Improve the support for invalid UTF-8 haystacks given a non-ASCII
needle when using the PCREv2 backend.
This is a more complete fix for a bug I started to fix in
870eea8166 (grep: do not enter PCRE2_UTF mode on fixed matching,
2019-07-26), now that PCREv2 has the PCRE2_MATCH_INVALID_UTF mode we
can make use of it.
This fixes the sort of case described in
8a5999838e (grep: stess test
PCRE v2 on invalid UTF-8 data, 2019-07-26), i.e.:
- The subject string is non-ASCII (e.g. "ævar")
- We're under a is_utf8_locale(), e.g. "en_US.UTF-8", not "C"
- We are using --ignore-case, or we're a non-fixed pattern
If those conditions were satisfied and we matched found non-valid
UTF-8 data PCREv2 might bark on it, in practice this only happened
under the JIT backend (turned on by default on most platforms).
Ultimately this fixes a "regression" in
b65abcafc7 ("grep: use PCRE v2
for optimized fixed-string search", 2019-07-01), I'm putting that in
scare-quotes because before then we wouldn't properly support these
complex case-folding, locale etc. cases either, it just broke in
different ways.
There was a bug related to this the PCRE2_NO_START_OPTIMIZE flag fixed
in PCREv2 10.36. It can be worked around by setting the
PCRE2_NO_START_OPTIMIZE flag. Let's do that in those cases, and add
tests for the bug.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
TEST_BUILTINS_OBJS += test-parse-options.o
TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
TEST_BUILTINS_OBJS += test-path-utils.o
+TEST_BUILTINS_OBJS += test-pcre2-config.o
TEST_BUILTINS_OBJS += test-pkt-line.o
TEST_BUILTINS_OBJS += test-prio-queue.o
TEST_BUILTINS_OBJS += test-proc-receive.o
}
if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) &&
!(!opt->ignore_case && (p->fixed || p->is_fixed)))
- options |= PCRE2_UTF;
+ options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
+
+ /* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */
+ if (PCRE2_MATCH_INVALID_UTF && options & (PCRE2_UTF | PCRE2_CASELESS)) {
+ struct strbuf buf;
+ int len;
+ int err;
+
+ if ((len = pcre2_config(PCRE2_CONFIG_VERSION, NULL)) < 0)
+ BUG("pcre2_config(..., NULL) failed: %d", len);
+ strbuf_init(&buf, len + 1);
+ if ((err = pcre2_config(PCRE2_CONFIG_VERSION, buf.buf)) < 0)
+ BUG("pcre2_config(..., buf.buf) failed: %d", err);
+ if (versioncmp(buf.buf, "10.36") < 0)
+ options |= PCRE2_NO_START_OPTIMIZE;
+ strbuf_release(&buf);
+ }
p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
p->patternlen, options, &error, &erroffset,
typedef int pcre2_match_data;
typedef int pcre2_compile_context;
#endif
+#ifndef PCRE2_MATCH_INVALID_UTF
+/* PCRE2_MATCH_* dummy also with !USE_LIBPCRE2, for test-pcre2-config.c */
+#define PCRE2_MATCH_INVALID_UTF 0
+#endif
#include "thread-utils.h"
#include "userdiff.h"
--- /dev/null
+#include "test-tool.h"
+#include "cache.h"
+#include "grep.h"
+
+int cmd__pcre2_config(int argc, const char **argv)
+{
+ if (argc == 2 && !strcmp(argv[1], "has-PCRE2_MATCH_INVALID_UTF")) {
+ int value = PCRE2_MATCH_INVALID_UTF;
+ return !value;
+ }
+ return 1;
+}
{ "parse-options", cmd__parse_options },
{ "parse-pathspec-file", cmd__parse_pathspec_file },
{ "path-utils", cmd__path_utils },
+ { "pcre2-config", cmd__pcre2_config },
{ "pkt-line", cmd__pkt_line },
{ "prio-queue", cmd__prio_queue },
{ "proc-receive", cmd__proc_receive},
int cmd__parse_options(int argc, const char **argv);
int cmd__parse_pathspec_file(int argc, const char** argv);
int cmd__path_utils(int argc, const char **argv);
+int cmd__pcre2_config(int argc, const char **argv);
int cmd__pkt_line(int argc, const char **argv);
int cmd__prio_queue(int argc, const char **argv);
int cmd__proc_receive(int argc, const char **argv);
printf "\\200\\n" >invalid-0x80 &&
echo "ævar" >expected &&
cat expected >>invalid-0x80 &&
- git add invalid-0x80
+ git add invalid-0x80 &&
+
+ # Test for PCRE2_MATCH_INVALID_UTF bug
+ # https://bugs.exim.org/show_bug.cgi?id=2642
+ printf "\\345Aæ\\n" >invalid-0xe5 &&
+ git add invalid-0xe5
'
test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep ASCII from invalid UTF-8 data' '
test_cmp expected actual
'
+test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep ASCII from invalid UTF-8 data (PCRE2 bug #2642)' '
+ git grep -h "Aæ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual &&
+ git grep -h "(*NO_JIT)Aæ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual
+'
+
test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep non-ASCII from invalid UTF-8 data' '
git grep -h "æ" invalid-0x80 >actual &&
test_cmp expected actual &&
test_cmp expected actual
'
+test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep non-ASCII from invalid UTF-8 data (PCRE2 bug #2642)' '
+ git grep -h "Aæ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual &&
+ git grep -h "(*NO_JIT)Aæ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual
+'
+
+test_lazy_prereq PCRE2_MATCH_INVALID_UTF '
+ test-tool pcre2-config has-PCRE2_MATCH_INVALID_UTF
+'
+
test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep non-ASCII from invalid UTF-8 data with -i' '
test_might_fail git grep -hi "Æ" invalid-0x80 >actual &&
test_might_fail git grep -hi "(*NO_JIT)Æ" invalid-0x80 >actual
'
+test_expect_success GETTEXT_LOCALE,LIBPCRE2,PCRE2_MATCH_INVALID_UTF 'PCRE v2: grep non-ASCII from invalid UTF-8 data with -i' '
+ git grep -hi "Æ" invalid-0x80 >actual &&
+ test_cmp expected actual &&
+ git grep -hi "(*NO_JIT)Æ" invalid-0x80 >actual &&
+ test_cmp expected actual
+'
+
+test_expect_success GETTEXT_LOCALE,LIBPCRE2,PCRE2_MATCH_INVALID_UTF 'PCRE v2: grep non-ASCII from invalid UTF-8 data with -i (PCRE2 bug #2642)' '
+ git grep -hi "Æ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual &&
+ git grep -hi "(*NO_JIT)Æ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual &&
+
+ # Only the case of grepping the ASCII part in a way that
+ # relies on -i fails
+ git grep -hi "aÆ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual &&
+ git grep -hi "(*NO_JIT)aÆ" invalid-0xe5 >actual &&
+ test_cmp invalid-0xe5 actual
+'
+
test_done