const char *ends, *ap = strcasestr(line, name);
size_t sz;
- if (!ap) {
- strbuf_setlen(attr, 0);
+ strbuf_setlen(attr, 0);
+ if (!ap)
return 0;
- }
ap += strlen(name);
if (*ap == '"') {
ap++;
case 'r': case 'R':
if (subject->len <= at + 3)
break;
- if (!memcmp(subject->buf + at + 1, "e:", 2)) {
+ if ((subject->buf[at + 1] == 'e' ||
+ subject->buf[at + 1] == 'E') &&
+ subject->buf[at + 2] == ':') {
strbuf_remove(subject, at, 3);
continue;
}
(7 <= remove &&
memmem(subject->buf + at, remove, "PATCH", 5)))
strbuf_remove(subject, at, remove);
- else
+ else {
at += remove;
+ /*
+ * If the input had a space after the ], keep
+ * it. We don't bother with finding the end of
+ * the space, since we later normalize it
+ * anyway.
+ */
+ if (isspace(subject->buf[at]))
+ at += 1;
+ }
continue;
}
break;
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))
+ if (same_encoding(metainfo_charset, charset))
return;
out = reencode_string(line->buf, metainfo_charset, charset);
if (!out)