utf8: accept alternate spellings of UTF-8

diff --git a/utf8.c b/utf8.c
index a544f15456656df642253533eaa28885ce3496a6..e7caef4721eafa66aba8f481675ebd69acdd6df8 100644 (file)
--- 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;