summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c41
1 files changed, 39 insertions, 2 deletions
diff --git a/utf8.c b/utf8.c
index a4ee6650ef..8f6e84b7b3 100644
--- a/utf8.c
+++ b/utf8.c
@@ -430,6 +430,27 @@ int same_encoding(const char *src, const char *dst)
}
/*
+ * Wrapper for fprintf and returns the total number of columns required
+ * for the printed string, assuming that the string is utf8.
+ */
+int utf8_fprintf(FILE *stream, const char *format, ...)
+{
+ struct strbuf buf = STRBUF_INIT;
+ va_list arg;
+ int columns;
+
+ va_start(arg, format);
+ strbuf_vaddf(&buf, format, arg);
+ va_end(arg);
+
+ columns = fputs(buf.buf, stream);
+ if (0 <= columns) /* keep the error from the I/O */
+ columns = utf8_strwidth(buf.buf);
+ strbuf_release(&buf);
+ return columns;
+}
+
+/*
* Given a buffer and its encoding, return it re-encoded
* with iconv. If the conversion fails, returns NULL.
*/
@@ -486,9 +507,25 @@ 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;