -----------------------------------------------------------------
http://git.savannah.gnu.org/cgit/grep.git/commit/?id=9311cf9c4f1e6a97c2e01e4a86f8f937c8010a01


commit 9311cf9c4f1e6a97c2e01e4a86f8f937c8010a01
Author: Jim Meyering <address@hidden>
Date:   Tue Dec 31 08:15:07 2013 -0800

    pcre: use PCRE_NO_UTF8_CHECK properly
    
    In order to obtain the behavior we want, i.e., to disable
    error-on-invalid-UTF-in-input, apply this PCRE option in
    pcre_exec, not when compiling.
    * src/pcresearch.c (Pexecute): Use PCRE_NO_UTF8_CHECK here, ...
    (Pcompile): ...rather than here.
    * tests/pcre-invalid-utf8-input: Adjust test case to test for this.

diff --git a/src/pcresearch.c b/src/pcresearch.c
index 664070d..4abd9c2 100644
--- a/src/pcresearch.c
+++ b/src/pcresearch.c
@@ -63,9 +63,9 @@ Pcompile (char const *pattern, size_t size)
 # if defined HAVE_LANGINFO_CODESET
   if (STREQ (nl_langinfo (CODESET), "UTF-8"))
     {
-      /* Enable PCRE's UTF-8 matching, but disable the check that would
-         make an invalid byte seqence *in the input* trigger a failure.   */
-      flags |= PCRE_UTF8 | PCRE_NO_UTF8_CHECK;
+      /* Enable PCRE's UTF-8 matching.  Note also the use of
+         PCRE_NO_UTF8_CHECK when calling pcre_extra, below.   */
+      flags |= PCRE_UTF8;
     }
 # endif
 
@@ -158,6 +158,10 @@ Pexecute (char const *buf, size_t size, size_t *match_size,
        e == PCRE_ERROR_NOMATCH && line_next < buf + size;
        start_ofs -= line_next - line_buf)
     {
+      /* Disable the check that would make an invalid byte
+         seqence *in the input* trigger a failure.   */
+      int options = PCRE_NO_UTF8_CHECK;
+
       line_buf = line_next;
       line_end = memchr (line_buf, eolbyte, (buf + size) - line_buf);
       if (line_end == NULL)
@@ -172,7 +176,7 @@ Pexecute (char const *buf, size_t size, size_t *match_size,
         error (EXIT_TROUBLE, 0, _("exceeded PCRE's line length limit"));
 
       e = pcre_exec (cre, extra, line_buf, line_end - line_buf,
-                     start_ofs < 0 ? 0 : start_ofs, 0,
+                     start_ofs < 0 ? 0 : start_ofs, options,
                      sub, sizeof sub / sizeof *sub);
     }
 
diff --git a/tests/pcre-invalid-utf8-input b/tests/pcre-invalid-utf8-input
index 52a5432..c70951f 100755
--- a/tests/pcre-invalid-utf8-input
+++ b/tests/pcre-invalid-utf8-input
@@ -13,13 +13,10 @@ require_en_utf8_locale_
 
 fail=0
 
-printf '\202\n' > in || framework_failure_
-printf 'grep: invalid UTF-8 byte sequence in input\n' \
-   > exp-err || framework_failure_
+printf 'j\202\nj\n' > in || framework_failure_
 
-LC_ALL=en_US.UTF-8 grep -P anything in > out 2> err
-test $? = 2 || fail=1
-compare /dev/null out || fail=1
-compare exp-err err || fail=1
+LC_ALL=en_US.UTF-8 grep -P j in > out 2>&1 || fail=1
+compare in out || fail=1
+compare /dev/null err || fail=1
 
 Exit $fail

-----------------------------------------------------------------------

Summary of changes:
 src/pcresearch.c              |   12 ++++++++----
 tests/pcre-invalid-utf8-input |   11 ++++-------
 2 files changed, 12 insertions(+), 11 deletions(-)


hooks/post-receive
-- 
grep