gvccp.c

GSview 4.6 PostScript previewer。Ghostscript在MS-Windows, OS/2 and Unix下的图形化接口

 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f,
 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 0x2518, 0x251c, 0x2524,
 0x252c, 0x2534, 0x253c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
 0x2591, 0x2592, 0x2593, 0x2320, 0x25a0, 0x2219, 0x221a, 0x2248,
 0x2264, 0x2265, 0x00a0, 0x2321, 0x00b0, 0x00b2, 0x00b7, 0x00f7,
 0x2550, 0x2551, 0x2552, 0x0451, 0x2553, 0x2554, 0x2555, 0x2556,
 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 0x255e,
 0x255f, 0x2560, 0x2561, 0x0401, 0x2562, 0x2563, 0x2564, 0x2565,
 0x2566, 0x2567, 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x00a9,
 0x044e, 0x0430, 0x0431, 0x0446, 0x0434, 0x0435, 0x0444, 0x0433,
 0x0445, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e,
 0x043f, 0x044f, 0x0440, 0x0441, 0x0442, 0x0443, 0x0436, 0x0432,
 0x044c, 0x044b, 0x0437, 0x0448, 0x044d, 0x0449, 0x0447, 0x044a,
 0x042e, 0x0410, 0x0411, 0x0426, 0x0414, 0x0415, 0x0424, 0x0413,
 0x0425, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e,
 0x041f, 0x042f, 0x0420, 0x0421, 0x0422, 0x0423, 0x0416, 0x0412,
 0x042c, 0x042b, 0x0417, 0x0428, 0x042d, 0x0429, 0x0427, 0x042a,
};

unsigned short cp_none[] = {
 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
};

/**************************************************************/

/* Convert UCS-2 to UTF-8 */
int
ucs2_to_utf8(unsigned char *dest, int destlen,
    const unsigned short *src, int srclen)
{
    int si;
    int di = 0;
    unsigned short uch;
    for (si=0; si<srclen; si++) {
	uch = src[si];
	if ((uch <= 0x7f) && (di+1 <= destlen)) {
	    dest[di++] = (unsigned char)(uch & 0x7f);
	}
	else if ((uch <= 0x7ff) && (di+2 <= destlen)) {
	    dest[di++] = (unsigned char)(0xc0 | ((uch >> 6) & 0x1f));
	    dest[di++] = (unsigned char)(0x80 | (uch & 0x3f));
	}
	else if ((uch <= 0xffff) && (di+3 <= destlen)) {
	    dest[di++] = (unsigned char)(0xe0 | ((uch >> 12) & 0xf));
	    dest[di++] = (unsigned char)(0x80 | ((uch >> 6) & 0x3f));
	    dest[di++] = (unsigned char)(0x80 | (uch & 0x3f));
	}
	else if (di+1 <= destlen) {
	    dest[di++] = '?';
	}
    }
    return di;
}

/* Convert UTF-8 to UCS-2 */
int
utf8_to_ucs2(unsigned short *dest, int destlen,
    const unsigned char *src, int srclen)
{
    int di = 0;
    int si;
    unsigned short uch;
    unsigned int ch;
    unsigned int ch2;
    unsigned int ch3;
    for (si=0; si<srclen; si++) {
	ch = src[si];
	if (di >= destlen)
	    return di;
	uch = '?';
	if ((ch & 0x80) == 0) {
	    uch = (unsigned short)(ch & 0x7f);
	}
	else if (((ch & 0xe0) == 0xc0) && (si+1 < srclen)) {
	    ch2 = src[++si];
	    uch = (unsigned short)(((ch & 0x1f) << 6) | (ch2 & 0x3f));
	}
	else if (((ch & 0xf0) == 0xe0) && (si+2 < srclen)) {
	    ch2 = src[++si];
	    ch3 = src[++si];
	    uch = (unsigned short)(((ch & 0xf) << 12) | ((ch2 & 0x3f) << 6) |
		(ch3 & 0x3f));
	}
	else {
	    /* Doesn't fit in UCS-2 */
	    si++;
	    while ((si < srclen) && ((src[si] & 0xe0) == 0x80))
		si++;
	}
	dest[di++] = uch;
    }
    return di;
}

/* Convert a UCS-2 character to the given codepage */
unsigned char
tocp(const unsigned short *cp, unsigned short uch)
{
    int i;
    if (uch <= 0x7f)	/* assume that first 128 characters are ASCII */
	return (unsigned char)uch;
    else {
	for (i=128; i<256; i++) {
	    if (uch == cp[i])
		return (unsigned char)i;
	}
    }
    return '?';
}

/* Convert UTF-8 to the given codepage */
int
utf8_to_cp(const unsigned short *cp, 
    unsigned char *dest, int destlen,
    const unsigned char *src, int srclen)
{
    int di = 0;
    int si;
    unsigned short uch;
    unsigned int ch;
    unsigned int ch2;
    unsigned int ch3;
    for (si=0; si<srclen; si++) {
	ch = src[si];
	if (di >= destlen)
	    return di;
	uch = '?';
	if ((ch & 0x80) == 0) {
	    uch = (unsigned short)(ch & 0x7f);
	}
	else if (((ch & 0xe0) == 0xc0) && (si+1 < srclen)) {
	    ch2 = src[++si];
	    uch = (unsigned short)(((ch & 0x1f) << 6) | (ch2 & 0x3f));
	}
	else if (((ch & 0xf0) == 0xe0) && (si+2 < srclen)) {
	    ch2 = src[++si];
	    ch3 = src[++si];
	    uch = (unsigned short)(((ch & 0xf) << 12) | ((ch2 & 0x3f) << 6) |
		(ch3 & 0x3f));
	}
	else {
	    /* Doesn't fit in UCS-2 */
	    si++;
	    while ((si < srclen) && ((src[si] & 0xe0) == 0x80))
		si++;
	}
	dest[di++] = tocp(cp, uch);
    }
    return di;
}


/**************************************************************/

codepage_t cptable[] = {
    {"437", "OEM US English", cp437, 547, 0, 0},
    {"850", "OEM Western Europe", cp850, 850, 0, 0},
    {"852", "OEM Eastern Europe", cp852, 852, 0, 0},
    {"866", "OEM Russian", cp866, 866, 0, 0},
    {"869", "OEM Modern Greek", cp869, 869, 0, 0},
    {"1250", "Windows Eastern Europe", cp1250, 1250, 0, 0},
    {"1251", "Windows Cyrillic", cp1251, 1251, 0, 0},
    {"1252", "Windows Western Europe", cp1252, 1252, 0, 0},
    {"1253", "Windows Greek", cp1253, 1253, 0, 0},
    {"8859-5", "ISO 8859-5 Cyrllic", cp28595, 28595, 0, 0},
    {"8859-7", "ISO 8859-7 Greek", cp28597, 28597, 0, 0},
    {"KOI8-R", "Russian KOI8", cp20866, 20866, 0, 0},
    {"UCS-2", "Unicode UCS-2", cp_none, 0, 1, 0},
    {"UTF-8", "Unicode UTF-8", cp_none, 65001, 0, 1},
    {NULL, NULL, NULL, 0, 1},
};

const unsigned short *
find_cp(const char *name)
{
    int i;
    for (i=0; cptable[i].name; i++) {
	if (strcmp(name, cptable[i].name)==0)
	    return cptable[i].table;
    }
    return NULL;
}