charset.c

有了操作系统、TCP/IP协议栈、文件系统

    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-6"))
        return 0;

    if (strstr (name, "ARABIC"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_6_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar >= 0xC1 && *mchar <= 0xF2) {
        return  *mchar - 0xC1 + 0x0621;
    }
    else {
        switch (*mchar) {
            case 0xAC:
                return 0x060C;
            case 0xBB:
                return 0x061B;
            case 0xBF:
                return 0x061F;
        }

        return (unsigned short) (*mchar);
    }
}
#endif

static CHARSETOPS CharsetOps_iso8859_6 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_6,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_6_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_6_conv_to_uc16
#endif
};

#endif /* _ARABIC_SUPPORT */

#ifdef _GREEK_SUPPORT

/************************* ISO8859-7 Specific Operations **********************/
static int iso8859_7_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-7"))
        return 0;

    if (strstr (name, "GREEK"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_7_unicode_map [] =
{
    0x2018, 0x2019, 0x00A3,
    0x00A4, 0x00A5, 0x00A6,
    0x00A7, 0x00A8, 0x00A9,
    0x00AA, 0x00AB, 0x00AC,
    0x00AD, 0x00AE, 0x2015,
    0x00B0, 0x00B1, 0x00B2,
    0x00B3, 0x0384, 0x0385,
    0x0386, 0x00B7, 0x0388,
    0x0389, 0x038A, 0x00BB,
    0x038C, 0x00BD
};

static unsigned short iso8859_7_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar >= 0xBE && *mchar <= 0xFE) {
        return  *mchar - 0xBE + 0x038E;
    }
    else if (*mchar >= 0xA1 && *mchar <= 0xBD) {
        return iso8859_7_unicode_map [*mchar - 0xA1];
    }
    else {
        return (unsigned short) (*mchar);
    }
}
#endif

static CHARSETOPS CharsetOps_iso8859_7 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_7,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_7_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_7_conv_to_uc16
#endif
};

#endif /* _GREEK_SUPPORT */

#ifdef _HEBREW_SUPPORT

/************************* ISO8859-8 Specific Operations **********************/
static int iso8859_8_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-8"))
        return 0;

    if (strstr (name, "HEBREW"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_8_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar >= 0xE0 && *mchar <= 0xFA) {
        return  *mchar - 0xE0 + 0x05D0;
    }
    else {
        switch (*mchar) {
            case 0xAA:
                return 0x00D7;
            case 0xBA:
                return 0x00F7;
            case 0xDF:
                return 0x2017;
            case 0xFD:
                return 0x200E;
            case 0xFE:
                return 0x200F;
        }
        return (unsigned short) (*mchar);
    }
}
#endif

static CHARSETOPS CharsetOps_iso8859_8 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_8,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_8_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_8_conv_to_uc16
#endif
};

#endif /* _GREEK_SUPPORT */

#ifdef _LATIN5_SUPPORT

/************************* ISO8859-9 Specific Operations **********************/
static int iso8859_9_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-9"))
        return 0;

    if (strstr (name, "LATIN5"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_9_conv_to_uc16 (const unsigned char* mchar, int len)
{
    switch (*mchar) {
        case 0xD0:
                return 0x011E;
        case 0xDD:
                return 0x0130;
        case 0xDE:
                return 0x015E;
        case 0xF0:
                return 0x011F;
        case 0xFD:
                return 0x0131;
        case 0xFE:
                return 0x015F;
    }

    return (unsigned short) (*mchar);
}
#endif

static CHARSETOPS CharsetOps_iso8859_9 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_9,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_9_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_9_conv_to_uc16
#endif
};

#endif /* _LATIN5_SUPPORT */

#ifdef _LATIN6_SUPPORT

/************************* ISO8859-10 Specific Operations **********************/
static int iso8859_10_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-10"))
        return 0;

    if (strstr (name, "LATIN6"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_10_unicode_map [] =
{
    0x0104, 0x0112, 0x0122,
    0x012A, 0x0128, 0x0136,
    0x00A7, 0x013B, 0x0110,
    0x0160, 0x0166, 0x017D,
    0x00AD, 0x016A, 0x014A,
    0x00B0, 0x0105, 0x0113,
    0x0123, 0x012B, 0x0129,
    0x0137, 0x00B7, 0x013C,
    0x0111, 0x0161, 0x0167,
    0x017E, 0x2015, 0x016B,
    0x014B, 0x0100, 0x00C1,
    0x00C2, 0x00C3, 0x00C4,
    0x00C5, 0x00C6, 0x012E,
    0x010C, 0x00C9, 0x0118,
    0x00CB, 0x0116, 0x00CD,
    0x00CE, 0x00CF, 0x00D0,
    0x0145, 0x014C, 0x00D3,
    0x00D4, 0x00D5, 0x00D6,
    0x0168, 0x00D8, 0x0172,
    0x00DA, 0x00DB, 0x00DC,
    0x00DD, 0x00DE, 0x00DF,
    0x0101, 0x00E1, 0x00E2,
    0x00E3, 0x00E4, 0x00E5,
    0x00E6, 0x012F, 0x010D,
    0x00E9, 0x0119, 0x00EB,
    0x0117, 0x00ED, 0x00EE,
    0x00EF, 0x00F0, 0x0146,
    0x014D, 0x00F3, 0x00F4,
    0x00F5, 0x00F6, 0x0169,
    0x00F8, 0x0173, 0x00FA,
    0x00FB, 0x00FC, 0x00FD,
    0x00FE, 0x0138
};

static unsigned short iso8859_10_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar < 0xA1)
        return (unsigned short) (*mchar);
    else
        return iso8859_10_unicode_map [*mchar - 0xA1];
}
#endif

static CHARSETOPS CharsetOps_iso8859_10 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_10,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_10_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_10_conv_to_uc16
#endif
};

#endif /* _LATIN6_SUPPORT */

#ifdef _THAI_SUPPORT

/************************* ISO8859-11 Specific Operations **********************/
static int iso8859_11_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-11"))
        return 0;

    if (strstr (name, "TIS") && strstr (name, "620"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_11_unicode_map [] =
{
    0x0E01, 0x0E02, 0x0E03,
    0x0E04, 0x0E05, 0x0E06,
    0x0E07, 0x0E08, 0x0E09,
    0x0E0A, 0x0E0B, 0x0E0C,
    0x0E0D, 0x0E0E, 0x0E0F,
    0x0E10, 0x0E11, 0x0E12,
    0x0E13, 0x0E14, 0x0E15,
    0x0E16, 0x0E17, 0x0E18,
    0x0E19, 0x0E1A, 0x0E1B,
    0x0E1C, 0x0E1D, 0x0E1E,
    0x0E1F, 0x0E20, 0x0E21,
    0x0E22, 0x0E23, 0x0E24,
    0x0E25, 0x0E26, 0x0E27,
    0x0E28, 0x0E29, 0x0E2A,
    0x0E2B, 0x0E2C, 0x0E2D,
    0x0E2E, 0x0E2F, 0x0E30,
    0x0E31, 0x0E32, 0x0E33,
    0x0E34, 0x0E35, 0x0E36,
    0x0E37, 0x0E38, 0x0E39,
    0x0E3A, 0x00DB, 0x00DC,
    0x00DD, 0x00DE, 0x0E3F,
    0x0E40, 0x0E41, 0x0E42,
    0x0E43, 0x0E44, 0x0E45,
    0x0E46, 0x0E47, 0x0E48,
    0x0E49, 0x0E4A, 0x0E4B,
    0x0E4C, 0x0E4D, 0x0E4E,
    0x0E4F, 0x0E50, 0x0E51,
    0x0E52, 0x0E53, 0x0E54,
    0x0E55, 0x0E56, 0x0E57,
    0x0E58, 0x0E59, 0x0E5A,
    0x0E5B, 0x00FC, 0x00FD,
    0x00FE, 0x00FF
};

static unsigned short iso8859_11_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar < 0xA1)
        return (unsigned short) (*mchar);
    else
        return iso8859_11_unicode_map [*mchar - 0xA1];
}
#endif

static CHARSETOPS CharsetOps_iso8859_11 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_11,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_11_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_11_conv_to_uc16
#endif
};

#endif /* _THAI_SUPPORT */

#ifdef _LATIN7_SUPPORT

/************************* ISO8859-13 Specific Operations **********************/
static int iso8859_13_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-13"))
        return 0;

    if (strstr (name, "LATIN7"))
        return 0;

    return 1;
}

#ifdef _UNICODE_SUPPORT
static unsigned short iso8859_13_unicode_map [] =
{
    0x201D, 0x00A2, 0x00A3,
    0x00A4, 0x201E, 0x00A6,
    0x00A7, 0x00D8, 0x00A9,
    0x0156, 0x00AB, 0x00AC,
    0x00AD, 0x00AE, 0x00C6,
    0x00B0, 0x00B1, 0x00B2,
    0x00B3, 0x201C, 0x00B5,
    0x00B6, 0x00B7, 0x00F8,
    0x00B9, 0x0157, 0x00BB,
    0x00BC, 0x00BD, 0x00BE,
    0x00E6, 0x0104, 0x012E,
    0x0100, 0x0106, 0x00C4,
    0x00C5, 0x0118, 0x0112,
    0x010C, 0x00C9, 0x0179,
    0x0116, 0x0122, 0x0136,
    0x012A, 0x013B, 0x0160,
    0x0143, 0x0145, 0x00D3,
    0x014C, 0x00D5, 0x00D6,
    0x00D7, 0x0172, 0x0141,
    0x015A, 0x016A, 0x00DC,
    0x017B, 0x017D, 0x00DF,
    0x0105, 0x012F, 0x0101,
    0x0107, 0x00E4, 0x00E5,
    0x0119, 0x0113, 0x010D,
    0x00E9, 0x017A, 0x0117,
    0x0123, 0x0137, 0x012B,
    0x013C, 0x0161, 0x0144,
    0x0146, 0x00F3, 0x014D,
    0x00F5, 0x00F6, 0x00F7,
    0x0173, 0x0142, 0x015B,
    0x016B, 0x00FC, 0x017C,
    0x017E, 0x2019
};

static unsigned short iso8859_13_conv_to_uc16 (const unsigned char* mchar, int len)
{
    if (*mchar < 0xA1)
        return (unsigned short) (*mchar);
    else
        return iso8859_13_unicode_map [*mchar - 0xA1];
}
#endif

static CHARSETOPS CharsetOps_iso8859_13 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_13,
    {' '},
    sb_len_first_char,
    sb_char_offset,
    sb_nr_chars_in_str,
    iso8859_13_is_this_charset,
    sb_len_first_substr,
    sb_get_next_word,
    sb_pos_first_char,
#ifdef _UNICODE_SUPPORT
    iso8859_13_conv_to_uc16
#endif
};

#endif /* _LATIN7_SUPPORT */

#ifdef _LATIN8_SUPPORT

/************************* ISO8859-14 Specific Operations **********************/
static int iso8859_14_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859-14"))
        return 0;

    if (strstr (name, "LATIN8"))
        return 0;