X-Git-Url: https://git.distorted.org.uk/~mdw/sgt/putty/blobdiff_plain/5def752285da767c159c1ef88fe7f927dc5286f2..8772ac697da9af645ce4ce9d73b6406f7d126f49:/unicode.c

diff --git a/unicode.c b/unicode.c
index 506aab3f..3c25c6ea 100644
--- a/unicode.c
+++ b/unicode.c
@@ -18,7 +18,7 @@
  */
 static char **uni_tbl;
 
-static WCHAR unitab_xterm_std[32] = {
+static const WCHAR unitab_xterm_std[32] = {
     0x2666, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
     0x2424, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba,
     0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c,
@@ -32,14 +32,15 @@ static WCHAR unitab_xterm_std[32] = {
  */
 
 /* 
- * Tables for ISO-8859-{1-9,13-16} derived from those downloaded
+ * Tables for ISO-8859-{1-10,13-16} derived from those downloaded
  * 2001-10-02 from <http://www.unicode.org/Public/MAPPINGS/> -- jtn
+ * Table for ISO-8859-11 derived from same on 2002-11-18. -- bjh21
  */
 
 /* XXX: This could be done algorithmically, but I'm not sure it's
  *      worth the hassle -- jtn */
 /* ISO/IEC 8859-1:1998 (Latin-1, "Western", "West European") */
-static wchar_t iso_8859_1[] = {
+static const wchar_t iso_8859_1[] = {
     0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
     0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
@@ -54,8 +55,8 @@ static wchar_t iso_8859_1[] = {
     0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF
 };
 
-/* ISO 8859-2:1999 (Latin-2, "Central European", "East European") */
-static wchar_t iso_8859_2[] = {
+/* ISO/IEC 8859-2:1999 (Latin-2, "Central European", "East European") */
+static const wchar_t iso_8859_2[] = {
     0x00A0, 0x0104, 0x02D8, 0x0141, 0x00A4, 0x013D, 0x015A, 0x00A7,
     0x00A8, 0x0160, 0x015E, 0x0164, 0x0179, 0x00AD, 0x017D, 0x017B,
     0x00B0, 0x0105, 0x02DB, 0x0142, 0x00B4, 0x013E, 0x015B, 0x02C7,
@@ -71,7 +72,7 @@ static wchar_t iso_8859_2[] = {
 };
 
 /* ISO/IEC 8859-3:1999 (Latin-3, "South European", "Maltese & Esperanto") */
-static wchar_t iso_8859_3[] = {
+static const wchar_t iso_8859_3[] = {
     0x00A0, 0x0126, 0x02D8, 0x00A3, 0x00A4, 0xFFFD, 0x0124, 0x00A7,
     0x00A8, 0x0130, 0x015E, 0x011E, 0x0134, 0x00AD, 0xFFFD, 0x017B,
     0x00B0, 0x0127, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x0125, 0x00B7,
@@ -87,7 +88,7 @@ static wchar_t iso_8859_3[] = {
 };
 
 /* ISO/IEC 8859-4:1998 (Latin-4, "North European") */
-static wchar_t iso_8859_4[] = {
+static const wchar_t iso_8859_4[] = {
     0x00A0, 0x0104, 0x0138, 0x0156, 0x00A4, 0x0128, 0x013B, 0x00A7,
     0x00A8, 0x0160, 0x0112, 0x0122, 0x0166, 0x00AD, 0x017D, 0x00AF,
     0x00B0, 0x0105, 0x02DB, 0x0157, 0x00B4, 0x0129, 0x013C, 0x02C7,
@@ -102,8 +103,8 @@ static wchar_t iso_8859_4[] = {
     0x00F8, 0x0173, 0x00FA, 0x00FB, 0x00FC, 0x0169, 0x016B, 0x02D9
 };
 
-/* ISO 8859-5:1999 (Latin/Cyrillic) */
-static wchar_t iso_8859_5[] = {
+/* ISO/IEC 8859-5:1999 (Latin/Cyrillic) */
+static const wchar_t iso_8859_5[] = {
     0x00A0, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407,
     0x0408, 0x0409, 0x040A, 0x040B, 0x040C, 0x00AD, 0x040E, 0x040F,
     0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
@@ -118,8 +119,8 @@ static wchar_t iso_8859_5[] = {
     0x0458, 0x0459, 0x045A, 0x045B, 0x045C, 0x00A7, 0x045E, 0x045F
 };
 
-/* ISO 8859-6:1999 (Latin/Arabic) */
-static wchar_t iso_8859_6[] = {
+/* ISO/IEC 8859-6:1999 (Latin/Arabic) */
+static const wchar_t iso_8859_6[] = {
     0x00A0, 0xFFFD, 0xFFFD, 0xFFFD, 0x00A4, 0xFFFD, 0xFFFD, 0xFFFD,
     0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x060C, 0x00AD, 0xFFFD, 0xFFFD,
     0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
@@ -135,7 +136,7 @@ static wchar_t iso_8859_6[] = {
 };
 
 /* ISO 8859-7:1987 (Latin/Greek) */
-static wchar_t iso_8859_7[] = {
+static const wchar_t iso_8859_7[] = {
     0x00A0, 0x2018, 0x2019, 0x00A3, 0xFFFD, 0xFFFD, 0x00A6, 0x00A7,
     0x00A8, 0x00A9, 0xFFFD, 0x00AB, 0x00AC, 0x00AD, 0xFFFD, 0x2015,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x0385, 0x0386, 0x00B7,
@@ -151,7 +152,7 @@ static wchar_t iso_8859_7[] = {
 };
 
 /* ISO/IEC 8859-8:1999 (Latin/Hebrew) */
-static wchar_t iso_8859_8[] = {
+static const wchar_t iso_8859_8[] = {
     0x00A0, 0xFFFD, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
     0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
@@ -167,7 +168,7 @@ static wchar_t iso_8859_8[] = {
 };
 
 /* ISO/IEC 8859-9:1999 (Latin-5, "Turkish") */
-static wchar_t iso_8859_9[] = {
+static const wchar_t iso_8859_9[] = {
     0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
     0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
@@ -182,15 +183,12 @@ static wchar_t iso_8859_9[] = {
     0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0131, 0x015F, 0x00FF
 };
 
-/* ISO 8859-10:1993? (Latin-6, "Nordic" [Sami, Inuit, Icelandic]) */
-/* Translation table from RDB. unicode.org (ISO/IEC 8859-10:1998) has
- * U+2015 (HORIZONTAL BAR) at codepoint 0xBD instead
- * (U+2014 is EM DASH). -- jtn */
-static wchar_t iso_8859_10[] = {
+/* ISO/IEC 8859-10:1998 (Latin-6, "Nordic" [Sami, Inuit, Icelandic]) */
+static const wchar_t iso_8859_10[] = {
     0x00A0, 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, 0x2014, 0x016B, 0x014B,
+    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,
@@ -201,10 +199,8 @@ static wchar_t iso_8859_10[] = {
     0x00F8, 0x0173, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x0138
 };
 
-/* "ISO 8859-11:1997" ("Thai", "TIS620") */
-/* From RDB -- ISO and unicode.org disclaim all knowledge of this one.
- * Maybe still in draft. --jtn */
-static wchar_t iso_8859_11[] = {
+/* ISO/IEC 8859-11:2001 ("Thai", "TIS620") */
+static const wchar_t iso_8859_11[] = {
     0x00A0, 0x0E01, 0x0E02, 0x0E03, 0x0E04, 0x0E05, 0x0E06, 0x0E07,
     0x0E08, 0x0E09, 0x0E0A, 0x0E0B, 0x0E0C, 0x0E0D, 0x0E0E, 0x0E0F,
     0x0E10, 0x0E11, 0x0E12, 0x0E13, 0x0E14, 0x0E15, 0x0E16, 0x0E17,
@@ -220,7 +216,7 @@ static wchar_t iso_8859_11[] = {
 };
 
 /* ISO/IEC 8859-13:1998 (Latin-7, "Baltic Rim") */
-static wchar_t iso_8859_13[] = {
+static const wchar_t iso_8859_13[] = {
     0x00A0, 0x201D, 0x00A2, 0x00A3, 0x00A4, 0x201E, 0x00A6, 0x00A7,
     0x00D8, 0x00A9, 0x0156, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00C6,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x201C, 0x00B5, 0x00B6, 0x00B7,
@@ -236,7 +232,7 @@ static wchar_t iso_8859_13[] = {
 };
 
 /* ISO/IEC 8859-14:1998 (Latin-8, "Celtic", "Gaelic/Welsh") */
-static wchar_t iso_8859_14[] = {
+static const wchar_t iso_8859_14[] = {
     0x00A0, 0x1E02, 0x1E03, 0x00A3, 0x010A, 0x010B, 0x1E0A, 0x00A7,
     0x1E80, 0x00A9, 0x1E82, 0x1E0B, 0x1EF2, 0x00AD, 0x00AE, 0x0178,
     0x1E1E, 0x1E1F, 0x0120, 0x0121, 0x1E40, 0x1E41, 0x00B6, 0x1E56,
@@ -252,7 +248,7 @@ static wchar_t iso_8859_14[] = {
 };
 
 /* ISO/IEC 8859-15:1999 (Latin-9 aka -0, "euro") */
-static wchar_t iso_8859_15[] = {
+static const wchar_t iso_8859_15[] = {
     0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AC, 0x00A5, 0x0160, 0x00A7,
     0x0161, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
     0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x017D, 0x00B5, 0x00B6, 0x00B7,
@@ -268,7 +264,7 @@ static wchar_t iso_8859_15[] = {
 };
 
 /* ISO/IEC 8859-16:2001 (Latin-10, "Balkan") */
-static wchar_t iso_8859_16[] = {
+static const wchar_t iso_8859_16[] = {
     0x00A0, 0x0104, 0x0105, 0x0141, 0x20AC, 0x201E, 0x0160, 0x00A7,
     0x0161, 0x00A9, 0x0218, 0x00AB, 0x0179, 0x00AD, 0x017A, 0x017B,
     0x00B0, 0x00B1, 0x010C, 0x0142, 0x017D, 0x201D, 0x00B6, 0x00B7,
@@ -283,7 +279,7 @@ static wchar_t iso_8859_16[] = {
     0x0171, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0119, 0x021B, 0x00FF
 };
 
-static wchar_t roman8[] = {
+static const wchar_t roman8[] = {
     0x00A0, 0x00C0, 0x00C2, 0x00C8, 0x00CA, 0x00CB, 0x00CE, 0x00CF,
     0x00B4, 0x02CB, 0x02C6, 0x00A8, 0x02DC, 0x00D9, 0x00DB, 0x20A4,
     0x00AF, 0x00DD, 0x00FD, 0x00B0, 0x00C7, 0x00E7, 0x00D1, 0x00F1,
@@ -298,7 +294,7 @@ static wchar_t roman8[] = {
     0x00BD, 0x00AA, 0x00BA, 0x00AB, 0x25A0, 0x00BB, 0x00B1, 0xFFFD
 };
 
-static wchar_t koi8_u[] = {
+static const wchar_t koi8_u[] = {
     0x2500, 0x2502, 0x250C, 0x2510, 0x2514, 0x2518, 0x251C, 0x2524,
     0x252C, 0x2534, 0x253C, 0x2580, 0x2584, 0x2588, 0x258C, 0x2590,
     0x2591, 0x2592, 0x2593, 0x2320, 0x25A0, 0x2022, 0x221A, 0x2248,
@@ -317,7 +313,7 @@ static wchar_t koi8_u[] = {
     0x042C, 0x042B, 0x0417, 0x0428, 0x042D, 0x0429, 0x0427, 0x042A
 };
 
-static wchar_t vscii[] = {
+static const wchar_t vscii[] = {
     0x0000, 0x0001, 0x1EB2, 0x0003, 0x0004, 0x1EB4, 0x1EAA, 0x0007,
     0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
     0x0010, 0x0011, 0x0012, 0x0013, 0x1EF6, 0x0015, 0x0016, 0x0017,
@@ -352,7 +348,7 @@ static wchar_t vscii[] = {
     0x1EE5, 0x00F9, 0x00FA, 0x0169, 0x1EE7, 0x00FD, 0x1EE3, 0x1EEE
 };
 
-static wchar_t dec_mcs[] = {
+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,
@@ -371,10 +367,10 @@ struct cp_list_item {
     char *name;
     int codepage;
     int cp_size;
-    wchar_t *cp_table;
+    const wchar_t *cp_table;
 };
 
-static struct cp_list_item cp_list[] = {
+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},
@@ -384,8 +380,8 @@ static struct cp_list_item cp_list[] = {
     {"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-8859-10:1993 (Latin-6, Nordic)", 0, 96, iso_8859_10},
-    {"ISO-8859-11:1997 (Latin/Thai)", 0, 96, iso_8859_11},
+    {"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},
@@ -420,7 +416,7 @@ static struct cp_list_item cp_list[] = {
 
 static void link_font(WCHAR * line_tbl, WCHAR * font_tbl, WCHAR attr);
 
-void init_ucs(void)
+void init_ucs(Config *cfg)
 {
     int i, j;
     int used_dtf = 0;
@@ -430,14 +426,14 @@ void init_ucs(void)
 	tbuf[i] = i;
 
     /* Decide on the Line and Font codepages */
-    line_codepage = decode_codepage(cfg.line_codepage);
+    line_codepage = decode_codepage(cfg->line_codepage);
 
     if (font_codepage <= 0) { 
 	font_codepage=0; 
 	dbcs_screenfont=0; 
     }
 
-    if (cfg.vtmode == VT_OEMONLY) {
+    if (cfg->vtmode == VT_OEMONLY) {
 	font_codepage = 437;
 	dbcs_screenfont = 0;
 	if (line_codepage <= 0)
@@ -457,7 +453,7 @@ void init_ucs(void)
 	if (font_codepage == 437)
 	    unitab_font[0] = unitab_font[255] = 0xFFFF;
     }
-    if (cfg.vtmode == VT_XWINDOWS)
+    if (cfg->vtmode == VT_XWINDOWS)
 	memcpy(unitab_font + 1, unitab_xterm_std,
 	       sizeof(unitab_xterm_std));
 
@@ -465,14 +461,14 @@ void init_ucs(void)
     get_unitab(CP_OEMCP, unitab_oemcp, 1);
 
     /* Collect CP437 ucs table for SCO acs */
-    if (cfg.vtmode == VT_OEMANSI || cfg.vtmode == VT_XWINDOWS)
+    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS)
 	memcpy(unitab_scoacs, unitab_oemcp, sizeof(unitab_scoacs));
     else
 	get_unitab(437, unitab_scoacs, 1);
 
     /* Collect line set ucs table */
     if (line_codepage == font_codepage &&
-	(dbcs_screenfont || cfg.vtmode == VT_POORMAN || font_codepage==0)) {
+	(dbcs_screenfont || cfg->vtmode == VT_POORMAN || font_codepage==0)) {
 
 	/* For DBCS and POOR fonts force direct to font */
 	used_dtf = 1;
@@ -539,14 +535,14 @@ void init_ucs(void)
 	    unitab_ctrl[i] = 0xFF;
 
     /* Generate line->screen direct conversion links. */
-    if (cfg.vtmode == VT_OEMANSI || cfg.vtmode == VT_XWINDOWS)
+    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS)
 	link_font(unitab_scoacs, unitab_oemcp, ATTR_OEMCP);
 
     link_font(unitab_line, unitab_font, ATTR_ACP);
     link_font(unitab_scoacs, unitab_font, ATTR_ACP);
     link_font(unitab_xterm, unitab_font, ATTR_ACP);
 
-    if (cfg.vtmode == VT_OEMANSI || cfg.vtmode == VT_XWINDOWS) {
+    if (cfg->vtmode == VT_OEMANSI || cfg->vtmode == VT_XWINDOWS) {
 	link_font(unitab_line, unitab_oemcp, ATTR_OEMCP);
 	link_font(unitab_xterm, unitab_oemcp, ATTR_OEMCP);
     }
@@ -559,7 +555,7 @@ void init_ucs(void)
     }
 
     /* Last chance, if !unicode then try poorman links. */
-    if (cfg.vtmode != VT_UNICODE) {
+    if (cfg->vtmode != VT_UNICODE) {
 	static char poorman_scoacs[] = 
 	    "CueaaaaceeeiiiAAE**ooouuyOUc$YPsaiounNao?++**!<>###||||++||++++++--|-+||++--|-+----++++++++##||#aBTPEsyt******EN=+><++-=... n2* ";
 	static char poorman_latin1[] =
@@ -982,7 +978,7 @@ int check_compose(int first, int second)
 int decode_codepage(char *cp_name)
 {
     char *s, *d;
-    struct cp_list_item *cpi;
+    const struct cp_list_item *cpi;
     int codepage = -1;
     CPINFO cpinfo;
 
@@ -1092,7 +1088,7 @@ int decode_codepage(char *cp_name)
 
 char *cp_name(int codepage)
 {
-    struct cp_list_item *cpi, *cpno;
+    const struct cp_list_item *cpi, *cpno;
     static char buf[32];
 
     if (codepage == -1) {