+++ /dev/null
-/*\r
- * charset.h - header file for general character set conversion\r
- * routines.\r
- */\r
-\r
-#ifndef charset_charset_h\r
-#define charset_charset_h\r
-\r
-#include <stddef.h>\r
-\r
-/*\r
- * Enumeration that lists all the multibyte or single-byte\r
- * character sets known to this library.\r
- */\r
-typedef enum {\r
- CS_NONE, /* used for reporting errors, etc */\r
- CS_ISO8859_1,\r
- CS_ISO8859_1_X11, /* X font encoding with VT100 glyphs */\r
- CS_ISO8859_2,\r
- CS_ISO8859_3,\r
- CS_ISO8859_4,\r
- CS_ISO8859_5,\r
- CS_ISO8859_6,\r
- CS_ISO8859_7,\r
- CS_ISO8859_8,\r
- CS_ISO8859_9,\r
- CS_ISO8859_10,\r
- CS_ISO8859_11,\r
- CS_ISO8859_13,\r
- CS_ISO8859_14,\r
- CS_ISO8859_15,\r
- CS_ISO8859_16,\r
- CS_CP437,\r
- CS_CP850,\r
- CS_CP866,\r
- CS_CP1250,\r
- CS_CP1251,\r
- CS_CP1252,\r
- CS_CP1253,\r
- CS_CP1254,\r
- CS_CP1255,\r
- CS_CP1256,\r
- CS_CP1257,\r
- CS_CP1258,\r
- CS_KOI8_R,\r
- CS_KOI8_U,\r
- CS_MAC_ROMAN,\r
- CS_MAC_TURKISH,\r
- CS_MAC_CROATIAN,\r
- CS_MAC_ICELAND,\r
- CS_MAC_ROMANIAN,\r
- CS_MAC_GREEK,\r
- CS_MAC_CYRILLIC,\r
- CS_MAC_THAI,\r
- CS_MAC_CENTEURO,\r
- CS_MAC_SYMBOL,\r
- CS_MAC_DINGBATS,\r
- CS_MAC_ROMAN_OLD,\r
- CS_MAC_CROATIAN_OLD,\r
- CS_MAC_ICELAND_OLD,\r
- CS_MAC_ROMANIAN_OLD,\r
- CS_MAC_GREEK_OLD,\r
- CS_MAC_CYRILLIC_OLD,\r
- CS_MAC_UKRAINE,\r
- CS_MAC_VT100,\r
- CS_MAC_VT100_OLD,\r
- CS_VISCII,\r
- CS_HP_ROMAN8,\r
- CS_DEC_MCS,\r
- CS_UTF8\r
-} charset_t;\r
-\r
-typedef struct {\r
- unsigned long s0;\r
-} charset_state;\r
-\r
-/*\r
- * Routine to convert a MB/SB character set to Unicode.\r
- * \r
- * This routine accepts some number of bytes, updates a state\r
- * variable, and outputs some number of Unicode characters. There\r
- * are no guarantees. You can't even guarantee that at most one\r
- * Unicode character will be output per byte you feed in; for\r
- * example, suppose you're reading UTF-8, you've seen E1 80, and\r
- * then you suddenly see FE. Now you need to output _two_ error\r
- * characters - one for the incomplete sequence E1 80, and one for\r
- * the completely invalid UTF-8 byte FE.\r
- * \r
- * Returns the number of wide characters output; will never output\r
- * more than the size of the buffer (as specified on input).\r
- * Advances the `input' pointer and decrements `inlen', to indicate\r
- * how far along the input string it got.\r
- * \r
- * The sequence of `errlen' wide characters pointed to by `errstr'\r
- * will be used to indicate a conversion error. If `errstr' is\r
- * NULL, `errlen' will be ignored, and the library will choose\r
- * something sensible to do on its own. For Unicode, this will be\r
- * U+FFFD (REPLACEMENT CHARACTER).\r
- */\r
-\r
-int charset_to_unicode(char **input, int *inlen, wchar_t *output, int outlen,\r
- int charset, charset_state *state,\r
- const wchar_t *errstr, int errlen);\r
-\r
-/*\r
- * Routine to convert Unicode to an MB/SB character set.\r
- * \r
- * This routine accepts some number of Unicode characters, updates\r
- * a state variable, and outputs some number of bytes.\r
- * \r
- * Returns the number of bytes characters output; will never output\r
- * more than the size of the buffer (as specified on input), and\r
- * will never output a partial MB character. Advances the `input'\r
- * pointer and decrements `inlen', to indicate how far along the\r
- * input string it got.\r
- * \r
- * The sequence of `errlen' characters pointed to by `errstr' will\r
- * be used to indicate a conversion error. If `errstr' is NULL,\r
- * `errlen' will be ignored, and the library will choose something\r
- * sensible to do on its own (which will vary depending on the\r
- * output charset).\r
- */\r
-\r
-int charset_from_unicode(wchar_t **input, int *inlen, char *output, int outlen,\r
- int charset, charset_state *state,\r
- const char *errstr, int errlen);\r
-\r
-/*\r
- * Convert X11 encoding names to and from our charset identifiers.\r
- */\r
-const char *charset_to_xenc(int charset);\r
-int charset_from_xenc(const char *name);\r
-\r
-/*\r
- * Convert MIME encoding names to and from our charset identifiers.\r
- */\r
-const char *charset_to_mimeenc(int charset);\r
-int charset_from_mimeenc(const char *name);\r
-\r
-/*\r
- * Convert our own encoding names to and from our charset\r
- * identifiers.\r
- */\r
-const char *charset_to_localenc(int charset);\r
-int charset_from_localenc(const char *name);\r
-int charset_localenc_nth(int n);\r
-\r
-/*\r
- * Convert Mac OS script/region/font to our charset identifiers.\r
- */\r
-int charset_from_macenc(int script, int region, int sysvers,\r
- const char *fontname);\r
-\r
-#endif /* charset_charset_h */\r
OSDN Git Service
