Merge branch 'jk/utf-8-can-be-spelled-differently' into maint

Some platforms and users spell UTF-8 differently; retry with the
most official "UTF-8" when the system does not understand the
user-supplied encoding name that are the common alternative
spellings of UTF-8.

* jk/utf-8-can-be-spelled-differently:
  utf8: accept alternate spellings of UTF-8

diff --git a/utf8.c b/utf8.c
index 1087870c51caff3dd86a852ec5e8bf5875f6d797..8f6e84b7b3cf589f437a81ee81fd0228b2faf2f2 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -507,9 +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;