2001-05-10 08:34:20 +00:00
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <ctype.h>
|
|
|
|
#include <time.h>
|
2002-10-26 11:08:59 +00:00
|
|
|
#include <assert.h>
|
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
#include "putty.h"
|
2002-10-22 16:11:33 +00:00
|
|
|
#include "terminal.h"
|
2001-08-12 19:25:21 +00:00
|
|
|
#include "misc.h"
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
/* Character conversion arrays; they are usually taken from windows,
|
|
|
|
* the xterm one has the four scanlines that have no unicode 2.0
|
2001-09-07 22:49:17 +00:00
|
|
|
* equivalents mapped to their unicode 3.0 locations.
|
2001-05-10 08:34:20 +00:00
|
|
|
*/
|
2002-10-30 18:12:22 +00:00
|
|
|
static const WCHAR unitab_xterm_std[32] = {
|
2001-05-10 08:34:20 +00:00
|
|
|
0x2666, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
|
|
|
|
0x2424, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba,
|
|
|
|
0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c,
|
|
|
|
0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x0020
|
|
|
|
};
|
|
|
|
|
2001-08-12 19:25:21 +00:00
|
|
|
/*
|
|
|
|
* If the codepage is non-zero it's a window codepage, zero means use a
|
|
|
|
* local codepage. The name is always converted to the first of any
|
|
|
|
* duplicate definitions.
|
|
|
|
*/
|
|
|
|
|
2019-09-08 19:29:00 +00:00
|
|
|
/*
|
2002-11-18 22:27:25 +00:00
|
|
|
* Tables for ISO-8859-{1-10,13-16} derived from those downloaded
|
2001-10-28 10:40:11 +00:00
|
|
|
* 2001-10-02 from <http://www.unicode.org/Public/MAPPINGS/> -- jtn
|
2002-11-18 20:06:46 +00:00
|
|
|
* Table for ISO-8859-11 derived from same on 2002-11-18. -- bjh21
|
2001-10-28 10:40:11 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
/* 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") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_1[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
|
|
|
|
0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
|
|
|
|
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
|
|
|
|
0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
|
|
|
|
0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
|
|
|
|
0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF
|
|
|
|
};
|
|
|
|
|
2002-11-18 20:06:46 +00:00
|
|
|
/* ISO/IEC 8859-2:1999 (Latin-2, "Central European", "East European") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_2[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x0104, 0x02D8, 0x0141, 0x00A4, 0x013D, 0x015A, 0x00A7,
|
|
|
|
0x00A8, 0x0160, 0x015E, 0x0164, 0x0179, 0x00AD, 0x017D, 0x017B,
|
|
|
|
0x00B0, 0x0105, 0x02DB, 0x0142, 0x00B4, 0x013E, 0x015B, 0x02C7,
|
|
|
|
0x00B8, 0x0161, 0x015F, 0x0165, 0x017A, 0x02DD, 0x017E, 0x017C,
|
|
|
|
0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7,
|
|
|
|
0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E,
|
|
|
|
0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7,
|
|
|
|
0x0158, 0x016E, 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF,
|
|
|
|
0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7,
|
|
|
|
0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F,
|
|
|
|
0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7,
|
|
|
|
0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ISO/IEC 8859-3:1999 (Latin-3, "South European", "Maltese & Esperanto") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_3[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x0126, 0x02D8, 0x00A3, 0x00A4, 0xFFFD, 0x0124, 0x00A7,
|
|
|
|
0x00A8, 0x0130, 0x015E, 0x011E, 0x0134, 0x00AD, 0xFFFD, 0x017B,
|
|
|
|
0x00B0, 0x0127, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x0125, 0x00B7,
|
|
|
|
0x00B8, 0x0131, 0x015F, 0x011F, 0x0135, 0x00BD, 0xFFFD, 0x017C,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0xFFFD, 0x00C4, 0x010A, 0x0108, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0xFFFD, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x0120, 0x00D6, 0x00D7,
|
|
|
|
0x011C, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x016C, 0x015C, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0xFFFD, 0x00E4, 0x010B, 0x0109, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0xFFFD, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x0121, 0x00F6, 0x00F7,
|
|
|
|
0x011D, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x016D, 0x015D, 0x02D9
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ISO/IEC 8859-4:1998 (Latin-4, "North European") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_4[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x0104, 0x0138, 0x0156, 0x00A4, 0x0128, 0x013B, 0x00A7,
|
|
|
|
0x00A8, 0x0160, 0x0112, 0x0122, 0x0166, 0x00AD, 0x017D, 0x00AF,
|
|
|
|
0x00B0, 0x0105, 0x02DB, 0x0157, 0x00B4, 0x0129, 0x013C, 0x02C7,
|
|
|
|
0x00B8, 0x0161, 0x0113, 0x0123, 0x0167, 0x014A, 0x017E, 0x014B,
|
|
|
|
0x0100, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x012E,
|
|
|
|
0x010C, 0x00C9, 0x0118, 0x00CB, 0x0116, 0x00CD, 0x00CE, 0x012A,
|
|
|
|
0x0110, 0x0145, 0x014C, 0x0136, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
|
|
|
|
0x00D8, 0x0172, 0x00DA, 0x00DB, 0x00DC, 0x0168, 0x016A, 0x00DF,
|
|
|
|
0x0101, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x012F,
|
|
|
|
0x010D, 0x00E9, 0x0119, 0x00EB, 0x0117, 0x00ED, 0x00EE, 0x012B,
|
|
|
|
0x0111, 0x0146, 0x014D, 0x0137, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
|
|
|
|
0x00F8, 0x0173, 0x00FA, 0x00FB, 0x00FC, 0x0169, 0x016B, 0x02D9
|
|
|
|
};
|
|
|
|
|
2002-11-18 20:06:46 +00:00
|
|
|
/* ISO/IEC 8859-5:1999 (Latin/Cyrillic) */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_5[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407,
|
|
|
|
0x0408, 0x0409, 0x040A, 0x040B, 0x040C, 0x00AD, 0x040E, 0x040F,
|
|
|
|
0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
|
|
|
|
0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
|
|
|
|
0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
|
|
|
|
0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
|
|
|
|
0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,
|
|
|
|
0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
|
|
|
|
0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
|
|
|
|
0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F,
|
|
|
|
0x2116, 0x0451, 0x0452, 0x0453, 0x0454, 0x0455, 0x0456, 0x0457,
|
|
|
|
0x0458, 0x0459, 0x045A, 0x045B, 0x045C, 0x00A7, 0x045E, 0x045F
|
|
|
|
};
|
|
|
|
|
2002-11-18 20:06:46 +00:00
|
|
|
/* ISO/IEC 8859-6:1999 (Latin/Arabic) */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_6[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0xFFFD, 0xFFFD, 0xFFFD, 0x00A4, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x060C, 0x00AD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0x061B, 0xFFFD, 0xFFFD, 0xFFFD, 0x061F,
|
|
|
|
0xFFFD, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627,
|
|
|
|
0x0628, 0x0629, 0x062A, 0x062B, 0x062C, 0x062D, 0x062E, 0x062F,
|
|
|
|
0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x0637,
|
|
|
|
0x0638, 0x0639, 0x063A, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0x0640, 0x0641, 0x0642, 0x0643, 0x0644, 0x0645, 0x0646, 0x0647,
|
|
|
|
0x0648, 0x0649, 0x064A, 0x064B, 0x064C, 0x064D, 0x064E, 0x064F,
|
|
|
|
0x0650, 0x0651, 0x0652, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ISO 8859-7:1987 (Latin/Greek) */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_7[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x2018, 0x2019, 0x00A3, 0xFFFD, 0xFFFD, 0x00A6, 0x00A7,
|
|
|
|
0x00A8, 0x00A9, 0xFFFD, 0x00AB, 0x00AC, 0x00AD, 0xFFFD, 0x2015,
|
|
|
|
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x0385, 0x0386, 0x00B7,
|
|
|
|
0x0388, 0x0389, 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E, 0x038F,
|
|
|
|
0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
|
|
|
|
0x0398, 0x0399, 0x039A, 0x039B, 0x039C, 0x039D, 0x039E, 0x039F,
|
|
|
|
0x03A0, 0x03A1, 0xFFFD, 0x03A3, 0x03A4, 0x03A5, 0x03A6, 0x03A7,
|
|
|
|
0x03A8, 0x03A9, 0x03AA, 0x03AB, 0x03AC, 0x03AD, 0x03AE, 0x03AF,
|
|
|
|
0x03B0, 0x03B1, 0x03B2, 0x03B3, 0x03B4, 0x03B5, 0x03B6, 0x03B7,
|
|
|
|
0x03B8, 0x03B9, 0x03BA, 0x03BB, 0x03BC, 0x03BD, 0x03BE, 0x03BF,
|
|
|
|
0x03C0, 0x03C1, 0x03C2, 0x03C3, 0x03C4, 0x03C5, 0x03C6, 0x03C7,
|
|
|
|
0x03C8, 0x03C9, 0x03CA, 0x03CB, 0x03CC, 0x03CD, 0x03CE, 0xFFFD
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ISO/IEC 8859-8:1999 (Latin/Hebrew) */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_8[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0xFFFD, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
|
|
|
|
0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
|
|
|
|
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
|
|
|
|
0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
|
|
|
|
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2017,
|
|
|
|
0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7,
|
|
|
|
0x05D8, 0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF,
|
|
|
|
0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7,
|
|
|
|
0x05E8, 0x05E9, 0x05EA, 0xFFFD, 0xFFFD, 0x200E, 0x200F, 0xFFFD
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ISO/IEC 8859-9:1999 (Latin-5, "Turkish") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_9[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
|
|
|
|
0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
|
|
|
|
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
|
|
|
|
0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0x011E, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
|
|
|
|
0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x0130, 0x015E, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0x011F, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
|
|
|
|
0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0131, 0x015F, 0x00FF
|
|
|
|
};
|
|
|
|
|
2002-11-18 22:27:25 +00:00
|
|
|
/* ISO/IEC 8859-10:1998 (Latin-6, "Nordic" [Sami, Inuit, Icelandic]) */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_10[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x00A0, 0x0104, 0x0112, 0x0122, 0x012A, 0x0128, 0x0136, 0x00A7,
|
|
|
|
0x013B, 0x0110, 0x0160, 0x0166, 0x017D, 0x00AD, 0x016A, 0x014A,
|
|
|
|
0x00B0, 0x0105, 0x0113, 0x0123, 0x012B, 0x0129, 0x0137, 0x00B7,
|
2002-11-18 22:27:25 +00:00
|
|
|
0x013C, 0x0111, 0x0161, 0x0167, 0x017E, 0x2015, 0x016B, 0x014B,
|
2001-08-12 19:25:21 +00:00
|
|
|
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
|
|
|
|
};
|
|
|
|
|
2002-11-18 18:24:35 +00:00
|
|
|
/* ISO/IEC 8859-11:2001 ("Thai", "TIS620") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_11[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x00A0, 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, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 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, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD
|
|
|
|
};
|
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
/* ISO/IEC 8859-13:1998 (Latin-7, "Baltic Rim") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_13[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x00A0, 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
|
|
|
|
};
|
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
/* ISO/IEC 8859-14:1998 (Latin-8, "Celtic", "Gaelic/Welsh") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_14[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x00A0, 0x1E02, 0x1E03, 0x00A3, 0x010A, 0x010B, 0x1E0A, 0x00A7,
|
|
|
|
0x1E80, 0x00A9, 0x1E82, 0x1E0B, 0x1EF2, 0x00AD, 0x00AE, 0x0178,
|
|
|
|
0x1E1E, 0x1E1F, 0x0120, 0x0121, 0x1E40, 0x1E41, 0x00B6, 0x1E56,
|
|
|
|
0x1E81, 0x1E57, 0x1E83, 0x1E60, 0x1EF3, 0x1E84, 0x1E85, 0x1E61,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0x0174, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x1E6A,
|
|
|
|
0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x0176, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0x0175, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x1E6B,
|
|
|
|
0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x0177, 0x00FF
|
|
|
|
};
|
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
/* ISO/IEC 8859-15:1999 (Latin-9 aka -0, "euro") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_15[] = {
|
2001-10-28 10:40:11 +00:00
|
|
|
0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AC, 0x00A5, 0x0160, 0x00A7,
|
|
|
|
0x0161, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
|
|
|
|
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x017D, 0x00B5, 0x00B6, 0x00B7,
|
|
|
|
0x017E, 0x00B9, 0x00BA, 0x00BB, 0x0152, 0x0153, 0x0178, 0x00BF,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
|
|
|
|
0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
|
|
|
|
0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF
|
2001-08-12 19:25:21 +00:00
|
|
|
};
|
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
/* ISO/IEC 8859-16:2001 (Latin-10, "Balkan") */
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t iso_8859_16[] = {
|
2001-09-07 22:41:38 +00:00
|
|
|
0x00A0, 0x0104, 0x0105, 0x0141, 0x20AC, 0x201E, 0x0160, 0x00A7,
|
|
|
|
0x0161, 0x00A9, 0x0218, 0x00AB, 0x0179, 0x00AD, 0x017A, 0x017B,
|
|
|
|
0x00B0, 0x00B1, 0x010C, 0x0142, 0x017D, 0x201D, 0x00B6, 0x00B7,
|
|
|
|
0x017E, 0x010D, 0x0219, 0x00BB, 0x0152, 0x0153, 0x0178, 0x017C,
|
|
|
|
0x00C0, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0106, 0x00C6, 0x00C7,
|
|
|
|
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
|
|
|
0x0110, 0x0143, 0x00D2, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x015A,
|
|
|
|
0x0170, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x0118, 0x021A, 0x00DF,
|
|
|
|
0x00E0, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x0107, 0x00E6, 0x00E7,
|
|
|
|
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
|
|
|
0x0111, 0x0144, 0x00F2, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x015B,
|
|
|
|
0x0171, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0119, 0x021B, 0x00FF
|
|
|
|
};
|
|
|
|
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t roman8[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x00A0, 0x00C0, 0x00C2, 0x00C8, 0x00CA, 0x00CB, 0x00CE, 0x00CF,
|
|
|
|
0x00B4, 0x02CB, 0x02C6, 0x00A8, 0x02DC, 0x00D9, 0x00DB, 0x20A4,
|
|
|
|
0x00AF, 0x00DD, 0x00FD, 0x00B0, 0x00C7, 0x00E7, 0x00D1, 0x00F1,
|
|
|
|
0x00A1, 0x00BF, 0x00A4, 0x00A3, 0x00A5, 0x00A7, 0x0192, 0x00A2,
|
|
|
|
0x00E2, 0x00EA, 0x00F4, 0x00FB, 0x00E1, 0x00E9, 0x00F3, 0x00FA,
|
|
|
|
0x00E0, 0x00E8, 0x00F2, 0x00F9, 0x00E4, 0x00EB, 0x00F6, 0x00FC,
|
|
|
|
0x00C5, 0x00EE, 0x00D8, 0x00C6, 0x00E5, 0x00ED, 0x00F8, 0x00E6,
|
|
|
|
0x00C4, 0x00EC, 0x00D6, 0x00DC, 0x00C9, 0x00EF, 0x00DF, 0x00D4,
|
|
|
|
0x00C1, 0x00C3, 0x00E3, 0x00D0, 0x00F0, 0x00CD, 0x00CC, 0x00D3,
|
|
|
|
0x00D2, 0x00D5, 0x00F5, 0x0160, 0x0161, 0x00DA, 0x0178, 0x00FF,
|
|
|
|
0x00DE, 0x00FE, 0x00B7, 0x00B5, 0x00B6, 0x00BE, 0x2014, 0x00BC,
|
|
|
|
0x00BD, 0x00AA, 0x00BA, 0x00AB, 0x25A0, 0x00BB, 0x00B1, 0xFFFD
|
|
|
|
};
|
|
|
|
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t koi8_u[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x2500, 0x2502, 0x250C, 0x2510, 0x2514, 0x2518, 0x251C, 0x2524,
|
|
|
|
0x252C, 0x2534, 0x253C, 0x2580, 0x2584, 0x2588, 0x258C, 0x2590,
|
|
|
|
0x2591, 0x2592, 0x2593, 0x2320, 0x25A0, 0x2022, 0x221A, 0x2248,
|
|
|
|
0x2264, 0x2265, 0x00A0, 0x2321, 0x00B0, 0x00B2, 0x00B7, 0x00F7,
|
|
|
|
0x2550, 0x2551, 0x2552, 0x0451, 0x0454, 0x2554, 0x0456, 0x0457,
|
|
|
|
0x2557, 0x2558, 0x2559, 0x255A, 0x255B, 0x0491, 0x255D, 0x255E,
|
|
|
|
0x255F, 0x2560, 0x2561, 0x0401, 0x0404, 0x2563, 0x0406, 0x0407,
|
|
|
|
0x2566, 0x2567, 0x2568, 0x2569, 0x256A, 0x0490, 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
|
|
|
|
};
|
|
|
|
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t vscii[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
0x0000, 0x0001, 0x1EB2, 0x0003, 0x0004, 0x1EB4, 0x1EAA, 0x0007,
|
|
|
|
0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
|
|
|
|
0x0010, 0x0011, 0x0012, 0x0013, 0x1EF6, 0x0015, 0x0016, 0x0017,
|
|
|
|
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
|
|
|
|
};
|
|
|
|
|
2002-10-30 18:12:22 +00:00
|
|
|
static const wchar_t dec_mcs[] = {
|
2001-08-12 19:25:21 +00:00
|
|
|
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
|
|
|
|
};
|
|
|
|
|
2004-08-05 14:10:24 +00:00
|
|
|
/* 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
|
|
|
|
};
|
|
|
|
|
2001-08-12 19:25:21 +00:00
|
|
|
struct cp_list_item {
|
2001-05-10 08:34:20 +00:00
|
|
|
char *name;
|
|
|
|
int codepage;
|
|
|
|
int cp_size;
|
2002-10-30 18:12:22 +00:00
|
|
|
const wchar_t *cp_table;
|
2001-08-12 19:25:21 +00:00
|
|
|
};
|
|
|
|
|
2002-10-30 18:12:22 +00:00
|
|
|
static const struct cp_list_item cp_list[] = {
|
2013-05-25 14:03:19 +00:00
|
|
|
{"UTF-8", CP_UTF8},
|
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
{"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},
|
2002-11-18 22:27:25 +00:00
|
|
|
{"ISO-8859-10:1998 (Latin-6, Nordic)", 0, 96, iso_8859_10},
|
2002-11-18 18:14:18 +00:00
|
|
|
{"ISO-8859-11:2001 (Latin/Thai)", 0, 96, iso_8859_11},
|
2001-10-28 10:40:11 +00:00
|
|
|
{"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},
|
2001-08-12 19:25:21 +00:00
|
|
|
|
|
|
|
{"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},
|
|
|
|
|
2001-09-05 21:01:04 +00:00
|
|
|
{"CP437", 437},
|
2004-08-05 14:10:24 +00:00
|
|
|
{"CP620 (Mazovia)", 0, 128, mazovia},
|
2001-08-12 19:25:21 +00:00
|
|
|
{"CP819", 28591},
|
2011-10-14 07:03:29 +00:00
|
|
|
{"CP852", 852},
|
2001-08-12 19:25:21 +00:00
|
|
|
{"CP878", 20866},
|
2001-09-05 21:01:04 +00:00
|
|
|
|
|
|
|
{"Use font encoding", -1},
|
|
|
|
|
2001-08-12 19:25:21 +00:00
|
|
|
{0, 0}
|
|
|
|
};
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2022-08-03 19:48:46 +00:00
|
|
|
static void link_font(WCHAR *line_tbl, WCHAR *font_tbl, WCHAR attr);
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2022-06-01 07:35:12 +00:00
|
|
|
/*
|
|
|
|
* We keep a collection of reverse mappings from Unicode back to code pages,
|
|
|
|
* in the form of array[256] of array[256] of char. These live forever in a
|
|
|
|
* local tree234, and we just make a new one whenever we find a need.
|
|
|
|
*/
|
|
|
|
typedef struct reverse_mapping {
|
|
|
|
int codepage;
|
|
|
|
char **blocks;
|
|
|
|
} reverse_mapping;
|
|
|
|
static tree234 *reverse_mappings = NULL;
|
|
|
|
|
|
|
|
static int reverse_mapping_cmp(void *av, void *bv)
|
|
|
|
{
|
|
|
|
const reverse_mapping *a = (const reverse_mapping *)av;
|
|
|
|
const reverse_mapping *b = (const reverse_mapping *)bv;
|
|
|
|
if (a->codepage < b->codepage)
|
|
|
|
return -1;
|
|
|
|
if (a->codepage > b->codepage)
|
|
|
|
return +1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int reverse_mapping_find(void *av, void *bv)
|
|
|
|
{
|
|
|
|
const reverse_mapping *a = (const reverse_mapping *)av;
|
|
|
|
int b_codepage = *(const int *)bv;
|
|
|
|
if (a->codepage < b_codepage)
|
|
|
|
return -1;
|
|
|
|
if (a->codepage > b_codepage)
|
|
|
|
return +1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static reverse_mapping *get_existing_reverse_mapping(int codepage)
|
|
|
|
{
|
|
|
|
if (!reverse_mappings)
|
|
|
|
return NULL;
|
|
|
|
return find234(reverse_mappings, &codepage, reverse_mapping_find);
|
|
|
|
}
|
|
|
|
|
|
|
|
static reverse_mapping *make_reverse_mapping_inner(
|
|
|
|
int codepage, const wchar_t *mapping)
|
|
|
|
{
|
|
|
|
if (!reverse_mappings)
|
|
|
|
reverse_mappings = newtree234(reverse_mapping_cmp);
|
|
|
|
|
|
|
|
reverse_mapping *rmap = snew(reverse_mapping);
|
|
|
|
rmap->blocks = snewn(256, char *);
|
|
|
|
memset(rmap->blocks, 0, 256 * sizeof(char *));
|
|
|
|
|
|
|
|
for (size_t i = 0; i < 256; i++) {
|
|
|
|
/* These special kinds of value correspond to no Unicode character */
|
|
|
|
if (DIRECT_CHAR(mapping[i]))
|
|
|
|
continue;
|
|
|
|
if (DIRECT_FONT(mapping[i]))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
size_t chr = mapping[i];
|
|
|
|
size_t block = chr >> 8, index = chr & 0xFF;
|
|
|
|
|
|
|
|
if (!rmap->blocks[block]) {
|
|
|
|
rmap->blocks[block] = snewn(256, char);
|
|
|
|
memset(rmap->blocks[block], 0, 256);
|
|
|
|
}
|
|
|
|
rmap->blocks[block][index] = i;
|
|
|
|
}
|
|
|
|
|
|
|
|
rmap->codepage = codepage;
|
|
|
|
reverse_mapping *added = add234(reverse_mappings, rmap);
|
|
|
|
assert(added == rmap); /* we already checked it wasn't already in there */
|
|
|
|
return added;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void make_reverse_mapping(int codepage, const wchar_t *mapping)
|
|
|
|
{
|
|
|
|
if (get_existing_reverse_mapping(codepage))
|
|
|
|
return; /* we've already got this one */
|
|
|
|
make_reverse_mapping_inner(codepage, mapping);
|
|
|
|
}
|
|
|
|
|
|
|
|
static reverse_mapping *get_reverse_mapping(int codepage)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Try harder to get a reverse mapping for a codepage we implement
|
|
|
|
* internally via a translation table, by hastily making it if it doesn't
|
|
|
|
* already exist.
|
|
|
|
*/
|
|
|
|
|
|
|
|
reverse_mapping *rmap = get_existing_reverse_mapping(codepage);
|
|
|
|
if (rmap)
|
|
|
|
return rmap;
|
|
|
|
|
|
|
|
if (codepage < 65536)
|
|
|
|
return NULL;
|
2022-09-07 13:18:21 +00:00
|
|
|
if (codepage >= 65536 + lenof(cp_list))
|
2022-06-01 07:35:12 +00:00
|
|
|
return NULL;
|
|
|
|
const struct cp_list_item *cp = &cp_list[codepage - 65536];
|
|
|
|
if (!cp->cp_table)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
wchar_t mapping[256];
|
|
|
|
get_unitab(codepage, mapping, 0);
|
|
|
|
return make_reverse_mapping_inner(codepage, mapping);
|
|
|
|
}
|
|
|
|
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
void init_ucs(Conf *conf, struct unicode_data *ucsdata)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
2022-06-01 07:35:12 +00:00
|
|
|
int i;
|
Convert a lot of 'int' variables to 'bool'.
My normal habit these days, in new code, is to treat int and bool as
_almost_ completely separate types. I'm still willing to use C's
implicit test for zero on an integer (e.g. 'if (!blob.len)' is fine,
no need to spell it out as blob.len != 0), but generally, if a
variable is going to be conceptually a boolean, I like to declare it
bool and assign to it using 'true' or 'false' rather than 0 or 1.
PuTTY is an exception, because it predates the C99 bool, and I've
stuck to its existing coding style even when adding new code to it.
But it's been annoying me more and more, so now that I've decided C99
bool is an acceptable thing to require from our toolchain in the first
place, here's a quite thorough trawl through the source doing
'boolification'. Many variables and function parameters are now typed
as bool rather than int; many assignments of 0 or 1 to those variables
are now spelled 'true' or 'false'.
I managed this thorough conversion with the help of a custom clang
plugin that I wrote to trawl the AST and apply heuristics to point out
where things might want changing. So I've even managed to do a decent
job on parts of the code I haven't looked at in years!
To make the plugin's work easier, I pushed platform front ends
generally in the direction of using standard 'bool' in preference to
platform-specific boolean types like Windows BOOL or GTK's gboolean;
I've left the platform booleans in places they _have_ to be for the
platform APIs to work right, but variables only used by my own code
have been converted wherever I found them.
In a few places there are int values that look very like booleans in
_most_ of the places they're used, but have a rarely-used third value,
or a distinction between different nonzero values that most users
don't care about. In these cases, I've _removed_ uses of 'true' and
'false' for the return values, to emphasise that there's something
more subtle going on than a simple boolean answer:
- the 'multisel' field in dialog.h's list box structure, for which
the GTK front end in particular recognises a difference between 1
and 2 but nearly everything else treats as boolean
- the 'urgent' parameter to plug_receive, where 1 vs 2 tells you
something about the specific location of the urgent pointer, but
most clients only care about 0 vs 'something nonzero'
- the return value of wc_match, where -1 indicates a syntax error in
the wildcard.
- the return values from SSH-1 RSA-key loading functions, which use
-1 for 'wrong passphrase' and 0 for all other failures (so any
caller which already knows it's not loading an _encrypted private_
key can treat them as boolean)
- term->esc_query, and the 'query' parameter in toggle_mode in
terminal.c, which _usually_ hold 0 for ESC[123h or 1 for ESC[?123h,
but can also hold -1 for some other intervening character that we
don't support.
In a few places there's an integer that I haven't turned into a bool
even though it really _can_ only take values 0 or 1 (and, as above,
tried to make the call sites consistent in not calling those values
true and false), on the grounds that I thought it would make it more
confusing to imply that the 0 value was in some sense 'negative' or
bad and the 1 positive or good:
- the return value of plug_accepting uses the POSIXish convention of
0=success and nonzero=error; I think if I made it bool then I'd
also want to reverse its sense, and that's a job for a separate
piece of work.
- the 'screen' parameter to lineptr() in terminal.c, where 0 and 1
represent the default and alternate screens. There's no obvious
reason why one of those should be considered 'true' or 'positive'
or 'success' - they're just indices - so I've left it as int.
ssh_scp_recv had particularly confusing semantics for its previous int
return value: its call sites used '<= 0' to check for error, but it
never actually returned a negative number, just 0 or 1. Now the
function and its call sites agree that it's a bool.
In a couple of places I've renamed variables called 'ret', because I
don't like that name any more - it's unclear whether it means the
return value (in preparation) for the _containing_ function or the
return value received from a subroutine call, and occasionally I've
accidentally used the same variable for both and introduced a bug. So
where one of those got in my way, I've renamed it to 'toret' or 'retd'
(the latter short for 'returned') in line with my usual modern
practice, but I haven't done a thorough job of finding all of them.
Finally, one amusing side effect of doing this is that I've had to
separate quite a few chained assignments. It used to be perfectly fine
to write 'a = b = c = TRUE' when a,b,c were int and TRUE was just a
the 'true' defined by stdbool.h, that idiom provokes a warning from
gcc: 'suggest parentheses around assignment used as truth value'!
2018-11-02 19:23:19 +00:00
|
|
|
bool used_dtf = false;
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
int vtmode;
|
2001-09-07 22:49:17 +00:00
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
/* Decide on the Line and Font codepages */
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
ucsdata->line_codepage = decode_codepage(conf_get_str(conf,
|
2019-09-08 19:29:00 +00:00
|
|
|
CONF_line_codepage));
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2019-09-08 19:29:00 +00:00
|
|
|
if (ucsdata->font_codepage <= 0) {
|
|
|
|
ucsdata->font_codepage=0;
|
|
|
|
ucsdata->dbcs_screenfont=false;
|
2001-05-19 15:21:05 +00:00
|
|
|
}
|
|
|
|
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
vtmode = conf_get_int(conf, CONF_vtmode);
|
|
|
|
if (vtmode == VT_OEMONLY) {
|
2019-09-08 19:29:00 +00:00
|
|
|
ucsdata->font_codepage = 437;
|
|
|
|
ucsdata->dbcs_screenfont = false;
|
|
|
|
if (ucsdata->line_codepage <= 0)
|
|
|
|
ucsdata->line_codepage = GetACP();
|
2003-01-14 18:28:23 +00:00
|
|
|
} else if (ucsdata->line_codepage <= 0)
|
2019-09-08 19:29:00 +00:00
|
|
|
ucsdata->line_codepage = ucsdata->font_codepage;
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
/* Collect screen font ucs table */
|
2003-01-14 18:28:23 +00:00
|
|
|
if (ucsdata->dbcs_screenfont || ucsdata->font_codepage == 0) {
|
2019-09-08 19:29:00 +00:00
|
|
|
get_unitab(ucsdata->font_codepage, ucsdata->unitab_font, 2);
|
|
|
|
for (i = 128; i < 256; i++)
|
|
|
|
ucsdata->unitab_font[i] = (WCHAR) (CSET_ACP + i);
|
2001-05-10 08:34:20 +00:00
|
|
|
} else {
|
2019-09-08 19:29:00 +00:00
|
|
|
get_unitab(ucsdata->font_codepage, ucsdata->unitab_font, 1);
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2019-09-08 19:29:00 +00:00
|
|
|
/* CP437 fonts are often broken ... */
|
|
|
|
if (ucsdata->font_codepage == 437)
|
|
|
|
ucsdata->unitab_font[0] = ucsdata->unitab_font[255] = 0xFFFF;
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
if (vtmode == VT_XWINDOWS)
|
2019-09-08 19:29:00 +00:00
|
|
|
memcpy(ucsdata->unitab_font + 1, unitab_xterm_std,
|
|
|
|
sizeof(unitab_xterm_std));
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
/* Collect OEMCP ucs table */
|
2003-01-14 18:28:23 +00:00
|
|
|
get_unitab(CP_OEMCP, ucsdata->unitab_oemcp, 1);
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2001-05-19 14:12:41 +00:00
|
|
|
/* Collect CP437 ucs table for SCO acs */
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
if (vtmode == VT_OEMANSI || vtmode == VT_XWINDOWS)
|
2019-09-08 19:29:00 +00:00
|
|
|
memcpy(ucsdata->unitab_scoacs, ucsdata->unitab_oemcp,
|
|
|
|
sizeof(ucsdata->unitab_scoacs));
|
2001-05-19 14:12:41 +00:00
|
|
|
else
|
2019-09-08 19:29:00 +00:00
|
|
|
get_unitab(437, ucsdata->unitab_scoacs, 1);
|
2001-05-19 14:12:41 +00:00
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
/* Collect line set ucs table */
|
2003-01-14 18:28:23 +00:00
|
|
|
if (ucsdata->line_codepage == ucsdata->font_codepage &&
|
2019-09-08 19:29:00 +00:00
|
|
|
(ucsdata->dbcs_screenfont ||
|
|
|
|
vtmode == VT_POORMAN || ucsdata->font_codepage==0)) {
|
|
|
|
|
|
|
|
/* For DBCS and POOR fonts force direct to font */
|
|
|
|
used_dtf = true;
|
|
|
|
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;
|
2001-05-10 08:34:20 +00:00
|
|
|
} else {
|
2019-09-08 19:29:00 +00:00
|
|
|
get_unitab(ucsdata->line_codepage, ucsdata->unitab_line, 0);
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
#if 0
|
Start using C99 variadic macros.
In the past, I've had a lot of macros which you call with double
parentheses, along the lines of debug(("format string", params)), so
that the inner parens protect the commas and permit the macro to treat
the whole printf-style argument list as one macro argument.
That's all very well, but it's a bit inconvenient (it doesn't leave
you any way to implement such a macro by prepending another argument
to the list), and now this code base's rules allow C99isms, I can
switch all those macros to using a single pair of parens, using the
C99 ability to say '...' in the parameter list of the #define and get
at the corresponding suffix of the arguments as __VA_ARGS__.
So I'm doing it. I've made the following printf-style macros variadic:
bpp_logevent, ppl_logevent, ppl_printf and debug.
While I'm here, I've also fixed up a collection of conditioned-out
calls to debug() in the Windows front end which were clearly expecting
a macro with a different calling syntax, because they had an integer
parameter first. If I ever have a need to condition those back in,
they should actually work now.
2018-12-08 20:32:31 +00:00
|
|
|
debug("Line cp%d, Font cp%d%s\n", ucsdata->line_codepage,
|
|
|
|
ucsdata->font_codepage, ucsdata->dbcs_screenfont ? " DBCS" : "");
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
for (i = 0; i < 256; i += 16) {
|
2019-09-08 19:29:00 +00:00
|
|
|
for (j = 0; j < 16; j++) {
|
|
|
|
debug("%04x%s", ucsdata->unitab_line[i + j], j == 15 ? "" : ",");
|
|
|
|
}
|
|
|
|
debug("\n");
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* VT100 graphics - NB: Broken for non-ascii CP's */
|
2003-01-14 18:28:23 +00:00
|
|
|
memcpy(ucsdata->unitab_xterm, ucsdata->unitab_line,
|
2019-09-08 19:29:00 +00:00
|
|
|
sizeof(ucsdata->unitab_xterm));
|
2003-01-14 18:28:23 +00:00
|
|
|
memcpy(ucsdata->unitab_xterm + '`', unitab_xterm_std,
|
2019-09-08 19:29:00 +00:00
|
|
|
sizeof(unitab_xterm_std));
|
2003-01-14 18:28:23 +00:00
|
|
|
ucsdata->unitab_xterm['_'] = ' ';
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
if (!used_dtf) {
|
2022-06-01 07:35:12 +00:00
|
|
|
/* Make sure a reverse mapping exists for this code page. */
|
|
|
|
make_reverse_mapping(ucsdata->line_codepage, ucsdata->unitab_line);
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Find the line control characters. */
|
|
|
|
for (i = 0; i < 256; i++)
|
2019-09-08 19:29:00 +00:00
|
|
|
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;
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
/* Generate line->screen direct conversion links. */
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
if (vtmode == VT_OEMANSI || vtmode == VT_XWINDOWS)
|
2019-09-08 19:29:00 +00:00
|
|
|
link_font(ucsdata->unitab_scoacs, ucsdata->unitab_oemcp, CSET_OEMCP);
|
2001-05-19 14:12:41 +00:00
|
|
|
|
Re-engineering of terminal emulator, phase 1.
The active terminal screen is no longer an array of `unsigned long'
encoding 16-bit Unicode plus 16 attribute bits. Now it's an array of
`termchar' structures, which currently have 32-bit Unicode and 32
attribute bits but which will probably expand further in future.
To prevent bloat of the memory footprint, I've introduced a mostly
RLE-like compression scheme for storing scrollback: each line is
compressed into a compact (but hard to modify) form when it moves
into the term->scrollback tree, and is temporarily decompressed when
the user wants to scroll back over it. My initial tests suggest that
this compression averages about 1/4 of the previous (32 bits per
character cell) data size in typical output, which means this is an
improvement even without counting the new ability to extend the
information stored in each character cell.
Another beneficial side effect is that the insane format in which
Unicode was passed to front ends through do_text() has now been
rendered sane.
Testing is incomplete; this _may_ still have instabilities. Windows
and Unix front ends both seem to work as far as I've looked, but I
haven't yet looked very hard. The Mac front end I've edited (it
seemed obvious how to change it) but I can't compile or test it.
As an immediate functional effect, the terminal emulator now
supports full 32-bit Unicode to whatever extent the host platform
allows it to. For example, if you output a 4-or-more-byte UTF-8
character in Unix pterm, it will not display it properly, but it
will correctly paste it back out in a UTF8_STRING selection. Windows
is more restricted, sadly.
[originally from svn r4609]
2004-10-13 11:50:16 +00:00
|
|
|
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);
|
2001-05-10 08:34:20 +00:00
|
|
|
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
if (vtmode == VT_OEMANSI || vtmode == VT_XWINDOWS) {
|
2019-09-08 19:29:00 +00:00
|
|
|
link_font(ucsdata->unitab_line, ucsdata->unitab_oemcp, CSET_OEMCP);
|
|
|
|
link_font(ucsdata->unitab_xterm, ucsdata->unitab_oemcp, CSET_OEMCP);
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
|
2003-01-14 18:28:23 +00:00
|
|
|
if (ucsdata->dbcs_screenfont &&
|
2019-09-08 19:29:00 +00:00
|
|
|
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 + '\\';
|
2001-09-15 15:54:24 +00:00
|
|
|
}
|
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
/* Last chance, if !unicode then try poorman links. */
|
Post-release destabilisation! Completely remove the struct type
'Config' in putty.h, which stores all PuTTY's settings and includes an
arbitrary length limit on every single one of those settings which is
stored in string form. In place of it is 'Conf', an opaque data type
everywhere outside the new file conf.c, which stores a list of (key,
value) pairs in which every key contains an integer identifying a
configuration setting, and for some of those integers the key also
contains extra parts (so that, for instance, CONF_environmt is a
string-to-string mapping). Everywhere that a Config was previously
used, a Conf is now; everywhere there was a Config structure copy,
conf_copy() is called; every lookup, adjustment, load and save
operation on a Config has been rewritten; and there's a mechanism for
serialising a Conf into a binary blob and back for use with Duplicate
Session.
User-visible effects of this change _should_ be minimal, though I
don't doubt I've introduced one or two bugs here and there which will
eventually be found. The _intended_ visible effects of this change are
that all arbitrary limits on configuration strings and lists (e.g.
limit on number of port forwardings) should now disappear; that list
boxes in the configuration will now be displayed in a sorted order
rather than the arbitrary order in which they were added to the list
(since the underlying data structure is now a sorted tree234 rather
than an ad-hoc comma-separated string); and one more specific change,
which is that local and dynamic port forwardings on the same port
number are now mutually exclusive in the configuration (putting 'D' in
the key rather than the value was a mistake in the first place).
One other reorganisation as a result of this is that I've moved all
the dialog.c standard handlers (dlg_stdeditbox_handler and friends)
out into config.c, because I can't really justify calling them generic
any more. When they took a pointer to an arbitrary structure type and
the offset of a field within that structure, they were independent of
whether that structure was a Config or something completely different,
but now they really do expect to talk to a Conf, which can _only_ be
used for PuTTY configuration, so I've renamed them all things like
conf_editbox_handler and moved them out of the nominally independent
dialog-box management module into the PuTTY-specific config.c.
[originally from svn r9214]
2011-07-14 18:52:21 +00:00
|
|
|
if (vtmode != VT_UNICODE) {
|
2019-09-08 19:29:00 +00:00
|
|
|
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] =
|
2022-08-03 19:48:46 +00:00
|
|
|
(WCHAR) (CSET_ACP + poorman_vt100[i - 96]);
|
2022-12-28 15:32:24 +00:00
|
|
|
for (i = 128; i < 256; i++)
|
2019-09-08 19:29:00 +00:00
|
|
|
if (!DIRECT_FONT(ucsdata->unitab_scoacs[i]))
|
|
|
|
ucsdata->unitab_scoacs[i] =
|
|
|
|
(WCHAR) (CSET_ACP + poorman_scoacs[i - 128]);
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2023-02-18 14:10:01 +00:00
|
|
|
void init_ucs_generic(Conf *conf, struct unicode_data *ucsdata)
|
|
|
|
{
|
|
|
|
init_ucs(conf, ucsdata);
|
|
|
|
}
|
|
|
|
|
2022-08-03 19:48:46 +00:00
|
|
|
static void link_font(WCHAR *line_tbl, WCHAR *font_tbl, WCHAR attr)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
2001-09-07 23:02:07 +00:00
|
|
|
int font_index, line_index, i;
|
|
|
|
for (line_index = 0; line_index < 256; line_index++) {
|
2019-09-08 19:29:00 +00:00
|
|
|
if (DIRECT_FONT(line_tbl[line_index]))
|
|
|
|
continue;
|
2022-12-28 15:32:24 +00:00
|
|
|
for (i = 0; i < 256; i++) {
|
2019-09-08 19:29:00 +00:00
|
|
|
font_index = ((32 + i) & 0xFF);
|
|
|
|
if (line_tbl[line_index] == font_tbl[font_index]) {
|
|
|
|
line_tbl[line_index] = (WCHAR) (attr + font_index);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2001-09-18 18:51:10 +00:00
|
|
|
wchar_t xlat_uskbd2cyrllic(int ch)
|
|
|
|
{
|
2003-01-14 18:43:45 +00:00
|
|
|
static const wchar_t cyrtab[] = {
|
2001-09-18 18:51:10 +00:00
|
|
|
0, 1, 2, 3, 4, 5, 6, 7,
|
|
|
|
8, 9, 10, 11, 12, 13, 14, 15,
|
|
|
|
16, 17, 18, 19, 20, 21, 22, 23,
|
|
|
|
24, 25, 26, 27, 28, 29, 30, 31,
|
|
|
|
32, 33, 0x042d, 35, 36, 37, 38, 0x044d,
|
|
|
|
40, 41, 42, 0x0406, 0x0431, 0x0454, 0x044e, 0x002e,
|
|
|
|
48, 49, 50, 51, 52, 53, 54, 55,
|
|
|
|
56, 57, 0x0416, 0x0436, 0x0411, 0x0456, 0x042e, 0x002c,
|
|
|
|
64, 0x0424, 0x0418, 0x0421, 0x0412, 0x0423, 0x0410, 0x041f,
|
|
|
|
0x0420, 0x0428, 0x041e, 0x041b, 0x0414, 0x042c, 0x0422, 0x0429,
|
|
|
|
0x0417, 0x0419, 0x041a, 0x042b, 0x0415, 0x0413, 0x041c, 0x0426,
|
|
|
|
0x0427, 0x041d, 0x042f, 0x0445, 0x0457, 0x044a, 94, 0x0404,
|
|
|
|
96, 0x0444, 0x0438, 0x0441, 0x0432, 0x0443, 0x0430, 0x043f,
|
|
|
|
0x0440, 0x0448, 0x043e, 0x043b, 0x0434, 0x044c, 0x0442, 0x0449,
|
|
|
|
0x0437, 0x0439, 0x043a, 0x044b, 0x0435, 0x0433, 0x043c, 0x0446,
|
|
|
|
0x0447, 0x043d, 0x044f, 0x0425, 0x0407, 0x042a, 126, 127
|
2022-08-03 19:48:46 +00:00
|
|
|
};
|
2001-09-18 18:51:10 +00:00
|
|
|
return cyrtab[ch&0x7F];
|
|
|
|
}
|
|
|
|
|
2022-09-03 11:02:48 +00:00
|
|
|
static int check_compose_internal(int first, int second, int recurse)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
|
|
|
|
2003-01-14 18:43:45 +00:00
|
|
|
static const struct {
|
2019-09-08 19:29:00 +00:00
|
|
|
char first, second;
|
2017-04-08 14:06:27 +00:00
|
|
|
wchar_t composed;
|
2001-05-10 08:34:20 +00:00
|
|
|
} composetbl[] = {
|
2017-04-08 14:06:27 +00:00
|
|
|
{0x2b, 0x2b, 0x0023},
|
|
|
|
{0x41, 0x41, 0x0040},
|
|
|
|
{0x28, 0x28, 0x005b},
|
|
|
|
{0x2f, 0x2f, 0x005c},
|
|
|
|
{0x29, 0x29, 0x005d},
|
|
|
|
{0x28, 0x2d, 0x007b},
|
|
|
|
{0x2d, 0x29, 0x007d},
|
|
|
|
{0x2f, 0x5e, 0x007c},
|
|
|
|
{0x21, 0x21, 0x00a1},
|
|
|
|
{0x43, 0x2f, 0x00a2},
|
|
|
|
{0x43, 0x7c, 0x00a2},
|
|
|
|
{0x4c, 0x2d, 0x00a3},
|
|
|
|
{0x4c, 0x3d, 0x20a4},
|
|
|
|
{0x58, 0x4f, 0x00a4},
|
|
|
|
{0x58, 0x30, 0x00a4},
|
|
|
|
{0x59, 0x2d, 0x00a5},
|
|
|
|
{0x59, 0x3d, 0x00a5},
|
|
|
|
{0x7c, 0x7c, 0x00a6},
|
|
|
|
{0x53, 0x4f, 0x00a7},
|
|
|
|
{0x53, 0x21, 0x00a7},
|
|
|
|
{0x53, 0x30, 0x00a7},
|
|
|
|
{0x22, 0x22, 0x00a8},
|
|
|
|
{0x43, 0x4f, 0x00a9},
|
|
|
|
{0x43, 0x30, 0x00a9},
|
|
|
|
{0x41, 0x5f, 0x00aa},
|
|
|
|
{0x3c, 0x3c, 0x00ab},
|
|
|
|
{0x2c, 0x2d, 0x00ac},
|
|
|
|
{0x2d, 0x2d, 0x00ad},
|
|
|
|
{0x52, 0x4f, 0x00ae},
|
|
|
|
{0x2d, 0x5e, 0x00af},
|
|
|
|
{0x30, 0x5e, 0x00b0},
|
|
|
|
{0x2b, 0x2d, 0x00b1},
|
|
|
|
{0x32, 0x5e, 0x00b2},
|
|
|
|
{0x33, 0x5e, 0x00b3},
|
|
|
|
{0x27, 0x27, 0x00b4},
|
|
|
|
{0x2f, 0x55, 0x00b5},
|
|
|
|
{0x50, 0x21, 0x00b6},
|
|
|
|
{0x2e, 0x5e, 0x00b7},
|
|
|
|
{0x2c, 0x2c, 0x00b8},
|
|
|
|
{0x31, 0x5e, 0x00b9},
|
|
|
|
{0x4f, 0x5f, 0x00ba},
|
|
|
|
{0x3e, 0x3e, 0x00bb},
|
|
|
|
{0x31, 0x34, 0x00bc},
|
|
|
|
{0x31, 0x32, 0x00bd},
|
|
|
|
{0x33, 0x34, 0x00be},
|
|
|
|
{0x3f, 0x3f, 0x00bf},
|
|
|
|
{0x60, 0x41, 0x00c0},
|
|
|
|
{0x27, 0x41, 0x00c1},
|
|
|
|
{0x5e, 0x41, 0x00c2},
|
|
|
|
{0x7e, 0x41, 0x00c3},
|
|
|
|
{0x22, 0x41, 0x00c4},
|
|
|
|
{0x2a, 0x41, 0x00c5},
|
|
|
|
{0x41, 0x45, 0x00c6},
|
|
|
|
{0x2c, 0x43, 0x00c7},
|
|
|
|
{0x60, 0x45, 0x00c8},
|
|
|
|
{0x27, 0x45, 0x00c9},
|
|
|
|
{0x5e, 0x45, 0x00ca},
|
|
|
|
{0x22, 0x45, 0x00cb},
|
|
|
|
{0x60, 0x49, 0x00cc},
|
|
|
|
{0x27, 0x49, 0x00cd},
|
|
|
|
{0x5e, 0x49, 0x00ce},
|
|
|
|
{0x22, 0x49, 0x00cf},
|
|
|
|
{0x2d, 0x44, 0x00d0},
|
|
|
|
{0x7e, 0x4e, 0x00d1},
|
|
|
|
{0x60, 0x4f, 0x00d2},
|
|
|
|
{0x27, 0x4f, 0x00d3},
|
|
|
|
{0x5e, 0x4f, 0x00d4},
|
|
|
|
{0x7e, 0x4f, 0x00d5},
|
|
|
|
{0x22, 0x4f, 0x00d6},
|
|
|
|
{0x58, 0x58, 0x00d7},
|
|
|
|
{0x2f, 0x4f, 0x00d8},
|
|
|
|
{0x60, 0x55, 0x00d9},
|
|
|
|
{0x27, 0x55, 0x00da},
|
|
|
|
{0x5e, 0x55, 0x00db},
|
|
|
|
{0x22, 0x55, 0x00dc},
|
|
|
|
{0x27, 0x59, 0x00dd},
|
|
|
|
{0x48, 0x54, 0x00de},
|
|
|
|
{0x73, 0x73, 0x00df},
|
|
|
|
{0x60, 0x61, 0x00e0},
|
|
|
|
{0x27, 0x61, 0x00e1},
|
|
|
|
{0x5e, 0x61, 0x00e2},
|
|
|
|
{0x7e, 0x61, 0x00e3},
|
|
|
|
{0x22, 0x61, 0x00e4},
|
|
|
|
{0x2a, 0x61, 0x00e5},
|
|
|
|
{0x61, 0x65, 0x00e6},
|
|
|
|
{0x2c, 0x63, 0x00e7},
|
|
|
|
{0x60, 0x65, 0x00e8},
|
|
|
|
{0x27, 0x65, 0x00e9},
|
|
|
|
{0x5e, 0x65, 0x00ea},
|
|
|
|
{0x22, 0x65, 0x00eb},
|
|
|
|
{0x60, 0x69, 0x00ec},
|
|
|
|
{0x27, 0x69, 0x00ed},
|
|
|
|
{0x5e, 0x69, 0x00ee},
|
|
|
|
{0x22, 0x69, 0x00ef},
|
|
|
|
{0x2d, 0x64, 0x00f0},
|
|
|
|
{0x7e, 0x6e, 0x00f1},
|
|
|
|
{0x60, 0x6f, 0x00f2},
|
|
|
|
{0x27, 0x6f, 0x00f3},
|
|
|
|
{0x5e, 0x6f, 0x00f4},
|
|
|
|
{0x7e, 0x6f, 0x00f5},
|
|
|
|
{0x22, 0x6f, 0x00f6},
|
|
|
|
{0x3a, 0x2d, 0x00f7},
|
|
|
|
{0x6f, 0x2f, 0x00f8},
|
|
|
|
{0x60, 0x75, 0x00f9},
|
|
|
|
{0x27, 0x75, 0x00fa},
|
|
|
|
{0x5e, 0x75, 0x00fb},
|
|
|
|
{0x22, 0x75, 0x00fc},
|
|
|
|
{0x27, 0x79, 0x00fd},
|
|
|
|
{0x68, 0x74, 0x00fe},
|
|
|
|
{0x22, 0x79, 0x00ff},
|
|
|
|
/* Unicode extras. */
|
|
|
|
{0x6f, 0x65, 0x0153},
|
|
|
|
{0x4f, 0x45, 0x0152},
|
|
|
|
/* Compose pairs from UCS */
|
|
|
|
{0x41, 0x2D, 0x0100},
|
|
|
|
{0x61, 0x2D, 0x0101},
|
|
|
|
{0x43, 0x27, 0x0106},
|
|
|
|
{0x63, 0x27, 0x0107},
|
|
|
|
{0x43, 0x5E, 0x0108},
|
|
|
|
{0x63, 0x5E, 0x0109},
|
|
|
|
{0x45, 0x2D, 0x0112},
|
|
|
|
{0x65, 0x2D, 0x0113},
|
|
|
|
{0x47, 0x5E, 0x011C},
|
|
|
|
{0x67, 0x5E, 0x011D},
|
|
|
|
{0x47, 0x2C, 0x0122},
|
|
|
|
{0x67, 0x2C, 0x0123},
|
|
|
|
{0x48, 0x5E, 0x0124},
|
|
|
|
{0x68, 0x5E, 0x0125},
|
|
|
|
{0x49, 0x7E, 0x0128},
|
|
|
|
{0x69, 0x7E, 0x0129},
|
|
|
|
{0x49, 0x2D, 0x012A},
|
|
|
|
{0x69, 0x2D, 0x012B},
|
|
|
|
{0x4A, 0x5E, 0x0134},
|
|
|
|
{0x6A, 0x5E, 0x0135},
|
|
|
|
{0x4B, 0x2C, 0x0136},
|
|
|
|
{0x6B, 0x2C, 0x0137},
|
|
|
|
{0x4C, 0x27, 0x0139},
|
|
|
|
{0x6C, 0x27, 0x013A},
|
|
|
|
{0x4C, 0x2C, 0x013B},
|
|
|
|
{0x6C, 0x2C, 0x013C},
|
|
|
|
{0x4E, 0x27, 0x0143},
|
|
|
|
{0x6E, 0x27, 0x0144},
|
|
|
|
{0x4E, 0x2C, 0x0145},
|
|
|
|
{0x6E, 0x2C, 0x0146},
|
|
|
|
{0x4F, 0x2D, 0x014C},
|
|
|
|
{0x6F, 0x2D, 0x014D},
|
|
|
|
{0x52, 0x27, 0x0154},
|
|
|
|
{0x72, 0x27, 0x0155},
|
|
|
|
{0x52, 0x2C, 0x0156},
|
|
|
|
{0x72, 0x2C, 0x0157},
|
|
|
|
{0x53, 0x27, 0x015A},
|
|
|
|
{0x73, 0x27, 0x015B},
|
|
|
|
{0x53, 0x5E, 0x015C},
|
|
|
|
{0x73, 0x5E, 0x015D},
|
|
|
|
{0x53, 0x2C, 0x015E},
|
|
|
|
{0x73, 0x2C, 0x015F},
|
|
|
|
{0x54, 0x2C, 0x0162},
|
|
|
|
{0x74, 0x2C, 0x0163},
|
|
|
|
{0x55, 0x7E, 0x0168},
|
|
|
|
{0x75, 0x7E, 0x0169},
|
|
|
|
{0x55, 0x2D, 0x016A},
|
|
|
|
{0x75, 0x2D, 0x016B},
|
|
|
|
{0x55, 0x2A, 0x016E},
|
|
|
|
{0x75, 0x2A, 0x016F},
|
|
|
|
{0x57, 0x5E, 0x0174},
|
|
|
|
{0x77, 0x5E, 0x0175},
|
|
|
|
{0x59, 0x5E, 0x0176},
|
|
|
|
{0x79, 0x5E, 0x0177},
|
|
|
|
{0x59, 0x22, 0x0178},
|
|
|
|
{0x5A, 0x27, 0x0179},
|
|
|
|
{0x7A, 0x27, 0x017A},
|
|
|
|
{0x47, 0x27, 0x01F4},
|
|
|
|
{0x67, 0x27, 0x01F5},
|
|
|
|
{0x4E, 0x60, 0x01F8},
|
|
|
|
{0x6E, 0x60, 0x01F9},
|
|
|
|
{0x45, 0x2C, 0x0228},
|
|
|
|
{0x65, 0x2C, 0x0229},
|
|
|
|
{0x59, 0x2D, 0x0232},
|
|
|
|
{0x79, 0x2D, 0x0233},
|
|
|
|
{0x44, 0x2C, 0x1E10},
|
|
|
|
{0x64, 0x2C, 0x1E11},
|
|
|
|
{0x47, 0x2D, 0x1E20},
|
|
|
|
{0x67, 0x2D, 0x1E21},
|
|
|
|
{0x48, 0x22, 0x1E26},
|
|
|
|
{0x68, 0x22, 0x1E27},
|
|
|
|
{0x48, 0x2C, 0x1E28},
|
|
|
|
{0x68, 0x2C, 0x1E29},
|
|
|
|
{0x4B, 0x27, 0x1E30},
|
|
|
|
{0x6B, 0x27, 0x1E31},
|
|
|
|
{0x4D, 0x27, 0x1E3E},
|
|
|
|
{0x6D, 0x27, 0x1E3F},
|
|
|
|
{0x50, 0x27, 0x1E54},
|
|
|
|
{0x70, 0x27, 0x1E55},
|
|
|
|
{0x56, 0x7E, 0x1E7C},
|
|
|
|
{0x76, 0x7E, 0x1E7D},
|
|
|
|
{0x57, 0x60, 0x1E80},
|
|
|
|
{0x77, 0x60, 0x1E81},
|
|
|
|
{0x57, 0x27, 0x1E82},
|
|
|
|
{0x77, 0x27, 0x1E83},
|
|
|
|
{0x57, 0x22, 0x1E84},
|
|
|
|
{0x77, 0x22, 0x1E85},
|
|
|
|
{0x58, 0x22, 0x1E8C},
|
|
|
|
{0x78, 0x22, 0x1E8D},
|
|
|
|
{0x5A, 0x5E, 0x1E90},
|
|
|
|
{0x7A, 0x5E, 0x1E91},
|
|
|
|
{0x74, 0x22, 0x1E97},
|
|
|
|
{0x77, 0x2A, 0x1E98},
|
|
|
|
{0x79, 0x2A, 0x1E99},
|
|
|
|
{0x45, 0x7E, 0x1EBC},
|
|
|
|
{0x65, 0x7E, 0x1EBD},
|
|
|
|
{0x59, 0x60, 0x1EF2},
|
|
|
|
{0x79, 0x60, 0x1EF3},
|
|
|
|
{0x59, 0x7E, 0x1EF8},
|
|
|
|
{0x79, 0x7E, 0x1EF9},
|
|
|
|
/* Compatible/possibles from UCS */
|
|
|
|
{0x49, 0x4A, 0x0132},
|
|
|
|
{0x69, 0x6A, 0x0133},
|
|
|
|
{0x4C, 0x4A, 0x01C7},
|
|
|
|
{0x4C, 0x6A, 0x01C8},
|
|
|
|
{0x6C, 0x6A, 0x01C9},
|
|
|
|
{0x4E, 0x4A, 0x01CA},
|
|
|
|
{0x4E, 0x6A, 0x01CB},
|
|
|
|
{0x6E, 0x6A, 0x01CC},
|
|
|
|
{0x44, 0x5A, 0x01F1},
|
|
|
|
{0x44, 0x7A, 0x01F2},
|
|
|
|
{0x64, 0x7A, 0x01F3},
|
|
|
|
{0x2E, 0x2E, 0x2025},
|
|
|
|
{0x21, 0x21, 0x203C},
|
|
|
|
{0x3F, 0x21, 0x2048},
|
|
|
|
{0x21, 0x3F, 0x2049},
|
|
|
|
{0x52, 0x73, 0x20A8},
|
|
|
|
{0x4E, 0x6F, 0x2116},
|
|
|
|
{0x53, 0x4D, 0x2120},
|
|
|
|
{0x54, 0x4D, 0x2122},
|
|
|
|
{0x49, 0x49, 0x2161},
|
|
|
|
{0x49, 0x56, 0x2163},
|
|
|
|
{0x56, 0x49, 0x2165},
|
|
|
|
{0x49, 0x58, 0x2168},
|
|
|
|
{0x58, 0x49, 0x216A},
|
|
|
|
{0x69, 0x69, 0x2171},
|
|
|
|
{0x69, 0x76, 0x2173},
|
|
|
|
{0x76, 0x69, 0x2175},
|
|
|
|
{0x69, 0x78, 0x2178},
|
|
|
|
{0x78, 0x69, 0x217A},
|
|
|
|
{0x31, 0x30, 0x2469},
|
|
|
|
{0x31, 0x31, 0x246A},
|
|
|
|
{0x31, 0x32, 0x246B},
|
|
|
|
{0x31, 0x33, 0x246C},
|
|
|
|
{0x31, 0x34, 0x246D},
|
|
|
|
{0x31, 0x35, 0x246E},
|
|
|
|
{0x31, 0x36, 0x246F},
|
|
|
|
{0x31, 0x37, 0x2470},
|
|
|
|
{0x31, 0x38, 0x2471},
|
|
|
|
{0x31, 0x39, 0x2472},
|
|
|
|
{0x32, 0x30, 0x2473},
|
|
|
|
{0x31, 0x2E, 0x2488},
|
|
|
|
{0x32, 0x2E, 0x2489},
|
|
|
|
{0x33, 0x2E, 0x248A},
|
|
|
|
{0x34, 0x2E, 0x248B},
|
|
|
|
{0x35, 0x2E, 0x248C},
|
|
|
|
{0x36, 0x2E, 0x248D},
|
|
|
|
{0x37, 0x2E, 0x248E},
|
|
|
|
{0x38, 0x2E, 0x248F},
|
|
|
|
{0x39, 0x2E, 0x2490},
|
|
|
|
{0x64, 0x61, 0x3372},
|
|
|
|
{0x41, 0x55, 0x3373},
|
|
|
|
{0x6F, 0x56, 0x3375},
|
|
|
|
{0x70, 0x63, 0x3376},
|
|
|
|
{0x70, 0x41, 0x3380},
|
|
|
|
{0x6E, 0x41, 0x3381},
|
|
|
|
{0x6D, 0x41, 0x3383},
|
|
|
|
{0x6B, 0x41, 0x3384},
|
|
|
|
{0x4B, 0x42, 0x3385},
|
|
|
|
{0x4D, 0x42, 0x3386},
|
|
|
|
{0x47, 0x42, 0x3387},
|
|
|
|
{0x70, 0x46, 0x338A},
|
|
|
|
{0x6E, 0x46, 0x338B},
|
|
|
|
{0x6D, 0x67, 0x338E},
|
|
|
|
{0x6B, 0x67, 0x338F},
|
|
|
|
{0x48, 0x7A, 0x3390},
|
|
|
|
{0x66, 0x6D, 0x3399},
|
|
|
|
{0x6E, 0x6D, 0x339A},
|
|
|
|
{0x6D, 0x6D, 0x339C},
|
|
|
|
{0x63, 0x6D, 0x339D},
|
|
|
|
{0x6B, 0x6D, 0x339E},
|
|
|
|
{0x50, 0x61, 0x33A9},
|
|
|
|
{0x70, 0x73, 0x33B0},
|
|
|
|
{0x6E, 0x73, 0x33B1},
|
|
|
|
{0x6D, 0x73, 0x33B3},
|
|
|
|
{0x70, 0x56, 0x33B4},
|
|
|
|
{0x6E, 0x56, 0x33B5},
|
|
|
|
{0x6D, 0x56, 0x33B7},
|
|
|
|
{0x6B, 0x56, 0x33B8},
|
|
|
|
{0x4D, 0x56, 0x33B9},
|
|
|
|
{0x70, 0x57, 0x33BA},
|
|
|
|
{0x6E, 0x57, 0x33BB},
|
|
|
|
{0x6D, 0x57, 0x33BD},
|
|
|
|
{0x6B, 0x57, 0x33BE},
|
|
|
|
{0x4D, 0x57, 0x33BF},
|
|
|
|
{0x42, 0x71, 0x33C3},
|
|
|
|
{0x63, 0x63, 0x33C4},
|
|
|
|
{0x63, 0x64, 0x33C5},
|
|
|
|
{0x64, 0x42, 0x33C8},
|
|
|
|
{0x47, 0x79, 0x33C9},
|
|
|
|
{0x68, 0x61, 0x33CA},
|
|
|
|
{0x48, 0x50, 0x33CB},
|
|
|
|
{0x69, 0x6E, 0x33CC},
|
|
|
|
{0x4B, 0x4B, 0x33CD},
|
|
|
|
{0x4B, 0x4D, 0x33CE},
|
|
|
|
{0x6B, 0x74, 0x33CF},
|
|
|
|
{0x6C, 0x6D, 0x33D0},
|
|
|
|
{0x6C, 0x6E, 0x33D1},
|
|
|
|
{0x6C, 0x78, 0x33D3},
|
|
|
|
{0x6D, 0x62, 0x33D4},
|
|
|
|
{0x50, 0x48, 0x33D7},
|
|
|
|
{0x50, 0x52, 0x33DA},
|
|
|
|
{0x73, 0x72, 0x33DB},
|
|
|
|
{0x53, 0x76, 0x33DC},
|
|
|
|
{0x57, 0x62, 0x33DD},
|
|
|
|
{0x66, 0x66, 0xFB00},
|
|
|
|
{0x66, 0x69, 0xFB01},
|
|
|
|
{0x66, 0x6C, 0xFB02},
|
|
|
|
{0x73, 0x74, 0xFB06},
|
|
|
|
{0, 0, 0}
|
2001-05-10 08:34:20 +00:00
|
|
|
}, *c;
|
|
|
|
|
|
|
|
int nc = -1;
|
|
|
|
|
|
|
|
for (c = composetbl; c->first; c++) {
|
2019-09-08 19:29:00 +00:00
|
|
|
if (c->first == first && c->second == second)
|
|
|
|
return c->composed;
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (recurse == 0) {
|
2019-09-08 19:29:00 +00:00
|
|
|
nc = check_compose_internal(second, first, 1);
|
|
|
|
if (nc == -1)
|
2023-03-05 13:15:57 +00:00
|
|
|
nc = check_compose_internal(toupper((unsigned char)first),
|
|
|
|
toupper((unsigned char)second), 1);
|
2019-09-08 19:29:00 +00:00
|
|
|
if (nc == -1)
|
2023-03-05 13:15:57 +00:00
|
|
|
nc = check_compose_internal(toupper((unsigned char)second),
|
|
|
|
toupper((unsigned char)first), 1);
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
return nc;
|
|
|
|
}
|
|
|
|
|
2003-01-14 18:43:45 +00:00
|
|
|
int check_compose(int first, int second)
|
|
|
|
{
|
|
|
|
return check_compose_internal(first, second, 0);
|
|
|
|
}
|
|
|
|
|
2022-06-01 07:29:29 +00:00
|
|
|
int decode_codepage(const char *cp_name)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
2022-06-01 07:29:29 +00:00
|
|
|
const char *s, *d;
|
2002-10-30 18:12:22 +00:00
|
|
|
const struct cp_list_item *cpi;
|
2001-05-10 08:34:20 +00:00
|
|
|
int codepage = -1;
|
|
|
|
CPINFO cpinfo;
|
|
|
|
|
2013-07-22 07:12:05 +00:00
|
|
|
if (!cp_name || !*cp_name)
|
2013-05-25 14:03:19 +00:00
|
|
|
return CP_UTF8; /* default */
|
2001-09-05 21:01:04 +00:00
|
|
|
|
2013-07-22 07:12:05 +00:00
|
|
|
for (cpi = cp_list; cpi->name; cpi++) {
|
|
|
|
s = cp_name;
|
|
|
|
d = cpi->name;
|
|
|
|
for (;;) {
|
2023-03-05 13:15:57 +00:00
|
|
|
while (*s && !isalnum((unsigned char)*s) && *s != ':')
|
2013-07-22 07:12:05 +00:00
|
|
|
s++;
|
2023-03-05 13:15:57 +00:00
|
|
|
while (*d && !isalnum((unsigned char)*d) && *d != ':')
|
2013-07-22 07:12:05 +00:00
|
|
|
d++;
|
|
|
|
if (*s == 0) {
|
|
|
|
codepage = cpi->codepage;
|
|
|
|
if (codepage == CP_UTF8)
|
|
|
|
goto break_break;
|
|
|
|
if (codepage == -1)
|
|
|
|
return codepage;
|
|
|
|
if (codepage == 0) {
|
|
|
|
codepage = 65536 + (cpi - cp_list);
|
|
|
|
goto break_break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (GetCPInfo(codepage, &cpinfo) != 0)
|
|
|
|
goto break_break;
|
|
|
|
}
|
2013-07-22 07:12:10 +00:00
|
|
|
if (tolower((unsigned char)*s++) != tolower((unsigned char)*d++))
|
2013-07-22 07:12:05 +00:00
|
|
|
break;
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
|
2013-07-22 07:12:05 +00:00
|
|
|
d = cp_name;
|
2013-07-22 07:12:10 +00:00
|
|
|
if (tolower((unsigned char)d[0]) == 'c' &&
|
|
|
|
tolower((unsigned char)d[1]) == 'p')
|
2013-07-22 07:12:05 +00:00
|
|
|
d += 2;
|
2013-07-22 07:12:10 +00:00
|
|
|
if (tolower((unsigned char)d[0]) == 'i' &&
|
|
|
|
tolower((unsigned char)d[1]) == 'b' &&
|
|
|
|
tolower((unsigned char)d[2]) == 'm')
|
2013-07-22 07:12:05 +00:00
|
|
|
d += 3;
|
|
|
|
for (s = d; *s >= '0' && *s <= '9'; s++);
|
|
|
|
if (*s == 0 && s != d)
|
2019-09-08 19:29:00 +00:00
|
|
|
codepage = atoi(d); /* CP999 or IBM999 */
|
2013-07-22 07:12:05 +00:00
|
|
|
|
|
|
|
if (codepage == CP_ACP)
|
|
|
|
codepage = GetACP();
|
|
|
|
if (codepage == CP_OEMCP)
|
|
|
|
codepage = GetOEMCP();
|
|
|
|
if (codepage > 65535)
|
|
|
|
codepage = -2;
|
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
break_break:;
|
|
|
|
if (codepage != -1) {
|
2019-09-08 19:29:00 +00:00
|
|
|
if (codepage != CP_UTF8 && codepage < 65536) {
|
|
|
|
if (GetCPInfo(codepage, &cpinfo) == 0) {
|
|
|
|
codepage = -2;
|
|
|
|
} else if (cpinfo.MaxCharSize > 1)
|
|
|
|
codepage = -3;
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
if (codepage == -1 && *cp_name)
|
2019-09-08 19:29:00 +00:00
|
|
|
codepage = -2;
|
2001-05-10 08:34:20 +00:00
|
|
|
return codepage;
|
|
|
|
}
|
|
|
|
|
2003-04-05 16:36:11 +00:00
|
|
|
const char *cp_name(int codepage)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
2002-10-30 18:12:22 +00:00
|
|
|
const struct cp_list_item *cpi, *cpno;
|
2001-05-10 08:34:20 +00:00
|
|
|
static char buf[32];
|
2001-09-05 21:01:04 +00:00
|
|
|
|
|
|
|
if (codepage == -1) {
|
2019-09-08 19:29:00 +00:00
|
|
|
sprintf(buf, "Use font encoding");
|
|
|
|
return buf;
|
2001-09-05 21:01:04 +00:00
|
|
|
}
|
|
|
|
|
2001-05-10 08:34:20 +00:00
|
|
|
if (codepage > 0 && codepage < 65536)
|
2019-09-08 19:29:00 +00:00
|
|
|
sprintf(buf, "CP%03d", codepage);
|
2001-05-10 08:34:20 +00:00
|
|
|
else
|
2019-09-08 19:29:00 +00:00
|
|
|
*buf = 0;
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
if (codepage >= 65536) {
|
2019-09-08 19:29:00 +00:00
|
|
|
cpno = 0;
|
|
|
|
for (cpi = cp_list; cpi->name; cpi++)
|
|
|
|
if (cpi == cp_list + (codepage - 65536)) {
|
|
|
|
cpno = cpi;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (cpno)
|
|
|
|
for (cpi = cp_list; cpi->name; cpi++) {
|
|
|
|
if (cpno->cp_table == cpi->cp_table)
|
|
|
|
return cpi->name;
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
} else {
|
2019-09-08 19:29:00 +00:00
|
|
|
for (cpi = cp_list; cpi->name; cpi++) {
|
|
|
|
if (codepage == cpi->codepage)
|
|
|
|
return cpi->name;
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
2001-08-12 19:25:21 +00:00
|
|
|
/*
|
|
|
|
* Return the nth code page in the list, for use in the GUI
|
|
|
|
* configurer.
|
|
|
|
*/
|
2003-04-05 16:36:11 +00:00
|
|
|
const char *cp_enumerate(int index)
|
2001-08-12 19:25:21 +00:00
|
|
|
{
|
|
|
|
if (index < 0 || index >= lenof(cp_list))
|
2019-09-08 19:29:00 +00:00
|
|
|
return NULL;
|
2001-08-12 19:25:21 +00:00
|
|
|
return cp_list[index].name;
|
|
|
|
}
|
|
|
|
|
2022-08-03 19:48:46 +00:00
|
|
|
void get_unitab(int codepage, wchar_t *unitab, int ftype)
|
2001-05-10 08:34:20 +00:00
|
|
|
{
|
|
|
|
char tbuf[4];
|
|
|
|
int i, max = 256, flg = MB_ERR_INVALID_CHARS;
|
|
|
|
|
|
|
|
if (ftype)
|
2019-09-08 19:29:00 +00:00
|
|
|
flg |= MB_USEGLYPHCHARS;
|
2001-05-10 08:34:20 +00:00
|
|
|
if (ftype == 2)
|
2019-09-08 19:29:00 +00:00
|
|
|
max = 128;
|
2001-05-10 08:34:20 +00:00
|
|
|
|
2001-10-28 10:40:11 +00:00
|
|
|
if (codepage == CP_UTF8) {
|
2019-09-08 19:29:00 +00:00
|
|
|
for (i = 0; i < max; i++)
|
|
|
|
unitab[i] = i;
|
|
|
|
return;
|
2001-10-28 10:40:11 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (codepage == CP_ACP)
|
2019-09-08 19:29:00 +00:00
|
|
|
codepage = GetACP();
|
2001-05-10 08:34:20 +00:00
|
|
|
else if (codepage == CP_OEMCP)
|
2019-09-08 19:29:00 +00:00
|
|
|
codepage = GetOEMCP();
|
2001-05-10 08:34:20 +00:00
|
|
|
|
|
|
|
if (codepage > 0 && codepage < 65536) {
|
2019-09-08 19:29:00 +00:00
|
|
|
for (i = 0; i < max; i++) {
|
|
|
|
tbuf[0] = i;
|
2001-05-10 08:34:20 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if (MultiByteToWideChar(codepage, flg, tbuf, 1, unitab+i, 1) != 1)
|
2019-09-08 19:29:00 +00:00
|
|
|
unitab[i] = 0xFFFD;
|
|
|
|
}
|
2001-05-10 08:34:20 +00:00
|
|
|
} else {
|
2019-09-08 19:29:00 +00:00
|
|
|
int j = 256 - cp_list[codepage & 0xFFFF].cp_size;
|
|
|
|
for (i = 0; i < max; i++)
|
|
|
|
unitab[i] = i;
|
|
|
|
for (i = j; i < max; i++)
|
|
|
|
unitab[i] = cp_list[codepage & 0xFFFF].cp_table[i - j];
|
2001-05-10 08:34:20 +00:00
|
|
|
}
|
|
|
|
}
|
2002-10-26 11:08:59 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
bool BinarySink_put_wc_to_mb(
|
|
|
|
BinarySink *bs, int codepage, const wchar_t *wcstr, int wclen,
|
|
|
|
const char *defchr)
|
2002-10-26 11:08:59 +00:00
|
|
|
{
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if (!wclen)
|
|
|
|
return true;
|
|
|
|
|
2022-06-01 07:35:12 +00:00
|
|
|
reverse_mapping *rmap = get_reverse_mapping(codepage);
|
|
|
|
|
|
|
|
if (rmap) {
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
size_t defchr_len = 0;
|
|
|
|
bool defchr_len_known = false;
|
|
|
|
|
2019-09-08 19:29:00 +00:00
|
|
|
/* Do this by array lookup if we can. */
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
for (size_t i = 0; i < wclen; i++) {
|
2019-09-08 19:29:00 +00:00
|
|
|
wchar_t ch = wcstr[i];
|
|
|
|
int by;
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
const char *blk;
|
2019-07-02 20:22:01 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if ((blk = rmap->blocks[(ch >> 8) & 0xFF]) != NULL &&
|
|
|
|
(by = blk[ch & 0xFF]) != '\0')
|
|
|
|
put_byte(bs, by);
|
2019-09-08 19:29:00 +00:00
|
|
|
else if (ch < 0x80)
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
put_byte(bs, ch);
|
|
|
|
else if (defchr) {
|
|
|
|
if (!defchr_len_known) {
|
|
|
|
defchr_len = strlen(defchr);
|
|
|
|
defchr_len_known = true;
|
|
|
|
}
|
|
|
|
put_data(bs, defchr, defchr_len);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
2019-07-02 20:22:01 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
{
|
|
|
|
char internalbuf[2048];
|
|
|
|
char *allocbuf = NULL;
|
|
|
|
size_t allocsize = 0;
|
|
|
|
char *currbuf = internalbuf;
|
|
|
|
size_t currsize = lenof(internalbuf);
|
|
|
|
bool success;
|
|
|
|
|
|
|
|
BOOL defused = false;
|
|
|
|
BOOL *defusedp = &defused;
|
|
|
|
|
|
|
|
if (codepage == CP_UTF8 || !defchr[0]) {
|
|
|
|
/*
|
|
|
|
* The Win32 API spec says that defchr and defused must be
|
|
|
|
* NULL when doing a UTF-8 conversion, on pain of
|
|
|
|
* ERROR_INVALID_PARAMETER.
|
|
|
|
*
|
|
|
|
* Also, translate defchr="" on input to NULL in the Win32
|
|
|
|
* API.
|
|
|
|
*/
|
|
|
|
defchr = NULL;
|
|
|
|
defusedp = NULL;
|
2019-09-08 19:29:00 +00:00
|
|
|
}
|
2022-03-12 16:16:01 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
while (true) {
|
|
|
|
int ret = WideCharToMultiByte(
|
|
|
|
codepage, 0, wcstr, wclen, currbuf, currsize,
|
|
|
|
defchr, defusedp);
|
2022-03-12 16:16:01 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if (ret) {
|
|
|
|
put_data(bs, currbuf, ret);
|
|
|
|
success = true;
|
|
|
|
break;
|
|
|
|
} else if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
|
|
|
|
success = false;
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
sgrowarray_nm(allocbuf, allocsize, currsize);
|
|
|
|
currbuf = allocbuf;
|
|
|
|
currsize = allocsize;
|
2022-03-12 16:16:01 +00:00
|
|
|
}
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
smemclr(allocbuf, allocsize);
|
|
|
|
if (success)
|
|
|
|
return true;
|
|
|
|
}
|
2022-03-12 16:16:01 +00:00
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
#ifdef LEGACY_WINDOWS
|
|
|
|
/*
|
|
|
|
* Fallback for legacy platforms too old to support UTF-8: if
|
|
|
|
* the codepage is UTF-8, we can do the translation ourselves.
|
|
|
|
*/
|
|
|
|
if (codepage == CP_UTF8 && wclen > 0) {
|
|
|
|
while (wclen > 0) {
|
|
|
|
unsigned long wc = (wclen--, *wcstr++);
|
|
|
|
if (wclen > 0 && IS_SURROGATE_PAIR(wc, *wcstr)) {
|
|
|
|
wc = FROM_SURROGATES(wc, *wcstr);
|
|
|
|
wclen--, wcstr++;
|
|
|
|
}
|
|
|
|
put_utf8_char(bs, wc);
|
2022-03-12 16:16:01 +00:00
|
|
|
}
|
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
return true;
|
2018-10-06 10:45:26 +00:00
|
|
|
}
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
#endif
|
|
|
|
|
|
|
|
/* No other fallbacks are available */
|
|
|
|
return false;
|
2002-10-26 11:08:59 +00:00
|
|
|
}
|
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
bool BinarySink_put_mb_to_wc(
|
|
|
|
BinarySink *bs, int codepage, const char *mbstr, int mblen)
|
2002-10-26 11:08:59 +00:00
|
|
|
{
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if (!mblen)
|
|
|
|
return true;
|
|
|
|
|
2022-05-31 12:13:57 +00:00
|
|
|
if (codepage >= 65536) {
|
|
|
|
/* Character set not known to Windows, so we'll have to
|
|
|
|
* translate it ourself */
|
|
|
|
size_t index = codepage - 65536;
|
|
|
|
if (index >= lenof(cp_list))
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
return false;
|
2022-05-31 12:13:57 +00:00
|
|
|
const struct cp_list_item *cp = &cp_list[index];
|
|
|
|
if (!cp->cp_table)
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
return false;
|
2022-05-31 12:13:57 +00:00
|
|
|
|
|
|
|
unsigned tablebase = 256 - cp->cp_size;
|
|
|
|
|
|
|
|
while (mblen > 0) {
|
|
|
|
mblen--;
|
|
|
|
unsigned c = 0xFF & *mbstr++;
|
|
|
|
wchar_t wc = (c < tablebase ? c : cp->cp_table[c - tablebase]);
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
put_data(bs, &wc, sizeof(wc));
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
{
|
|
|
|
wchar_t internalbuf[1024];
|
|
|
|
wchar_t *allocbuf = NULL;
|
|
|
|
size_t allocsize = 0;
|
|
|
|
wchar_t *currbuf = internalbuf;
|
|
|
|
size_t currsize = lenof(internalbuf);
|
|
|
|
bool success;
|
|
|
|
|
|
|
|
while (true) {
|
|
|
|
int ret = MultiByteToWideChar(
|
|
|
|
codepage, 0, mbstr, mblen, currbuf, currsize);
|
|
|
|
|
|
|
|
if (ret > 0) {
|
|
|
|
put_data(bs, currbuf, ret * sizeof(wchar_t));
|
|
|
|
success = true;
|
|
|
|
break;
|
|
|
|
} else if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
|
|
|
|
success = false;
|
|
|
|
break;
|
2022-05-31 12:13:57 +00:00
|
|
|
} else {
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
sgrowarray_nm(allocbuf, allocsize, currsize);
|
|
|
|
currbuf = allocbuf;
|
|
|
|
currsize = allocsize;
|
2022-05-31 12:13:57 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
smemclr(allocbuf, allocsize * sizeof(wchar_t));
|
|
|
|
if (success)
|
|
|
|
return true;
|
2022-05-31 12:13:57 +00:00
|
|
|
}
|
|
|
|
|
2022-03-12 16:16:01 +00:00
|
|
|
#ifdef LEGACY_WINDOWS
|
|
|
|
/*
|
|
|
|
* Fallback for legacy platforms too old to support UTF-8: if the
|
|
|
|
* codepage is UTF-8, we can do the translation ourselves.
|
|
|
|
*/
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
if (codepage == CP_UTF8 && mblen > 0) {
|
2022-11-09 19:01:04 +00:00
|
|
|
BinarySource src[1];
|
|
|
|
BinarySource_BARE_INIT(src, mbstr, mblen);
|
|
|
|
|
|
|
|
while (get_avail(src)) {
|
2022-03-12 16:16:01 +00:00
|
|
|
wchar_t wcbuf[2];
|
decode_utf8: add an enumeration of failure reasons.
Now you can optionally get back an enum value indicating whether the
character was successfully decoded, or whether U+FFFD was substituted
due to some kind of problem, and if the latter, what problem.
For a start, this allows distinguishing 'real' U+FFFD (encoded
legitimately in the input) from one invented by the decoder. Also, it
allows the recipient of the decode to treat failures differently,
either by passing on a useful error report to the user (as
utf8_unknown_char now does) or by doing something special.
In particular, there are two distinct error codes for a truncated
UTF-8 encoding, depending on whether it was truncated by the end of
the input or by encountering a non-continuation byte. The former code
means that the string is not legal UTF-8 _as it is_, but doesn't rule
out it being a (bytewise) prefix of a legal UTF-8 string - so if a
client is receiving UTF-8 data a byte at a time, they can treat that
error code specially and not make it a fatal error.
2023-02-17 16:39:09 +00:00
|
|
|
size_t nwc = decode_utf8_to_wchar(src, wcbuf, NULL);
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
put_data(bs, wcbuf, nwc * sizeof(wchar_t));
|
2022-03-12 16:16:01 +00:00
|
|
|
}
|
|
|
|
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
return true;
|
2022-03-12 16:16:01 +00:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* No other fallbacks are available */
|
Rework Unicode conversion APIs to use a BinarySink.
The previous mb_to_wc and wc_to_mb had horrible and also buggy APIs.
This commit introduces a fresh pair of functions to replace them,
which generate output by writing to a BinarySink. So it's now up to
the caller to decide whether it wants the output written to a
fixed-size buffer with overflow checking (via buffer_sink), or
dynamically allocated, or even written directly to some other output
channel.
Nothing uses the new functions yet. I plan to migrate things over in
upcoming commits.
What was wrong with the old APIs: they had that awkward undocumented
Windows-specific 'flags' parameter that I described in the previous
commit and took out of the dup_X_to_Y wrappers. But much worse, the
semantics for buffer overflow were not just undocumented but actually
inconsistent. dup_wc_to_mb() in utils assumed that the underlying
wc_to_mb would fill the buffer nearly full and return the size of data
it wrote. In fact, this was untrue in the case where wc_to_mb called
WideCharToMultiByte: that returns straight-up failure, setting the
Windows error code to ERROR_INSUFFICIENT_BUFFER. It _does_ partially
fill the output buffer, but doesn't tell you how much it wrote!
What's wrong with the new API: it's a bit awkward to write a sequence
of wchar_t in native byte order to a byte-oriented BinarySink, so
people using put_mb_to_wc directly have to do some annoying pointer
casting. But I think that's less horrible than the previous APIs.
Another change: in the new API for wc_to_mb, defchr can be "", but not
NULL.
2024-09-24 07:18:48 +00:00
|
|
|
return false;
|
2002-10-26 11:08:59 +00:00
|
|
|
}
|
|
|
|
|
Convert a lot of 'int' variables to 'bool'.
My normal habit these days, in new code, is to treat int and bool as
_almost_ completely separate types. I'm still willing to use C's
implicit test for zero on an integer (e.g. 'if (!blob.len)' is fine,
no need to spell it out as blob.len != 0), but generally, if a
variable is going to be conceptually a boolean, I like to declare it
bool and assign to it using 'true' or 'false' rather than 0 or 1.
PuTTY is an exception, because it predates the C99 bool, and I've
stuck to its existing coding style even when adding new code to it.
But it's been annoying me more and more, so now that I've decided C99
bool is an acceptable thing to require from our toolchain in the first
place, here's a quite thorough trawl through the source doing
'boolification'. Many variables and function parameters are now typed
as bool rather than int; many assignments of 0 or 1 to those variables
are now spelled 'true' or 'false'.
I managed this thorough conversion with the help of a custom clang
plugin that I wrote to trawl the AST and apply heuristics to point out
where things might want changing. So I've even managed to do a decent
job on parts of the code I haven't looked at in years!
To make the plugin's work easier, I pushed platform front ends
generally in the direction of using standard 'bool' in preference to
platform-specific boolean types like Windows BOOL or GTK's gboolean;
I've left the platform booleans in places they _have_ to be for the
platform APIs to work right, but variables only used by my own code
have been converted wherever I found them.
In a few places there are int values that look very like booleans in
_most_ of the places they're used, but have a rarely-used third value,
or a distinction between different nonzero values that most users
don't care about. In these cases, I've _removed_ uses of 'true' and
'false' for the return values, to emphasise that there's something
more subtle going on than a simple boolean answer:
- the 'multisel' field in dialog.h's list box structure, for which
the GTK front end in particular recognises a difference between 1
and 2 but nearly everything else treats as boolean
- the 'urgent' parameter to plug_receive, where 1 vs 2 tells you
something about the specific location of the urgent pointer, but
most clients only care about 0 vs 'something nonzero'
- the return value of wc_match, where -1 indicates a syntax error in
the wildcard.
- the return values from SSH-1 RSA-key loading functions, which use
-1 for 'wrong passphrase' and 0 for all other failures (so any
caller which already knows it's not loading an _encrypted private_
key can treat them as boolean)
- term->esc_query, and the 'query' parameter in toggle_mode in
terminal.c, which _usually_ hold 0 for ESC[123h or 1 for ESC[?123h,
but can also hold -1 for some other intervening character that we
don't support.
In a few places there's an integer that I haven't turned into a bool
even though it really _can_ only take values 0 or 1 (and, as above,
tried to make the call sites consistent in not calling those values
true and false), on the grounds that I thought it would make it more
confusing to imply that the 0 value was in some sense 'negative' or
bad and the 1 positive or good:
- the return value of plug_accepting uses the POSIXish convention of
0=success and nonzero=error; I think if I made it bool then I'd
also want to reverse its sense, and that's a job for a separate
piece of work.
- the 'screen' parameter to lineptr() in terminal.c, where 0 and 1
represent the default and alternate screens. There's no obvious
reason why one of those should be considered 'true' or 'positive'
or 'success' - they're just indices - so I've left it as int.
ssh_scp_recv had particularly confusing semantics for its previous int
return value: its call sites used '<= 0' to check for error, but it
never actually returned a negative number, just 0 or 1. Now the
function and its call sites agree that it's a bool.
In a couple of places I've renamed variables called 'ret', because I
don't like that name any more - it's unclear whether it means the
return value (in preparation) for the _containing_ function or the
return value received from a subroutine call, and occasionally I've
accidentally used the same variable for both and introduced a bug. So
where one of those got in my way, I've renamed it to 'toret' or 'retd'
(the latter short for 'returned') in line with my usual modern
practice, but I haven't done a thorough job of finding all of them.
Finally, one amusing side effect of doing this is that I've had to
separate quite a few chained assignments. It used to be perfectly fine
to write 'a = b = c = TRUE' when a,b,c were int and TRUE was just a
the 'true' defined by stdbool.h, that idiom provokes a warning from
gcc: 'suggest parentheses around assignment used as truth value'!
2018-11-02 19:23:19 +00:00
|
|
|
bool is_dbcs_leadbyte(int codepage, char byte)
|
2002-10-26 11:08:59 +00:00
|
|
|
{
|
|
|
|
return IsDBCSLeadByteEx(codepage, byte);
|
|
|
|
}
|