summaryrefslogtreecommitdiff
path: root/builtin
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2012-06-28 11:24:14 -0700
committerLibravatar Junio C Hamano <gitster@pobox.com>2012-08-21 16:10:53 -0700
commit08a94a145c3231c0fa36469682591a3c45222271 (patch)
treef25e5463156188f41e00da2f284fd8eb1b756bf2 /builtin
parentgit-submodule.sh: fix filename in comment. (diff)
downloadtgif-08a94a145c3231c0fa36469682591a3c45222271.tar.xz
commit/commit-tree: correct latin1 to utf-8
When a line in the message is not a valid utf-8, "git mailinfo" attempts to convert it to utf-8 assuming the input is latin1 (and punt if it does not convert cleanly). Using the same heuristics in "git commit" and "git commit-tree" lets the editor output be in latin1 to make the overall system more consistent. Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'builtin')
-rw-r--r--builtin/mailinfo.c28
1 files changed, 2 insertions, 26 deletions
diff --git a/builtin/mailinfo.c b/builtin/mailinfo.c
index eaf9e157a3..dd4f925475 100644
--- a/builtin/mailinfo.c
+++ b/builtin/mailinfo.c
@@ -481,36 +481,12 @@ static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
return out;
}
-/*
- * When there is no known charset, guess.
- *
- * Right now we assume that if the target is UTF-8 (the default),
- * and it already looks like UTF-8 (which includes US-ASCII as its
- * subset, of course) then that is what it is and there is nothing
- * to do.
- *
- * Otherwise, we default to assuming it is Latin1 for historical
- * reasons.
- */
-static const char *guess_charset(const struct strbuf *line, const char *target_charset)
-{
- if (is_encoding_utf8(target_charset)) {
- if (is_utf8(line->buf))
- return NULL;
- }
- return "ISO8859-1";
-}
-
static void convert_to_utf8(struct strbuf *line, const char *charset)
{
char *out;
- if (!charset || !*charset) {
- charset = guess_charset(line, metainfo_charset);
- if (!charset)
- return;
- }
-
+ if (!charset || !*charset)
+ return;
if (!strcasecmp(metainfo_charset, charset))
return;
out = reencode_string(line->buf, metainfo_charset, charset);