wok-6.x view html2text/stuff/patch-utf8-html2text-1.3.2a.diff @ rev 22891

updated gtest (1.7.0 -> 1.10.0)
author Hans-G?nter Theisgen
date Sun Feb 23 08:12:43 2020 +0100 (2020-02-23)
parents
children
line source
1 diff -r -u -bB html2text-1.3.2a/Area.C html2text-1.3.2a-patched/Area.C
2 --- html2text-1.3.2a/Area.C 2003-11-23 12:05:29.000000000 +0100
3 +++ html2text-1.3.2a-patched/Area.C 2005-05-13 22:19:59.862137688 +0200
4 @@ -36,10 +36,13 @@
5 #include <iostream>
6
7 #include "Area.h"
8 +#include "html.h"
9 #include "string.h"
10
11 #define LATIN1_nbsp 160
12
13 +extern int use_encoding;
14 +
15 /* ------------------------------------------------------------------------- */
16
17 #define malloc_array(type, size)\
18 @@ -81,6 +84,27 @@
19
20 /* ------------------------------------------------------------------------- */
21
22 +/* utf_length() and utf_width()
23 + *
24 + * Very simplified algorithm of calculating length of UTF-8
25 + * string. No check for errors. Counting only ASCII bytes and
26 + * leading bytes of UTF-8 multibyte sequences. All bytes like
27 + * 10xxxxxx are dropped. If USE_UTF8 is false then returns
28 + * usual length. --YS
29 + */
30 +
31 +unsigned int
32 +Line::utf_length(size_type f, size_type t) const
33 +{
34 + size_type m = (t < length_ ? t : length_);
35 + size_type r = m - f;
36 + if(USE_UTF8) {
37 + for (int i = f; i < m; i++)
38 + if((cells_[i].character & 0xc0) == 0x80) r--;
39 + }
40 + return r;
41 +}
42 +
43 void
44 Line::resize(size_type l)
45 {
46 @@ -236,6 +260,23 @@
47 return *this;
48 }
49
50 +unsigned int
51 +Area::utf_width()
52 +{
53 + size_type r = width_;
54 + if(USE_UTF8) { r = 0;
55 + for (size_type yy = 0; yy < height_; yy++) {
56 + size_type r1 = 0;
57 + for (int i = width_ - 1; i >= 0; i--) {
58 + if(!r1 && isspace(cells_[yy][i].character)) continue;
59 + if((cells_[yy][i].character & 0xc0) != 0x80) r1++;
60 + }
61 + if(r < r1) r = r1;
62 + }
63 + }
64 + return r;
65 +}
66 +
67 void
68 Area::resize(size_type w, size_type h)
69 {
70 @@ -439,7 +480,7 @@
71 char c = p->character;
72 char a = p->attribute;
73
74 - if (c == (char) LATIN1_nbsp) c = ' ';
75 + if (c == (char) LATIN1_nbsp && !USE_UTF8) c = ' ';
76
77 if (a == Cell::NONE) {
78 os << c;
79 Nur in html2text-1.3.2a-patched/: Area.C.orig.
80 diff -r -u -bB html2text-1.3.2a/Area.h html2text-1.3.2a-patched/Area.h
81 --- html2text-1.3.2a/Area.h 2003-11-23 12:05:29.000000000 +0100
82 +++ html2text-1.3.2a-patched/Area.h 2005-05-13 22:19:59.863137536 +0200
83 @@ -81,6 +81,8 @@
84 Cell &operator[](size_type x) { return cells_[x]; }
85 const Cell *cells() const { return cells_; }
86
87 + unsigned int utf_length(size_type f, size_type t) const;
88 +
89 void resize(size_type l);
90 void enlarge(size_type l) { if (l > length_) resize(l); }
91
92 @@ -134,6 +136,8 @@
93 Cell *operator[](size_type y) { return cells_[y]; }
94 const Area &operator>>=(size_type rs);
95
96 + unsigned int utf_width();
97 +
98 void resize(size_type w, size_type h);
99 void enlarge(size_type w, size_type h);
100
101 Nur in html2text-1.3.2a-patched/: Area.h.orig.
102 diff -r -u -bB html2text-1.3.2a/format.C html2text-1.3.2a-patched/format.C
103 --- html2text-1.3.2a/format.C 2003-11-23 12:05:29.000000000 +0100
104 +++ html2text-1.3.2a-patched/format.C 2005-05-13 22:19:59.865137232 +0200
105 @@ -1210,6 +1210,7 @@
106 }
107
108 Line::size_type to = from + 1;
109 + int to_from;
110
111 Line::size_type lbp = (Line::size_type) -1; // "Last break position".
112
113 @@ -1238,18 +1239,20 @@
114 to++;
115 }
116
117 - if (to - from > w && lbp != (Area::size_type) -1) { to = lbp; break; }
118 + if (line.utf_length(from,to) > w && lbp != (Area::size_type) -1)
119 + { to = lbp; break; }
120 }
121
122 + to_from = line.utf_length(from,to);
123 /*
124 * Copy the "from...to" range from the "line" to the bottom of the "res"
125 * Area.
126 */
127 Area::size_type x = 0;
128 Area::size_type len = to - from;
129 - if (halign == Area::LEFT || len >= w) { ; } else
130 - if (halign == Area::CENTER) { x += (w - len) / 2; } else
131 - if (halign == Area::RIGHT) { x += w - len; }
132 + if (halign == Area::LEFT || to_from >= w) { ; } else
133 + if (halign == Area::CENTER) { x += (w - to_from) / 2; } else
134 + if (halign == Area::RIGHT) { x += w - to_from; }
135 res->insert(line.cells() + from, len, x, res->height());
136
137 /*
138 Nur in html2text-1.3.2a-patched/: format.C.orig.
139 diff -r -u -bB html2text-1.3.2a/html2text.C html2text-1.3.2a-patched/html2text.C
140 --- html2text-1.3.2a/html2text.C 2003-11-23 12:05:29.000000000 +0100
141 +++ html2text-1.3.2a-patched/html2text.C 2005-05-13 22:19:59.868136776 +0200
142 @@ -148,9 +148,10 @@
143 -o <file> Redirect output into <file>\n\
144 -nobs Do not use backspaces for boldface and underlining\n\
145 -ascii Use plain ASCII for output instead of ISO-8859-1\n\
146 + -utf8 Assume both terminal and input stream are in UTF-8 mode\n\
147 ";
148
149 -int use_iso8859 = 1;
150 +int use_encoding = ISO8859;
151
152 int
153 main(int argc, char **argv)
154 @@ -199,7 +200,8 @@
155 if (!strcmp(arg, "-width" )) { width = atoi(argv[++i]); } else
156 if (!strcmp(arg, "-o" )) { output_file_name = argv[++i]; } else
157 if (!strcmp(arg, "-nobs" )) { use_backspaces = false; } else
158 - if (!strcmp(arg, "-ascii" )) { use_iso8859 = false; } else
159 + if (!strcmp(arg, "-ascii" )) { use_encoding = ASCII; } else
160 + if (!strcmp(arg, "-utf8" )) { use_encoding = UTF8; } else
161 {
162 std::cerr
163 << "Unrecognized command line option \""
164 Nur in html2text-1.3.2a-patched/: html2text.C.orig.
165 diff -r -u -bB html2text-1.3.2a/html.h html2text-1.3.2a-patched/html.h
166 --- html2text-1.3.2a/html.h 2001-10-04 22:03:54.000000000 +0200
167 +++ html2text-1.3.2a-patched/html.h 2005-05-13 22:19:59.866137080 +0200
168 @@ -61,6 +61,11 @@
169
170 /* ------------------------------------------------------------------------- */
171
172 +enum {ASCII, ISO8859, UTF8};
173 +#define USE_ISO8859 (use_encoding == ISO8859)
174 +#define USE_ASCII (use_encoding == ASCII)
175 +#define USE_UTF8 (use_encoding == UTF8)
176 +
177 #define LATIN1_nbsp 160
178 #define LATIN1_iexcl 161
179 #define LATIN1_cent 162
180 diff -r -u -bB html2text-1.3.2a/sgml.C html2text-1.3.2a-patched/sgml.C
181 --- html2text-1.3.2a/sgml.C 2003-11-23 12:09:11.000000000 +0100
182 +++ html2text-1.3.2a-patched/sgml.C 2005-05-13 22:19:59.870136472 +0200
183 @@ -62,261 +62,280 @@
184 char name[8];
185 int iso8859code;
186 char *asciistr;
187 + unsigned long unicode;
188 } entities[] = {
189 - { "AElig", LATIN1_AElig, "AE" },
190 - { "AMP", 0, "&" },
191 - { "Aacute", LATIN1_Aacute, "A'" },
192 - { "Acirc", LATIN1_Acirc, "A^" },
193 - { "Agrave", LATIN1_Agrave, "A`" },
194 - { "Alpha", 0, "A" },
195 - { "Aring", LATIN1_Aring, "AA" },
196 - { "Atilde", LATIN1_Atilde, "A~" },
197 - { "Auml", LATIN1_Auml, "A\"" },
198 - { "Beta", 0, "B" },
199 - { "Ccedil", LATIN1_Ccedil, "C," },
200 - { "Chi", 0, "H" },
201 - { "Dagger", 0, "++" },
202 - { "Delta", 0, "D" },
203 - { "ETH", LATIN1_ETH, "D-" },
204 - { "Eacute", LATIN1_Eacute, "E'" },
205 - { "Ecirc", LATIN1_Ecirc, "E^" },
206 - { "Egrave", LATIN1_Egrave, "E`" },
207 - { "Epsilon", 0, "E" },
208 - { "Eta", 0, "E" },
209 - { "Euml", LATIN1_Euml, "E\"" },
210 - { "GT", 0, ">" },
211 - { "Gamma", 0, "G" },
212 - { "Iacute", LATIN1_Iacute, "I'" },
213 - { "Icirc", LATIN1_Icirc, "I^" },
214 - { "Igrave", LATIN1_Igrave, "I`" },
215 - { "Iota", 0, "I" },
216 - { "Iuml", LATIN1_Iuml, "I\"" },
217 - { "Kappa", 0, "K" },
218 - { "LT", 0, "<" },
219 - { "Lambda", 0, "L" },
220 - { "Mu", 0, "M" },
221 - { "Ntilde", LATIN1_Ntilde, "N~" },
222 - { "Nu", 0, "N" },
223 - { "OElig", 0, "OE" },
224 - { "Oacute", LATIN1_Oacute, "O'" },
225 - { "Ocirc", LATIN1_Ocirc, "O^" },
226 - { "Ograve", LATIN1_Ograve, "O`" },
227 - { "Omega", 0, "O" },
228 - { "Omicron", 0, "O" },
229 - { "Oslash", LATIN1_Oslash, "O/" },
230 - { "Otilde", LATIN1_Otilde, "O~" },
231 - { "Ouml", LATIN1_Ouml, "O\"" },
232 - { "Phi", 0, "F" },
233 - { "Pi", 0, "P" },
234 - { "Prime", 0, "''" },
235 - { "Psi", 0, "PS" },
236 - { "QUOT", 0, "\"" },
237 - { "Rho", 0, "R" },
238 - { "Scaron", 0, "S" },
239 - { "Sigma", 0, "S" },
240 - { "THORN", LATIN1_THORN, "TH" },
241 - { "Tau", 0, "T" },
242 - { "Theta", 0, "TH" },
243 - { "Uacute", LATIN1_Uacute, "U'" },
244 - { "Ucirc", LATIN1_Ucirc, "U^" },
245 - { "Ugrave", LATIN1_Ugrave, "U`" },
246 - { "Upsilon", 0, "U" },
247 - { "Uuml", LATIN1_Uuml, "U\"" },
248 - { "Xi", 0, "X" },
249 - { "Yacute", LATIN1_Yacute, "Y'" },
250 - { "Yuml", 0, "Y\"" },
251 - { "Zeta", 0, "Z" },
252 - { "aacute", LATIN1_aacute, "a'" },
253 - { "acirc", LATIN1_acirc, "a^" },
254 - { "acute", LATIN1_acute, "'" },
255 - { "aelig", LATIN1_aelig, "ae" },
256 - { "agrave", LATIN1_agrave, "a`" },
257 + { "AElig", LATIN1_AElig, "AE", 0x00c6},
258 + { "AMP", 0, "&", 0x0026},
259 + { "Aacute", LATIN1_Aacute, "A'", 0x00c1},
260 + { "Acirc", LATIN1_Acirc, "A^", 0x00c2},
261 + { "Agrave", LATIN1_Agrave, "A`", 0x00c0},
262 + { "Alpha", 0, "A", 0x0391},
263 + { "Aring", LATIN1_Aring, "AA", 0x00c5},
264 + { "Atilde", LATIN1_Atilde, "A~", 0x00c3},
265 + { "Auml", LATIN1_Auml, "A\"", 0x00c4},
266 + { "Beta", 0, "B", 0x0392},
267 + { "Ccedil", LATIN1_Ccedil, "C,", 0x00c7},
268 + { "Chi", 0, "H", 0x03a7},
269 + { "Dagger", 0, "++", 0x2020},
270 + { "Delta", 0, "D", 0x0394},
271 + { "ETH", LATIN1_ETH, "D-", 0x00d0},
272 + { "Eacute", LATIN1_Eacute, "E'", 0x00c9},
273 + { "Ecirc", LATIN1_Ecirc, "E^", 0x00ca},
274 + { "Egrave", LATIN1_Egrave, "E`", 0x00c8},
275 + { "Epsilon", 0, "E", 0x0395},
276 + { "Eta", 0, "E", 0x0397},
277 + { "Euml", LATIN1_Euml, "E\"", 0x00cb},
278 + { "GT", 0, ">", 0x003e},
279 + { "Gamma", 0, "G", 0x0393},
280 + { "Iacute", LATIN1_Iacute, "I'", 0x00cd},
281 + { "Icirc", LATIN1_Icirc, "I^", 0x00ce},
282 + { "Igrave", LATIN1_Igrave, "I`", 0x00cc},
283 + { "Iota", 0, "I", 0x0399},
284 + { "Iuml", LATIN1_Iuml, "I\"", 0x00cf},
285 + { "Kappa", 0, "K", 0x039a},
286 + { "LT", 0, "<", 0x003c},
287 + { "Lambda", 0, "L", 0x039b},
288 + { "Mu", 0, "M", 0x039c},
289 + { "Ntilde", LATIN1_Ntilde, "N~", 0x00d1},
290 + { "Nu", 0, "N", 0x039d},
291 + { "OElig", 0, "OE", 0x0152},
292 + { "Oacute", LATIN1_Oacute, "O'", 0x00d3},
293 + { "Ocirc", LATIN1_Ocirc, "O^", 0x00d4},
294 + { "Ograve", LATIN1_Ograve, "O`", 0x00d2},
295 + { "Omega", 0, "O", 0x03a9},
296 + { "Omicron", 0, "O", 0x039f},
297 + { "Oslash", LATIN1_Oslash, "O/", 0x00d8},
298 + { "Otilde", LATIN1_Otilde, "O~", 0x00d5},
299 + { "Ouml", LATIN1_Ouml, "O\"", 0x00d6},
300 + { "Phi", 0, "F", 0x03a6},
301 + { "Pi", 0, "P", 0x03a0},
302 + { "Prime", 0, "''", },
303 + { "Psi", 0, "PS", 0x03a8},
304 + { "QUOT", 0, "\"", },
305 + { "Rho", 0, "R", 0x03a1},
306 + { "Scaron", 0, "S", 0x0161},
307 + { "Sigma", 0, "S", 0x03a3},
308 + { "THORN", LATIN1_THORN, "TH", 0x00de},
309 + { "Tau", 0, "T", 0x03a4},
310 + { "Theta", 0, "TH", 0x0398},
311 + { "Uacute", LATIN1_Uacute, "U'", 0x00da},
312 + { "Ucirc", LATIN1_Ucirc, "U^", 0x00db},
313 + { "Ugrave", LATIN1_Ugrave, "U`", 0x00d9},
314 + { "Upsilon", 0, "U", 0x03a5},
315 + { "Uuml", LATIN1_Uuml, "U\"", 0x00dc},
316 + { "Xi", 0, "X", 0x039e},
317 + { "Yacute", LATIN1_Yacute, "Y'", 0x00dd},
318 + { "Yuml", 0, "Y\"", 0x0178},
319 + { "Zeta", 0, "Z", 0x0396},
320 + { "aacute", LATIN1_aacute, "a'", 0x00e1},
321 + { "acirc", LATIN1_acirc, "a^", 0x00e2},
322 + { "acute", LATIN1_acute, "'", 0x00b4},
323 + { "aelig", LATIN1_aelig, "ae", 0x00e6},
324 + { "agrave", LATIN1_agrave, "a`", 0x00e0},
325 { "alefsym", 0, "Aleph" },
326 - { "alpha", 0, "a" },
327 + { "alpha", 0, "a", 0x03b1},
328 { "amp", 0, "&" },
329 { "and", 0, "AND" },
330 { "ang", 0, "-V" },
331 { "apos", 0, "'" },
332 - { "aring", LATIN1_aring, "aa" },
333 - { "asymp", 0, "~=" },
334 - { "atilde", LATIN1_atilde, "a~" },
335 - { "auml", LATIN1_auml, "a\"" },
336 + { "aring", LATIN1_aring, "aa", 0x00e5},
337 + { "asymp", 0, "~=", 0x2248},
338 + { "atilde", LATIN1_atilde, "a~", 0x00e3},
339 + { "auml", LATIN1_auml, "a\"", 0x00e5},
340 { "bdquo", 0, "\"" },
341 - { "beta", 0, "b" },
342 - { "brvbar", LATIN1_brvbar, "|" },
343 - { "bull", 0, " o " },
344 + { "beta", 0, "b", 0x03b2},
345 + { "brvbar", LATIN1_brvbar, "|", 0x00a6},
346 + { "bull", 0, " o ", 0x2022},
347 { "cap", 0, "(U" },
348 - { "ccedil", LATIN1_ccedil, "c," },
349 - { "cedil", LATIN1_cedil, "," },
350 - { "cent", LATIN1_cent, "-c-" },
351 - { "chi", 0, "h" },
352 - { "circ", 0, "^" },
353 + { "ccedil", LATIN1_ccedil, "c,", 0x00e7},
354 + { "cedil", LATIN1_cedil, ",", 0x00b8},
355 + { "cent", LATIN1_cent, "-c-", 0x00a2},
356 + { "chi", 0, "h", 0x03c7},
357 + { "circ", 0, "^", 0x005e},
358 // { "clubs", 0, "[clubs]" },
359 { "cong", 0, "?=" },
360 - { "copy", LATIN1_copy, "(c)" },
361 + { "copy", LATIN1_copy, "(c)", 0x00a9},
362 { "crarr", 0, "<-'" },
363 { "cup", 0, ")U" },
364 - { "curren", LATIN1_curren, "CUR" },
365 + { "curren", LATIN1_curren, "CUR", 0x00a4},
366 { "dArr", 0, "vv" },
367 - { "dagger", 0, "+" },
368 + { "dagger", 0, "+", 0x2020},
369 { "darr", 0, "v" },
370 - { "deg", LATIN1_deg, "DEG" },
371 - { "delta", 0, "d" },
372 + { "deg", LATIN1_deg, "DEG", 0x00b0},
373 + { "delta", 0, "d", 0x03b4},
374 // { "diams", 0, "[diamonds]" },
375 - { "divide", LATIN1_divide, "/" },
376 - { "eacute", LATIN1_eacute, "e'" },
377 - { "ecirc", LATIN1_ecirc, "e^" },
378 - { "egrave", LATIN1_egrave, "e`" },
379 + { "divide", LATIN1_divide, "/", 0x00f7},
380 + { "eacute", LATIN1_eacute, "e'", 0x00e9},
381 + { "ecirc", LATIN1_ecirc, "e^", 0x00ea},
382 + { "egrave", LATIN1_egrave, "e`", 0x00e8},
383 { "empty", 0, "{}" },
384 - { "epsilon", 0, "e" },
385 - { "equiv", 0, "==" },
386 - { "eta", 0, "e" },
387 - { "eth", LATIN1_eth, "d-" },
388 - { "euml", LATIN1_euml, "e\"" },
389 - { "euro", 0, "EUR" },
390 + { "epsilon", 0, "e", 0x03b5},
391 + { "equiv", 0, "==", 0x2261},
392 + { "eta", 0, "e", 0x03b7},
393 + { "eth", LATIN1_eth, "d-", 0x00f0},
394 + { "euml", LATIN1_euml, "e\"", 0x00eb},
395 + { "euro", 0, "EUR", 0x20ac},
396 { "exist", 0, "TE" },
397 { "fnof", 0, "f" },
398 { "forall", 0, "FA" },
399 - { "frac12", LATIN1_frac12, " 1/2" },
400 - { "frac14", LATIN1_frac14, " 1/4" },
401 - { "frac34", LATIN1_frac34, " 3/4" },
402 + { "frac12", LATIN1_frac12, " 1/2",0x00bd},
403 + { "frac14", LATIN1_frac14, " 1/4",0x00bc},
404 + { "frac34", LATIN1_frac34, " 3/4",0x00be},
405 { "frasl", 0, "/" },
406 - { "gamma", 0, "g" },
407 - { "ge", 0, ">=" },
408 - { "gt", 0, ">" },
409 + { "gamma", 0, "g", 0x03b3},
410 + { "ge", 0, ">=", 0x2265},
411 + { "gt", 0, ">", 0x003e},
412 { "hArr", 0, "<=>" },
413 { "harr", 0, "<->" },
414 // { "hearts", 0, "[hearts]" },
415 - { "hellip", 0, "..." },
416 - { "iacute", LATIN1_iacute, "i'" },
417 - { "icirc", LATIN1_icirc, "i^" },
418 - { "iexcl", LATIN1_iexcl, "!" },
419 - { "igrave", LATIN1_igrave, "i`" },
420 + { "hellip", 0, "...", 0x2026},
421 + { "iacute", LATIN1_iacute, "i'", 0x00ed},
422 + { "icirc", LATIN1_icirc, "i^", 0x00ee},
423 + { "iexcl", LATIN1_iexcl, "!", 0x00a1},
424 + { "igrave", LATIN1_igrave, "i`", 0x00ec},
425 { "image", 0, "Im" },
426 - { "infin", 0, "oo" },
427 - { "int", 0, "INT" },
428 - { "iota", 0, "i" },
429 - { "iquest", LATIN1_iquest, "?" },
430 + { "infin", 0, "oo", 0x221e},
431 + { "int", 0, "INT", 0x222b},
432 + { "iota", 0, "i", 0x03b9},
433 + { "iquest", LATIN1_iquest, "?", 0x00bf},
434 { "isin", 0, "(-" },
435 - { "iuml", LATIN1_iuml, "i\"" },
436 - { "kappa", 0, "k" },
437 + { "iuml", LATIN1_iuml, "i\"", 0x00ef},
438 + { "kappa", 0, "k", 0x03ba},
439 { "lArr", 0, "<=" },
440 - { "lambda", 0, "l" },
441 + { "lambda", 0, "l", 0x03bb},
442 { "lang", 0, "</" },
443 { "laquo", LATIN1_laquo, "<<" },
444 - { "larr", 0, "<-" },
445 + { "larr", 0, "<-", 0x2190},
446 // { "lceil", 0, "<|" },
447 { "ldquo", 0, "\"" },
448 - { "le", 0, "<=" },
449 + { "le", 0, "<=", 0x2264},
450 // { "lfloor", 0, "|<" },
451 { "lowast", 0, "*" },
452 { "loz", 0, "<>" },
453 { "lsaquo", 0, "<" },
454 { "lsquo", 0, "`" },
455 - { "lt", 0, "<" },
456 - { "macr", LATIN1_macr, "-" },
457 + { "lt", 0, "<", 0x003c},
458 + { "macr", LATIN1_macr, "-", 0x00af},
459 { "mdash", 0, "--" },
460 - { "micro", LATIN1_micro, "my" },
461 - { "middot", LATIN1_middot, "." },
462 - { "minus", 0, "-" },
463 - { "mu", 0, "m" },
464 + { "micro", LATIN1_micro, "my", 0x00b5},
465 + { "middot", LATIN1_middot, ".", 0x00b7},
466 + { "minus", 0, "-", 0x2212},
467 + { "mu", 0, "m", 0x03bc},
468 { "nabla", 0, "Nabla" },
469 - { "nbsp", LATIN1_nbsp, " " },
470 + { "nbsp", LATIN1_nbsp, " ", 0x00a0},
471 { "ndash", 0, "-" },
472 - { "ne", 0, "!=" },
473 + { "ne", 0, "!=", 0x2260},
474 { "ni", 0, "-)" },
475 { "not", LATIN1_not, "NOT" },
476 { "notin", 0, "!(-" },
477 { "nsub", 0, "!(C" },
478 - { "ntilde", LATIN1_ntilde, "n~" },
479 - { "nu", 0, "n" },
480 - { "oacute", LATIN1_oacute, "o'" },
481 - { "ocirc", LATIN1_ocirc, "o^" },
482 + { "ntilde", LATIN1_ntilde, "n~", 0x00f1},
483 + { "nu", 0, "n", 0x03bd},
484 + { "oacute", LATIN1_oacute, "o'", 0x00f3},
485 + { "ocirc", LATIN1_ocirc, "o^", 0x00f4},
486 { "oelig", 0, "oe" },
487 - { "ograve", LATIN1_ograve, "o`" },
488 + { "ograve", LATIN1_ograve, "o`", 0x00f2},
489 { "oline", LATIN1_macr, "-" },
490 - { "omega", 0, "o" },
491 - { "omicron", 0, "o" },
492 + { "omega", 0, "o", 0x03c9},
493 + { "omicron", 0, "o", 0x03bf},
494 { "oplus", 0, "(+)" },
495 { "or", 0, "OR" },
496 - { "ordf", LATIN1_ordf, "-a" },
497 - { "ordm", LATIN1_ordm, "-o" },
498 - { "oslash", LATIN1_oslash, "o/" },
499 - { "otilde", LATIN1_otilde, "o~" },
500 + { "ordf", LATIN1_ordf, "-a", 0x00aa},
501 + { "ordm", LATIN1_ordm, "-o", 0x00ba},
502 + { "oslash", LATIN1_oslash, "o/", 0x00f8},
503 + { "otilde", LATIN1_otilde, "o~", 0x00f5},
504 { "otimes", 0, "(x)" },
505 - { "ouml", LATIN1_ouml, "o\"" },
506 - { "para", LATIN1_para, "P:" },
507 - { "part", 0, "PART" },
508 - { "permil", 0, " 0/00" },
509 + { "ouml", LATIN1_ouml, "o\"", 0x00f6},
510 + { "para", LATIN1_para, "P:", 0x00b6},
511 + { "part", 0, "PART",0x2202},
512 + { "permil", 0, " 0/00",0x2030},
513 { "perp", 0, "-T" },
514 - { "phi", 0, "f" },
515 - { "pi", 0, "p" },
516 + { "phi", 0, "f", 0x03c6},
517 + { "pi", 0, "p", 0x03c0},
518 { "piv", 0, "Pi" },
519 - { "plusmn", LATIN1_plusmn, "+/-" },
520 - { "pound", LATIN1_pound, "-L-" },
521 + { "plusmn", LATIN1_plusmn, "+/-", 0x00b1},
522 + { "pound", LATIN1_pound, "-L-", 0x00a3},
523 { "prime", 0, "'" },
524 - { "prod", 0, "PROD" },
525 + { "prod", 0, "PROD",0x220f},
526 { "prop", 0, "0(" },
527 - { "psi", 0, "ps" },
528 + { "psi", 0, "ps", 0x03c8},
529 { "quot", 0, "\"" },
530 { "rArr", 0, "=>" },
531 - { "radic", 0, "SQRT" },
532 + { "radic", 0, "SQRT",0x221a},
533 { "rang", 0, "/>" },
534 { "raquo", LATIN1_raquo, ">>" },
535 - { "rarr", 0, "->" },
536 + { "rarr", 0, "->", 0x2192},
537 // { "rceil", 0, ">|" },
538 { "rdquo", 0, "\"" },
539 { "real", 0, "Re" },
540 - { "reg", LATIN1_reg, "(R)" },
541 + { "reg", LATIN1_reg, "(R)", 0x00ae},
542 // { "rfloor", 0, "|>" },
543 - { "rho", 0, "r" },
544 + { "rho", 0, "r", 0x03c1},
545 { "rsaquo", 0, ">" },
546 { "rsquo", 0, "'" },
547 { "sbquo", 0, "'" },
548 - { "scaron", 0, "s" },
549 + { "scaron", 0, "s", 0x0161},
550 { "sdot", 0, "DOT" },
551 - { "sect", LATIN1_sect, "S:" },
552 + { "sect", LATIN1_sect, "S:", 0x00a7},
553 { "shy", LATIN1_shy, "" },
554 - { "sigma", 0, "s" },
555 - { "sigmaf", 0, "s" },
556 + { "sigma", 0, "s", 0x03c3},
557 + { "sigmaf", 0, "s", 0x03c2},
558 { "sim", 0, "~" },
559 // { "spades", 0, "[spades]" },
560 { "sub", 0, "(C" },
561 { "sube", 0, "(_" },
562 - { "sum", 0, "SUM" },
563 + { "sum", 0, "SUM", 0x2211},
564 { "sup", 0, ")C" },
565 - { "sup1", LATIN1_sup1, "^1" },
566 - { "sup2", LATIN1_sup2, "^2" },
567 - { "sup3", LATIN1_sup3, "^3" },
568 + { "sup1", LATIN1_sup1, "^1", 0x00b9},
569 + { "sup2", LATIN1_sup2, "^2", 0x00b2},
570 + { "sup3", LATIN1_sup3, "^3", 0x00b3},
571 { "supe", 0, ")_" },
572 - { "szlig", LATIN1_szlig, "ss" },
573 - { "tau", 0, "t" },
574 + { "szlig", LATIN1_szlig, "ss", 0x00df},
575 + { "tau", 0, "t", 0x03c4},
576 { "there4", 0, ".:" },
577 - { "theta", 0, "th" },
578 - { "thorn", LATIN1_thorn, "th" },
579 - { "tilde", 0, "~" },
580 - { "times", LATIN1_times, "x" },
581 - { "trade", 0, "[TM]" },
582 + { "theta", 0, "th", 0x03b8},
583 + { "thorn", LATIN1_thorn, "th", 0x00fe},
584 + { "tilde", 0, "~", 0x02dc},
585 + { "times", LATIN1_times, "x", 0x00d7},
586 + { "trade", 0, "[TM]",0x2122},
587 { "uArr", 0, "^^" },
588 - { "uacute", LATIN1_uacute, "u'" },
589 + { "uacute", LATIN1_uacute, "u'", 0x00fa},
590 { "uarr", 0, "^" },
591 - { "ucirc", LATIN1_ucirc, "u^" },
592 - { "ugrave", LATIN1_ugrave, "u`" },
593 - { "uml", LATIN1_uml, "\"" },
594 - { "upsilon", 0, "u" },
595 - { "uuml", LATIN1_uuml, "u\"" },
596 + { "ucirc", LATIN1_ucirc, "u^", 0x00fb},
597 + { "ugrave", LATIN1_ugrave, "u`", 0x00f9},
598 + { "uml", LATIN1_uml, "\"", 0x00a8},
599 + { "upsilon", 0, "u", 0x03c5},
600 + { "uuml", LATIN1_uuml, "u\"", 0x00fc},
601 { "weierp", 0, "P" },
602 - { "xi", 0, "x" },
603 - { "yacute", LATIN1_yacute, "y'" },
604 - { "yen", LATIN1_yen, "YEN" },
605 - { "yuml", LATIN1_yuml, "y\"" },
606 - { "zeta", 0, "z" },
607 + { "xi", 0, "x", 0x03be},
608 + { "yacute", LATIN1_yacute, "y'", 0x00fd},
609 + { "yen", LATIN1_yen, "YEN", 0x00a5},
610 + { "yuml", LATIN1_yuml, "y\"", 0x00ff},
611 + { "zeta", 0, "z", 0x03b6},
612 };
613
614 -extern int use_iso8859;
615 +extern int use_encoding;
616
617 /* ------------------------------------------------------------------------- */
618
619 +char ubuf[4];
620 +
621 +char *mkutf(unsigned long x)
622 +{
623 + memset(ubuf, 0, 4);
624 + if(x < 128) ubuf[0] = x;
625 + else if(x < 0x800) {
626 + ubuf[0] = (0xc0 | ((x >> 6) & 0x1f));
627 + ubuf[1] = (0x80 | (x & 0x3f));
628 + }
629 + else {
630 + ubuf[0] = (0xe0 | ((x >> 12) & 0x0f));
631 + ubuf[1] = (0x80 | ((x >> 6) & 0x3f));
632 + ubuf[2] = (0x80 | (x & 0x3f));
633 + }
634 + return ubuf;
635 +}
636 +
637 void
638 replace_sgml_entities(string *s)
639 {
640 @@ -330,9 +349,9 @@
641 */
642 while (j < l && s->at(j) != '&') ++j;
643 /*
644 - * We could convert high-bit chars to "&#233;" here if use_iso8859
645 - * is off, then let them be translated or not. Is the purpose of
646 - * !use_iso8859 to allow SGML entities to be seen, or to strongly
647 + * We could convert high-bit chars to "&#233;" here if USE_ASCII
648 + * is on, then let them be translated or not. Is the purpose of
649 + * USE_ASCII to allow SGML entities to be seen, or to strongly
650 * filter against high-ASCII chars that might blow up a terminal
651 * that doesn't speak ISO8859? For the moment, "allow SGML entities
652 * to be seen" -- no filtering here.
653 @@ -370,7 +389,11 @@
654 if (!isdigit(c)) break;
655 x = 10 * x + c - '0';
656 }
657 - if (use_iso8859 || (x < 128)) {
658 + if (USE_UTF8) {
659 + s->replace(beg, j - beg, mkutf(x));
660 + j = beg + 1;
661 + }
662 + else if (USE_ISO8859 && (x < 256) || USE_ASCII && (x < 128)) {
663 s->replace(beg, j - beg, 1, (char) x);
664 j = beg + 1;
665 } else {
666 @@ -408,13 +431,17 @@
667 (int (*)(const void *, const void *)) strcmp
668 );
669 if (entity != NULL) {
670 - if (use_iso8859 && entity->iso8859code) {
671 + if (USE_ISO8859 && entity->iso8859code) {
672 s->replace(beg, j - beg, 1, (char) entity->iso8859code);
673 j = beg + 1;
674 - } else if (entity->asciistr) {
675 + } else if (USE_ASCII && entity->asciistr) {
676 s->replace(beg, j - beg, entity->asciistr);
677 j = beg + 1;
678 } /* else don't replace it at all, we don't have a translation */
679 + else if(USE_UTF8 && entity->unicode) {
680 + s->replace(beg, j - beg, mkutf(entity->unicode));
681 + j = beg + 1;
682 + }
683 }
684 } else {
685 ; /* EXTENSION: Allow literal '&' sometimes. */
686 diff -r -u -bB html2text-1.3.2a/table.C html2text-1.3.2a-patched/table.C
687 --- html2text-1.3.2a/table.C 2002-07-22 13:32:50.000000000 +0200
688 +++ html2text-1.3.2a-patched/table.C 2005-05-13 22:19:59.871136320 +0200
689 @@ -175,7 +175,7 @@
690 - (*number_of_columns_return - 1) * (column_spacing + 0),
691 Area::LEFT // Yields better results than "p->halign"!
692 ));
693 - p->width = tmp.get() ? tmp->width() : 0;
694 + p->width = tmp.get() ? tmp->utf_width() : 0;
695 }
696 p->minimized = false;
697
698 @@ -308,7 +308,7 @@
699 left_of_column + old_column_width - 1,
700 Area::LEFT // Yields better results than "lc.halign"!
701 ));
702 - w = tmp->width();
703 + w = tmp->utf_width();
704 if (w >= left_of_column + old_column_width) lc.minimized = true;
705 }
706 if (w > left_of_column + new_column_width) {