mdw@git.distorted.org.uk Git - sgt/charset/blob - mimeenc.c

   1 /*
   2  * mimeenc.c - translate our internal character set codes to and
   3  * from MIME standard character-set names.
   4  *
   5  */
   6
   7 #include <ctype.h>
   8 #include "charset.h"
   9 #include "internal.h"
  10
  11 static const struct {
  12     const char *name;
  13     int charset;
  14 } mimeencs[] = {
  15     /*
  16      * Most of these names are taken from
  17      *
  18      *   http://www.iana.org/assignments/character-sets
  19      *
  20      * Where multiple encoding names map to the same encoding id
  21      * (such as the variety of aliases for ISO-8859-1), the first
  22      * is considered canonical and will be returned when
  23      * translating the id to a string.
  24      *
  25      * I also list here a few names which aren't in the above web
  26      * page, but which I've seen in the wild in real mail. These
  27      * are marked with a comment saying WILD.
  28      */
  29
  30     { "US-ASCII", CS_ASCII },
  31     { "ANSI_X3.4-1968", CS_ASCII },
  32     { "iso-ir-6", CS_ASCII },
  33     { "ANSI_X3.4-1986", CS_ASCII },
  34     { "ISO_646.irv:1991", CS_ASCII },
  35     { "ASCII", CS_ASCII },
  36     { "ISO646-US", CS_ASCII },
  37     { "us", CS_ASCII },
  38     { "IBM367", CS_ASCII },
  39     { "cp367", CS_ASCII },
  40     { "csASCII", CS_ASCII },
  41     { "646", CS_ASCII },               /* WILD */
  42
  43     { "BS_4730", CS_BS4730 },
  44     { "iso-ir-4", CS_BS4730 },
  45     { "ISO646-GB", CS_BS4730 },
  46     { "gb", CS_BS4730 },
  47     { "uk", CS_BS4730 },
  48     { "csISO4UnitedKingdom", CS_BS4730 },
  49
  50     { "ISO-8859-1", CS_ISO8859_1 },
  51     { "ISO8859-1", CS_ISO8859_1 },     /* WILD */
  52     { "iso-ir-100", CS_ISO8859_1 },
  53     { "ISO_8859-1", CS_ISO8859_1 },
  54     { "ISO_8859-1:1987", CS_ISO8859_1 },
  55     { "latin1", CS_ISO8859_1 },
  56     { "l1", CS_ISO8859_1 },
  57     { "IBM819", CS_ISO8859_1 },
  58     { "CP819", CS_ISO8859_1 },
  59     { "csISOLatin1", CS_ISO8859_1 },
  60
  61     { "ISO-8859-2", CS_ISO8859_2 },
  62     { "ISO8859-2", CS_ISO8859_2 },     /* WILD */
  63     { "ISO_8859-2:1987", CS_ISO8859_2 },
  64     { "iso-ir-101", CS_ISO8859_2 },
  65     { "ISO_8859-2", CS_ISO8859_2 },
  66     { "latin2", CS_ISO8859_2 },
  67     { "l2", CS_ISO8859_2 },
  68     { "csISOLatin2", CS_ISO8859_2 },
  69
  70     { "ISO-8859-3", CS_ISO8859_3 },
  71     { "ISO8859-3", CS_ISO8859_3 },     /* WILD */
  72     { "ISO_8859-3:1988", CS_ISO8859_3 },
  73     { "iso-ir-109", CS_ISO8859_3 },
  74     { "ISO_8859-3", CS_ISO8859_3 },
  75     { "latin3", CS_ISO8859_3 },
  76     { "l3", CS_ISO8859_3 },
  77     { "csISOLatin3", CS_ISO8859_3 },
  78
  79     { "ISO-8859-4", CS_ISO8859_4 },
  80     { "ISO8859-4", CS_ISO8859_4 },     /* WILD */
  81     { "ISO_8859-4:1988", CS_ISO8859_4 },
  82     { "iso-ir-110", CS_ISO8859_4 },
  83     { "ISO_8859-4", CS_ISO8859_4 },
  84     { "latin4", CS_ISO8859_4 },
  85     { "l4", CS_ISO8859_4 },
  86     { "csISOLatin4", CS_ISO8859_4 },
  87
  88     { "ISO-8859-5", CS_ISO8859_5 },
  89     { "ISO8859-5", CS_ISO8859_5 },     /* WILD */
  90     { "ISO_8859-5:1988", CS_ISO8859_5 },
  91     { "iso-ir-144", CS_ISO8859_5 },
  92     { "ISO_8859-5", CS_ISO8859_5 },
  93     { "cyrillic", CS_ISO8859_5 },
  94     { "csISOLatinCyrillic", CS_ISO8859_5 },
  95
  96     { "ISO-8859-6", CS_ISO8859_6 },
  97     { "ISO8859-6", CS_ISO8859_6 },     /* WILD */
  98     { "ISO_8859-6:1987", CS_ISO8859_6 },
  99     { "iso-ir-127", CS_ISO8859_6 },
 100     { "ISO_8859-6", CS_ISO8859_6 },
 101     { "ECMA-114", CS_ISO8859_6 },
 102     { "ASMO-708", CS_ISO8859_6 },
 103     { "arabic", CS_ISO8859_6 },
 104     { "csISOLatinArabic", CS_ISO8859_6 },
 105
 106     { "ISO-8859-7", CS_ISO8859_7 },
 107     { "ISO8859-7", CS_ISO8859_7 },     /* WILD */
 108     { "ISO_8859-7:1987", CS_ISO8859_7 },
 109     { "iso-ir-126", CS_ISO8859_7 },
 110     { "ISO_8859-7", CS_ISO8859_7 },
 111     { "ELOT_928", CS_ISO8859_7 },
 112     { "ECMA-118", CS_ISO8859_7 },
 113     { "greek", CS_ISO8859_7 },
 114     { "greek8", CS_ISO8859_7 },
 115     { "csISOLatinGreek", CS_ISO8859_7 },
 116
 117     { "ISO-8859-8", CS_ISO8859_8 },
 118     { "ISO8859-8", CS_ISO8859_8 },     /* WILD */
 119     { "ISO_8859-8:1988", CS_ISO8859_8 },
 120     { "iso-ir-138", CS_ISO8859_8 },
 121     { "ISO_8859-8", CS_ISO8859_8 },
 122     { "hebrew", CS_ISO8859_8 },
 123     { "csISOLatinHebrew", CS_ISO8859_8 },
 124
 125     { "ISO-8859-9", CS_ISO8859_9 },
 126     { "ISO8859-9", CS_ISO8859_9 },     /* WILD */
 127     { "ISO_8859-9:1989", CS_ISO8859_9 },
 128     { "iso-ir-148", CS_ISO8859_9 },
 129     { "ISO_8859-9", CS_ISO8859_9 },
 130     { "latin5", CS_ISO8859_9 },
 131     { "l5", CS_ISO8859_9 },
 132     { "csISOLatin5", CS_ISO8859_9 },
 133
 134     { "ISO-8859-10", CS_ISO8859_10 },
 135     { "ISO8859-10", CS_ISO8859_10 },   /* WILD */
 136     { "iso-ir-157", CS_ISO8859_10 },
 137     { "l6", CS_ISO8859_10 },
 138     { "ISO_8859-10:1992", CS_ISO8859_10 },
 139     { "csISOLatin6", CS_ISO8859_10 },
 140     { "latin6", CS_ISO8859_10 },
 141
 142     { "TIS-620", CS_ISO8859_11 },
 143
 144     { "ISO-8859-13", CS_ISO8859_13 },
 145     { "ISO8859-13", CS_ISO8859_13 },   /* WILD */
 146
 147     { "ISO-8859-14", CS_ISO8859_14 },
 148     { "ISO8859-14", CS_ISO8859_14 },   /* WILD */
 149     { "iso-ir-199", CS_ISO8859_14 },
 150     { "ISO_8859-14:1998", CS_ISO8859_14 },
 151     { "ISO_8859-14", CS_ISO8859_14 },
 152     { "latin8", CS_ISO8859_14 },
 153     { "iso-celtic", CS_ISO8859_14 },
 154     { "l8", CS_ISO8859_14 },
 155
 156     { "ISO-8859-15", CS_ISO8859_15 },
 157     { "ISO8859-15", CS_ISO8859_15 },   /* WILD */
 158     { "ISO_8859-15", CS_ISO8859_15 },
 159     { "Latin-9", CS_ISO8859_15 },
 160
 161     { "ISO-8859-16", CS_ISO8859_16 },
 162     { "ISO8859-16", CS_ISO8859_16 },   /* WILD */
 163     { "iso-ir-226", CS_ISO8859_16 },
 164     { "ISO_8859-16", CS_ISO8859_16 },
 165     { "ISO_8859-16:2001", CS_ISO8859_16 },
 166     { "latin10", CS_ISO8859_16 },
 167     { "l10", CS_ISO8859_16 },
 168
 169     { "IBM437", CS_CP437 },
 170     { "cp437", CS_CP437 },
 171     { "437", CS_CP437 },
 172     { "csPC8CodePage437", CS_CP437 },
 173
 174     { "IBM850", CS_CP850 },
 175     { "cp850", CS_CP850 },
 176     { "850", CS_CP850 },
 177     { "csPC850Multilingual", CS_CP850 },
 178
 179     { "windows-1250", CS_CP1250 },
 180     { "win-1250", CS_CP1250 },         /* WILD */
 181
 182     { "windows-1251", CS_CP1251 },
 183     { "win-1251", CS_CP1251 },         /* WILD */
 184
 185     { "windows-1252", CS_CP1252 },
 186     { "win-1252", CS_CP1252 },         /* WILD */
 187
 188     { "windows-1253", CS_CP1253 },
 189     { "win-1253", CS_CP1253 },         /* WILD */
 190
 191     { "windows-1254", CS_CP1254 },
 192     { "win-1254", CS_CP1254 },         /* WILD */
 193
 194     { "windows-1255", CS_CP1255 },
 195     { "win-1255", CS_CP1255 },         /* WILD */
 196
 197     { "windows-1256", CS_CP1256 },
 198     { "win-1256", CS_CP1256 },         /* WILD */
 199
 200     { "windows-1257", CS_CP1257 },
 201     { "win-1257", CS_CP1257 },         /* WILD */
 202
 203     { "windows-1258", CS_CP1258 },
 204     { "win-1258", CS_CP1258 },         /* WILD */
 205
 206     { "KOI8-R", CS_KOI8_R },
 207     { "csKOI8R", CS_KOI8_R },
 208
 209     { "KOI8-U", CS_KOI8_U },
 210
 211     { "KOI8-RU", CS_KOI8_RU },         /* WILD */
 212
 213     { "JIS_X0201", CS_JISX0201 },
 214     { "X0201", CS_JISX0201 },
 215     { "csHalfWidthKatakana", CS_JISX0201 },
 216
 217     { "macintosh", CS_MAC_ROMAN_OLD },
 218     { "mac", CS_MAC_ROMAN_OLD },
 219     { "csMacintosh", CS_MAC_ROMAN_OLD },
 220
 221     { "VISCII", CS_VISCII },
 222     { "csVISCII", CS_VISCII },
 223
 224     { "hp-roman8", CS_HP_ROMAN8 },
 225     { "roman8", CS_HP_ROMAN8 },
 226     { "r8", CS_HP_ROMAN8 },
 227     { "csHPRoman8", CS_HP_ROMAN8 },
 228
 229     { "DEC-MCS", CS_DEC_MCS },
 230     { "dec", CS_DEC_MCS },
 231     { "csDECMCS", CS_DEC_MCS },
 232
 233     { "UTF-8", CS_UTF8 },
 234
 235     { "UTF-7", CS_UTF7 },
 236     { "UNICODE-1-1-UTF-7", CS_UTF7 },
 237     { "csUnicode11UTF7", CS_UTF7 },
 238
 239     /*
 240      * Quite why the EUC-CN encoding is known to MIME by the name
 241      * of its underlying character set, I'm not entirely sure, but
 242      * it is. Shrug.
 243      */
 244     { "GB2312", CS_EUC_CN },
 245     { "csGB2312", CS_EUC_CN },
 246
 247     { "EUC-KR", CS_EUC_KR },
 248     { "csEUCKR", CS_EUC_KR },
 249
 250     { "EUC-JP", CS_EUC_JP },
 251     { "csEUCPkdFmtJapanese", CS_EUC_JP },
 252     { "Extended_UNIX_Code_Packed_Format_for_Japanese", CS_EUC_JP },
 253
 254     { "ISO-2022-JP", CS_ISO2022_JP },
 255     { "csISO2022JP", CS_ISO2022_JP },
 256
 257     { "ISO-2022-KR", CS_ISO2022_KR },
 258     { "csISO2022KR", CS_ISO2022_KR },
 259
 260     { "Big5", CS_BIG5 },
 261     { "csBig5", CS_BIG5 },
 262     { "Big-5", CS_BIG5 },              /* WILD */
 263     { "ChineseBig5", CS_BIG5 },        /* WILD */
 264
 265     { "Shift_JIS", CS_SHIFT_JIS },
 266     { "MS_Kanji", CS_SHIFT_JIS },
 267     { "csShiftJIS", CS_SHIFT_JIS },
 268
 269     { "HZ-GB-2312", CS_HZ },
 270
 271     { "UTF-16BE", CS_UTF16BE },
 272
 273     { "UTF-16LE", CS_UTF16LE },
 274
 275     { "UTF-16", CS_UTF16 },
 276
 277     /*
 278      * This bit is fiddly and possibly technically incorrect; but
 279      * rumour has it that the KSC 5601 encoding is a subset of
 280      * Microsoft CP949, and that MS products tend to announce CP949
 281      * as KSC 5601 in much the same way they seem willing to
 282      * announce CP1252 as its subset ISO 8859-1. So I cheat
 283      * shamelessly here by letting KSC 5601 map to CP949.
 284      */
 285     { "KS_C_5601-1987", CS_CP949 },
 286     { "iso-ir-149", CS_CP949 },
 287     { "KS_C_5601-1989", CS_CP949 },
 288     { "KSC_5601", CS_CP949 },
 289     { "korean", CS_CP949 },
 290     { "csKSC56011987", CS_CP949 },
 291     { "KSC5601", CS_CP949 },           /* WILD */
 292
 293 #if 0
 294     { "ISO-2022-JP-2", CS_ISO2022_JP_2 },
 295     { "csISO2022JP2", CS_ISO2022_JP_2 },
 296 #endif
 297 };
 298
 299 const char *charset_to_mimeenc(int charset)
 300 {
 301     int i;
 302
 303     for (i = 0; i < (int)lenof(mimeencs); i++)
 304         if (charset == mimeencs[i].charset)
 305             return mimeencs[i].name;
 306
 307     return NULL;                       /* not found */
 308 }
 309
 310 int charset_from_mimeenc(const char *name)
 311 {
 312     int i;
 313
 314     for (i = 0; i < (int)lenof(mimeencs); i++) {
 315         const char *p, *q;
 316         p = name;
 317         q = mimeencs[i].name;
 318         while (*p || *q) {
 319             if (tolower(*p) != tolower(*q))
 320                 break;
 321             p++; q++;
 322         }
 323         if (!*p && !*q)
 324             return mimeencs[i].charset;
 325     }
 326
 327     return CS_NONE;                    /* not found */
 328 }