use gperf for the charsets as well.

[apps/madmutt.git] / charset.c

diff --git a/charset.c b/charset.c
index bbaf8ca..544b357 100644 (file)
--- a/charset.c
+++ b/charset.c
@@ -40,126 +40,7 @@
 char *Charset;
 int Charset_is_utf8 = 0;
 
-/* 
- * The following list has been created manually from the data under:
- * http://www.isi.edu/in-notes/iana/assignments/character-sets
- * Last update: 2000-09-07
- *
- * Note that it includes only the subset of character sets for which
- * a preferred MIME name is given.
- */
-
-static struct {
-    const char *key;
-    const char *pref;
-} PreferredMIMENames[] = {
-    {"ansi_x3.4-1968", "us-ascii"},
-    {"iso-ir-6", "us-ascii"},
-    {"iso_646.irv:1991", "us-ascii"},
-    {"ascii", "us-ascii"},
-    {"iso646-us", "us-ascii"},
-    {"us", "us-ascii"},
-    {"ibm367", "us-ascii"},
-    {"cp367", "us-ascii"},
-    {"csascii", "us-ascii"},
-    {"csiso2022kr", "iso-2022-kr"},
-    {"cseuckr", "euc-kr"},
-    {"csiso2022jp", "iso-2022-jp"},
-    {"csiso2022jp2", "iso-2022-jp-2"},
-    {"iso_8859-1:1987", "iso-8859-1"},
-    {"iso-ir-100", "iso-8859-1"},
-    {"iso_8859-1", "iso-8859-1"},
-    {"latin1", "iso-8859-1"},
-    {"l1", "iso-8859-1"},
-    {"ibm819", "iso-8859-1"},
-    {"cp819", "iso-8859-1"},
-    {"csisolatin1", "iso-8859-1"},
-    {"iso_8859-2:1987", "iso-8859-2"},
-    {"iso-ir-101", "iso-8859-2"},
-    {"iso_8859-2", "iso-8859-2"},
-    {"latin2", "iso-8859-2"},
-    {"l2", "iso-8859-2"},
-    {"csisolatin2", "iso-8859-2"},
-    {"iso_8859-3:1988", "iso-8859-3"},
-    {"iso-ir-109", "iso-8859-3"},
-    {"iso_8859-3", "iso-8859-3"},
-    {"latin3", "iso-8859-3"},
-    {"l3", "iso-8859-3"},
-    {"csisolatin3", "iso-8859-3"},
-    {"iso_8859-4:1988", "iso-8859-4"},
-    {"iso-ir-110", "iso-8859-4"},
-    {"iso_8859-4", "iso-8859-4"},
-    {"latin4", "iso-8859-4"},
-    {"l4", "iso-8859-4"},
-    {"csisolatin4", "iso-8859-4"},
-    {"iso_8859-6:1987", "iso-8859-6"},
-    {"iso-ir-127", "iso-8859-6"},
-    {"iso_8859-6", "iso-8859-6"},
-    {"ecma-114", "iso-8859-6"},
-    {"asmo-708", "iso-8859-6"},
-    {"arabic", "iso-8859-6"},
-    {"csisolatinarabic", "iso-8859-6"},
-    {"iso_8859-7:1987", "iso-8859-7"},
-    {"iso-ir-126", "iso-8859-7"},
-    {"iso_8859-7", "iso-8859-7"},
-    {"elot_928", "iso-8859-7"},
-    {"ecma-118", "iso-8859-7"},
-    {"greek", "iso-8859-7"},
-    {"greek8", "iso-8859-7"},
-    {"csisolatingreek", "iso-8859-7"},
-    {"iso_8859-8:1988", "iso-8859-8"},
-    {"iso-ir-138", "iso-8859-8"},
-    {"iso_8859-8", "iso-8859-8"},
-    {"hebrew", "iso-8859-8"},
-    {"csisolatinhebrew", "iso-8859-8"},
-    {"iso_8859-5:1988", "iso-8859-5"},
-    {"iso-ir-144", "iso-8859-5"},
-    {"iso_8859-5", "iso-8859-5"},
-    {"cyrillic", "iso-8859-5"},
-    {"csisolatincyrillic", "iso8859-5"},
-    {"iso_8859-9:1989", "iso-8859-9"},
-    {"iso-ir-148", "iso-8859-9"},
-    {"iso_8859-9", "iso-8859-9"},
-    {"latin5", "iso-8859-9"},
-    {"l5", "iso-8859-9"},
-    {"csisolatin5", "iso-8859-9"},
-    {"iso_8859-10:1992", "iso-8859-10"},
-    {"iso-ir-157", "iso-8859-10"},
-    {"latin6", "iso-8859-10"},
-    {"l6", "iso-8859-10"},
-    {"csisolatin6", "iso-8859-10"},
-    {"cskoi8r", "koi8-r"},
-    {"ms_kanji", "shift_jis"},
-    {"csshiftjis", "shift_jis"},
-    {"extended_unix_code_packed_format_for_japanese", "euc-jp"},
-    {"cseucpkdfmtjapanese", "euc-jp"},
-    {"csgb2312", "gb2312"},
-    {"csbig5", "big5"},
-    /* end of official brain damage.
-       what follows has been taken * from glibc's localedata files.  */
-    {"iso_8859-13", "iso-8859-13"},
-    {"iso-ir-179", "iso-8859-13"},
-    {"latin7", "iso-8859-13"},
-    {"l7", "iso-8859-13"},
-    {"iso_8859-14", "iso-8859-14"},
-    {"latin8", "iso-8859-14"},
-    {"l8", "iso-8859-14"},
-    {"iso_8859-15", "iso-8859-15"},
-    {"latin9", "iso-8859-15"},
-    {"latin0", "iso-8859-15"},
-    {"iso_8859-16", "iso-8859-16"},
-    {"latin10", "iso-8859-16"},
-    {"646", "us-ascii"},
-    {"eucjp", "euc-jp"},
-    {"pck", "shift_jis"},
-    {"ko_kr-euc", "euc-kr"},
-    {"zh_tw-big5", "big5"},
-    {"sjis", "shift_jis"},
-    {"euc-jp-ms", "eucjp-ms"},
-    {NULL, NULL}
-};
-
-void mutt_set_langinfo_charset (void)
+void mutt_set_langinfo_charset(void)
 {
 #ifdef HAVE_LANGINFO_CODESET
     char buff[LONG_STRING];
@@ -174,36 +55,28 @@ void mutt_set_langinfo_charset (void)
         Charset = m_strdup("iso-8859-1");
 }
 
+#include "charset.gperf"
 
 void mutt_canonical_charset(char *dest, ssize_t dlen, const char *name)
 {
-    ssize_t i;
-    char *p;
+    const struct cset_pair *cp;
     char scratch[LONG_STRING];
+    int i;
 
-    m_strcpy(scratch, sizeof(scratch), name);
-    m_strtolower(scratch);
-
-    /* catch some common iso-8859-something misspellings */
-    if (!strncmp(scratch, "8859", 4)) {
-        snprintf(scratch, sizeof(scratch), "iso-8859-%s",
-                 name + 4 + (name[4] == '-'));
-        m_strtolower(scratch);
-    } else
-    if (!strncmp(scratch, "iso8859", 7)) {
-        snprintf(scratch, sizeof(scratch), "iso-8859-%s",
-                 name + 7 + (name[7] == '-'));
-        m_strtolower(scratch);
-    }
+    // canonize name: only keep a-z0-9 and dots, put into lowercase
+    for (i = 0; i < ssizeof(scratch); i++) {
+        if (isalnum(*name) || *name == '.') {
+            scratch[i++] = tolower((unsigned char)*name);
+        }
 
-    for (i = 0; PreferredMIMENames[i].key; i++) {
-        if (!strcmp(scratch, PreferredMIMENames[i].key)) {
-            m_strcpy(dest, dlen, PreferredMIMENames[i].pref);
-            return;
+        if (!*name || *name == ':') {
+            scratch[i] = '\0';
+            break;
         }
     }
 
-    m_strcpy(dest, dlen, scratch);
+    cp = mutt_canonical_charset_aux(scratch, strlen(scratch));
+    m_strcpy(dest, dlen, cp ? cp->pref : name);
 }
 
 static int mutt_chscmp(const char *s, const char *chs)