kanji.c

MC Linux/Unix 终端下文件管理器

		*out++ = junet_kana2;
		shifted = _KJ_KANA;
		break;
	    }
	    *out++ = ((int) *from++) - 0x80;
	} else {
	    switch (shifted) {
	    case _KJ_KANA:
	    case _KJ_KANJI:		/* to ROMAN */
		*out++ = jis_esc;
		*out++ = jis_si1;
		*out++ = jis_si2;
		shifted = _KJ_ROMAN;
		break;
	    }
	    *out++ = *from++;
	}
    }
    switch (shifted) {
    case _KJ_KANA:
    case _KJ_KANJI:			/* to ROMAN */
	*out++ = jis_esc;
	*out++ = jis_si1;
	*out++ = jis_si2;
	break;
    }
    *out = 0;
    if (overwrite) {
	pstrcpy (save, (char *) cvtbuf);
	return save;
    } else {
	return cvtbuf;
    }
}

/*******************************************************************
  HEX <-> SJIS
********************************************************************/
/* ":xx" -> a byte */
static char *hex_to_sj(char *from, BOOL overwrite)
{
    char *sp, *dp;
    
    sp = (char *) from;
    dp = cvtbuf;
    while (*sp) {
	if (*sp == hex_tag && isxdigit((int)sp[1]) && isxdigit((int)sp[2])) {
	    *dp++ = (hex2bin (sp[1])<<4) | (hex2bin (sp[2]));
	    sp += 3;
	} else
	    *dp++ = *sp++;
    }
    *dp = '\0';
    if (overwrite) {
	pstrcpy ((char *) from, (char *) cvtbuf);
	return (char *) from;
    } else {
	return cvtbuf;
    }
}
 
/*******************************************************************
  kanji/kana -> ":xx" 
********************************************************************/
static char *sj_to_hex(char *from, BOOL overwrite)
{
    unsigned char *sp, *dp;
    
    sp = (unsigned char*) from;
    dp = (unsigned char*) cvtbuf;
    while (*sp) {
	if (is_kana(*sp)) {
	    *dp++ = hex_tag;
	    *dp++ = bin2hex (((*sp)>>4)&0x0f);
	    *dp++ = bin2hex ((*sp)&0x0f);
	    sp++;
	} else if (is_shift_jis (*sp) && is_shift_jis2 (sp[1])) {
	    *dp++ = hex_tag;
	    *dp++ = bin2hex (((*sp)>>4)&0x0f);
	    *dp++ = bin2hex ((*sp)&0x0f);
	    sp++;
	    *dp++ = hex_tag;
	    *dp++ = bin2hex (((*sp)>>4)&0x0f);
	    *dp++ = bin2hex ((*sp)&0x0f);
	    sp++;
	} else
	    *dp++ = *sp++;
    }
    *dp = '\0';
    if (overwrite) {
	pstrcpy ((char *) from, (char *) cvtbuf);
	return (char *) from;
    } else {
	return cvtbuf;
    }
}

/*******************************************************************
  CAP <-> SJIS
********************************************************************/
/* ":xx" CAP -> a byte */
static char *cap_to_sj(char *from, BOOL overwrite)
{
    char *sp, *dp;

    sp = (char *) from;
    dp = cvtbuf;
    while (*sp) {
        /*
         * The only change between this and hex_to_sj is here. sj_to_cap only
         * translates characters greater or equal to 0x80 - make sure that here
         * we only do the reverse (that's why the strchr is used rather than
         * isxdigit. Based on fix from [e-mail] (Arthur David Olson).
         */
        if (*sp == hex_tag && (strchr ("89abcdefABCDEF", sp[1]) != NULL) && isxdigit((int)sp[2])) {
            *dp++ = (hex2bin (sp[1])<<4) | (hex2bin (sp[2]));
            sp += 3;
        } else
            *dp++ = *sp++;
    }
    *dp = '\0';
    if (overwrite) {
        pstrcpy ((char *) from, (char *) cvtbuf);
        return (char *) from;
    } else {
        return cvtbuf;
    }
}

/*******************************************************************
  kanji/kana -> ":xx" - CAP format.
********************************************************************/
static char *sj_to_cap(char *from, BOOL overwrite)
{
    unsigned char *sp, *dp;

    sp = (unsigned char*) from;
    dp = (unsigned char*) cvtbuf;
    while (*sp) {
	if (*sp >= 0x80) {
	    *dp++ = hex_tag;
	    *dp++ = bin2hex (((*sp)>>4)&0x0f);
	    *dp++ = bin2hex ((*sp)&0x0f);
	    sp++;
	} else {
	    *dp++ = *sp++;
	}
    }
    *dp = '\0';
    if (overwrite) {
	pstrcpy ((char *) from, (char *) cvtbuf);
	return (char *) from;
    } else {
	return cvtbuf;
    }
}

/*******************************************************************
 sj to sj
********************************************************************/
static char *sj_to_sj(char *from, BOOL overwrite)
{
    if (!overwrite) {
	pstrcpy (cvtbuf, (char *) from);
	return cvtbuf;
    } else {
	return (char *) from;
    }
}

/************************************************************************
 conversion:
 _dos_to_unix		_unix_to_dos
************************************************************************/

static void setup_string_function(int codes)
{
    switch (codes) {
    default:
        _dos_to_unix = dos2unix_format;
        _unix_to_dos = unix2dos_format;
        break;

    case SJIS_CODE:
	_dos_to_unix = sj_to_sj;
	_unix_to_dos = sj_to_sj;
	break;
	
    case EUC_CODE:
	_dos_to_unix = sj_to_euc;
	_unix_to_dos = euc_to_sj;
	break;
	
    case JIS7_CODE:
	_dos_to_unix = sj_to_jis7;
	_unix_to_dos = jis7_to_sj;
	break;

    case JIS8_CODE:
	_dos_to_unix = sj_to_jis8;
	_unix_to_dos = jis8_to_sj;
	break;

    case JUNET_CODE:
	_dos_to_unix = sj_to_junet;
	_unix_to_dos = junet_to_sj;
	break;

    case HEX_CODE:
	_dos_to_unix = sj_to_hex;
	_unix_to_dos = hex_to_sj;
	break;

    case CAP_CODE:
	_dos_to_unix = sj_to_cap;
	_unix_to_dos = cap_to_sj;
	break;
    }
}

/************************************************************************
 Interpret coding system.
************************************************************************/

void interpret_coding_system(char *str)
{
    int codes = UNKNOWN_CODE;
    
    if (strequal (str, "sjis")) {
	codes = SJIS_CODE;
    } else if (strequal (str, "euc")) {
	codes = EUC_CODE;
    } else if (strequal (str, "cap")) {
	codes = CAP_CODE;
	hex_tag = HEXTAG;
    } else if (strequal (str, "hex")) {
	codes = HEX_CODE;
	hex_tag = HEXTAG;
    } else if (!strncasecmp (str, "hex", 3)) {
	codes = HEX_CODE;
	hex_tag = (str[3] ? str[3] : HEXTAG);
    } else if (strequal (str, "j8bb")) {
	codes = JIS8_CODE;
	jis_kso = 'B';
	jis_ksi = 'B';
    } else if (strequal (str, "j8bj") || strequal (str, "jis8")) {
	codes = JIS8_CODE;
	jis_kso = 'B';
	jis_ksi = 'J';
    } else if (strequal (str, "j8bh")) {
	codes = JIS8_CODE;
	jis_kso = 'B';
	jis_ksi = 'H';
    } else if (strequal (str, "j8@b")) {
	codes = JIS8_CODE;
	jis_kso = '@';
	jis_ksi = 'B';
    } else if (strequal (str, "j8@j")) {
	codes = JIS8_CODE;
	jis_kso = '@';
	jis_ksi = 'J';
    } else if (strequal (str, "j8@h")) {
	codes = JIS8_CODE;
	jis_kso = '@';
	jis_ksi = 'H';
    } else if (strequal (str, "j7bb")) {
	codes = JIS7_CODE;
	jis_kso = 'B';
	jis_ksi = 'B';
    } else if (strequal (str, "j7bj") || strequal (str, "jis7")) {
	codes = JIS7_CODE;
	jis_kso = 'B';
	jis_ksi = 'J';
    } else if (strequal (str, "j7bh")) {
	codes = JIS7_CODE;
	jis_kso = 'B';
	jis_ksi = 'H';
    } else if (strequal (str, "j7@b")) {
	codes = JIS7_CODE;
	jis_kso = '@';
	jis_ksi = 'B';
    } else if (strequal (str, "j7@j")) {
	codes = JIS7_CODE;
	jis_kso = '@';
	jis_ksi = 'J';
    } else if (strequal (str, "j7@h")) {
	codes = JIS7_CODE;
	jis_kso = '@';
	jis_ksi = 'H';
    } else if (strequal (str, "jubb")) {
	codes = JUNET_CODE;
	jis_kso = 'B';
	jis_ksi = 'B';
    } else if (strequal (str, "jubj") || strequal (str, "junet")) {
	codes = JUNET_CODE;
	jis_kso = 'B';
	jis_ksi = 'J';
    } else if (strequal (str, "jubh")) {
	codes = JUNET_CODE;
	jis_kso = 'B';
	jis_ksi = 'H';
    } else if (strequal (str, "ju@b")) {
	codes = JUNET_CODE;
	jis_kso = '@';
	jis_ksi = 'B';
    } else if (strequal (str, "ju@j")) {
	codes = JUNET_CODE;
	jis_kso = '@';
	jis_ksi = 'J';
    } else if (strequal (str, "ju@h")) {
	codes = JUNET_CODE;
	jis_kso = '@';
	jis_ksi = 'H';
    }	
    setup_string_function (codes);
}

/*******************************************************************
 Non multibyte char function.
*******************************************************************/
   
static size_t skip_non_multibyte_char(char c)
{
  return 0;
}

/*******************************************************************
 Function that always says a character isn't multibyte.
*******************************************************************/

static BOOL not_multibyte_char_1(char c)
{
  return False;
}

/*******************************************************************
 Function to determine if we are in a multibyte code page.
*******************************************************************/

static BOOL is_multibyte_codepage_val = False;

BOOL is_multibyte_codepage(void)
{
  return is_multibyte_codepage_val;
}

/*******************************************************************
 Setup the function pointers for the functions that are replaced
 when multi-byte codepages are used.

 The dos_to_unix and unix_to_dos function pointers are only
 replaced by setup_string_function called by interpret_coding_system
 above.
*******************************************************************/

void initialize_multibyte_vectors( int client_codepage)
{
  switch( client_codepage )
  {
  case KANJI_CODEPAGE:
    multibyte_strchr = sj_strchr;
    multibyte_strrchr = sj_strrchr;
    multibyte_strstr = sj_strstr;
    multibyte_strtok = sj_strtok;
    _skip_multibyte_char = skip_kanji_multibyte_char;
    is_multibyte_char_1 = is_kanji_multibyte_char_1;
    is_multibyte_codepage_val = True;
    break;
  case HANGUL_CODEPAGE:
    multibyte_strchr = generic_multibyte_strchr;
    multibyte_strrchr = generic_multibyte_strrchr;
    multibyte_strstr = generic_multibyte_strstr;
    multibyte_strtok = generic_multibyte_strtok;
    _skip_multibyte_char = skip_generic_multibyte_char;
    is_multibyte_char_1 = hangul_is_multibyte_char_1;
    is_multibyte_codepage_val = True;
    break;
  case BIG5_CODEPAGE:
    multibyte_strchr = generic_multibyte_strchr;
    multibyte_strrchr = generic_multibyte_strrchr;
    multibyte_strstr = generic_multibyte_strstr;
    multibyte_strtok = generic_multibyte_strtok;
    _skip_multibyte_char = skip_generic_multibyte_char;
    is_multibyte_char_1 = big5_is_multibyte_char_1;
    is_multibyte_codepage_val = True;
    break;
  case SIMPLIFIED_CHINESE_CODEPAGE:
    multibyte_strchr = generic_multibyte_strchr;
    multibyte_strrchr = generic_multibyte_strrchr;
    multibyte_strstr = generic_multibyte_strstr;
    multibyte_strtok = generic_multibyte_strtok;
    _skip_multibyte_char = skip_generic_multibyte_char;
    is_multibyte_char_1 = simpch_is_multibyte_char_1;
    is_multibyte_codepage_val = True;
    break;
  /*
   * Single char size code page.
   */
  default:
    multibyte_strchr = (const char *(*)(const char *, int )) strchr;
    multibyte_strrchr = (const char *(*)(const char *, int )) strrchr;
    multibyte_strstr = (const char *(*)(const char *, const char *)) strstr;
    multibyte_strtok = (char *(*)(char *, const char *)) strtok;
    _skip_multibyte_char = skip_non_multibyte_char;
    is_multibyte_char_1 = not_multibyte_char_1;
    is_multibyte_codepage_val = False;
    break; 
  }
}