utf8: accept alternate spellings of UTF-8

diff --git a/utf8.c b/utf8.c
index 8acbc660d31a3552a4451749353139e0dcd371bd..e7caef4721eafa66aba8f481675ebd69acdd6df8 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -433,19 +433,12 @@ int is_encoding_utf8(const char *name)
 #else
        typedef char * iconv_ibp;
 #endif
-char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding)
+char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv)
 {
-       iconv_t conv;
-       size_t insz, outsz, outalloc;
+       size_t outsz, outalloc;
        char *out, *outpos;
        iconv_ibp cp;
 
-       if (!in_encoding)
-               return NULL;
-       conv = iconv_open(out_encoding, in_encoding);
-       if (conv == (iconv_t) -1)
-               return NULL;
-       insz = strlen(in);
        outsz = insz;
        outalloc = outsz + 1; /* for terminating NUL */
        out = xmalloc(outalloc);
@@ -459,7 +452,6 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
                        size_t sofar;
                        if (errno != E2BIG) {
                                free(out);
-                               iconv_close(conv);
                                return NULL;
                        }
                        /* insz has remaining number of bytes.
@@ -478,6 +470,36 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
                        break;
                }
        }
+       return out;
+}
+
+char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding)
+{
+       iconv_t conv;
+       char *out;
+
+       if (!in_encoding)
+               return NULL;
+
+       conv = iconv_open(out_encoding, in_encoding);
+       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;
 }