From 95ca1f987edd23389e3079d0a7fe6d0f89927b68 Mon Sep 17 00:00:00 2001 From: Ævar Arnfjörð Bjarmason Date: Sun, 24 Jan 2021 18:28:13 +0100 Subject: grep/pcre2: better support invalid UTF-8 haystacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Signed-off-by: Junio C Hamano --- grep.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'grep.c') diff --git a/grep.c b/grep.c index efeb6dc58d..ad0af66a26 100644 --- a/grep.c +++ b/grep.c @@ -492,7 +492,23 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } 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, -- cgit v1.3