summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
authorÆvar Arnfjörð Bjarmason <avarab@gmail.com>2019-06-27 23:39:05 (GMT)
committerJunio C Hamano <gitster@pobox.com>2019-06-28 16:11:09 (GMT)
commit44570188a0e324048decf06b845d34c45b08a4fa (patch)
tree34599afabc8325f61c8da6d4b3eba0b2807fc666 /grep.c
parent4e2443b1813dded87c9cc1138f22af73748022b8 (diff)
downloadgit-44570188a0e324048decf06b845d34c45b08a4fa.zip
git-44570188a0e324048decf06b845d34c45b08a4fa.tar.gz
git-44570188a0e324048decf06b845d34c45b08a4fa.tar.bz2
grep: don't use PCRE2?_UTF8 with "log --encoding=<non-utf8>"
Fix a bug introduced in 18547aacf5 ("grep/pcre: support utf-8", 2016-06-25) that was missed due to a blindspot in our tests, as discussed in the previous commit. I then blindly copied the same bug in 94da9193a6 ("grep: add support for PCRE v2", 2017-06-01) when adding the PCRE v2 code. We should not tell PCRE that we're processing UTF-8 just because we're dealing with non-ASCII. In the case of e.g. "log --encoding=<...>" under is_utf8_locale() the haystack might be in ISO-8859-1, and the needle might be in a non-UTF-8 encoding. Maybe we should be more strict here and die earlier? Should we also be converting the needle to the encoding in question, and failing if it's not a string that's valid in that encoding? Maybe. But for now matching this as non-UTF8 at least has some hope of producing sensible results, since we know that our default heuristic of assuming the text to be matched is in the user locale encoding isn't true when we've explicitly encoded it to be in a different encoding. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c8
1 files changed, 4 insertions, 4 deletions
diff --git a/grep.c b/grep.c
index f7c3a58..1de4ab4 100644
--- a/grep.c
+++ b/grep.c
@@ -388,11 +388,11 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
int options = PCRE_MULTILINE;
if (opt->ignore_case) {
- if (has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && has_non_ascii(p->pattern))
p->pcre1_tables = pcre_maketables();
options |= PCRE_CASELESS;
}
- if (is_utf8_locale() && has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE_UTF8;
p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
@@ -498,14 +498,14 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
p->pcre2_compile_context = NULL;
if (opt->ignore_case) {
- if (has_non_ascii(p->pattern)) {
+ if (!opt->ignore_locale && has_non_ascii(p->pattern)) {
character_tables = pcre2_maketables(NULL);
p->pcre2_compile_context = pcre2_compile_context_create(NULL);
pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
}
options |= PCRE2_CASELESS;
}
- if (is_utf8_locale() && has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE2_UTF;
p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,