X-Git-Url: http://git.marmaro.de/?p=mmh;a=blobdiff_plain;f=sbr%2Fcheck_charset.c;h=d6b8ca34a70a12fefda673c03d4dd088c6a5f2a2;hp=5d98774c5e12e895b681ac8bfb25d3ec0169d8a5;hb=fb49dd82ec42997b9df97f221c920f6596102c0a;hpb=6c42153ad9362cc676ea66563bf400d7511b3b68

diff --git a/sbr/check_charset.c b/sbr/check_charset.c
index 5d98774..d6b8ca3 100644
--- a/sbr/check_charset.c
+++ b/sbr/check_charset.c
@@ -10,6 +10,25 @@
  */
 
 #include <h/mh.h>
+#ifdef HAVE_LANGINFO_H
+# include <langinfo.h>
+#endif
+
+
+/*
+ * Get the current character set
+ */
+char *
+get_charset ()
+{
+    char *charset = getenv ("MM_CHARSET");
+#if defined(HAVE_NL_LANGINFO) && defined(CODESET)
+    if (!charset)
+	charset = norm_charmap(nl_langinfo (CODESET));
+#endif
+    return charset;
+}
+
 
 /*
  * Check if we can display a given character set natively.
@@ -28,12 +47,13 @@ check_charset (char *str, int len)
 
     /* Cache the name of our default character set */
     if (!mm_charset) {
-	if (!(mm_charset = getenv ("MM_CHARSET")))
+	if (!(mm_charset = get_charset ()))
 	    mm_charset = "US-ASCII";
 	mm_len = strlen (mm_charset);
 
-	/* US-ASCII is a subset of the ISO-8859-X character sets */
-	if (!strncasecmp("ISO-8859-", mm_charset, 9)) {
+	/* US-ASCII is a subset of the ISO-8859-X and UTF-8 character sets */
+	if (!strncasecmp("ISO-8859-", mm_charset, 9) ||
+		!strcasecmp("UTF-8", mm_charset)) {
 	    alt_charset = "US-ASCII";
 	    alt_len = strlen (alt_charset);
 	}
@@ -62,7 +82,7 @@ write_charset_8bit (void)
      * Cache the name of the character set to
      * use for 8bit text.
      */
-    if (!mm_charset && !(mm_charset = getenv ("MM_CHARSET")))
+    if (!mm_charset && !(mm_charset = get_charset ()))
 	    mm_charset = "x-unknown";
 
     return mm_charset;