mirror of
https://github.com/git/git
synced 2024-08-27 19:49:21 +00:00
![Torsten Bögershausen](/assets/img/avatar_default.png)
Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
185 lines
4.6 KiB
C
185 lines
4.6 KiB
C
/*
|
|
* Converts filenames from decomposed unicode into precomposed unicode.
|
|
* Used on MacOS X.
|
|
*/
|
|
|
|
#define PRECOMPOSE_UNICODE_C
|
|
|
|
#include "cache.h"
|
|
#include "config.h"
|
|
#include "utf8.h"
|
|
#include "precompose_utf8.h"
|
|
|
|
typedef char *iconv_ibp;
|
|
static const char *repo_encoding = "UTF-8";
|
|
static const char *path_encoding = "UTF-8-MAC";
|
|
|
|
static size_t has_non_ascii(const char *s, size_t maxlen, size_t *strlen_c)
|
|
{
|
|
const uint8_t *ptr = (const uint8_t *)s;
|
|
size_t strlen_chars = 0;
|
|
size_t ret = 0;
|
|
|
|
if (!ptr || !*ptr)
|
|
return 0;
|
|
|
|
while (*ptr && maxlen) {
|
|
if (*ptr & 0x80)
|
|
ret++;
|
|
strlen_chars++;
|
|
ptr++;
|
|
maxlen--;
|
|
}
|
|
if (strlen_c)
|
|
*strlen_c = strlen_chars;
|
|
|
|
return ret;
|
|
}
|
|
|
|
|
|
void probe_utf8_pathname_composition(void)
|
|
{
|
|
struct strbuf path = STRBUF_INIT;
|
|
static const char *auml_nfc = "\xc3\xa4";
|
|
static const char *auml_nfd = "\x61\xcc\x88";
|
|
int output_fd;
|
|
if (precomposed_unicode != -1)
|
|
return; /* We found it defined in the global config, respect it */
|
|
git_path_buf(&path, "%s", auml_nfc);
|
|
output_fd = open(path.buf, O_CREAT|O_EXCL|O_RDWR, 0600);
|
|
if (output_fd >= 0) {
|
|
close(output_fd);
|
|
git_path_buf(&path, "%s", auml_nfd);
|
|
precomposed_unicode = access(path.buf, R_OK) ? 0 : 1;
|
|
git_config_set("core.precomposeunicode",
|
|
precomposed_unicode ? "true" : "false");
|
|
git_path_buf(&path, "%s", auml_nfc);
|
|
if (unlink(path.buf))
|
|
die_errno(_("failed to unlink '%s'"), path.buf);
|
|
}
|
|
strbuf_release(&path);
|
|
}
|
|
|
|
|
|
void precompose_argv(int argc, const char **argv)
|
|
{
|
|
int i = 0;
|
|
const char *oldarg;
|
|
char *newarg;
|
|
iconv_t ic_precompose;
|
|
|
|
if (precomposed_unicode != 1)
|
|
return;
|
|
|
|
ic_precompose = iconv_open(repo_encoding, path_encoding);
|
|
if (ic_precompose == (iconv_t) -1)
|
|
return;
|
|
|
|
while (i < argc) {
|
|
size_t namelen;
|
|
oldarg = argv[i];
|
|
if (has_non_ascii(oldarg, (size_t)-1, &namelen)) {
|
|
newarg = reencode_string_iconv(oldarg, namelen, ic_precompose, 0, NULL);
|
|
if (newarg)
|
|
argv[i] = newarg;
|
|
}
|
|
i++;
|
|
}
|
|
iconv_close(ic_precompose);
|
|
}
|
|
|
|
|
|
PREC_DIR *precompose_utf8_opendir(const char *dirname)
|
|
{
|
|
PREC_DIR *prec_dir = xmalloc(sizeof(PREC_DIR));
|
|
prec_dir->dirent_nfc = xmalloc(sizeof(dirent_prec_psx));
|
|
prec_dir->dirent_nfc->max_name_len = sizeof(prec_dir->dirent_nfc->d_name);
|
|
|
|
prec_dir->dirp = opendir(dirname);
|
|
if (!prec_dir->dirp) {
|
|
free(prec_dir->dirent_nfc);
|
|
free(prec_dir);
|
|
return NULL;
|
|
} else {
|
|
int ret_errno = errno;
|
|
prec_dir->ic_precompose = iconv_open(repo_encoding, path_encoding);
|
|
/* if iconv_open() fails, die() in readdir() if needed */
|
|
errno = ret_errno;
|
|
}
|
|
|
|
return prec_dir;
|
|
}
|
|
|
|
struct dirent_prec_psx *precompose_utf8_readdir(PREC_DIR *prec_dir)
|
|
{
|
|
struct dirent *res;
|
|
res = readdir(prec_dir->dirp);
|
|
if (res) {
|
|
size_t namelenz = strlen(res->d_name) + 1; /* \0 */
|
|
size_t new_maxlen = namelenz;
|
|
|
|
int ret_errno = errno;
|
|
|
|
if (new_maxlen > prec_dir->dirent_nfc->max_name_len) {
|
|
size_t new_len = sizeof(dirent_prec_psx) + new_maxlen -
|
|
sizeof(prec_dir->dirent_nfc->d_name);
|
|
|
|
prec_dir->dirent_nfc = xrealloc(prec_dir->dirent_nfc, new_len);
|
|
prec_dir->dirent_nfc->max_name_len = new_maxlen;
|
|
}
|
|
|
|
prec_dir->dirent_nfc->d_ino = res->d_ino;
|
|
prec_dir->dirent_nfc->d_type = res->d_type;
|
|
|
|
if ((precomposed_unicode == 1) && has_non_ascii(res->d_name, (size_t)-1, NULL)) {
|
|
if (prec_dir->ic_precompose == (iconv_t)-1) {
|
|
die("iconv_open(%s,%s) failed, but needed:\n"
|
|
" precomposed unicode is not supported.\n"
|
|
" If you want to use decomposed unicode, run\n"
|
|
" \"git config core.precomposeunicode false\"\n",
|
|
repo_encoding, path_encoding);
|
|
} else {
|
|
iconv_ibp cp = (iconv_ibp)res->d_name;
|
|
size_t inleft = namelenz;
|
|
char *outpos = &prec_dir->dirent_nfc->d_name[0];
|
|
size_t outsz = prec_dir->dirent_nfc->max_name_len;
|
|
errno = 0;
|
|
iconv(prec_dir->ic_precompose, &cp, &inleft, &outpos, &outsz);
|
|
if (errno || inleft) {
|
|
/*
|
|
* iconv() failed and errno could be E2BIG, EILSEQ, EINVAL, EBADF
|
|
* MacOS X avoids illegal byte sequences.
|
|
* If they occur on a mounted drive (e.g. NFS) it is not worth to
|
|
* die() for that, but rather let the user see the original name
|
|
*/
|
|
namelenz = 0; /* trigger strlcpy */
|
|
}
|
|
}
|
|
} else
|
|
namelenz = 0;
|
|
|
|
if (!namelenz)
|
|
strlcpy(prec_dir->dirent_nfc->d_name, res->d_name,
|
|
prec_dir->dirent_nfc->max_name_len);
|
|
|
|
errno = ret_errno;
|
|
return prec_dir->dirent_nfc;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
|
|
int precompose_utf8_closedir(PREC_DIR *prec_dir)
|
|
{
|
|
int ret_value;
|
|
int ret_errno;
|
|
ret_value = closedir(prec_dir->dirp);
|
|
ret_errno = errno;
|
|
if (prec_dir->ic_precompose != (iconv_t)-1)
|
|
iconv_close(prec_dir->ic_precompose);
|
|
free(prec_dir->dirent_nfc);
|
|
free(prec_dir);
|
|
errno = ret_errno;
|
|
return ret_value;
|
|
}
|