diff -ur unrtf_0.20.1/src/convert.c.codepages unrtf_0.20.1/src/convert.c
--- unrtf_0.20.1/src/convert.c.codepages 2006-03-15 04:00:20.000000000 +0300
+++ unrtf_0.20.1/src/convert.c 2006-06-14 17:43:40.000000000 +0400
@@ -1,4 +1,6 @@
+
+
/*===========================================================================
GNU UnRTF, a command-line program to convert RTF documents to other formats.
Copyright (C) 2000,2001,2004 Zachary Thayer Smith
@@ -93,6 +95,429 @@
#include "attr.h"
+static CodepageInfo codepages[14] =
+{
+/*-- cp850 --*/
+{
+ 850,
+ {
+ /* 0x80 */
+ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7,
+ 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5,
+ /* 0x90 */
+ 0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9,
+ 0x00ff, 0x00d6, 0x00dc, 0x00f8, 0x00a3, 0x00d8, 0x00d7, 0x0192,
+ /* 0xa0 */
+ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba,
+ 0x00bf, 0x00ae, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb,
+ /* 0xb0 */
+ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, 0x00c2, 0x00c0,
+ 0x00a9, 0x2563, 0x2551, 0x2557, 0x255d, 0x00a2, 0x00a5, 0x2510,
+ /* 0xc0 */
+ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x00e3, 0x00c3,
+ 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4,
+ /* 0xd0 */
+ 0x00f0, 0x00d0, 0x00ca, 0x00cb, 0x00c8, 0x0131, 0x00cd, 0x00ce,
+ 0x00cf, 0x2518, 0x250c, 0x2588, 0x2584, 0x00a6, 0x00cc, 0x2580,
+ /* 0xe0 */
+ 0x00d3, 0x00df, 0x00d4, 0x00d2, 0x00f5, 0x00d5, 0x00b5, 0x00fe,
+ 0x00de, 0x00da, 0x00db, 0x00d9, 0x00fd, 0x00dd, 0x00af, 0x00b4,
+ /* 0xf0 */
+ 0x00ad, 0x00b1, 0x2017, 0x00be, 0x00b6, 0x00a7, 0x00f7, 0x00b8,
+ 0x00b0, 0x00a8, 0x00b7, 0x00b9, 0x00b3, 0x00b2, 0x25a0, 0x00a0,
+ }
+},
+/*-- cp866 --*/
+{
+ 866,
+ {
+ /* 0x80 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0x90 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xa0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xb0 */
+ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
+ 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510,
+ /* 0xc0 */
+ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f,
+ 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567,
+ /* 0xd0 */
+ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b,
+ 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580,
+ /* 0xe0 */
+ 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
+ 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f,
+ /* 0xf0 */
+ 0x0401, 0x0451, 0x0404, 0x0454, 0x0407, 0x0457, 0x040e, 0x045e,
+ 0x00b0, 0x2219, 0x00b7, 0x221a, 0x2116, 0x00a4, 0x25a0, 0x00a0,
+ }
+},
+/*-- cp874 --*/
+{
+ 874,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0x2026, 0xfffd, 0xfffd,
+ 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0xa0 */
+ 0x00a0, 0x0e01, 0x0e02, 0x0e03, 0x0e04, 0x0e05, 0x0e06, 0x0e07,
+ 0x0e08, 0x0e09, 0x0e0a, 0x0e0b, 0x0e0c, 0x0e0d, 0x0e0e, 0x0e0f,
+ /* 0xb0 */
+ 0x0e10, 0x0e11, 0x0e12, 0x0e13, 0x0e14, 0x0e15, 0x0e16, 0x0e17,
+ 0x0e18, 0x0e19, 0x0e1a, 0x0e1b, 0x0e1c, 0x0e1d, 0x0e1e, 0x0e1f,
+ /* 0xc0 */
+ 0x0e20, 0x0e21, 0x0e22, 0x0e23, 0x0e24, 0x0e25, 0x0e26, 0x0e27,
+ 0x0e28, 0x0e29, 0x0e2a, 0x0e2b, 0x0e2c, 0x0e2d, 0x0e2e, 0x0e2f,
+ /* 0xd0 */
+ 0x0e30, 0x0e31, 0x0e32, 0x0e33, 0x0e34, 0x0e35, 0x0e36, 0x0e37,
+ 0x0e38, 0x0e39, 0x0e3a, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0x0e3f,
+ /* 0xe0 */
+ 0x0e40, 0x0e41, 0x0e42, 0x0e43, 0x0e44, 0x0e45, 0x0e46, 0x0e47,
+ 0x0e48, 0x0e49, 0x0e4a, 0x0e4b, 0x0e4c, 0x0e4d, 0x0e4e, 0x0e4f,
+ /* 0xf0 */
+ 0x0e50, 0x0e51, 0x0e52, 0x0e53, 0x0e54, 0x0e55, 0x0e56, 0x0e57,
+ 0x0e58, 0x0e59, 0x0e5a, 0x0e5b, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ }
+},
+/*-- cp1133 --*/
+{
+ 1133,
+ {
+ /* 0x80 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0x90 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xa0 */
+ 0x00a0, 0x0e81, 0x0e82, 0x0e84, 0x0e87, 0x0e88, 0x0eaa, 0x0e8a,
+ 0x0e8d, 0x0e94, 0x0e95, 0x0e96, 0x0e97, 0x0e99, 0x0e9a, 0x0e9b,
+ /* 0xb0 */
+ 0x0e9c, 0x0e9d, 0x0e9e, 0x0e9f, 0x0ea1, 0x0ea2, 0x0ea3, 0x0ea5,
+ 0x0ea7, 0x0eab, 0x0ead, 0x0eae, 0xfffd, 0xfffd, 0xfffd, 0x0eaf,
+ /* 0xc0 */
+ 0x0eb0, 0x0eb2, 0x0eb3, 0x0eb4, 0x0eb5, 0x0eb6, 0x0eb7, 0x0eb8,
+ 0x0eb9, 0x0ebc, 0x0eb1, 0x0ebb, 0x0ebd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0xd0 */
+ 0x0ec0, 0x0ec1, 0x0ec2, 0x0ec3, 0x0ec4, 0x0ec8, 0x0ec9, 0x0eca,
+ 0x0ecb, 0x0ecc, 0x0ecd, 0x0ec6, 0xfffd, 0x0edc, 0x0edd, 0x20ad,
+ /* 0xe0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xf0 */
+ 0x0ed0, 0x0ed1, 0x0ed2, 0x0ed3, 0x0ed4, 0x0ed5, 0x0ed6, 0x0ed7,
+ 0x0ed8, 0x0ed9, 0xfffd, 0xfffd, 0x00a2, 0x00ac, 0x00a6, 0xfffd,
+ }
+},
+/*-- cp1250 --*/
+{
+ 1250,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0xfffd, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0xfffd, 0x2030, 0x0160, 0x2039, 0x015a, 0x0164, 0x017d, 0x0179,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0xfffd, 0x2122, 0x0161, 0x203a, 0x015b, 0x0165, 0x017e, 0x017a,
+ /* 0xa0 */
+ 0x00a0, 0x02c7, 0x02d8, 0x0141, 0x00a4, 0x0104, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x015e, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x017b,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x02db, 0x0142, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x0105, 0x015f, 0x00bb, 0x013d, 0x02dd, 0x013e, 0x017c,
+ /* 0xc0 */
+ 0x0154, 0x00c1, 0x00c2, 0x0102, 0x00c4, 0x0139, 0x0106, 0x00c7,
+ 0x010c, 0x00c9, 0x0118, 0x00cb, 0x011a, 0x00cd, 0x00ce, 0x010e,
+ /* 0xd0 */
+ 0x0110, 0x0143, 0x0147, 0x00d3, 0x00d4, 0x0150, 0x00d6, 0x00d7,
+ 0x0158, 0x016e, 0x00da, 0x0170, 0x00dc, 0x00dd, 0x0162, 0x00df,
+ /* 0xe0 */
+ 0x0155, 0x00e1, 0x00e2, 0x0103, 0x00e4, 0x013a, 0x0107, 0x00e7,
+ 0x010d, 0x00e9, 0x0119, 0x00eb, 0x011b, 0x00ed, 0x00ee, 0x010f,
+ /* 0xf0 */
+ 0x0111, 0x0144, 0x0148, 0x00f3, 0x00f4, 0x0151, 0x00f6, 0x00f7,
+ 0x0159, 0x016f, 0x00fa, 0x0171, 0x00fc, 0x00fd, 0x0163, 0x02d9,
+ }
+},
+/*-- cp1251 --*/
+{
+ 1251,
+ {
+ /* 0x80 */
+ 0x0402, 0x0403, 0x201a, 0x0453, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x20ac, 0x2030, 0x0409, 0x2039, 0x040a, 0x040c, 0x040b, 0x040f,
+ /* 0x90 */
+ 0x0452, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0xfffd, 0x2122, 0x0459, 0x203a, 0x045a, 0x045c, 0x045b, 0x045f,
+ /* 0xa0 */
+ 0x00a0, 0x040e, 0x045e, 0x0408, 0x00a4, 0x0490, 0x00a6, 0x00a7,
+ 0x0401, 0x00a9, 0x0404, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x0407,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x0406, 0x0456, 0x0491, 0x00b5, 0x00b6, 0x00b7,
+ 0x0451, 0x2116, 0x0454, 0x00bb, 0x0458, 0x0405, 0x0455, 0x0457,
+ /* 0xc0 */
+ 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
+ 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f,
+ /* 0xd0 */
+ 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
+ 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f,
+ /* 0xe0 */
+ 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,
+ 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f,
+ /* 0xf0 */
+ 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
+ 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f,
+ }
+},
+/*-- cp1252 --*/
+{
+ 1252,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x02c6, 0x2030, 0x0160, 0x2039, 0x0152, 0xfffd, 0x017d, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x02dc, 0x2122, 0x0161, 0x203a, 0x0153, 0xfffd, 0x017e, 0x0178,
+ /* 0xa0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xb0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xc0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xd0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xe0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xf0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ }
+},
+/*-- cp1253 --*/
+{
+ 1253,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0xfffd, 0x2030, 0xfffd, 0x2039, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0xfffd, 0x2122, 0xfffd, 0x203a, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0xa0 */
+ 0x00a0, 0x0385, 0x0386, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0xfffd, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x2015,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x0384, 0x00b5, 0x00b6, 0x00b7,
+ 0x0388, 0x0389, 0x038a, 0x00bb, 0x038c, 0x00bd, 0x038e, 0x038f,
+ /* 0xc0 */
+ 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
+ 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f,
+ /* 0xd0 */
+ 0x03a0, 0x03a1, 0xfffd, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7,
+ 0x03a8, 0x03a9, 0x03aa, 0x03ab, 0x03ac, 0x03ad, 0x03ae, 0x03af,
+ /* 0xe0 */
+ 0x03b0, 0x03b1, 0x03b2, 0x03b3, 0x03b4, 0x03b5, 0x03b6, 0x03b7,
+ 0x03b8, 0x03b9, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03be, 0x03bf,
+ /* 0xf0 */
+ 0x03c0, 0x03c1, 0x03c2, 0x03c3, 0x03c4, 0x03c5, 0x03c6, 0x03c7,
+ 0x03c8, 0x03c9, 0x03ca, 0x03cb, 0x03cc, 0x03cd, 0x03ce, 0xfffd,
+ }
+},
+/*-- 1254 --*/
+{
+ 1254,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x02c6, 0x2030, 0x0160, 0x2039, 0x0152, 0xfffd, 0xfffd, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x02dc, 0x2122, 0x0161, 0x203a, 0x0153, 0xfffd, 0xfffd, 0x0178,
+ /* 0xa0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xb0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xc0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xd0 */
+ 0x011e, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
+ 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x0130, 0x015e, 0x00df,
+ /* 0xe0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xf0 */
+ 0x011f, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
+ 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x0131, 0x015f, 0x00ff,
+ }
+},
+/*-- cp1255 --*/
+{
+ 1255,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x02c6, 0x2030, 0xfffd, 0x2039, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x02dc, 0x2122, 0xfffd, 0x203a, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0xa0 */
+ 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x20aa, 0x00a5, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
+ /* 0xc0 */
+ 0x05b0, 0x05b1, 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7,
+ 0x05b8, 0x05b9, 0xfffd, 0x05bb, 0x05bc, 0x05bd, 0x05be, 0x05bf,
+ /* 0xd0 */
+ 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f0, 0x05f1, 0x05f2, 0x05f3,
+ 0x05f4, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+ /* 0xe0 */
+ 0x05d0, 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7,
+ 0x05d8, 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df,
+ /* 0xf0 */
+ 0x05e0, 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7,
+ 0x05e8, 0x05e9, 0x05ea, 0xfffd, 0xfffd, 0x200e, 0x200f, 0xfffd,
+ }
+},
+/*-- cp1256 --*/
+{
+ 1256,
+ {
+ /* 0x80 */
+ 0x20ac, 0x067e, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x02c6, 0x2030, 0x0679, 0x2039, 0x0152, 0x0686, 0x0698, 0x0688,
+ /* 0x90 */
+ 0x06af, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x06a9, 0x2122, 0x0691, 0x203a, 0x0153, 0x200c, 0x200d, 0x06ba,
+ /* 0xa0 */
+ 0x00a0, 0x060c, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x06be, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x00b9, 0x061b, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x061f,
+ /* 0xc0 */
+ 0x06c1, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627,
+ 0x0628, 0x0629, 0x062a, 0x062b, 0x062c, 0x062d, 0x062e, 0x062f,
+ /* 0xd0 */
+ 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x00d7,
+ 0x0637, 0x0638, 0x0639, 0x063a, 0x0640, 0x0641, 0x0642, 0x0643,
+ /* 0xe0 */
+ 0x00e0, 0x0644, 0x00e2, 0x0645, 0x0646, 0x0647, 0x0648, 0x00e7,
+ 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x0649, 0x064a, 0x00ee, 0x00ef,
+ /* 0xf0 */
+ 0x064b, 0x064c, 0x064d, 0x064e, 0x00f4, 0x064f, 0x0650, 0x00f7,
+ 0x0651, 0x00f9, 0x0652, 0x00fb, 0x00fc, 0x200e, 0x200f, 0x06d2,
+ }
+},
+{
+ 1257,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0xfffd, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0xfffd, 0x2030, 0xfffd, 0x2039, 0xfffd, 0x00a8, 0x02c7, 0x00b8,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0xfffd, 0x2122, 0xfffd, 0x203a, 0xfffd, 0x00af, 0x02db, 0xfffd,
+ /* 0xa0 */
+ 0x00a0, 0xfffd, 0x00a2, 0x00a3, 0x00a4, 0xfffd, 0x00a6, 0x00a7,
+ 0x00d8, 0x00a9, 0x0156, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00c6,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00f8, 0x00b9, 0x0157, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00e6,
+ /* 0xc0 */
+ 0x0104, 0x012e, 0x0100, 0x0106, 0x00c4, 0x00c5, 0x0118, 0x0112,
+ 0x010c, 0x00c9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012a, 0x013b,
+ /* 0xd0 */
+ 0x0160, 0x0143, 0x0145, 0x00d3, 0x014c, 0x00d5, 0x00d6, 0x00d7,
+ 0x0172, 0x0141, 0x015a, 0x016a, 0x00dc, 0x017b, 0x017d, 0x00df,
+ /* 0xe0 */
+ 0x0105, 0x012f, 0x0101, 0x0107, 0x00e4, 0x00e5, 0x0119, 0x0113,
+ 0x010d, 0x00e9, 0x017a, 0x0117, 0x0123, 0x0137, 0x012b, 0x013c,
+ /* 0xf0 */
+ 0x0161, 0x0144, 0x0146, 0x00f3, 0x014d, 0x00f5, 0x00f6, 0x00f7,
+ 0x0173, 0x0142, 0x015b, 0x016b, 0x00fc, 0x017c, 0x017e, 0x02d9,
+ }
+},
+{
+ 1258,
+ {
+ /* 0x80 */
+ 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x02c6, 0x2030, 0xfffd, 0x2039, 0x0152, 0xfffd, 0xfffd, 0xfffd,
+ /* 0x90 */
+ 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x02dc, 0x2122, 0xfffd, 0x203a, 0x0153, 0xfffd, 0xfffd, 0x0178,
+ /* 0xa0 */
+ 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
+ /* 0xb0 */
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
+ /* 0xc0 */
+ 0x00c0, 0x00c1, 0x00c2, 0x0102, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
+ 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x0300, 0x00cd, 0x00ce, 0x00cf,
+ /* 0xd0 */
+ 0x0110, 0x00d1, 0x0309, 0x00d3, 0x00d4, 0x01a0, 0x00d6, 0x00d7,
+ 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x01af, 0x0303, 0x00df,
+ /* 0xe0 */
+ 0x00e0, 0x00e1, 0x00e2, 0x0103, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
+ 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x0301, 0x00ed, 0x00ee, 0x00ef,
+ /* 0xf0 */
+ 0x0111, 0x00f1, 0x0323, 0x00f3, 0x00f4, 0x01a1, 0x00f6, 0x00f7,
+ 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x01b0, 0x20ab, 0x00ff,
+ }
+},
+/*-- null --*/
+{
+ 0,
+ {
+ /* 0x80 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0x90 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xa0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xb0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xc0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xd0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xe0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ /* 0xf0 */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ }
+},
+};
+
+
extern int nopict_mode;
/*
@@ -101,6 +526,7 @@
static int charset_type=CHARSET_ANSI;
+static CodepageInfo * charset_codepage;
/* Nested tables aren't supported.
@@ -511,7 +937,7 @@
int ch = h2toi (&s2[2]);
char *s3;
- s3 = op_translate_char (op, charset_type, ch, numchar_table);
+ s3 = op_translate_char (op, charset_type, charset_codepage, ch, numchar_table);
if (!s3 || !*s3)
{
printf(op->comment_begin);
@@ -1943,6 +2369,34 @@
}
/*========================================================================
+ * Name: cmd_ansicpg
+ * Purpose: Executes the \ansicpg command.
+ * Args: Word, paragraph align info, and numeric param if any.
+ * Returns: Flag, true only if rest of Words on line should be ignored.
+ *=======================================================================*/
+
+static int cmd_ansicpg (Word *w, int align, char has_param, int param) {
+ int i;
+ for (i = 0; i < sizeof(codepages) / sizeof(CodepageInfo); i ++) {
+ charset_codepage = &codepages[i];
+ if (charset_codepage->cp == param) {
+ if (op->comment_begin) {
+ printf(op->comment_begin);
+ printf("document uses ANSI codepage %d character set", param);
+ printf(op->comment_end);
+ }
+ break;
+ }
+ }
+ if ((charset_codepage == NULL || charset_codepage->cp == 0) && op->comment_begin) {
+ printf(op->comment_begin);
+ printf("document uses default ANSI codepage character set");
+ printf(op->comment_end);
+ }
+ return FALSE;
+}
+
+/*========================================================================
* Name: cmd_pc
* Purpose: Executes the \pc command.
* Args: Word, paragraph align info, and numeric param if any.
@@ -2326,6 +2780,7 @@
};
static HashItem hashArray_a [] = {
{ "ansi", &cmd_ansi , NULL },
+ { "ansicpg", &cmd_ansicpg , NULL },
{ NULL, NULL, NULL}
};
static HashItem hashArray_b [] = {
@@ -2642,9 +3097,9 @@
if (ch >= 0x20 && ch < 0x80) {
#if 1 /* daved - 0.19.6 */
- post_trans = op_translate_char (op, charset_type, ch, numchar_table);
+ post_trans = op_translate_char (op, charset_type, charset_codepage, ch, numchar_table);
#else
- post_trans = op_translate_char (op, charset_type, ch);
+ post_trans = op_translate_char (op, charset_type, charset_codepage, ch);
#endif
#if 1 /* daved - 0.20.1 */
if(post_trans)
@@ -3007,9 +3462,9 @@
char *s2;
#if 1 /* daved - 0.19.6 */
- s2 = op_translate_char (op, charset_type, ch, numchar_table);
+ s2 = op_translate_char (op, charset_type, charset_codepage, ch, numchar_table);
#else
- s2 = op_translate_char (op, charset_type, ch);
+ s2 = op_translate_char (op, charset_type, charset_codepage, ch);
#endif
if (!s2 || !*s2) {
diff -ur unrtf_0.20.1/src/convert.h.codepages unrtf_0.20.1/src/convert.h
--- unrtf_0.20.1/src/convert.h.codepages 2006-03-15 04:00:05.000000000 +0300
+++ unrtf_0.20.1/src/convert.h 2006-06-14 15:40:23.000000000 +0400
@@ -38,7 +38,7 @@
CHARSET_ANSI=1,
CHARSET_MAC,
CHARSET_CP437,
- CHARSET_CP850
+ CHARSET_CP850,
};
#ifndef _WORD
diff -ur unrtf_0.20.1/src/html.c.codepages unrtf_0.20.1/src/html.c
--- unrtf_0.20.1/src/html.c.codepages 2006-03-15 04:00:05.000000000 +0300
+++ unrtf_0.20.1/src/html.c 2006-06-14 17:31:40.000000000 +0400
@@ -878,6 +878,24 @@
/*========================================================================
+ * Name: html_unisymbol_print
+ * Purpose: Outputs arbitrary unicode symbol
+ * Args: Unsigned Short.
+ * Returns: String representing symbol.
+ *=======================================================================*/
+
+char *
+html_unisymbol_print (unsigned short c)
+{
+ char r[8];
+ snprintf(r, 8, "&#%04d;", c);
+ return my_strdup(r);
+}
+
+
+
+
+/*========================================================================
* Name: html_init
* Purpose: Generates the HTML output personality.
* Args: None.
@@ -1098,5 +1116,7 @@
op->symbol_translation_table = symbol;
#endif
+ op->unisymbol_print = html_unisymbol_print;
+
return op;
}
diff -ur unrtf_0.20.1/src/output.c.codepages unrtf_0.20.1/src/output.c
--- unrtf_0.20.1/src/output.c.codepages 2006-03-15 04:00:05.000000000 +0300
+++ unrtf_0.20.1/src/output.c 2006-06-14 18:28:43.000000000 +0400
@@ -111,9 +111,9 @@
char *
#if 1 /* daved - 0.19.6 */
-op_translate_char (OutputPersonality *op, int charset, int ch, int ntable)
+op_translate_char (OutputPersonality *op, int charset, CodepageInfo *codepage, int ch, int ntable)
#else
-op_translate_char (OutputPersonality *op, int charset, int ch)
+op_translate_char (OutputPersonality *op, int charset, CodepageInfo *codepage, int ch)
#endif
{
short start;
@@ -146,10 +146,16 @@
else
switch (charset) {
case CHARSET_ANSI:
+ if (codepage != NULL && op->unisymbol_print != NULL && codepage->cp) {
+ if (codepage->chars[ch - 0x80]) {
+ result = op->unisymbol_print(codepage->chars[ch - 0x80]);
+ }
+ } else {
start = op->ansi_first_char;
- if (ch >= start &&
- ch <= op->ansi_last_char)
- result = op->ansi_translation_table [ch-start];
+ if (ch >= start &&
+ ch <= op->ansi_last_char)
+ result = op->ansi_translation_table [ch-start];
+ }
break;
case CHARSET_MAC:
start = op->mac_first_char;
diff -ur unrtf_0.20.1/src/output.h.codepages unrtf_0.20.1/src/output.h
--- unrtf_0.20.1/src/output.h.codepages 2006-03-15 04:00:05.000000000 +0300
+++ unrtf_0.20.1/src/output.h 2006-06-14 17:31:10.000000000 +0400
@@ -33,6 +33,11 @@
#ifndef _OUTPUT
+typedef struct {
+ int cp;
+ unsigned short chars[128];
+} CodepageInfo;
+
typedef struct {
char *comment_begin;
@@ -276,6 +281,8 @@
char **symbol_translation_table;
#endif
+ char *(*unisymbol_print) (unsigned short);
+
void (*write_set_foreground) (int,int,int);
}
OutputPersonality;
@@ -284,9 +291,9 @@
extern OutputPersonality* op_create(void);
extern void op_free (OutputPersonality*);
#if 1 /* daved - 0.19.6 */
-extern char* op_translate_char (OutputPersonality*,int,int, int);
+extern char* op_translate_char (OutputPersonality*,int,CodepageInfo*,int, int);
#else
-extern char* op_translate_char (OutputPersonality*,int,int);
+extern char* op_translate_char (OutputPersonality*,int,CodepageInfo*,int);
#endif
extern void op_begin_std_fontsize (OutputPersonality*, int);