Silly of me to overlook it: another obvious way you might like to

[sgt/charset] / localenc.c

diff --git a/localenc.c b/localenc.c
index 775dd98..f5fabee 100644 (file)
--- a/localenc.c
+++ b/localenc.c
@@ -6,6 +6,12 @@
  * enumeration functions which return a list of supported
  * encodings one by one.
  * 
+ * Also in this table are other ways people might plausibly refer
+ * to a charset (for example, Win1252 as well as CP1252). Where
+ * more than one string is given for a particular character set,
+ * the first one is the canonical one returned by
+ * charset_to_localenc.
+ * 
  * charset_from_localenc will attempt all other text translations
  * as well as this table, to maximise the number of different ways
  * you can select a supported charset.
@@ -22,6 +28,7 @@ static const struct {
 } localencs[] = {
     { "<UNKNOWN>", CS_NONE, 0 },
     { "ASCII", CS_ASCII, 1 },
+    { "BS 4730", CS_BS4730, 1 },
     { "ISO-8859-1", CS_ISO8859_1, 1 },
     { "ISO-8859-1 with X11 line drawing", CS_ISO8859_1_X11, 0 },
     { "ISO-8859-2", CS_ISO8859_2, 1 },
@@ -40,18 +47,36 @@ static const struct {
     { "ISO-8859-16", CS_ISO8859_16, 1 },
     { "CP437", CS_CP437, 1 },
     { "CP850", CS_CP850, 1 },
+    { "CP852", CS_CP852, 1 },
+    { "CP866", CS_CP866, 1 },
+    { "CP874", CS_CP874, 1 },
+    { "Win874", CS_CP874, 0 },
+    { "Win-874", CS_CP874, 0 },
     { "CP1250", CS_CP1250, 1 },
+    { "Win1250", CS_CP1250, 0 },
     { "CP1251", CS_CP1251, 1 },
+    { "Win1251", CS_CP1251, 0 },
     { "CP1252", CS_CP1252, 1 },
+    { "Win1252", CS_CP1252, 0 },
     { "CP1253", CS_CP1253, 1 },
+    { "Win1253", CS_CP1253, 0 },
     { "CP1254", CS_CP1254, 1 },
+    { "Win1254", CS_CP1254, 0 },
     { "CP1255", CS_CP1255, 1 },
+    { "Win1255", CS_CP1255, 0 },
     { "CP1256", CS_CP1256, 1 },
+    { "Win1256", CS_CP1256, 0 },
     { "CP1257", CS_CP1257, 1 },
+    { "Win1257", CS_CP1257, 0 },
     { "CP1258", CS_CP1258, 1 },
+    { "Win1258", CS_CP1258, 0 },
     { "KOI8-R", CS_KOI8_R, 1 },
     { "KOI8-U", CS_KOI8_U, 1 },
     { "KOI8-RU", CS_KOI8_RU, 1 },
+    { "JIS X 0201", CS_JISX0201, 1 },
+    { "JIS-X-0201", CS_JISX0201, 0 },
+    { "JIS_X_0201", CS_JISX0201, 0 },
+    { "JISX0201", CS_JISX0201, 0 },
     { "Mac Roman", CS_MAC_ROMAN, 1 },
     { "Mac Turkish", CS_MAC_TURKISH, 1 },
     { "Mac Croatian", CS_MAC_CROATIAN, 1 },
@@ -75,12 +100,16 @@ static const struct {
     { "VISCII", CS_VISCII, 1 },
     { "HP ROMAN8", CS_HP_ROMAN8, 1 },
     { "DEC MCS", CS_DEC_MCS, 1 },
+    { "DEC graphics", CS_DEC_GRAPHICS, 1 },
+    { "DEC-graphics", CS_DEC_GRAPHICS, 0 },
+    { "DECgraphics", CS_DEC_GRAPHICS, 0 },
     { "UTF-8", CS_UTF8, 1 },
     { "UTF-7", CS_UTF7, 1 },
     { "UTF-7-conservative", CS_UTF7_CONSERVATIVE, 0 },
     { "EUC-CN", CS_EUC_CN, 1 },
     { "EUC-KR", CS_EUC_KR, 1 },
     { "EUC-JP", CS_EUC_JP, 1 },
+    { "EUC-TW", CS_EUC_TW, 1 },
     { "ISO-2022-JP", CS_ISO2022_JP, 1 },
     { "ISO-2022-KR", CS_ISO2022_KR, 1 },
     { "Big5", CS_BIG5, 1 },
@@ -91,6 +120,14 @@ static const struct {
     { "UTF-16", CS_UTF16, 1 },
     { "CP949", CS_CP949, 1 },
     { "PDFDocEncoding", CS_PDF, 1 },
+    { "StandardEncoding", CS_PSSTD, 1 },
+    { "COMPOUND_TEXT", CS_CTEXT, 1 },
+    { "COMPOUND-TEXT", CS_CTEXT, 0 },
+    { "COMPOUND TEXT", CS_CTEXT, 0 },
+    { "COMPOUNDTEXT", CS_CTEXT, 0 },
+    { "CTEXT", CS_CTEXT, 0 },
+    { "ISO-2022", CS_ISO2022, 1 },
+    { "ISO2022", CS_ISO2022, 0 },
 };
 
 const char *charset_to_localenc(int charset)
@@ -112,13 +149,15 @@ int charset_from_localenc(const char *name)
        return i;
     if ( (i = charset_from_xenc(name)) != CS_NONE)
        return i;
+    if ( (i = charset_from_emacsenc(name)) != CS_NONE)
+       return i;
 
     for (i = 0; i < (int)lenof(localencs); i++) {
        const char *p, *q;
        p = name;
        q = localencs[i].name;
        while (*p || *q) {
-           if (tolower(*p) != tolower(*q))
+               if (tolower((unsigned char)*p) != tolower((unsigned char)*q))
                break;
            p++; q++;
        }