reencode_string(): introduce and use same_encoding()
Callers of reencode_string() that re-encodes a string from one encoding to another all used ad-hoc way to bypass the case where the input and the output encodings are the same. Some did strcmp(), some did strcasecmp(), yet some others when converting to UTF-8 used is_encoding_utf8(). Introduce same_encoding() helper function to make these callers use the same logic. Notably, is_encoding_utf8() has a work-around for common misconfiguration to use "utf8" to name UTF-8 encoding, which does not match "UTF-8" hence strcasecmp() would not consider the same. Make use of it in this helper function. Signed-off-by: Junio C Hamano <gitster@pobox.com>
Junio C Hamano committed
Oct 18, 2012 at 22:41 UTC
0e18bcd5e937b9e5857892e7f5c80c3c5b1da5d4
6 files changed
+12
-4
builtin/mailinfo.c
+1
-1
@@ -507,7 +507,7 @@ static void convert_to_utf8(struct strbuf *line, const char *charset)
507
return;
508
}
509
510
- if (!strcasecmp(metainfo_charset, charset))
510
+ if (same_encoding(metainfo_charset, charset))
511
return;
512
out = reencode_string(line->buf, metainfo_charset, charset);
513
if (!out)
notes.c
+1
-1
@@ -1221,7 +1221,7 @@ void format_note(struct notes_tree *t, const unsigned char *object_sha1,
1221
}
1222
1223
if (output_encoding && *output_encoding &&
1224
- strcmp(utf8, output_encoding)) {
1224
+ !is_encoding_utf8(output_encoding)) {
1225
char *reencoded = reencode_string(msg, output_encoding, utf8);
1226
if (reencoded) {
1227
free(msg);
pretty.c
+1
-1
@@ -504,7 +504,7 @@ char *logmsg_reencode(const struct commit *commit,
504
return NULL;
505
encoding = get_header(commit, "encoding");
506
use_encoding = encoding ? encoding : utf8;
507
- if (!strcmp(use_encoding, output_encoding))
507
+ if (same_encoding(use_encoding, output_encoding))
508
if (encoding) /* we'll strip encoding header later */
509
out = xstrdup(commit->buffer);
510
else
sequencer.c
+1
-1
@@ -58,7 +58,7 @@ static int get_message(struct commit *commit, struct commit_message *out)
58
59
out->reencoded_message = NULL;
60
out->message = commit->buffer;
61
- if (strcmp(encoding, git_commit_encoding))
61
+ if (same_encoding(encoding, git_commit_encoding))
62
out->reencoded_message = reencode_string(commit->buffer,
63
git_commit_encoding, encoding);
64
if (out->reencoded_message)
utf8.c
+7
@@ -423,6 +423,13 @@ int is_encoding_utf8(const char *name)
423
return 0;
424
}
425
426
+int same_encoding(const char *src, const char *dst)
427
+{
428
+ if (is_encoding_utf8(src) && is_encoding_utf8(dst))
429
+ return 1;
430
+ return !strcasecmp(src, dst);
431
+}
432
+
433
/*
434
* Given a buffer and its encoding, return it re-encoded
435
* with iconv. If the conversion fails, returns NULL.
utf8.h
+1
@@ -7,6 +7,7 @@ int utf8_width(const char **start, size_t *remainder_p);
7
int utf8_strwidth(const char *string);
8
int is_utf8(const char *text);
9
int is_encoding_utf8(const char *name);
10
+int same_encoding(const char *, const char *);
11
12
int strbuf_add_wrapped_text(struct strbuf *buf,
13
const char *text, int indent, int indent2, int width);