зеркало из https://github.com/microsoft/git.git
utf8: refactor code to decide fallback encoding
The codepath we use to call iconv_open() has a provision to use a fallback encoding when it fails, hoping that "UTF-8" being spelled differently could be the reason why the library function did not like the encoding names we gave it. Essentially, we turn what we have observed to be used as variants of "UTF-8" (e.g. "utf8") into the most official spelling and use that as a fallback. We do the same thing for input and output encoding. Introduce a helper function to do just one side and call that twice. Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Родитель
0b65a8dbdb
Коммит
3270741ea8
29
utf8.c
29
utf8.c
|
@ -489,6 +489,21 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs
|
||||||
return out;
|
return out;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static const char *fallback_encoding(const char *name)
|
||||||
|
{
|
||||||
|
/*
|
||||||
|
* Some platforms do not have the variously spelled variants of
|
||||||
|
* UTF-8, so let's fall back to trying the most official
|
||||||
|
* spelling. We do so only as a fallback in case the platform
|
||||||
|
* does understand the user's spelling, but not our official
|
||||||
|
* one.
|
||||||
|
*/
|
||||||
|
if (is_encoding_utf8(name))
|
||||||
|
return "UTF-8";
|
||||||
|
|
||||||
|
return name;
|
||||||
|
}
|
||||||
|
|
||||||
char *reencode_string_len(const char *in, int insz,
|
char *reencode_string_len(const char *in, int insz,
|
||||||
const char *out_encoding, const char *in_encoding,
|
const char *out_encoding, const char *in_encoding,
|
||||||
int *outsz)
|
int *outsz)
|
||||||
|
@ -501,17 +516,9 @@ char *reencode_string_len(const char *in, int insz,
|
||||||
|
|
||||||
conv = iconv_open(out_encoding, in_encoding);
|
conv = iconv_open(out_encoding, in_encoding);
|
||||||
if (conv == (iconv_t) -1) {
|
if (conv == (iconv_t) -1) {
|
||||||
/*
|
in_encoding = fallback_encoding(in_encoding);
|
||||||
* Some platforms do not have the variously spelled variants of
|
out_encoding = fallback_encoding(out_encoding);
|
||||||
* UTF-8, so let's fall back to trying the most official
|
|
||||||
* spelling. We do so only as a fallback in case the platform
|
|
||||||
* does understand the user's spelling, but not our official
|
|
||||||
* one.
|
|
||||||
*/
|
|
||||||
if (is_encoding_utf8(in_encoding))
|
|
||||||
in_encoding = "UTF-8";
|
|
||||||
if (is_encoding_utf8(out_encoding))
|
|
||||||
out_encoding = "UTF-8";
|
|
||||||
conv = iconv_open(out_encoding, in_encoding);
|
conv = iconv_open(out_encoding, in_encoding);
|
||||||
if (conv == (iconv_t) -1)
|
if (conv == (iconv_t) -1)
|
||||||
return NULL;
|
return NULL;
|
||||||
|
|
Загрузка…
Ссылка в новой задаче