summaryrefslogtreecommitdiff
path: root/ext/standard/html.c
blob: cf933df0a18a8c82fbb839019286fdc9652171df (plain)
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
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
/*
   +----------------------------------------------------------------------+
   | PHP Version 4                                                        |
   +----------------------------------------------------------------------+
   | Copyright (c) 1997-2002 The PHP Group                                |
   +----------------------------------------------------------------------+
   | This source file is subject to version 2.02 of the PHP license,      |
   | that is bundled with this package in the file LICENSE, and is        |
   | available at through the world-wide-web at                           |
   | http://www.php.net/license/2_02.txt.                                 |
   | If you did not receive a copy of the PHP license and are unable to   |
   | obtain it through the world-wide-web, please send a note to          |
   | license@php.net so we can mail you a copy immediately.               |
   +----------------------------------------------------------------------+
   | Authors: Rasmus Lerdorf <rasmus@php.net>                             |
   |          Jaakko Hyvätti <jaakko.hyvatti@iki.fi>                      |
   |          Wez Furlong <wez@thebrainroom.com>                          |
   +----------------------------------------------------------------------+
*/

/* $Id$ */

#include "php.h"
#include "reg.h"
#include "html.h"
#include "php_string.h"
#if HAVE_LOCALE_H
#include <locale.h>
#endif
#if HAVE_LANGINFO_H
#include <langinfo.h>
#endif

enum entity_charset { cs_terminator, cs_8859_1, cs_cp1252,
					  cs_8859_15, cs_utf_8, cs_big5, cs_gb2312, 
 					  cs_big5hkscs, cs_sjis, cs_eucjp};
typedef const char *entity_table_t;

/* codepage 1252 is a Windows extension to iso-8859-1. */
static entity_table_t ent_cp_1252[] = {
	NULL, NULL, "sbquo", "fnof", "bdquo", "hellip", "dagger",
	"Dagger", "circ", "permil", "Scaron", "lsaquo", "OElig",
	NULL, NULL, NULL, NULL, "lsquo", "rsquo", "ldquo", "rdquo",
	"bull", "ndash", "mdash", "tilde", "trade", "scaron", "rsaquo",
	"oelig", NULL, NULL, "Yuml" 
};

static entity_table_t ent_iso_8859_1[] = {
	"nbsp", "iexcl", "cent", "pound", "curren", "yen", "brvbar",
	"sect", "uml", "copy", "ordf", "laquo", "not", "shy", "reg",
	"macr", "deg", "plusmn", "sup2", "sup3", "acute", "micro",
	"para", "middot", "cedil", "sup1", "ordm", "raquo", "frac14",
	"frac12", "frac34", "iquest", "Agrave", "Aacute", "Acirc",
	"Atilde", "Auml", "Aring", "AElig", "Ccedil", "Egrave",
	"Eacute", "Ecirc", "Euml", "Igrave", "Iacute", "Icirc",
	"Iuml", "ETH", "Ntilde", "Ograve", "Oacute", "Ocirc", "Otilde",
	"Ouml", "times", "Oslash", "Ugrave", "Uacute", "Ucirc", "Uuml",
	"Yacute", "THORN", "szlig", "agrave", "aacute", "acirc",
	"atilde", "auml", "aring", "aelig", "ccedil", "egrave",
	"eacute", "ecirc", "euml", "igrave", "iacute", "icirc",
	"iuml", "eth", "ntilde", "ograve", "oacute", "ocirc", "otilde",
	"ouml", "divide", "oslash", "ugrave", "uacute", "ucirc",
	"uuml", "yacute", "thorn", "yuml"
};

static entity_table_t ent_iso_8859_15[] = {
	"nbsp", "iexcl", "cent", "pound", "euro", "yen", "Scaron",
	"sect", "scaron", "copy", "ordf", "laquo", "not", "shy", "reg",
	"macr", "deg", "plusmn", "sup2", "sup3", NULL, /* Zcaron */
	"micro", "para", "middot", NULL, /* zcaron */ "sup1", "ordm",
	"raquo", "OElig", "oelig", "Yuml", "iquest", "Agrave", "Aacute",
	"Acirc", "Atilde", "Auml", "Aring", "AElig", "Ccedil", "Egrave",
	"Eacute", "Ecirc", "Euml", "Igrave", "Iacute", "Icirc",
	"Iuml", "ETH", "Ntilde", "Ograve", "Oacute", "Ocirc", "Otilde",
	"Ouml", "times", "Oslash", "Ugrave", "Uacute", "Ucirc", "Uuml",
	"Yacute", "THORN", "szlig", "agrave", "aacute", "acirc",
	"atilde", "auml", "aring", "aelig", "ccedil", "egrave",
	"eacute", "ecirc", "euml", "igrave", "iacute", "icirc",
	"iuml", "eth", "ntilde", "ograve", "oacute", "ocirc", "otilde",
	"ouml", "divide", "oslash", "ugrave", "uacute", "ucirc",
	"uuml", "yacute", "thorn", "yuml"
};

static entity_table_t ent_uni_338_402[] = {
	/* 338 */
	"OElig", "oelig", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL,
	/* 352 */
	"Scaron", "scaron",
	/* 354 - 375 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 376 */
	"Yuml",
	/* 377 - 401 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 402 */
	"fnof"
};

static entity_table_t ent_uni_spacing[] = {
	/* 710 */
	"circ",
	/* 711 - 731 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 732 */
	"tilde",
};

static entity_table_t ent_uni_greek[] = {
	/* 913 */
	"Alpha", "Beta", "Gamma", "Delta", "Epsilon", "Zeta", "Eta", "Theta",
	"Iota", "Kappa", "Lambda", "Mu", "Nu", "X1", "Omicron", "P1", "Rho",
	NULL, "Sigma", "Tau", "Upsilon", "Ph1", "Ch1", "Ps1", "Omega",
	/* 938 - 944 are not mapped */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	"alpha", "beta", "gamma", "delta", "epsilon", "zeta", "eta", "theta",
	"iota", "kappa", "lamda", "mu", "nu", "x1", "omicron", "p1", "rho",
	"sigmaf", "sigma", "tau", "upsilon", "ph1", "ch1", "ps1", "omega",
	/* 970 - 976 are not mapped */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	"thetasym", "ups1h",
	NULL, NULL, NULL,
	"p1v" 
};

static entity_table_t ent_uni_punct[] = {
	/* 8194 */
	"ensp", "emsp", NULL, NULL, NULL, NULL, NULL,
	"thinsp", NULL, NULL, "zwnj", "zwj", "lrm", "rlm",
	NULL, NULL, NULL, "ndash", "mdash", NULL, NULL, NULL,
	"lsquo", "rsquo", "sbquo", NULL, "ldquo", "rdquo", "bdquo",
	"dagger", "Dagger",	"bull", NULL, NULL, NULL, "hellip",
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "permil", NULL,
	"prime", "Prime", NULL, NULL, NULL, NULL, NULL, "lsaquo", "rsaquo",
	NULL, NULL, NULL, "oline", NULL, NULL, NULL, NULL, NULL,
	"frasl"
};

static entity_table_t ent_uni_8465_8501[] = {
	/* 8465 */
	"image", NULL, NULL, NULL, NULL, NULL, NULL,
	/* 8472 */
	"weierp", NULL, NULL, NULL,
	/* 8476 */
	"real", NULL, NULL, NULL, NULL, NULL,
	/* 8482 */
	"trade", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 8501 */
	"alefsym",
};

static entity_table_t ent_uni_8592_9002[] = {
	/* 8592 */
	"larr", "uarr", "rarr", "darr", "harr",
	/* 8597 - 8628 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL,
	/* 8629 */
	"crarr",
	/* 8630 - 8655 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, 
	/* 8656 */
	"lArr", "uArr", "rArr", "dArr", "hArr",
	/* 8661 - 8703 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL,
	/* 8704 */
	"forall", "part", "exist", NULL, "empty", NULL, "nabla", "isin",
	"notin", NULL, "n1", NULL, NULL, NULL, "prod", NULL, "sum", "minus",
	NULL, NULL, NULL, NULL,	"lowast", NULL, NULL, "radic", NULL, NULL,
	"prop", "infin", NULL, "ang", NULL, NULL, NULL, NULL, NULL, NULL,
	"and", "or", "cap", "cup", "int", NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, "there4", NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, "sim", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	"cong", NULL, NULL, "asymp",
	/* 8777 - 8799 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, 
	/* 8800 */
	"ne", "equiv", NULL, NULL, "le", "ge",
	/* 8806 - 8833 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 8834 */
	"sub", "sup", "nsub", NULL, "sube", "supe",
	/* 8840 - 8852 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 8853 */
	"oplus", NULL, "otimes",
	/* 8856 - 8868 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	/* 8869 */
	"perp",
	/* 8870 - 8901 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL,
	/* 8901 */
	"sdot",
	/* 8902 - 8967 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL,
	/* 8968 */
	"lceil", "rceil", "lfloor", "rfloor",
	/* 8969 - 9000 */
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
	NULL,
	/* 9001 */
	"lang", "rang",
};

static entity_table_t ent_uni_9674[] = {
	/* 9674 */
	"loz"
};

static entity_table_t ent_uni_9824_9830[] = {
	/* 9824 */
	"spades", NULL, NULL, "clubs", NULL, "hearts", "diams"
};

struct html_entity_map {
	enum entity_charset charset;	/* charset identifier */
	unsigned short basechar;			/* char code at start of table */
	unsigned short endchar;			/* last char code in the table */
	entity_table_t *table;			/* the table of mappings */
};

static const struct html_entity_map entity_map[] = {
	{ cs_cp1252, 		0x80, 0x9f, ent_cp_1252 },
	{ cs_cp1252, 		0xa0, 0xff, ent_iso_8859_1 },
	{ cs_8859_1, 		0xa0, 0xff, ent_iso_8859_1 },
	{ cs_8859_15, 		0xa0, 0xff, ent_iso_8859_15 },
	{ cs_utf_8, 		0xa0, 0xff, ent_iso_8859_1 },
	{ cs_utf_8, 		338,  402,  ent_uni_338_402 },
	{ cs_utf_8, 		710,  732,  ent_uni_spacing },
	{ cs_utf_8, 		913,  982,  ent_uni_greek },
	{ cs_utf_8, 		8194, 8260, ent_uni_punct },
	{ cs_utf_8, 		8465, 8501, ent_uni_8465_8501 },
	{ cs_utf_8, 		8592, 9002, ent_uni_8592_9002 },
	{ cs_utf_8, 		9674, 9674, ent_uni_9674 },
	{ cs_utf_8, 		9824, 9830, ent_uni_9824_9830 },
	{ cs_big5, 			0xa0, 0xff, ent_iso_8859_1 },
	{ cs_gb2312, 		0xa0, 0xff, ent_iso_8859_1 },
	{ cs_big5hkscs, 	0xa0, 0xff, ent_iso_8859_1 },
 	{ cs_sjis,			0xa0, 0xff, ent_iso_8859_1 },
 	{ cs_eucjp,			0xa0, 0xff, ent_iso_8859_1 },
	{ cs_terminator }
};

static const struct {
	const char *codeset;
	enum entity_charset charset;
} charset_map[] = {
	{ "ISO-8859-1", 	cs_8859_1 },
	{ "ISO-8859-15", 	cs_8859_15 },
	{ "utf-8", 			cs_utf_8 },
	{ "cp1252", 		cs_cp1252 },
	{ "BIG5",			cs_big5 },
	{ "GB2312",			cs_gb2312 },
	{ "BIG5-HKSCS",		cs_big5hkscs },
 	{ "Shift_JIS",		cs_sjis },
 	{ "SJIS",   		cs_sjis },
 	{ "EUCJP",   		cs_eucjp },
 	{ "EUC-JP",   		cs_eucjp },
	{ NULL }
};

static const struct {
	unsigned short charcode;
	char *entity;
	int entitylen;
	int flags;
} basic_entities[] = {
	{ '&',	"&amp;",	5,	0 },
	{ '"',	"&quot;",	6,	ENT_HTML_QUOTE_DOUBLE },
	{ '\'',	"&#039;",	6,	ENT_HTML_QUOTE_SINGLE },
	{ '<',	"&lt;",		4,	0 },
	{ '>',	"&gt;",		4,	0 },
	{ 0, NULL, 0, 0 }
};
	
#define MB_RETURN { \
			*newpos = pos;       \
		  	mbseq[mbpos] = '\0'; \
		  	*mbseqlen = mbpos;   \
		  	return this_char; }
					
#define MB_WRITE(mbchar) { \
			mbspace--;  \
			if (mbspace == 0) {      \
				MB_RETURN;           \
			}                        \
			mbseq[mbpos++] = (mbchar); }

/* {{{ get_next_char
 */
inline static unsigned short get_next_char(enum entity_charset charset,
		unsigned char * str,
		int * newpos,
		unsigned char * mbseq,
		int * mbseqlen)
{
	int pos = *newpos;
	int mbpos = 0;
	int mbspace = *mbseqlen;
	unsigned short this_char = str[pos++];
	
	if (mbspace <= 0) {
		*mbseqlen = 0;
		return this_char;
	}
	
	MB_WRITE((unsigned char)this_char);
	
	switch(charset)	{
		case cs_utf_8:
			{
				unsigned long utf = 0;
				int stat = 0;
				int more = 1;

				/* unpack utf-8 encoding into a wide char.
				 * Code stolen from the mbstring extension */

				do {
					if (this_char < 0x80)	{
						more = 0;
						break;
					}
					else if (this_char < 0xc0)	{
						switch(stat)	{
							case 0x10:	/* 2, 2nd */
							case 0x21:	/* 3, 3rd */
							case 0x32:	/* 4, 4th */
							case 0x43:	/* 5, 5th */
							case 0x54:	/* 6, 6th */
								/* last byte in sequence */
								more = 0;
								utf |= (this_char & 0x3f);
								this_char = (unsigned short)utf;
								break;
							case 0x20:	/* 3, 2nd */
							case 0x31:	/* 4, 3rd */
							case 0x42:	/* 5, 4th */
							case 0x53:	/* 6, 5th */
								/* penultimate char */
								utf |= ((this_char & 0x3f) << 6);
								stat++;
								break;
							case 0x30:	/* 4, 2nd */
							case 0x41:	/* 5, 3rd */
							case 0x52:	/* 6, 4th */
								utf |= ((this_char & 0x3f) << 12);
								stat++;
								break;
							case 0x40:	/* 5, 2nd */
							case 0x51:
								utf |= ((this_char & 0x3f) << 18);
								stat++;
								break;
							case 0x50:	/* 6, 2nd */
								utf |= ((this_char & 0x3f) << 24);
								stat++;
							default:
								/* invalid */
								more = 0;
						}
					}
					/* lead byte */
					else if (this_char < 0xe0) {
						stat = 0x10;	/* 2 byte */
						utf = (this_char & 0x1f) << 6;
					} else if (this_char < 0xf0)	{
						stat = 0x20;	/* 3 byte */
						utf = (this_char & 0xf) << 12;
					} else if (this_char < 0xf8) {
						stat = 0x30;	/* 4 byte */
						utf = (this_char & 0x7) << 18;
					} else if (this_char < 0xfc)	{
						stat = 0x40;	/* 5 byte */
						utf = (this_char & 0x3) << 24;
					} else if (this_char < 0xfe)	{
						stat = 0x50;	/* 6 byte */
						utf = (this_char & 0x1) << 30;
					}
					else	{
						/* invalid; bail */
						more = 0;
						break;
					}
					if (more)
					{
						this_char = str[pos++];
						MB_WRITE((unsigned char)this_char);
					}
				} while(more);
			}
			break;
		case cs_big5:
		case cs_gb2312:
		case cs_big5hkscs:
			{
				/* check if this is the first of a 2-byte sequence */
				if (this_char >= 0xa1 && this_char <= 0xf9)	{
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if ((next_char >= 0x40 && next_char <= 0x73) ||
							(next_char >= 0xa1 && next_char <= 0xfe))
					{
						/* yes, this a wide char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				}
				break;
			}
		case cs_sjis:
			{
				/* check if this is the first of a 2-byte sequence */
				if ( (this_char >= 0x81 && this_char <= 0x9f) ||
					 (this_char >= 0xe0 && this_char <= 0xef)
					)	{
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if ((next_char >= 0x40 && next_char <= 0x7e) ||
						(next_char >= 0x80 && next_char <= 0xfc))
					{
						/* yes, this a wide char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				}
				break;
			}
		case cs_eucjp:
			{
				/* check if this is the first of a multi-byte sequence */
				if (this_char >= 0xa1 && this_char <= 0xfe)	{
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if (next_char >= 0xa1 && next_char <= 0xfe)
					{
						/* yes, this a jis kanji char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				} else if (this_char == 0x8e)	{
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if (next_char >= 0xa1 && next_char <= 0xdf)
					{
						/* JIS X 0201 kana */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				} else if (this_char == 0x8f)	{
					/* peek at the next two char */
					unsigned char next_char = str[pos];
					unsigned char next2_char = str[pos+1];
					if ((next_char >= 0xa1 && next_char <= 0xfe) &&
						(next2_char >= 0xa1 && next2_char <= 0xfe))
					{
						/* JIS X 0212 hojo-kanji */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
						this_char <<= 8;
						MB_WRITE(next2_char);
						this_char |= next2_char;
						pos++;
					}
					
				}
				break;
			}
		default:
			{
				break;
			}
	}
	MB_RETURN;
}
/* }}} */

/* {{{ entity_charset determine_charset
 * returns the charset identifier based on current locale or a hint.
 * defaults to iso-8859-1 */
static enum entity_charset determine_charset(char *charset_hint)
{
	int i;
	enum entity_charset charset = cs_8859_1;
	int len;

	/* Guarantee default behaviour for backwards compatibility */
	if (charset_hint == NULL)
		return cs_8859_1;

	if (strlen(charset_hint) == 0)	{
		/* try to detect the charset for the locale */
#if HAVE_NL_LANGINFO && HAVE_LOCALE_H && defined(CODESET)
		charset_hint = nl_langinfo(CODESET);
#endif
#if HAVE_LOCALE_H
		if (charset_hint == NULL)
		{
			/* try to figure out the charset from the locale */
			char *localename;
			char *dot, *at;

			/* lang[_territory][.codeset][@modifier] */
			localename = setlocale(LC_CTYPE, NULL);

			dot = strchr(localename, '.');
			if (dot)	{
				dot++;
				/* locale specifies a codeset */
				at = strchr(dot, '@');
				if (at)
					len = at - dot;
				else
					len = strlen(dot);
				charset_hint = dot;
			}
			else	{
				/* no explicit name; see if the name itself
				 * is the charset */
				charset_hint = localename;
				len = strlen(charset_hint);
			}
		}
		else
			len = strlen(charset_hint);
#else
		if (charset_hint)
			len = strlen(charset_hint);
#endif
	}
	if (charset_hint)	{
		/* now walk the charset map and look for the codeset */
		for (i = 0; charset_map[i].codeset; i++)	{
			if (strncasecmp(charset_hint, charset_map[i].codeset, len) == 0)	{
				charset = charset_map[i].charset;
				break;
			}
		}
	}
	return charset;
}
/* }}} */

/* {{{ php_unescape_html_entities
 */
PHPAPI char *php_unescape_html_entities(unsigned char *old, int oldlen, int *newlen, int all, int quote_style, char *hint_charset)
{
	int retlen;
	int j, k;
	char *replaced, *ret;
	enum entity_charset charset = determine_charset(hint_charset);
	unsigned char replacement[15];
	
	ret = estrdup(old);
	retlen = oldlen;
	
	if (all)	{
		/* look for a match in the maps for this charset */
		for (j=0; entity_map[j].charset != cs_terminator; j++)	{
			if (entity_map[j].charset != charset)
				continue;

			for (k = entity_map[j].basechar; k <= entity_map[j].endchar; k++)	{
				unsigned char entity[32];
				int entity_length = 0;

				if (entity_map[j].table[k - entity_map[j].basechar] == NULL)
					continue;
			
				
				entity[0] = '&';
				entity_length = strlen(entity_map[j].table[k - entity_map[j].basechar]);
				strncpy(&entity[1], entity_map[j].table[k - entity_map[j].basechar], sizeof(entity) - 2);
				entity[entity_length+1] = ';';
				entity[entity_length+2] = '\0';
				entity_length += 2;

				/* When we have MBCS entities in the tables above, this will need to handle it */
				if (k > 0xff)	
					zend_error(E_WARNING, "cannot yet handle MBCS in html_entity_decode()!");
				replacement[0] = k;
				replacement[1] = '\0';

				replaced = php_str_to_str(ret, retlen, entity, entity_length, replacement, 1, &retlen);
				efree(ret);
				ret = replaced;
			}
		}
	}

	for (j = 0; basic_entities[j].charcode != 0; j++)	{

		if (basic_entities[j].flags && (quote_style & basic_entities[j].flags) == 0)
			continue;
		
		replacement[0] = (unsigned char)basic_entities[j].charcode;
		replacement[1] = '\0';
		
		replaced = php_str_to_str(ret, retlen, basic_entities[j].entity, basic_entities[j].entitylen, replacement, 1, &retlen);
		efree(ret);
		ret = replaced;
	}
	
	*newlen = retlen;
	return ret;
}
/* }}} */




/* {{{ php_escape_html_entities
 */
PHPAPI char *php_escape_html_entities(unsigned char *old, int oldlen, int *newlen, int all, int quote_style, char *hint_charset)
{
	int i, j, maxlen, len;
	char *replaced;
	enum entity_charset charset = determine_charset(hint_charset);
	int matches_map;

	maxlen = 2 * oldlen;
	if (maxlen < 128)
		maxlen = 128;
	replaced = emalloc (maxlen);
	len = 0;

	i = 0;
	while (i < oldlen) {
		unsigned char mbsequence[16];	/* allow up to 15 characters in a multibyte sequence */
		int mbseqlen = sizeof(mbsequence);
		unsigned short this_char = get_next_char(charset, old, &i, mbsequence, &mbseqlen);

		matches_map = 0;

		if (len + 9 > maxlen)
			replaced = erealloc (replaced, maxlen += 128);

		if (all)	{
			/* look for a match in the maps for this charset */
			unsigned char *rep;


			for (j=0; entity_map[j].charset != cs_terminator; j++)	{
				if (entity_map[j].charset == charset
						&& this_char >= entity_map[j].basechar
						&& this_char <= entity_map[j].endchar)
				{
					rep = (unsigned char*)entity_map[j].table[this_char - entity_map[j].basechar];
					if (rep == NULL)	{
						/* there is no entity for this position; fall through and
						 * just output the character itself */
						break;
					}

					matches_map = 1;
					break;
				}
			}

			if (matches_map)	{
				replaced[len++] = '&';
				strcpy(replaced + len, rep);
				len += strlen(rep);
				replaced[len++] = ';';
			}
		}
		if (!matches_map)	{	
			int is_basic = 0;

			for (j = 0; basic_entities[j].charcode != 0; j++)	{
				if ((basic_entities[j].charcode != this_char) ||
					(basic_entities[j].flags && (quote_style & basic_entities[j].flags) == 0))
					continue;

				memcpy(replaced + len, basic_entities[j].entity, basic_entities[j].entitylen);
				len += basic_entities[j].entitylen;
				
				is_basic = 1;
				break;

			}
			if (!is_basic)	{
				if (this_char > 0xff)	{
					/* a wide char without a named entity; pass through the original sequence */
					memcpy(replaced + len, mbsequence, mbseqlen);
					len += mbseqlen;

				} else
					replaced [len++] = (unsigned char)this_char;
			}
		}
	}
	replaced [len] = '\0';
	*newlen = len;

	return replaced;


}
/* }}} */

/* {{{ php_html_entities
 */
static void php_html_entities(INTERNAL_FUNCTION_PARAMETERS, int all)
{
	char *str, *hint_charset = NULL;
	int str_len, hint_charset_len, len, quote_style = ENT_COMPAT;
	char *replaced;

	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s|ls", &str, &str_len,
							  &quote_style, &hint_charset, &hint_charset_len) == FAILURE) {
		return;
	}

	replaced = php_escape_html_entities(str, str_len, &len, all, quote_style, hint_charset);
	RETVAL_STRINGL(replaced, len, 0);
}
/* }}} */

#define HTML_SPECIALCHARS 	0
#define HTML_ENTITIES	 	1

/* {{{ register_html_constants
 */
void register_html_constants(INIT_FUNC_ARGS)
{
	REGISTER_LONG_CONSTANT("HTML_SPECIALCHARS", HTML_SPECIALCHARS, CONST_PERSISTENT|CONST_CS);
	REGISTER_LONG_CONSTANT("HTML_ENTITIES", HTML_ENTITIES, CONST_PERSISTENT|CONST_CS);
	REGISTER_LONG_CONSTANT("ENT_COMPAT", ENT_COMPAT, CONST_PERSISTENT|CONST_CS);
	REGISTER_LONG_CONSTANT("ENT_QUOTES", ENT_QUOTES, CONST_PERSISTENT|CONST_CS);
	REGISTER_LONG_CONSTANT("ENT_NOQUOTES", ENT_NOQUOTES, CONST_PERSISTENT|CONST_CS);
}
/* }}} */

/* {{{ proto string htmlspecialchars(string string [, int quote_style][, string charset])
   Convert special characters to HTML entities */
PHP_FUNCTION(htmlspecialchars)
{
	php_html_entities(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0);
}
/* }}} */

/* {{{ proto string html_entity_decode(string string [, int quote_style][, string charset])
   Convert all applicable characters to HTML entities */
PHP_FUNCTION(html_entity_decode)
{
	char *str, *hint_charset = NULL;
	int str_len, hint_charset_len, len, quote_style = ENT_COMPAT;
	char *replaced;

	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s|ls", &str, &str_len,
							  &quote_style, &hint_charset, &hint_charset_len) == FAILURE) {
		return;
	}

	replaced = php_unescape_html_entities(str, str_len, &len, 1, quote_style, hint_charset);
	RETVAL_STRINGL(replaced, len, 0);
}
/* }}} */


/* {{{ proto string htmlentities(string string [, int quote_style][, string charset])
   Convert all applicable characters to HTML entities */
PHP_FUNCTION(htmlentities)
{
	php_html_entities(INTERNAL_FUNCTION_PARAM_PASSTHRU, 1);
}
/* }}} */

/* {{{ proto array get_html_translation_table([int table [, int quote_style]])
   Returns the internal translation table used by htmlspecialchars and htmlentities */
PHP_FUNCTION(get_html_translation_table)
{
	int which = HTML_SPECIALCHARS, quote_style = ENT_COMPAT;
	int i, j;
	char ind[2];
	enum entity_charset charset = determine_charset(NULL);

	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|ll", &which, &quote_style) == FAILURE) {
		return;
	}

	array_init(return_value);

	ind[1] = 0;

	switch (which) {
		case HTML_ENTITIES:
			for (j=0; entity_map[j].charset != cs_terminator; j++)	{
				if (entity_map[j].charset != charset)
					continue;
				for (i = 0; i < entity_map[j].endchar - entity_map[j].basechar; i++)
				{
					char buffer[16];

					if (entity_map[j].table[i] == NULL)
						continue;
					/* what about wide chars here ?? */
					ind[0] = i + entity_map[j].basechar;
					sprintf(buffer, "&%s;", entity_map[j].table[i]);
					add_assoc_string(return_value, ind, buffer, 1);

				}
			}
			/* break thru */

		case HTML_SPECIALCHARS:
			for (j = 0; basic_entities[j].charcode != 0; j++)	{

				if (basic_entities[j].flags && (quote_style & basic_entities[j].flags) == 0)
					continue;
				
				ind[0] = (unsigned char)basic_entities[j].charcode;
				add_assoc_string(return_value, ind, basic_entities[j].entity, 1);
			}
			break;
	}
}
/* }}} */

/*
 * Local variables:
 * tab-width: 4
 * c-basic-offset: 4
 * End:
 * vim600: sw=4 ts=4 fdm=marker
 * vim<600: sw=4 ts=4
 */