95ca1f987e
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 in870eea8166(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 in8a5999838e(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" inb65abcafc7("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>
75 lines
3.3 KiB
C
75 lines
3.3 KiB
C
#ifndef TEST_TOOL_H
|
|
#define TEST_TOOL_H
|
|
|
|
#define USE_THE_INDEX_COMPATIBILITY_MACROS
|
|
#include "git-compat-util.h"
|
|
|
|
int cmd__advise_if_enabled(int argc, const char **argv);
|
|
int cmd__bloom(int argc, const char **argv);
|
|
int cmd__chmtime(int argc, const char **argv);
|
|
int cmd__config(int argc, const char **argv);
|
|
int cmd__crontab(int argc, const char **argv);
|
|
int cmd__ctype(int argc, const char **argv);
|
|
int cmd__date(int argc, const char **argv);
|
|
int cmd__delta(int argc, const char **argv);
|
|
int cmd__dir_iterator(int argc, const char **argv);
|
|
int cmd__drop_caches(int argc, const char **argv);
|
|
int cmd__dump_cache_tree(int argc, const char **argv);
|
|
int cmd__dump_fsmonitor(int argc, const char **argv);
|
|
int cmd__dump_split_index(int argc, const char **argv);
|
|
int cmd__dump_untracked_cache(int argc, const char **argv);
|
|
int cmd__example_decorate(int argc, const char **argv);
|
|
int cmd__fast_rebase(int argc, const char **argv);
|
|
int cmd__genrandom(int argc, const char **argv);
|
|
int cmd__genzeros(int argc, const char **argv);
|
|
int cmd__hashmap(int argc, const char **argv);
|
|
int cmd__hash_speed(int argc, const char **argv);
|
|
int cmd__index_version(int argc, const char **argv);
|
|
int cmd__json_writer(int argc, const char **argv);
|
|
int cmd__lazy_init_name_hash(int argc, const char **argv);
|
|
int cmd__match_trees(int argc, const char **argv);
|
|
int cmd__mergesort(int argc, const char **argv);
|
|
int cmd__mktemp(int argc, const char **argv);
|
|
int cmd__oidmap(int argc, const char **argv);
|
|
int cmd__online_cpus(int argc, const char **argv);
|
|
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);
|
|
int cmd__progress(int argc, const char **argv);
|
|
int cmd__reach(int argc, const char **argv);
|
|
int cmd__read_cache(int argc, const char **argv);
|
|
int cmd__read_graph(int argc, const char **argv);
|
|
int cmd__read_midx(int argc, const char **argv);
|
|
int cmd__ref_store(int argc, const char **argv);
|
|
int cmd__regex(int argc, const char **argv);
|
|
int cmd__repository(int argc, const char **argv);
|
|
int cmd__revision_walking(int argc, const char **argv);
|
|
int cmd__run_command(int argc, const char **argv);
|
|
int cmd__scrap_cache_tree(int argc, const char **argv);
|
|
int cmd__serve_v2(int argc, const char **argv);
|
|
int cmd__sha1(int argc, const char **argv);
|
|
int cmd__oid_array(int argc, const char **argv);
|
|
int cmd__sha256(int argc, const char **argv);
|
|
int cmd__sigchain(int argc, const char **argv);
|
|
int cmd__strcmp_offset(int argc, const char **argv);
|
|
int cmd__string_list(int argc, const char **argv);
|
|
int cmd__submodule_config(int argc, const char **argv);
|
|
int cmd__submodule_nested_repo_config(int argc, const char **argv);
|
|
int cmd__subprocess(int argc, const char **argv);
|
|
int cmd__trace2(int argc, const char **argv);
|
|
int cmd__urlmatch_normalization(int argc, const char **argv);
|
|
int cmd__xml_encode(int argc, const char **argv);
|
|
int cmd__wildmatch(int argc, const char **argv);
|
|
#ifdef GIT_WINDOWS_NATIVE
|
|
int cmd__windows_named_pipe(int argc, const char **argv);
|
|
#endif
|
|
int cmd__write_cache(int argc, const char **argv);
|
|
|
|
int cmd_hash_impl(int ac, const char **av, int algo);
|
|
|
|
#endif
|