Rework in charset code. (Includes renaming.)

[mmh] / sbr / charset.c

diff --git a/sbr/charset.c b/sbr/charset.c
new file mode 100644 (file)
index 0000000..56f085c
--- /dev/null
+++ b/sbr/charset.c
@@ -0,0 +1,70 @@
+/*
+** charset.c -- routines for character sets
+**
+** This code is Copyright (c) 2002, by the authors of nmh.  See the
+** COPYRIGHT file in the root directory of the nmh distribution for
+** complete copyright information.
+*/
+
+#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.
+*/
+int
+is_native_charset(char *str)
+{
+       char *mm_charset = NULL;
+
+       if (!(mm_charset = get_charset())) {
+               mm_charset = "US-ASCII";
+       }
+       if (mh_strcasecmp(str, mm_charset)==0) {
+               return 1;
+       }
+
+       /* US-ASCII is a subset of the ISO-8859-X and UTF-8 character sets */
+       if (strncasecmp("ISO-8859-", mm_charset, 9)==0 ||
+                       mh_strcasecmp("UTF-8", mm_charset)==0) {
+               if (mh_strcasecmp(str, "US-ASCII")==0) {
+                       return 1;
+               }
+       }
+       return 0;
+}
+
+
+/*
+** Return the name of the character set we are
+** using for 8bit text.
+*/
+char *
+write_charset_8bit(void)
+{
+       char *mm_charset = NULL;
+
+       if (!(mm_charset = get_charset())) {
+               mm_charset = "x-unknown";
+       }
+       return mm_charset;
+}