X-Git-Url: http://git.marmaro.de/?p=mmh;a=blobdiff_plain;f=sbr%2Fnorm_charmap.c;h=02e6a3cf29089ca1e22cc51591c7acaa7c90c8d8;hp=ae81046f0ea233eb24c91ddec4f0fff4cfcc5fc1;hb=4112940aea5591648b03a81907408752c08b33aa;hpb=adc954633908e3fc97dfa94c08f964e1bbb94086 diff --git a/sbr/norm_charmap.c b/sbr/norm_charmap.c index ae81046..02e6a3c 100644 --- a/sbr/norm_charmap.c +++ b/sbr/norm_charmap.c @@ -1,28 +1,28 @@ /* - * The Single Unix Specification function nl_langinfo(CODESET) - * returns the name of the encoding used by the currently selected - * locale: - * - * http://www.opengroup.org/onlinepubs/7908799/xsh/langinfo.h.html - * - * Unfortunately the encoding names are not yet standardized. - * This function knows about the encoding names used on many - * different systems and converts them where possible into - * the corresponding MIME charset name registered in - * - * http://www.iana.org/assignments/character-sets - * - * Please extend it as needed and suggest improvements to the author. - * - * Markus.Kuhn@cl.cam.ac.uk -- 2002-03-11 - * Permission to use, copy, modify, and distribute this software - * for any purpose and without fee is hereby granted. The author - * disclaims all warranties with regard to this software. - * - * Latest version: - * - * http://www.cl.cam.ac.uk/~mgk25/ucs/norm_charmap.c - */ +** The Single Unix Specification function nl_langinfo(CODESET) +** returns the name of the encoding used by the currently selected +** locale: +** +** http://www.opengroup.org/onlinepubs/7908799/xsh/langinfo.h.html +** +** Unfortunately the encoding names are not yet standardized. +** This function knows about the encoding names used on many +** different systems and converts them where possible into +** the corresponding MIME charset name registered in +** +** http://www.iana.org/assignments/character-sets +** +** Please extend it as needed and suggest improvements to the author. +** +** Markus.Kuhn@cl.cam.ac.uk -- 2002-03-11 +** Permission to use, copy, modify, and distribute this software +** for any purpose and without fee is hereby granted. The author +** disclaims all warranties with regard to this software. +** +** Latest version: +** +** http://www.cl.cam.ac.uk/~mgk25/ucs/norm_charmap.c +*/ #include @@ -33,80 +33,86 @@ static char buf[16]; char * norm_charmap(char *name) { - char *p; - - if (!name) - return name; - - /* Many need no remapping, but they are listed here so you - * can see what output to expect, and modify for your needs - * as necessary. */ - if (!strcmp(name, "UTF-8")) - return "UTF-8"; - if (!strcmp(name, "EUC-JP")) - return "EUC-JP"; - if (!strcmp(name, "EUC-KR")) - return "EUC-KR"; - if (!strcmp(name, "EUC-TW")) - return "EUC-TW"; - if (!strcmp(name, "KOI8-R")) - return "KOI8-R"; - if (!strcmp(name, "KOI8-U")) - return "KOI8-U"; - if (!strcmp(name, "GBK")) - return "GBK"; - if (!strcmp(name, "GB2312")) - return "GB2312"; - if (!strcmp(name, "GB18030")) - return "GB18030"; - if (!strcmp(name, "VSCII")) - return "VSCII"; - - /* ASCII comes in many names */ - if (!strcmp(name, "ASCII") || - !strcmp(name, "US-ASCII") || - !strcmp(name, "ANSI_X3.4-1968") || - !strcmp(name, "646") || - !strcmp(name, "ISO646") || - !strcmp(name, "ISO_646.IRV")) - return "US-ASCII"; + char *p; - /* ISO 8859 will be converted to "ISO-8859-x" */ - if ((p = strstr(name, "8859-"))) { - memcpy(buf, "ISO-8859-\0\0", 12); - p += 5; - if (digit(*p)) { - buf[9] = *p++; - if (digit(*p)) buf[10] = *p++; - return buf; - } - } + if (!name) + return name; - /* Windows code pages will be converted to "WINDOWS-12xx" */ - if ((p = strstr(name, "CP12"))) { - memcpy(buf, "WINDOWS-12\0\0", 13); - p += 4; - if (digit(*p)) { - buf[10] = *p++; - if (digit(*p)) buf[11] = *p++; - return buf; - } - } + /* + ** Many need no remapping, but they are listed here so you + ** can see what output to expect, and modify for your needs + ** as necessary. + */ + if (strcmp(name, "UTF-8")==0) + return "UTF-8"; + if (strcmp(name, "EUC-JP")==0) + return "EUC-JP"; + if (strcmp(name, "EUC-KR")==0) + return "EUC-KR"; + if (strcmp(name, "EUC-TW")==0) + return "EUC-TW"; + if (strcmp(name, "KOI8-R")==0) + return "KOI8-R"; + if (strcmp(name, "KOI8-U")==0) + return "KOI8-U"; + if (strcmp(name, "GBK")==0) + return "GBK"; + if (strcmp(name, "GB2312")==0) + return "GB2312"; + if (strcmp(name, "GB18030")==0) + return "GB18030"; + if (strcmp(name, "VSCII")==0) + return "VSCII"; - /* TIS-620 comes in at least the following two forms */ - if (!strcmp(name, "TIS-620") || - !strcmp(name, "TIS620.2533")) - return "ISO-8859-11"; + /* ASCII comes in many names */ + if (strcmp(name, "ASCII")==0 || + strcmp(name, "US-ASCII")==0 || + strcmp(name, "ANSI_X3.4-1968")==0 || + strcmp(name, "646")==0 || + strcmp(name, "ISO646")==0 || + strcmp(name, "ISO_646.IRV")==0) + return "US-ASCII"; - /* For some, uppercase/lowercase might differ */ - if (!strcmp(name, "Big5") || !strcmp(name, "BIG5")) - return "Big5"; - if (!strcmp(name, "Big5HKSCS") || !strcmp(name, "BIG5HKSCS")) - return "Big5HKSCS"; + /* ISO 8859 will be converted to "ISO-8859-x" */ + if ((p = strstr(name, "8859-"))) { + memcpy(buf, "ISO-8859-\0\0", 12); + p += 5; + if (digit(*p)) { + buf[9] = *p++; + if (digit(*p)) + buf[10] = *p++; + return buf; + } + } - /* I don't know of any implementation of nl_langinfo(CODESET) out - * there that returns anything else (and I'm not even certain all of - * the above occur in the wild), but just in case, as a fallback, - * return the unmodified name. */ - return name; + /* Windows code pages will be converted to "WINDOWS-12xx" */ + if ((p = strstr(name, "CP12"))) { + memcpy(buf, "WINDOWS-12\0\0", 13); + p += 4; + if (digit(*p)) { + buf[10] = *p++; + if (digit(*p)) + buf[11] = *p++; + return buf; + } + } + + /* TIS-620 comes in at least the following two forms */ + if (strcmp(name, "TIS-620")==0 || + strcmp(name, "TIS620.2533")==0) + return "ISO-8859-11"; + + /* For some, uppercase/lowercase might differ */ + if (strcmp(name, "Big5")==0 || strcmp(name, "BIG5")==0) + return "Big5"; + if (strcmp(name, "Big5HKSCS")==0 || strcmp(name, "BIG5HKSCS")==0) + return "Big5HKSCS"; + + /* + ** I don't know of any implementation of nl_langinfo(CODESET) out + ** there that returns anything else (and I'm not even certain all of + ** the above occur in the wild), but just in case, as a fallback, + ** return the unmodified name. + */ + return name; }