mirror of
https://github.com/git/git
synced 2024-10-01 06:05:20 +00:00
be39144954
Since 1819ad327b (grep: fix multibyte regex handling under macOS,
2022-08-26) we use the system library for all regular expression
matching on macOS, not just for git grep. It supports multi-byte
strings and rejects invalid multi-byte characters.
This broke all built-in userdiff word regexes in UTF-8 locales because
they all include such invalid bytes in expressions that are intended to
match multi-byte characters without explicit support for that from the
regex engine.
"|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" is added to all built-in word
regexes to match a single non-space or multi-byte character. The \xNN
characters are invalid if interpreted as UTF-8 because they have their
high bit set, which indicates they are part of a multi-byte character,
but they are surrounded by single-byte characters.
Replace that expression with "|[^[:space:]]" if the regex engine
supports multi-byte matching, as there is no need to have an explicit
range for multi-byte characters then. Check for that capability at
runtime, because it depends on the locale and thus on environment
variables. Construct the full replacement expression at build time
and just switch it in if necessary to avoid string manipulation and
allocations at runtime.
Additionally the word regex for tex contains the expression
"[a-zA-Z0-9\x80-\xff]+" with a similarly invalid range. The best
replacement with only valid characters that I can come up with is
"([a-zA-Z0-9]|[^\x01-\x7f])+". Unlike the original it matches NUL
characters, though. Assuming that tex files usually don't contain NUL
this should be acceptable.
Reported-by: D. Ben Knoble <ben.knoble@gmail.com>
Reported-by: Eric Sunshine <sunshine@sunshineco.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: René Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
52 lines
1.4 KiB
C
52 lines
1.4 KiB
C
#ifndef USERDIFF_H
|
|
#define USERDIFF_H
|
|
|
|
#include "notes-cache.h"
|
|
|
|
struct index_state;
|
|
struct repository;
|
|
|
|
struct userdiff_funcname {
|
|
const char *pattern;
|
|
int cflags;
|
|
};
|
|
|
|
struct userdiff_driver {
|
|
const char *name;
|
|
const char *external;
|
|
int binary;
|
|
struct userdiff_funcname funcname;
|
|
const char *word_regex;
|
|
const char *word_regex_multi_byte;
|
|
const char *textconv;
|
|
struct notes_cache *textconv_cache;
|
|
int textconv_want_cache;
|
|
};
|
|
enum userdiff_driver_type {
|
|
USERDIFF_DRIVER_TYPE_BUILTIN = 1<<0,
|
|
USERDIFF_DRIVER_TYPE_CUSTOM = 1<<1,
|
|
};
|
|
typedef int (*each_userdiff_driver_fn)(struct userdiff_driver *,
|
|
enum userdiff_driver_type, void *);
|
|
|
|
int userdiff_config(const char *k, const char *v);
|
|
struct userdiff_driver *userdiff_find_by_name(const char *name);
|
|
struct userdiff_driver *userdiff_find_by_path(struct index_state *istate,
|
|
const char *path);
|
|
|
|
/*
|
|
* Initialize any textconv-related fields in the driver and return it, or NULL
|
|
* if it does not have textconv enabled at all.
|
|
*/
|
|
struct userdiff_driver *userdiff_get_textconv(struct repository *r,
|
|
struct userdiff_driver *driver);
|
|
|
|
/*
|
|
* Iterate over all userdiff drivers. The userdiff_driver_type
|
|
* argument to each_userdiff_driver_fn indicates their type. Return
|
|
* non-zero to exit early from the loop.
|
|
*/
|
|
int for_each_userdiff_driver(each_userdiff_driver_fn, void *);
|
|
|
|
#endif /* USERDIFF */
|