summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2013-02-25 15:31:00 -0500
committerJunio C Hamano <gitster@pobox.com>2013-02-25 13:17:22 -0800
commit5c680be113ec8aca49ddfbe93a9f43684d3d261e (patch)
tree8977da4c459254384b7740b6203a752ba866644b /utf8.c
parent7e2010537e96d0a1144520222f20ba1dc3d61441 (diff)
downloadgit-5c680be113ec8aca49ddfbe93a9f43684d3d261e.tar.gz
utf8: accept alternate spellings of UTF-8
The iconv implementation on many platforms will accept variants of UTF-8, including "UTF8", "utf-8", and "utf8", but some do not. We make allowances in our code to treat them all identically, but we sometimes hand the string from the user directly to iconv. In this case, the platform iconv may or may not work. There are really four levels of platform iconv support for these synonyms: 1. All synonyms understood (e.g., glibc). 2. Only the official "UTF-8" understood (e.g., Windows). 3. Official "UTF-8" not understood, but some other synonym understood (it's not known whether such a platform exists). 4. Neither "UTF-8" nor any synonym understood (e.g., ancient systems, or ones without utf8 support installed). This patch teaches git to fall back to using the official "UTF-8" spelling when iconv_open fails (and the encoding was one of the synonym spellings). This makes things more convenient to users of type 2 systems, as they can now use any of the synonyms for the log output encoding. Type 1 systems are not affected, as iconv already works on the first try. Type 4 systems are not affected, as both attempts already fail. Type 3 systems will not benefit from the feature, but because we only use "UTF-8" as a fallback, they will not be regressed (i.e., you can continue to use "utf8" if your platform supports it). We could try all the various synonyms, but since such systems are not even known to exist, it's not worth the effort. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c20
1 files changed, 18 insertions, 2 deletions
diff --git a/utf8.c b/utf8.c
index a544f15456..e7caef4721 100644
--- a/utf8.c
+++ b/utf8.c
@@ -480,9 +480,25 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
if (!in_encoding)
return NULL;
+
conv = iconv_open(out_encoding, in_encoding);
- if (conv == (iconv_t) -1)
- return NULL;
+ if (conv == (iconv_t) -1) {
+ /*
+ * 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(in_encoding))
+ in_encoding = "UTF-8";
+ if (is_encoding_utf8(out_encoding))
+ out_encoding = "UTF-8";
+ conv = iconv_open(out_encoding, in_encoding);
+ if (conv == (iconv_t) -1)
+ return NULL;
+ }
+
out = reencode_string_iconv(in, strlen(in), conv);
iconv_close(conv);
return out;