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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
|
#include "HTUtils.h"
#include "tcp.h"
#include "HTCJK.h"
#include "UCDefs.h"
#include "HTStream.h"
#include "UCAux.h"
extern HTCJKlang HTCJK;
extern LYUCcharset LYCharSet_UC[];
PUBLIC UCTQ_t UCCanUniTranslateFrom ARGS1(
int, from)
{
if (from < 0)
return TQ_NO;
if (LYCharSet_UC[from].enc == UCT_ENC_7BIT ||
LYCharSet_UC[from].enc == UCT_ENC_UTF8)
return TQ_EXCELLENT;
if (LYCharSet_UC[from].codepoints & (UCT_CP_SUBSETOF_LAT1))
return TQ_EXCELLENT;
return ((LYCharSet_UC[from].UChndl >= 0) ? TQ_GOOD : TQ_NO);
}
PUBLIC UCTQ_t UCCanTranslateUniTo ARGS1(
int, to)
{
if (to < 0)
return TQ_NO;
if (LYCharSet_UC[to].enc == UCT_ENC_7BIT)
return TQ_POOR;
if (LYCharSet_UC[to].enc == UCT_ENC_UTF8)
return TQ_EXCELLENT;
if (LYCharSet_UC[to].enc == UCT_ENC_CJK)
return TQ_POOR;
if (LYCharSet_UC[to].UChndl >= 0)
return TQ_GOOD;
return TQ_GOOD; /* at least some characters, we don't know more */
}
PUBLIC UCTQ_t UCCanTranslateFromTo ARGS2(
int, from,
int, to)
{
if (from == to)
return TQ_EXCELLENT;
if (from < 0 || to < 0)
return TQ_NO;
if (from == 0)
return UCCanTranslateUniTo(to);
if (to == 0 || LYCharSet_UC[to].enc == UCT_ENC_UTF8)
return UCCanUniTranslateFrom(from);
{
CONST char * fromname = LYCharSet_UC[from].MIMEname;
CONST char * toname = LYCharSet_UC[to].MIMEname;
UCTQ_t tqmin = TQ_NO, tqmax = TQ_GOOD;
if (!strcmp(fromname, "x-transparent") ||
!strcmp(toname, "x-transparent")) {
return TQ_GOOD;
} else if (!strcmp(fromname, "us-ascii")) {
return TQ_GOOD;
}
if (LYCharSet_UC[from].enc == UCT_ENC_CJK) {
/*
** CJK mode may be off (i.e., HTCJK == NOCJK) because
** the current document is not CJK, but the check may
** be for capability in relation to another document,
** for which CJK mode might be turned on when retrieved.
** Thus, when the from charset is CJK, check if the to
** charset is CJK, and return TQ_NO or TQ_GOOD depending on
** that. - FM
*/
if (LYCharSet_UC[to].enc != UCT_ENC_CJK)
return TQ_NO;
if ((!strcmp(toname, "euc-jp") ||
!strcmp(toname, "shift_jis")) &&
(!strcmp(fromname, "euc-jp") ||
!strcmp(fromname, "shift_jis")))
return TQ_GOOD;
/*
** The other charsets for CJK were handled
** by the (from == to) above, so we need not
** check those. - FM
**/
return TQ_NO;
}
if (!strcmp(fromname, "koi8-r")) {
/*
* Will try to use stripping of high bit...
*/
tqmin = TQ_POOR;
}
if (!strcmp(fromname, "koi8-r") || /* from cyrillic */
!strcmp(fromname, "iso-8859-5") ||
!strcmp(fromname, "cp866") ||
!strcmp(fromname, "cp1251") ||
!strcmp(fromname, "koi-8")) {
if (strcmp(toname, "iso-8859-5") &&
strcmp(toname, "koi8-r") &&
strcmp(toname, "cp866") &&
strcmp(toname, "cp1251"))
tqmax = TQ_POOR;
}
return ((LYCharSet_UC[from].UChndl >= 0) ? tqmax : tqmin);
}
}
/*
** Returns YES if no tranlation necessary (because
** charsets are equal, are equivalent, etc.).
*/
PUBLIC BOOL UCNeedNotTranslate ARGS2(
int, from,
int, to)
{
CONST char *fromname;
CONST char *toname;
if (from == to)
return YES;
if (from < 0)
return NO; /* ??? */
if (LYCharSet_UC[from].enc == UCT_ENC_7BIT) {
return YES; /* Only 7bit chars. */
}
fromname = LYCharSet_UC[from].MIMEname;
if (!strcmp(fromname, "x-transparent") ||
!strcmp(fromname, "us-ascii")) {
return YES;
}
if (to < 0)
return NO; /* ??? */
if (to == 0) {
if (LYCharSet_UC[from].codepoints & (UCT_CP_SUBSETOF_LAT1))
return YES;
}
toname = LYCharSet_UC[to].MIMEname;
if (!strcmp(toname, "x-transparent")) {
return YES;
}
if (LYCharSet_UC[to].enc == UCT_ENC_UTF8) {
return NO;
}
if (from == 0) {
if (LYCharSet_UC[from].codepoints & (UCT_CP_SUPERSETOF_LAT1))
return YES;
}
if (LYCharSet_UC[from].enc == UCT_ENC_CJK) {
if (HTCJK == NOCJK) /* Use that global flag, for now. */
return NO;
if (HTCJK == JAPANESE &&
/*
** Always strip the "x-" from "x-euc-jp",
** or convert "x-shift-jis" to "shift_jis",
** before calling this function, and so
** don't check for them here. - FM
*/
(!strcmp(fromname, "euc-jp") ||
!strncmp(fromname, "iso-2022-jp",11) ||
!strcmp(fromname, "shift_jis")))
return YES; /* ??? */
return NO; /* If not handled by (from == to) above. */
}
return NO;
}
/*
** The idea here is that any stage of the stream pipe which is interested
** in some charset dependent processing will call this function.
** Given input and ouptput charsets, this function will set various flags
** in a UCTransParams structure that _suggest_ to the caller what to do.
**
** Should be called once when a stage starts processing text (and the
** input and output charsets are known), or whenever one of input or
** output charsets has changed (e.g. by SGML.c stage after HTML.c stage
** has processed a META tag).
** The global flags (LYRawMode, HTPassEightBitRaw etc.) are currently
** not taken into account here (except for HTCJK, somewhat), it's still
** up to the caller to do something about them. - KW
*/
PUBLIC void UCSetTransParams ARGS5(
UCTransParams *, pT,
int, cs_in,
CONST LYUCcharset*, p_in,
int, cs_out,
CONST LYUCcharset*, p_out)
{
/*
** Initialize this element to FALSE, and set it TRUE
** below if we're dealing with VISCII. - FM
*/
pT->trans_C0_to_uni = FALSE;
/*
** The "transparent" display character set is a
** "super raw mode". - FM
*/
pT->transp = (!strcmp(p_in->MIMEname, "x-transparent") ||
!strcmp(p_out->MIMEname, "x-transparent"));
if (pT->transp) {
/*
** Set up the structure for "transparent". - FM
*/
pT->do_cjk = FALSE;
pT->decode_utf8 = FALSE;
pT->output_utf8 = FALSE; /* We may, but won't know about it. - KW */
pT->do_8bitraw = TRUE;
pT->use_raw_char_in = TRUE;
pT->strip_raw_char_in = FALSE;
pT->pass_160_173_raw = TRUE;
pT->repl_translated_C0 = (p_out->enc == UCT_ENC_8BIT_C0);
pT->trans_C0_to_uni = (p_in->enc == UCT_ENC_8BIT_C0 ||
p_out->enc == UCT_ENC_8BIT_C0);
} else {
/*
** Initialize local flags. - FM
*/
BOOL intm_ucs = FALSE;
BOOL use_ucs = FALSE;
/*
** Set this element if we want to treat
** the input as CJK. - FM
*/
pT->do_cjk = ((p_in->enc == UCT_ENC_CJK) && (HTCJK != NOCJK));
/*
** Set these elements based on whether
** we are dealing with UTF-8. - FM
*/
pT->decode_utf8 = (p_in->enc == UCT_ENC_UTF8);
pT->output_utf8 = (p_out->enc == UCT_ENC_UTF8);
if (pT->do_cjk) {
/*
** Set up the structure for a CJK input with
** a CJK output (HTCJK != NOCJK). - FM
*/
intm_ucs = FALSE;
pT->trans_to_uni = FALSE;
use_ucs = FALSE;
pT->do_8bitraw = FALSE;
pT->pass_160_173_raw = TRUE;
pT->use_raw_char_in = FALSE; /* Not used for CJK. - KW */
pT->repl_translated_C0 = FALSE;
pT->trans_from_uni = FALSE; /* Not used for CJK. - KW */
} else {
/*
** Set up for all other charset combinations.
** The intm_ucs flag is set TRUE if the input
** charset is iso-8859-1 or UTF-8, or largely
** equivalent to them, i.e. if we have UCS without
** having to do a table translation.
*/
intm_ucs = (cs_in == 0 || pT->decode_utf8 ||
(p_in->codepoints &
(UCT_CP_SUBSETOF_LAT1|UCT_CP_SUBSETOF_UCS2)));
/*
** pT->trans_to_uni is set TRUE if we do not have that as
** input already, and we can translate to Unicode. Note
** that UTF-8 always is converted to Unicode in functions
** that use the transformation structure, so it is
** treated as already Unicode here.
*/
pT->trans_to_uni = (!intm_ucs &&
UCCanUniTranslateFrom(cs_in) != TQ_NO);
/*
** We set this if we are translating to Unicode and
** what normally are low value control characters in
** fact are encoding octets for the input charset
** (presently, this applies to VISCII). - FM
*/
pT->trans_C0_to_uni = (pT->trans_to_uni &&
p_in->enc == UCT_ENC_8BIT_C0);
/*
** We set this, presently, for VISCII. - FM
*/
pT->repl_translated_C0 = (p_out->enc == UCT_ENC_8BIT_C0);
/*
** This is a flag for whether we are dealing with koi8-r
** as the input, and could do 8th-bit stripping for other
** output charsets. Note that this always sets 8th-bit
** stripping if the input charset is KOI8-R and the output
** charset needs it, i.e., regardless of the RawMode and
** consequent HTPassEightBitRaw setting, so you can't look
** at raw koi8-r without selecting that as the display
** character set (or transparent). That's just as well,
** but worth noting for developers - FM
*/
pT->strip_raw_char_in = ((!intm_ucs ||
(p_out->enc == UCT_ENC_7BIT) ||
(p_out->repertoire &
UCT_REP_SUBSETOF_LAT1)) &&
cs_in != cs_out &&
!strcmp(p_in->MIMEname, "koi8-r"));
/*
** use_ucs should be set TRUE if we have or will create
** Unicode values for input octets or UTF multibytes. - FM
*/
use_ucs = (intm_ucs || pT->trans_to_uni);
/*
** This is set TRUE if use_ucs was set FALSE. It is
** parallel to the HTPassEightBitRaw flag, which
** is set TRUE or FALSE elsewhere based on the raw mode
** setting in relation to the current Display Character
** Set. - FM
*/
pT->do_8bitraw = (!use_ucs);
/*
** This is set TRUE when 160 and 173 should not be treated
** specially as nbsp and shy, respectively. - FM
*/
pT->pass_160_173_raw = (!use_ucs &&
!(p_in->like8859 & UCT_R_8859SPECL));
/*
** This is set when the input and output charsets match,
** and they are not ones which should go through a Unicode
** translation process anyway. - FM
*/
pT->use_raw_char_in = (!pT->output_utf8 &&
cs_in == cs_out &&
!pT->trans_C0_to_uni);
/*
** This should be set TRUE when we expect to have
** done translation to Unicode or had the equivalent
** as input, can translate it to our output charset,
** and normally want to do so. The latter depends on
** the pT->do_8bitraw and pT->use_raw_char_in values set
** above, but also on HTPassEightBitRaw in any functions
** which use the transformation structure.. - FM
*/
pT->trans_from_uni = (use_ucs && !pT->do_8bitraw &&
!pT->use_raw_char_in &&
UCCanTranslateUniTo(cs_out) != TQ_NO);
}
}
}
/*
** This function initalizes the transformation
** structure by setting all its elements to
** FALSE. - KW
*/
PUBLIC void UCTransParams_clear ARGS1(
UCTransParams *, pT)
{
pT->transp = FALSE;
pT->do_cjk = FALSE;
pT->decode_utf8 = FALSE;
pT->output_utf8 = FALSE;
pT->do_8bitraw = FALSE;
pT->use_raw_char_in = FALSE;
pT->strip_raw_char_in = FALSE;
pT->pass_160_173_raw = FALSE;
pT->trans_to_uni = FALSE;
pT->trans_C0_to_uni = FALSE;
pT->repl_translated_C0 = FALSE;
pT->trans_from_uni = FALSE;
}
/*
* If terminal is in UTF-8 mode, it probably cannot understand
* box drawing chars as (n)curses handles them. (This may also
* be true for other display character sets, but isn't currently
* checked.) In that case set the chars for hori and vert drawing
* chars to displayable ASCII chars if '0' was requested. They'll
* stay as they are otherwise. - kw
*/
PUBLIC void UCSetBoxChars ARGS5(
int, cset,
int *, pvert_out,
int *, phori_out,
int, vert_in,
int, hori_in)
{
if (cset >= -1 && LYCharSet_UC[cset].enc == UCT_ENC_UTF8) {
*pvert_out = (vert_in ? vert_in : '|');
*phori_out = (hori_in ? hori_in : '-');
} else {
*pvert_out = vert_in;
*phori_out = hori_in;
}
}
/*
* Given an output target HTStream* (can also be a HTStructured* via
* typecast), the target stream's put_character method, and a unicode
* character, CPutUtf8_charstring() will either output the UTF8
* encoding of the unicode and return YES, or do nothing and return
* NO (if conversion would be unnecessary or the unicode character is
* considered invalid).
*
* [Could be used more generally, but is currently only used for &#nnnnn
* stuff - generation of UTF8 from 8-bit encoded charsets not yet done
* by SGML.c etc.]
*/
#define PUTC(ch) ((*myPutc)(target, (char)(ch)))
#define PUTC2(ch) ((*myPutc)(target,(char)(0x80|(0x3f &(ch)))))
PUBLIC BOOL UCPutUtf8_charstring ARGS3(
HTStream *, target,
putc_func_t *, myPutc,
long, code)
{
if (code < 128)
return NO; /* indicate to caller we didn't handle it */
else if (code < 0x800L) {
PUTC(0xc0 | (code>>6));
PUTC2(code);
} else if (code < 0x10000L) {
PUTC(0xe0 | (code>>12));
PUTC2(code>>6);
PUTC2(code);
} else if (code < 0x200000L) {
PUTC(0xf0 | (code>>18));
PUTC2(code>>12);
PUTC2(code>>6);
PUTC2(code);
} else if (code < 0x4000000L) {
PUTC(0xf8 | (code>>24));
PUTC2(code>>18);
PUTC2(code>>12);
PUTC2(code>>6);
PUTC2(code);
} else if (code <= 0x7fffffffL) {
PUTC(0xfc | (code>>30));
PUTC2(code>>24);
PUTC2(code>>18);
PUTC2(code>>12);
PUTC2(code>>6);
PUTC2(code);
} else
return NO;
return YES;
}
/*
** This function converts a Unicode (UCode_t) value
** to a multibyte UTF-8 character, which is loaded
** into the buffer received as an argument. The
** buffer should be large enough to hold at least
** seven characters (but should be declared as 8
** to minimize byte alignment problems with some
** compilers). - FM
*/
PUBLIC BOOL UCConvertUniToUtf8 ARGS2(
UCode_t, code,
char *, buffer)
{
char *ch = buffer;
if (!ch)
return NO;
if (code <= 0 || code > 0x7fffffffL) {
*ch = '\0';
return NO;
}
if (code < 0x800L) {
*ch++ = (char)(0xc0 | (code>>6));
*ch++ = (char)(0x80 | (0x3f & (code)));
*ch = '\0';
} else if (code < 0x10000L) {
*ch++ = (char)(0xe0 | (code>>12));
*ch++ = (char)(0x80 | (0x3f & (code>>6)));
*ch++ = (char)(0x80 | (0x3f & (code)));
*ch = '\0';
} else if (code < 0x200000L) {
*ch++ = (char)(0xf0 | (code>>18));
*ch++ = (char)(0x80 | (0x3f & (code>>12)));
*ch++ = (char)(0x80 | (0x3f & (code>>6)));
*ch++ = (char)(0x80 | (0x3f & (code)));
*ch = '\0';
} else if (code < 0x4000000L) {
*ch++ = (char)(0xf8 | (code>>24));
*ch++ = (char)(0x80 | (0x3f & (code>>18)));
*ch++ = (char)(0x80 | (0x3f & (code>>12)));
*ch++ = (char)(0x80 | (0x3f & (code>>6)));
*ch++ = (char)(0x80 | (0x3f & (code)));
*ch = '\0';
} else {
*ch++ = (char)(0xfc | (code>>30));
*ch++ = (char)(0x80 | (0x3f & (code>>24)));
*ch++ = (char)(0x80 | (0x3f & (code>>18)));
*ch++ = (char)(0x80 | (0x3f & (code>>12)));
*ch++ = (char)(0x80 | (0x3f & (code>>6)));
*ch++ = (char)(0x80 | (0x3f & (code)));
*ch = '\0';
}
return YES;
}
|