[PATCH v5 0/2] grep: better support invalid UTF-8 haystacks
From: Ævar Arnfjörð Bjarmason <hidden>
Date: 2021-01-24 17:29:38
Fixes a version comparison typo/thinko, pointed out by Ramsay Jones.
Ævar Arnfjörð Bjarmason (2):
grep/pcre2 tests: don't rely on invalid UTF-8 data test
grep/pcre2: better support invalid UTF-8 haystacks
Makefile | 1 +
grep.c | 18 ++++++++++-
grep.h | 4 +++
t/helper/test-pcre2-config.c | 12 ++++++++
t/helper/test-tool.c | 1 +
t/helper/test-tool.h | 1 +
t/t7812-grep-icase-non-ascii.sh | 53 ++++++++++++++++++++++++++++-----
7 files changed, 82 insertions(+), 8 deletions(-)
create mode 100644 t/helper/test-pcre2-config.c
Range-diff:
1: 699bb6b324 = 1: 699bb6b324 grep/pcre2 tests: don't rely on invalid UTF-8 data test
2: e4807d6879 ! 2: 04c87c04d7 grep/pcre2: better support invalid UTF-8 haystacks
@@ grep.c: static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_
- options |= PCRE2_UTF;
+ options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
+
-+ if (PCRE2_MATCH_INVALID_UTF &&
-+ options & (PCRE2_UTF | PCRE2_CASELESS) &&
-+ !(PCRE2_MAJOR >= 10 && PCRE2_MAJOR >= 36))
-+ /* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */
-+ options |= PCRE2_NO_START_OPTIMIZE;
++ /* 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,
--
2.29.2.222.g5d2a92d10f8