winucs.c

来自「putty」· C语言 代码 · 共 1,252 行 · 第 1/4 页

    0x0018, 0x1EF8, 0x001a, 0x001b, 0x001c, 0x001d, 0x1EF4, 0x001f,
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
    0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
    0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
    0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,
    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,
    0x1EA0, 0x1EAE, 0x1EB0, 0x1EB6, 0x1EA4, 0x1EA6, 0x1EA8, 0x1EAC,
    0x1EBC, 0x1EB8, 0x1EBE, 0x1EC0, 0x1EC2, 0x1EC4, 0x1EC6, 0x1ED0,
    0x1ED2, 0x1ED4, 0x1ED6, 0x1ED8, 0x1EE2, 0x1EDA, 0x1EDC, 0x1EDE,
    0x1ECA, 0x1ECE, 0x1ECC, 0x1EC8, 0x1EE6, 0x0168, 0x1EE4, 0x1EF2,
    0x00D5, 0x1EAF, 0x1EB1, 0x1EB7, 0x1EA5, 0x1EA7, 0x1EA8, 0x1EAD,
    0x1EBD, 0x1EB9, 0x1EBF, 0x1EC1, 0x1EC3, 0x1EC5, 0x1EC7, 0x1ED1,
    0x1ED3, 0x1ED5, 0x1ED7, 0x1EE0, 0x01A0, 0x1ED9, 0x1EDD, 0x1EDF,
    0x1ECB, 0x1EF0, 0x1EE8, 0x1EEA, 0x1EEC, 0x01A1, 0x1EDB, 0x01AF,
    0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x1EA2, 0x0102, 0x1EB3, 0x1EB5,
    0x00C8, 0x00C9, 0x00CA, 0x1EBA, 0x00CC, 0x00CD, 0x0128, 0x1EF3,
    0x0110, 0x1EE9, 0x00D2, 0x00D3, 0x00D4, 0x1EA1, 0x1EF7, 0x1EEB,
    0x1EED, 0x00D9, 0x00DA, 0x1EF9, 0x1EF5, 0x00DD, 0x1EE1, 0x01B0,
    0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x1EA3, 0x0103, 0x1EEF, 0x1EAB,
    0x00E8, 0x00E9, 0x00EA, 0x1EBB, 0x00EC, 0x00ED, 0x0129, 0x1EC9,
    0x0111, 0x1EF1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x1ECF, 0x1ECD,
    0x1EE5, 0x00F9, 0x00FA, 0x0169, 0x1EE7, 0x00FD, 0x1EE3, 0x1EEE
};

static const wchar_t dec_mcs[] = {
    0x00A0, 0x00A1, 0x00A2, 0x00A3, 0xFFFD, 0x00A5, 0xFFFD, 0x00A7,
    0x00A4, 0x00A9, 0x00AA, 0x00AB, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0xFFFD, 0x00B5, 0x00B6, 0x00B7,
    0xFFFD, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0xFFFD, 0x00BF,
    0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
    0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
    0xFFFD, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x0152,
    0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x0178, 0xFFFD, 0x00DF,
    0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
    0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
    0xFFFD, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x0153,
    0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FF, 0xFFFD, 0xFFFD
};

/* Mazovia (Polish) aka CP620
 * from "Mazowia to Unicode table", 04/24/96, Mikolaj Jedrzejak */
static const wchar_t mazovia[] = {
    /* Code point 0x9B is "zloty" symbol (zŽ), which is not
     *   widely used and for which there is no Unicode equivalent.
     * One reference shows 0xA8 as U+00A7 SECTION SIGN, but we're
     *   told that's incorrect. */
    0x00C7, 0x00FC, 0x00E9, 0x00E2, 0x00E4, 0x00E0, 0x0105, 0x00E7,
    0x00EA, 0x00EB, 0x00E8, 0x00EF, 0x00EE, 0x0107, 0x00C4, 0x0104,
    0x0118, 0x0119, 0x0142, 0x00F4, 0x00F6, 0x0106, 0x00FB, 0x00F9,
    0x015a, 0x00D6, 0x00DC, 0xFFFD, 0x0141, 0x00A5, 0x015b, 0x0192,
    0x0179, 0x017b, 0x00F3, 0x00d3, 0x0144, 0x0143, 0x017a, 0x017c,
    0x00BF, 0x2310, 0x00AC, 0x00BD, 0x00BC, 0x00A1, 0x00AB, 0x00BB,
    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
    0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,
    0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F,
    0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,
    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B,
    0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,
    0x03B1, 0x00DF, 0x0393, 0x03C0, 0x03A3, 0x03C3, 0x00B5, 0x03C4,
    0x03A6, 0x0398, 0x03A9, 0x03B4, 0x221E, 0x03C6, 0x03B5, 0x2229,
    0x2261, 0x00B1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00F7, 0x2248,
    0x00B0, 0x2219, 0x00B7, 0x221A, 0x207F, 0x00B2, 0x25A0, 0x00A0
};

struct cp_list_item {
    char *name;
    int codepage;
    int cp_size;
    const wchar_t *cp_table;
};

static const struct cp_list_item cp_list[] = {
    {"ISO-8859-1:1998 (Latin-1, West Europe)", 0, 96, iso_8859_1},
    {"ISO-8859-2:1999 (Latin-2, East Europe)", 0, 96, iso_8859_2},
    {"ISO-8859-3:1999 (Latin-3, South Europe)", 0, 96, iso_8859_3},
    {"ISO-8859-4:1998 (Latin-4, North Europe)", 0, 96, iso_8859_4},
    {"ISO-8859-5:1999 (Latin/Cyrillic)", 0, 96, iso_8859_5},
    {"ISO-8859-6:1999 (Latin/Arabic)", 0, 96, iso_8859_6},
    {"ISO-8859-7:1987 (Latin/Greek)", 0, 96, iso_8859_7},
    {"ISO-8859-8:1999 (Latin/Hebrew)", 0, 96, iso_8859_8},
    {"ISO-8859-9:1999 (Latin-5, Turkish)", 0, 96, iso_8859_9},
    {"ISO-8859-10:1998 (Latin-6, Nordic)", 0, 96, iso_8859_10},
    {"ISO-8859-11:2001 (Latin/Thai)", 0, 96, iso_8859_11},
    {"ISO-8859-13:1998 (Latin-7, Baltic)", 0, 96, iso_8859_13},
    {"ISO-8859-14:1998 (Latin-8, Celtic)", 0, 96, iso_8859_14},
    {"ISO-8859-15:1999 (Latin-9, \"euro\")", 0, 96, iso_8859_15},
    {"ISO-8859-16:2001 (Latin-10, Balkan)", 0, 96, iso_8859_16},

    {"UTF-8", CP_UTF8},

    {"KOI8-U", 0, 128, koi8_u},
    {"KOI8-R", 20866},
    {"HP-ROMAN8", 0, 96, roman8},
    {"VSCII", 0, 256, vscii},
    {"DEC-MCS", 0, 96, dec_mcs},

    {"Win1250 (Central European)", 1250},
    {"Win1251 (Cyrillic)", 1251},
    {"Win1252 (Western)", 1252},
    {"Win1253 (Greek)", 1253},
    {"Win1254 (Turkish)", 1254},
    {"Win1255 (Hebrew)", 1255},
    {"Win1256 (Arabic)", 1256},
    {"Win1257 (Baltic)", 1257},
    {"Win1258 (Vietnamese)", 1258},

    {"CP437", 437},
    {"CP620 (Mazovia)", 0, 128, mazovia},
    {"CP819", 28591},
    {"CP878", 20866},

    {"Use font encoding", -1},

    {0, 0}
};

static void link_font(WCHAR * line_tbl, WCHAR * font_tbl, WCHAR attr);

void init_ucs(Config *cfg, struct unicode_data *ucsdata)
{
    int i, j;
    int used_dtf = 0;
    char tbuf[256];

    for (i = 0; i < 256; i++)
	tbuf[i] = i;

    /* Decide on the Line and Font codepages */
    ucsdata->line_codepage = decode_codepage(cfg->line_codepage);

    if (ucsdata->font_codepage <= 0) { 
	ucsdata->font_codepage=0; 
	ucsdata->dbcs_screenfont=0; 
    }

    if (cfg->vtmode == VT_OEMONLY) {
	ucsdata->font_codepage = 437;
	ucsdata->dbcs_screenfont = 0;
	if (ucsdata->line_codepage <= 0)
	    ucsdata->line_codepage = GetACP();
    } else if (ucsdata->line_codepage <= 0)
	ucsdata->line_codepage = ucsdata->font_codepage;

    /* Collect screen font ucs table */
    if (ucsdata->dbcs_screenfont || ucsdata->font_codepage == 0) {
	get_unitab(ucsdata->font_codepage, ucsdata->unitab_font, 2);
	for (i = 128; i < 256; i++)
	    ucsdata->unitab_font[i] = (WCHAR) (CSET_ACP + i);
    } else {
	get_unitab(ucsdata->font_codepage, ucsdata->unitab_font, 1);

	/* CP437 fonts are often broken ... */
	if (ucsdata->font_codepage == 437)
	    ucsdata->unitab_font[0] = ucsdata->unitab_font[255] = 0xFFFF;
    }
    if (cfg->vtmode == VT_XWINDOWS)
	memcpy(ucsdata->unitab_font + 1, unitab_xterm_std,
	       sizeof(unitab_xterm_std));

    /* Collect OEMCP ucs table */
    get_unitab(CP_OEMCP, ucsdata->unitab_oemcp, 1);

    /* Collect CP437 ucs table for SCO acs */
    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS)
	memcpy(ucsdata->unitab_scoacs, ucsdata->unitab_oemcp,
	       sizeof(ucsdata->unitab_scoacs));
    else
	get_unitab(437, ucsdata->unitab_scoacs, 1);

    /* Collect line set ucs table */
    if (ucsdata->line_codepage == ucsdata->font_codepage &&
	(ucsdata->dbcs_screenfont ||
	 cfg->vtmode == VT_POORMAN || ucsdata->font_codepage==0)) {

	/* For DBCS and POOR fonts force direct to font */
	used_dtf = 1;
	for (i = 0; i < 32; i++)
	    ucsdata->unitab_line[i] = (WCHAR) i;
	for (i = 32; i < 256; i++)
	    ucsdata->unitab_line[i] = (WCHAR) (CSET_ACP + i);
	ucsdata->unitab_line[127] = (WCHAR) 127;
    } else {
	get_unitab(ucsdata->line_codepage, ucsdata->unitab_line, 0);
    }

#if 0
    debug(
	  ("Line cp%d, Font cp%d%s\n", ucsdata->line_codepage,
	   ucsdata->font_codepage, ucsdata->dbcs_screenfont ? " DBCS" : ""));

    for (i = 0; i < 256; i += 16) {
	for (j = 0; j < 16; j++) {
	    debug(("%04x%s", ucsdata->unitab_line[i + j], j == 15 ? "" : ","));
	}
	debug(("\n"));
    }
#endif

    /* VT100 graphics - NB: Broken for non-ascii CP's */
    memcpy(ucsdata->unitab_xterm, ucsdata->unitab_line,
	   sizeof(ucsdata->unitab_xterm));
    memcpy(ucsdata->unitab_xterm + '`', unitab_xterm_std,
	   sizeof(unitab_xterm_std));
    ucsdata->unitab_xterm['_'] = ' ';

    /* Generate UCS ->line page table. */
    if (ucsdata->uni_tbl) {
	for (i = 0; i < 256; i++)
	    if (ucsdata->uni_tbl[i])
		sfree(ucsdata->uni_tbl[i]);
	sfree(ucsdata->uni_tbl);
	ucsdata->uni_tbl = 0;
    }
    if (!used_dtf) {
	for (i = 0; i < 256; i++) {
	    if (DIRECT_CHAR(ucsdata->unitab_line[i]))
		continue;
	    if (DIRECT_FONT(ucsdata->unitab_line[i]))
		continue;
	    if (!ucsdata->uni_tbl) {
		ucsdata->uni_tbl = snewn(256, char *);
		memset(ucsdata->uni_tbl, 0, 256 * sizeof(char *));
	    }
	    j = ((ucsdata->unitab_line[i] >> 8) & 0xFF);
	    if (!ucsdata->uni_tbl[j]) {
		ucsdata->uni_tbl[j] = snewn(256, char);
		memset(ucsdata->uni_tbl[j], 0, 256 * sizeof(char));
	    }
	    ucsdata->uni_tbl[j][ucsdata->unitab_line[i] & 0xFF] = i;
	}
    }

    /* Find the line control characters. */
    for (i = 0; i < 256; i++)
	if (ucsdata->unitab_line[i] < ' '
	    || (ucsdata->unitab_line[i] >= 0x7F && 
		ucsdata->unitab_line[i] < 0xA0))
	    ucsdata->unitab_ctrl[i] = i;
	else
	    ucsdata->unitab_ctrl[i] = 0xFF;

    /* Generate line->screen direct conversion links. */
    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS)
	link_font(ucsdata->unitab_scoacs, ucsdata->unitab_oemcp, CSET_OEMCP);

    link_font(ucsdata->unitab_line, ucsdata->unitab_font, CSET_ACP);
    link_font(ucsdata->unitab_scoacs, ucsdata->unitab_font, CSET_ACP);
    link_font(ucsdata->unitab_xterm, ucsdata->unitab_font, CSET_ACP);

    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS) {
	link_font(ucsdata->unitab_line, ucsdata->unitab_oemcp, CSET_OEMCP);
	link_font(ucsdata->unitab_xterm, ucsdata->unitab_oemcp, CSET_OEMCP);
    }

    if (ucsdata->dbcs_screenfont &&
	ucsdata->font_codepage != ucsdata->line_codepage) {
	/* F***ing Microsoft fonts, Japanese and Korean codepage fonts
	 * have a currency symbol at 0x5C but their unicode value is 
	 * still given as U+005C not the correct U+00A5. */
	ucsdata->unitab_line['\\'] = CSET_OEMCP + '\\';
    }

    /* Last chance, if !unicode then try poorman links. */
    if (cfg->vtmode != VT_UNICODE) {
	static const char poorman_scoacs[] = 
	    "CueaaaaceeeiiiAAE**ooouuyOUc$YPsaiounNao?++**!<>###||||++||++++++--|-+||++--|-+----++++++++##||#aBTPEsyt******EN=+><++-=... n2* ";
	static const char poorman_latin1[] =
	    " !cL.Y|S\"Ca<--R~o+23'u|.,1o>///?AAAAAAACEEEEIIIIDNOOOOOxOUUUUYPBaaaaaaaceeeeiiiionooooo/ouuuuypy";
	static const char poorman_vt100[] = "*#****o~**+++++-----++++|****L.";

	for (i = 160; i < 256; i++)
	    if (!DIRECT_FONT(ucsdata->unitab_line[i]) &&
		ucsdata->unitab_line[i] >= 160 &&
		ucsdata->unitab_line[i] < 256) {
		ucsdata->unitab_line[i] =
		    (WCHAR) (CSET_ACP +
			     poorman_latin1[ucsdata->unitab_line[i] - 160]);
	    }
	for (i = 96; i < 127; i++)
	    if (!DIRECT_FONT(ucsdata->unitab_xterm[i]))
		ucsdata->unitab_xterm[i] =
	    (WCHAR) (CSET_ACP + poorman_vt100[i - 96]);
	for(i=128;i<256;i++) 
	    if (!DIRECT_FONT(ucsdata->unitab_scoacs[i]))
		ucsdata->unitab_scoacs[i] = 
		    (WCHAR) (CSET_ACP + poorman_scoacs[i - 128]);
    }
}

static void link_font(WCHAR * line_tbl, WCHAR * font_tbl, WCHAR attr)
{
    int font_index, line_index, i;
    for (line_index = 0; line_index < 256; line_index++) {
	if (DIRECT_FONT(line_tbl[line_index]))
	    continue;
	for(i = 0; i < 256; i++) {
	    font_index = ((32 + i) & 0xFF);
	    if (line_tbl[line_index] == font_tbl[font_index]) {
		line_tbl[line_index] = (WCHAR) (attr + font_index);
		break;
	    }
	}
    }
}

wchar_t xlat_uskbd2cyrllic(int ch)