about summary refs log blame commit diff stats
path: root/WWW/Library/Implementation/HTPlain.c
blob: b3e80c6f6b031fb7308369258537036ee8ee2b24 (plain) (tree)
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
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722

















































































































































































































































































































































































































































































































































































































































































































































                                                                                                          
/*
 * $LynxId: HTPlain.c,v 1.49 2011/06/11 12:09:07 tom Exp $
 *
 *		Plain text object		HTWrite.c
 *		=================
 *
 *	This version of the stream object just writes to a socket.
 *	The socket is assumed open and left open.
 *
 *	Bugs:
 *		strings written must be less than buffer size.
 */

#define HTSTREAM_INTERNAL 1

#include <HTUtils.h>
#include <LYCharVals.h>		/* S/390 -- gil -- 0288 */

#include <HTPlain.h>

#include <HTChunk.h>
#include <HText.h>
#include <HTStyle.h>
#define Lynx_HTML_Handler
#include <HTML.h>		/* styles[] */

#define BUFFER_SIZE 4096;	/* Tradeoff */

#include <HTMLDTD.h>
#include <HTCJK.h>
#include <UCMap.h>
#include <UCDefs.h>
#include <UCAux.h>

#include <LYCharSets.h>
#include <LYStrings.h>
#include <LYLeaks.h>

static int HTPlain_lastraw = -1;
static int HTPlain_bs_pending = 0;	/* 1:bs 2:underline 3:underline+bs - kw */

/*		HTML Object
 *		-----------
 */
struct _HTStream {
    const HTStreamClass *isa;
    HText *text;
    /*
     * The node_anchor UCInfo and handle for the input (PARSER) stage.  - FM
     */
    LYUCcharset *inUCI;
    int inUCLYhndl;
    /*
     * The node_anchor UCInfo and handle for the output (HTEXT) stage.  - FM
     */
    LYUCcharset *outUCI;
    int outUCLYhndl;
    /*
     * Counter, value, buffer and pointer for UTF-8 handling.  - FM
     */
    char utf_count;
    UCode_t utf_char;
    char utf_buf[8];
    char *utf_buf_p;
    /*
     * The charset transformation structure.  - FM
     */
    UCTransParams T;
};

static char replace_buf[64];	/* buffer for replacement strings */

static void HTPlain_getChartransInfo(HTStream *me, HTParentAnchor *anchor)
{
    if (me->inUCLYhndl < 0) {
	HTAnchor_copyUCInfoStage(anchor, UCT_STAGE_PARSER, UCT_STAGE_MIME,
				 UCT_SETBY_PARSER);
	me->inUCLYhndl = HTAnchor_getUCLYhndl(anchor, UCT_STAGE_PARSER);
    }
    if (me->outUCLYhndl < 0) {
	int chndl = HTAnchor_getUCLYhndl(anchor, UCT_STAGE_HTEXT);

	if (chndl < 0) {
	    chndl = current_char_set;
	    HTAnchor_setUCInfoStage(anchor, chndl,
				    UCT_STAGE_HTEXT, UCT_SETBY_DEFAULT);
	}
	HTAnchor_setUCInfoStage(anchor, chndl,
				UCT_STAGE_HTEXT, UCT_SETBY_DEFAULT);
	me->outUCLYhndl = HTAnchor_getUCLYhndl(anchor, UCT_STAGE_HTEXT);
    }
    me->inUCI = HTAnchor_getUCInfoStage(anchor, UCT_STAGE_PARSER);
    me->outUCI = HTAnchor_getUCInfoStage(anchor, UCT_STAGE_HTEXT);
}

/*	Write the buffer out to the socket
 *	----------------------------------
 */

/*_________________________________________________________________________
 *
 *			A C T I O N	R O U T I N E S
 */

static void HTPlain_write(HTStream *me, const char *s,
			  int l);

/*	Character handling
 *	------------------
 */
static void HTPlain_put_character(HTStream *me, int c)
{
#ifdef REMOVE_CR_ONLY
    /*
     * Throw away \r's.
     */
    if (c != '\r') {
	HText_appendCharacter(me->text, c);
    }
#else
    /*
     * See HTPlain_write() for explanations of the following code (we've been
     * called via HTPlain_put_string() to do for each character of a terminated
     * string what HTPlain_write() does via a while loop for each character in
     * a stream of given length).  - FM
     */
    if ((HTPlain_lastraw == '\r') && c == '\n') {
	HTPlain_lastraw = -1;
	return;
    }
    if (c == '\b' || c == '_' || HTPlain_bs_pending) {
	char temp[1];

	temp[0] = (char) c;
	HTPlain_write(me, temp, 1);
	return;
    }
    HTPlain_lastraw = UCH(c);
    if (c == '\r') {
	HText_appendCharacter(me->text, '\n');
    } else if (TOASCII(UCH(c)) >= 127) {	/* S/390 -- gil -- 0305 */
	char temp[1];

	temp[0] = (char) c;
	/*
	 * For now, don't repeat everything here that has been done below - KW
	 */
	HTPlain_write(me, temp, 1);
    } else if (IS_CJK_TTY) {
	HText_appendCharacter(me->text, c);
    } else if (TOASCII(UCH(c)) >= 127 && TOASCII(UCH(c)) < 161 &&
	       HTPassHighCtrlRaw) {
	HText_appendCharacter(me->text, c);
    } else if (UCH(c) == CH_NBSP) {	/* S/390 -- gil -- 0341 */
	HText_appendCharacter(me->text, ' ');
    } else if (UCH(c) == CH_SHY) {
	return;
    } else if ((UCH(c) >= ' ' && TOASCII(UCH(c)) < 127) ||
	       c == '\n' || c == '\t') {
	HText_appendCharacter(me->text, c);
    } else if (TOASCII(UCH(c)) > 160) {
	if (!HTPassEightBitRaw &&
	    !((me->outUCLYhndl == LATIN1) ||
	      (me->outUCI->enc & (UCT_CP_SUPERSETOF_LAT1)))) {
	    int len, high, low, i, diff = 1;
	    const char *name;
	    UCode_t value = (UCode_t) FROMASCII((TOASCII(UCH(c)) - 160));

	    name = HTMLGetEntityName(value);
	    len = (int) strlen(name);
	    for (low = 0, high = (int) HTML_dtd.number_of_entities;
		 high > low;
		 diff < 0 ? (low = i + 1) : (high = i)) {
		/* Binary search */
		i = (low + (high - low) / 2);
		diff = AS_ncmp(HTML_dtd.entity_names[i], name, (unsigned) len);
		if (diff == 0) {
		    HText_appendText(me->text,
				     LYCharSets[me->outUCLYhndl][i]);
		    break;
		}
	    }
	    if (diff) {
		HText_appendCharacter(me->text, c);
	    }
	} else {
	    HText_appendCharacter(me->text, c);
	}
    }
#endif /* REMOVE_CR_ONLY */
}

/*	String handling
 *	---------------
 *
 */
static void HTPlain_put_string(HTStream *me, const char *s)
{
#ifdef REMOVE_CR_ONLY
    HText_appendText(me->text, s);
#else
    const char *p;

    if (s == NULL)
	return;
    for (p = s; *p; p++) {
	HTPlain_put_character(me, *p);
    }
#endif /* REMOVE_CR_ONLY */
}

/*
 *	Entry function for displayed text/plain and WWW_SOURCE strings. - FM
 *	---------------------------------------------------------------
 */
static void HTPlain_write(HTStream *me, const char *s, int l)
{
    const char *p;
    const char *e = s + l;
    char c;
    unsigned c_unsign;
    BOOL chk;
    UCode_t code, uck = -1;
    char saved_char_in = '\0';

    for (p = s; p < e; p++) {
#ifdef REMOVE_CR_ONLY
	/*
	 * Append the whole string, but remove any \r's.  - FM
	 */
	if (*p != '\r') {
	    HText_appendCharacter(me->text, *p);
	}
#else
	if (*p == '\b') {
	    if (HTPlain_lastraw >= UCH(' ') &&
		HTPlain_lastraw != '\r' && HTPlain_lastraw != '\n') {
		if (!HTPlain_bs_pending) {
		    HTPlain_bs_pending = 1;
		    continue;
		} else if (HTPlain_bs_pending == 2) {
		    HTPlain_bs_pending = 3;
		    continue;
		}
	    }
	    if (HTPlain_bs_pending >= 2)
		HText_appendCharacter(me->text, '_');
	    HTPlain_bs_pending = 0;
	} else if (*p == '_') {
	    if (!HTPlain_bs_pending) {
		HTPlain_bs_pending = 2;
		HTPlain_lastraw = UCH(*p);
		continue;
#if 0
	    } else if (HTPlain_bs_pending != 2) {
		HTPlain_bs_pending--;	/* 1 -> 0, 3 -> 2 */
		HTPlain_lastraw = UCH(*p);
		continue;
#endif
	    }
	}

	/*
	 * Try to handle lone LFs, CRLFs and lone CRs as newline, and to deal
	 * with control, ASCII, and 8-bit characters based on best guesses of
	 * what's appropriate.  - FM
	 */
	if ((HTPlain_lastraw == '\r') && *p == '\n') {
	    HTPlain_lastraw = -1;
	    continue;
	}

	if (HTPlain_bs_pending &&
	    !(UCH(*p) >= ' ' && *p != '\r' && *p != '\n' &&
	      (HTPlain_lastraw == UCH(*p) ||
	       HTPlain_lastraw == UCH('_') ||
	       *p == '_'))) {
	    if (HTPlain_bs_pending >= 2)
		HText_appendCharacter(me->text, '_');
	    HTPlain_bs_pending = 0;
	} else if (HTPlain_bs_pending == 1) {
	    HTPlain_bs_pending = 0;
	    continue;		/* ignore last two of "X\bX" or "X\b_" - kw */
	} else if (HTPlain_bs_pending == 3) {
	    if (*p == '_') {
		HTPlain_bs_pending = 2;
		continue;	/* ignore last two of "_\b_" - kw */
	    } else {
		HTPlain_bs_pending = 0;
		/* ignore first two of "_\bX" - kw */
	    }
	} else if (HTPlain_bs_pending == 2) {
	    HText_appendCharacter(me->text, '_');
	    if (*p == '_')
		continue;	/* keep second of "__" pending - kw */
	    HTPlain_bs_pending = 0;
	} else {
	    HTPlain_bs_pending = 0;
	}
	HTPlain_lastraw = UCH(*p);
	if (*p == '\r') {
	    HText_appendCharacter(me->text, '\n');
	    continue;
	}
	/*
	 * Make sure the character is handled as Unicode whenever that's
	 * appropriate.  - FM
	 */
	c = *p;
	c_unsign = UCH(c);
	code = (UCode_t) c_unsign;
	saved_char_in = '\0';
	/*
	 * Combine any UTF-8 multibytes into Unicode to check for special
	 * characters.  - FM
	 */
	if (me->T.decode_utf8) {
	    /*
	     * Combine UTF-8 into Unicode.  Incomplete characters silently
	     * ignored.  from Linux kernel's console.c - KW
	     */
	    if (TOASCII(c_unsign) > 127) {	/* S/390 -- gil -- 0371 */
		/*
		 * We have an octet from a multibyte character.  - FM
		 */
		if (me->utf_count > 0 && (c & 0xc0) == 0x80) {
		    /*
		     * Adjust the UCode_t value, add the octet to the buffer,
		     * and decrement the byte count.  - FM
		     */
		    me->utf_char = (me->utf_char << 6) | (c & 0x3f);
		    me->utf_count--;
		    *(me->utf_buf_p) = c;
		    (me->utf_buf_p)++;
		    if (me->utf_count == 0) {
			/*
			 * Got a complete multibyte character.
			 */
			*(me->utf_buf_p) = '\0';
			code = me->utf_char;
			if (code > 0 && code < 256) {
			    c = FROMASCII((char) code);
			    c_unsign = UCH(c);
			}
		    } else {
			/*
			 * Get the next byte.  - FM
			 */
			continue;
		    }
		} else {
		    /*
		     * Start handling a new multibyte character.  - FM
		     */
		    me->utf_buf_p[0] = c;
		    me->utf_buf_p = &me->utf_buf[1];
		    if ((*p & 0xe0) == 0xc0) {
			me->utf_count = 1;
			me->utf_char = (c & 0x1f);
		    } else if ((*p & 0xf0) == 0xe0) {
			me->utf_count = 2;
			me->utf_char = (c & 0x0f);
		    } else if ((*p & 0xf8) == 0xf0) {
			me->utf_count = 3;
			me->utf_char = (c & 0x07);
		    } else if ((*p & 0xfc) == 0xf8) {
			me->utf_count = 4;
			me->utf_char = (c & 0x03);
		    } else if ((*p & 0xfe) == 0xfc) {
			me->utf_count = 5;
			me->utf_char = (c & 0x01);
		    } else {
			/*
			 * We got garbage, so ignore it.  - FM
			 */
			me->utf_count = 0;
			me->utf_buf_p[0] = '\0';
			me->utf_buf_p = me->utf_buf;
		    }
		    /*
		     * Get the next byte.  - FM
		     */
		    continue;
		}
	    } else if (me->utf_count > 0) {
		/*
		 * Got an ASCII character when expecting UTF-8 multibytes, so
		 * ignore the buffered multibye characters and fall through
		 * with the current ASCII character.  - FM
		 */
		me->utf_count = 0;
		me->utf_buf[0] = '\0';
		me->utf_buf_p = me->utf_buf;
		code = (UCode_t) c_unsign;
	    } else {
		/*
		 * Got a valid ASCII character, so fall through with it.  - FM
		 */
		code = (UCode_t) c_unsign;
	    }
	}
	/*
	 * Convert characters from non-UTF-8 charsets to Unicode (if
	 * appropriate).  - FM
	 */
	if (!(me->T.decode_utf8 &&
	      UCH(*p) > 127)) {
#ifdef NOTDEFINED
	    if (me->T.strip_raw_char_in)
		saved_char_in = c;
#endif /* NOTDEFINED */
	    if (me->T.trans_to_uni &&
		(TOASCII(code) >= LYlowest_eightbit[me->inUCLYhndl] ||	/* S/390 -- gil -- 0389 */
		 (code < ' ' && code != 0 &&
		  me->T.trans_C0_to_uni))) {
		/*
		 * Convert the octet to Unicode.  - FM
		 */
		code = (UCode_t) UCTransToUni(c, me->inUCLYhndl);
		if (code > 0) {
		    saved_char_in = c;
		    if (code < 256) {
			c = FROMASCII((char) code);
			c_unsign = UCH(c);
		    }
		}
	    } else if (code < 32 && code != 0 &&
		       me->T.trans_C0_to_uni) {
		/*
		 * Quote from SGML.c:
		 * "This else if may be too ugly to keep.  - KW"
		 */
		if (me->T.trans_from_uni &&
		    (((code = UCTransToUni(c, me->inUCLYhndl)) >= 32) ||
		     (me->T.transp &&
		      (code = UCTransToUni(c, me->inUCLYhndl)) > 0))) {
		    saved_char_in = c;
		    if (code < 256) {
			c = FROMASCII((char) code);
			c_unsign = UCH(c);
		    }
		} else {
		    uck = -1;
		    if (me->T.transp) {
			uck = UCTransCharStr(replace_buf, 60, c,
					     me->inUCLYhndl,
					     me->inUCLYhndl, NO);
		    }
		    if (!me->T.transp || uck < 0) {
			uck = UCTransCharStr(replace_buf, 60, c,
					     me->inUCLYhndl,
					     me->outUCLYhndl, YES);
		    }
		    if (uck == 0) {
			continue;
		    } else if (uck < 0) {
			me->utf_buf[0] = '\0';
		    } else {
			c = replace_buf[0];
			if (c && replace_buf[1]) {
			    HText_appendText(me->text, replace_buf);
			    continue;
			}
		    }
		    me->utf_buf[0] = '\0';
		    code = UCH(c);
		}		/*  Next line end of ugly stuff for C0. - KW */
	    } else {
		me->utf_buf[0] = '\0';
		code = UCH(c);
	    }
	}
	/*
	 * At this point we have either code in Unicode (and c in latin1 if
	 * code is in the latin1 range), or code and c will have to be passed
	 * raw.
	 */

	/*
	 * If CJK mode is on, we'll assume the document matches the user's
	 * display character set, and if not, the user should toggle off
	 * raw/CJK mode to reload.  - FM
	 */
	if (IS_CJK_TTY) {
	    HText_appendCharacter(me->text, c);

#define PASSHICTRL (me->T.transp || \
		    code >= LYlowest_eightbit[me->inUCLYhndl])
#define PASS8859SPECL me->T.pass_160_173_raw
#define PASSHI8BIT (HTPassEightBitRaw || \
		    (me->T.do_8bitraw && !me->T.trans_from_uni))
	    /*
	     * If HTPassHighCtrlRaw is set (e.g., for KOI8-R) assume the
	     * document matches and pass 127-160 8-bit characters.  If it
	     * doesn't match, the user should toggle raw/CJK mode off.  - FM
	     */
	} else if (TOASCII(code) >= 127 && TOASCII(code) < 161 &&	/* S/390 -- gil -- 0427 */
		   PASSHICTRL && PASS8859SPECL) {
	    HText_appendCharacter(me->text, c);
	} else if (code == CH_SHY && PASS8859SPECL) {
	    HText_appendCharacter(me->text, c);
	    /*
	     * If neither HTPassHighCtrlRaw nor CJK is set, play it safe and
	     * treat 160 (nbsp) as an ASCII space (32).  - FM
	     */
	} else if (code == CH_NBSP) {
	    HText_appendCharacter(me->text, ' ');
	    /*
	     * If neither HTPassHighCtrlRaw nor CJK is set, play it safe and
	     * ignore 173 (shy).  - FM
	     * Now only ignore it for color style, which doesn't handle it
	     * anyway.  Otherwise pass it on as LY_SOFT_HYPHEN and let HText
	     * deal with it.  It should be either ignored, or displayed as a
	     * hyphen if it was indeed at the end of a line.  Well it should. 
	     * - kw
	     */
	} else if (code == CH_SHY) {
#ifndef USE_COLOR_STYLE
	    HText_appendCharacter(me->text, LY_SOFT_HYPHEN);
#endif
	    continue;
	    /*
	     * If we get to here, pass the displayable ASCII characters.  - FM
	     */
	} else if ((code >= ' ' && TOASCII(code) < 127) ||
		   (PASSHI8BIT &&
		    c >= LYlowest_eightbit[me->outUCLYhndl]) ||
		   *p == '\n' || *p == '\t') {
	    HText_appendCharacter(me->text, c);
	    /*
	     * Use an ASCII space (32) for ensp, emsp or thinsp.  - FM
	     */
	} else if (code == 8194 || code == 8195 || code == 8201) {
	    HText_appendCharacter(me->text, ' ');
	    /*
	     * If we want the raw character, pass it now.  - FM
	     */
	} else if (me->T.use_raw_char_in && saved_char_in) {
	    HText_appendCharacter(me->text, saved_char_in);
/******************************************************************
 * I.  LATIN-1 OR UCS2 TO DISPLAY CHARSET
 ******************************************************************/
	} else if ((chk = (BOOL) (me->T.trans_from_uni && code >= 160)) &&
		   (uck = UCTransUniChar(code,
					 me->outUCLYhndl)) >= ' ' &&	/* S/390 -- gil -- 0464 */
		   uck < 256) {
	    CTRACE((tfp, "UCTransUniChar returned 0x%.2" PRI_UCode_t
		    ":'%c'.\n",
		    uck, FROMASCII(UCH(uck))));
	    HText_appendCharacter(me->text, ((char) (uck & 0xff)));
	} else if (chk &&
		   (uck == -4 ||
		    (me->T.repl_translated_C0 && uck > 0 && uck < ' ')) &&	/* S/390 -- gil -- 0481 */
	    /*
	     * Not found; look for replacement string.
	     */
		   (uck = UCTransUniCharStr(replace_buf, 60, code,
					    me->outUCLYhndl, 0) >= 0)) {
	    /*
	     * No further tests for valididy - assume that whoever defined
	     * replacement strings knew what she was doing.
	     */
	    HText_appendText(me->text, replace_buf);
	    /*
	     * If we get to here, and should have translated, translation has
	     * failed so far.
	     */
	} else if (chk && TOASCII(code) > 127 && me->T.output_utf8) {	/* S/390 -- gil -- 0498 */
	    /*
	     * We want UTF-8 output, so do it now.  - FM
	     */
	    if (*me->utf_buf) {
		HText_appendText(me->text, me->utf_buf);
		me->utf_buf[0] = '\0';
		me->utf_buf_p = me->utf_buf;
	    } else if (UCConvertUniToUtf8(code, replace_buf)) {
		HText_appendText(me->text, replace_buf);
	    } else {
		/*
		 * Out of luck, so use the UHHH notation (ugh).  - gil
		 */
		/* S/390 -- gil -- 0517 */
		sprintf(replace_buf, "U%.2lX", (unsigned long) TOASCII(code));
		HText_appendText(me->text, replace_buf);
	    }
#ifdef NOTDEFINED
	} else if (me->T.strip_raw_char_in &&
		   UCH(*p) >= 192 &&
		   UCH(*p) < 255) {
	    /*
	     * KOI special:  strip high bit, gives (somewhat) readable ASCII.
	     */
	    HText_appendCharacter(me->text, (char) (*p & 0x7f));
#endif /* NOTDEFINED */
	    /*
	     * If we don't actually want the character, make it safe and output
	     * that now.  - FM
	     */
	} else if ((c_unsign > 0 &&
		    (int) c_unsign < LYlowest_eightbit[me->outUCLYhndl]) ||
		   (me->T.trans_from_uni && !HTPassEightBitRaw)) {
	    /*
	     * If we do not have the "7-bit approximations" as our output
	     * character set (in which case we did it already) seek a
	     * translation for that.  Otherwise, or if the translation fails,
	     * use UHHH notation.  - FM
	     */
	    if ((chk = (BOOL) (me->outUCLYhndl !=
			       UCGetLYhndl_byMIME("us-ascii"))) &&
		(uck = UCTransUniChar(code,
				      UCGetLYhndl_byMIME("us-ascii")))
		>= ' ' && TOASCII(uck) < 127) {		/* S/390 -- gil -- 0535 */
		/*
		 * Got an ASCII character (yippey).  - FM
		 */
		c = FROMASCII((char) uck);
		HText_appendCharacter(me->text, c);
	    } else if ((chk && uck == -4) &&
		       (uck = UCTransUniCharStr(replace_buf,
						60, code,
						UCGetLYhndl_byMIME("us-ascii"),
						0) >= 0)) {
		/*
		 * Got a repacement string (yippey).  - FM
		 */
		HText_appendText(me->text, replace_buf);
	    } else if (code == 8204 || code == 8205) {
		/*
		 * Ignore 8204 (zwnj) or 8205 (zwj), if we get to here.  - FM
		 */
		CTRACE((tfp, "HTPlain_write: Ignoring '%" PRI_UCode_t "'.\n", code));
	    } else if (code == 8206 || code == 8207) {
		/*
		 * Ignore 8206 (lrm) or 8207 (rlm), if we get to here.  - FM
		 */
		CTRACE((tfp, "HTPlain_write: Ignoring '%" PRI_UCode_t "'.\n", code));
	    } else {
		/*
		 * Out of luck, so use the UHHH notation (ugh).  - FM
		 */
		/* do not print UHHH for now
		   sprintf(replace_buf, "U%.2lX", code);
		   HText_appendText(me->text, replace_buf);
		 */
	    }
	    /*
	     * If we get to here and have a monobyte character, pass it.  - FM
	     */
	} else if (c_unsign != 0 && c_unsign < 256) {
	    HText_appendCharacter(me->text, c);
	}
#endif /* REMOVE_CR_ONLY */
    }
}

/*	Free an HTML object
 *	-------------------
 *
 *	Note that the SGML parsing context is freed, but the created object is
 *	not, as it takes on an existence of its own unless explicitly freed.
 */
static void HTPlain_free(HTStream *me)
{
    if (HTPlain_bs_pending >= 2)
	HText_appendCharacter(me->text, '_');
    FREE(me);
}

/*	End writing
*/
static void HTPlain_abort(HTStream *me, HTError e GCC_UNUSED)
{
    HTPlain_free(me);
}

/*		Structured Object Class
 *		-----------------------
 */
static const HTStreamClass HTPlain =
{
    "PlainPresenter",
    HTPlain_free,
    HTPlain_abort,
    HTPlain_put_character, HTPlain_put_string, HTPlain_write,
};

/*		New object
 *		----------
 */
HTStream *HTPlainPresent(HTPresentation *pres GCC_UNUSED, HTParentAnchor *anchor,
			 HTStream *sink GCC_UNUSED)
{

    HTStream *me = (HTStream *) malloc(sizeof(*me));

    if (me == NULL)
	outofmem(__FILE__, "HTPlain_new");

    assert(me != NULL);

    me->isa = &HTPlain;

    HTPlain_lastraw = -1;

    me->utf_count = 0;
    me->utf_char = 0;
    me->utf_buf[0] = me->utf_buf[6] = me->utf_buf[7] = '\0';
    me->utf_buf_p = me->utf_buf;
    me->outUCLYhndl = HTAnchor_getUCLYhndl(anchor, UCT_STAGE_HTEXT);
    me->inUCLYhndl = HTAnchor_getUCLYhndl(anchor, UCT_STAGE_PARSER);
    HTPlain_getChartransInfo(me, anchor);
    UCSetTransParams(&me->T,
		     me->inUCLYhndl, me->inUCI,
		     me->outUCLYhndl,
		     HTAnchor_getUCInfoStage(anchor, UCT_STAGE_HTEXT));

    me->text = HText_new(anchor);
    HText_setStyle(me->text, LYstyles(HTML_XMP));
    HText_beginAppend(me->text);

    return (HTStream *) me;
}