diff options
| author | Paolo Bonzini <bonzini@gnu.org> | 2010-03-23 16:07:56 +0100 |
|---|---|---|
| committer | Paolo Bonzini <bonzini@gnu.org> | 2010-03-23 16:12:00 +0100 |
| commit | 3220317a428d63a4303ffee0fb45becf835cf1fd (patch) | |
| tree | 70ffe675e50d2f6e5b7eb0f449f359c2191612d5 | |
| parent | 90cc2ba27bd3f368b945f89a60be4220b73baac7 (diff) | |
| download | grep-3220317a428d63a4303ffee0fb45becf835cf1fd.tar.gz | |
dfa: fix sigsegv on multibyte character classes
Reported by Jaroslav Škarvada <jskarvad@redhat.com>. This is
unfortunate. grep needs an automatic testcase generator.
* NEWS: Document bug.
* THANKS: Mention reporter.
* src/dfa.c (set_bit_casefold): Change type of first argument for
self-documentation.
(parse_bracket_exp): Fix call.
* tests/Makefile.am: Add new testcase.
* tests/char-class-multibyte: New testcase.
| -rw-r--r-- | NEWS | 4 | ||||
| -rw-r--r-- | THANKS | 1 | ||||
| -rw-r--r-- | src/dfa.c | 4 | ||||
| -rw-r--r-- | tests/Makefile.am | 1 | ||||
| -rw-r--r-- | tests/char-class-multibyte | 23 |
5 files changed, 31 insertions, 2 deletions
@@ -2,6 +2,10 @@ GNU grep NEWS -*- outline -*- * Noteworthy changes in release ?.? (????-??-??) [?] +** Bug fixes + + Character classes could cause a segmentation fault if they included a + multibyte character. This is a regression from 2.5.4. * Noteworthy changes in release 2.6 (2010-03-23) [stable] @@ -33,6 +33,7 @@ Harald Hanche-Olsen <hanche@math.ntnu.no> Hans-Bernhard Broeker <broeker@physik.rwth-aachen.de> Heikki Korpela <heko@iki.fi> Isamu Hasegawa <isamu@yamato.ibm.com> +Jaroslav Škarvada <jskarvad@redhat.com> Jeff Bailey <jbailey@nisa.net> Jim Hand <jhand@austx.tandem.com> Jim Meyering <meyering@redhat.com> @@ -243,7 +243,7 @@ dfasyntax (reg_syntax_t bits, int fold, unsigned char eol) For MB_CUR_MAX > 1, one or both of the two cases may not be set, so the resulting charset may only be used as an optimization. */ static void -setbit_case_fold (unsigned int b, charclass c) +setbit_case_fold (wint_t b, charclass c) { if (case_fold) { @@ -691,7 +691,7 @@ parse_bracket_exp (void) continue; } - setbit_case_fold (c, ccl); + setbit_case_fold (wc, ccl); #ifdef MBS_SUPPORT /* Build normal characters. */ if (MB_CUR_MAX > 1) diff --git a/tests/Makefile.am b/tests/Makefile.am index 67763b2f..02db64c4 100644 --- a/tests/Makefile.am +++ b/tests/Makefile.am @@ -22,6 +22,7 @@ TESTS = \ case-fold-char-class \ case-fold-char-range \ case-fold-char-type \ + char-class-multibyte \ dfaexec-multibyte \ empty.sh \ ere.sh \ diff --git a/tests/char-class-multibyte b/tests/char-class-multibyte new file mode 100644 index 00000000..d77c6de0 --- /dev/null +++ b/tests/char-class-multibyte @@ -0,0 +1,23 @@ +#!/bin/sh +# This would segfault for grep-2.6 +: ${srcdir=.} +. "$srcdir/init.sh"; path_prepend_ ../src + +printf 'É\n' > exp1 || framework_failure +fail=0 + +for LOC in en_US.UTF-8 $LOCALE_FR_UTF8; do + out=out1-$LOC + printf 'á\nç\nÉ\n' | LC_ALL=$LOC grep '[é]' > $out || fail=1 + compare $out exp1 || fail=1 +done + +printf 'é\n' > exp2 || framework_failure + +for LOC in en_US.UTF-8 $LOCALE_FR_UTF8; do + out=out2-$LOC + printf 'á\nç\né\n' | LC_ALL=$LOC grep '[É]' > $out || fail=1 + compare $out exp2 || fail=1 +done + +Exit $fail |