From 870eea81669bfff4333b37b11fedd870cd05fd90 Mon Sep 17 00:00:00 2001 From: Ævar Arnfjörð Bjarmason Date: Fri, 26 Jul 2019 17:08:17 +0200 Subject: grep: do not enter PCRE2_UTF mode on fixed matching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As discussed in the last commit partially fix a bug introduced in b65abcafc7 ("grep: use PCRE v2 for optimized fixed-string search", 2019-07-01). Because PCRE v2, unlike kwset, validates its UTF-8 input we'd die on e.g.: fatal: pcre2_match failed with error code -22: UTF-8 error: isolated byte with 0x80 bit set When grepping a non-ASCII fixed string. This is a more general problem that's hard to fix, but we can at least fix the most common case of grepping for a fixed string without "-i". I can't think of a reason for why we'd turn on PCRE2_UTF when matching byte-for-byte like that. Signed-off-by: Ævar Arnfjörð Bjarmason Signed-off-by: Junio C Hamano --- grep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'grep.c') diff --git a/grep.c b/grep.c index 5bc0f4f32a..c7c06ae08d 100644 --- a/grep.c +++ b/grep.c @@ -472,7 +472,8 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } options |= PCRE2_CASELESS; } - if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern)) + if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) && + !(!opt->ignore_case && (p->fixed || p->is_fixed))) options |= PCRE2_UTF; p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern, -- cgit 1.2.3-korg