forked from php/php-src
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathhtml_document.c
1333 lines (1210 loc) · 45.6 KB
/
html_document.c
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
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
+----------------------------------------------------------------------+
| Copyright (c) The PHP Group |
+----------------------------------------------------------------------+
| This source file is subject to version 3.01 of the PHP license, |
| that is bundled with this package in the file LICENSE, and is |
| available through the world-wide-web at the following url: |
| https://www.php.net/license/3_01.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 |
| [email protected] so we can mail you a copy immediately. |
+----------------------------------------------------------------------+
| Authors: Niels Dossche <[email protected]> |
+----------------------------------------------------------------------+
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "php.h"
#if defined(HAVE_LIBXML) && defined(HAVE_DOM)
#include "php_dom.h"
#include "html5_parser.h"
#include "html5_serializer.h"
#include "namespace_compat.h"
#include <Zend/zend_smart_string.h>
#include <lexbor/html/encoding.h>
#include <lexbor/encoding/encoding.h>
/* Implementation defined, but as HTML5 defaults in all other cases to UTF-8, we'll do the same. */
#define DOM_FALLBACK_ENCODING_NAME "UTF-8"
#define DOM_FALLBACK_ENCODING_ID LXB_ENCODING_UTF_8
typedef struct _dom_line_column_cache {
size_t last_line;
size_t last_column;
size_t last_offset;
} dom_line_column_cache;
typedef struct _dom_lexbor_libxml2_bridge_application_data {
const char *input_name;
const lxb_codepoint_t *current_input_codepoints;
const char *current_input_characters;
size_t current_input_length;
size_t current_total_offset;
dom_line_column_cache cache_tokenizer;
bool html_no_implied;
} dom_lexbor_libxml2_bridge_application_data;
typedef struct _dom_character_encoding_data {
const lxb_encoding_data_t *encoding_data;
size_t bom_shift;
} dom_character_encoding_data;
typedef zend_result (*dom_write_output)(void*, const char *, size_t);
typedef struct _dom_output_ctx {
const lxb_encoding_data_t *encoding_data;
const lxb_encoding_data_t *decoding_data;
lxb_encoding_encode_t *encode;
lxb_encoding_decode_t *decode;
lxb_codepoint_t *codepoints;
lxb_char_t *encoding_output;
void *output_data;
dom_write_output write_output;
} dom_output_ctx;
typedef struct _dom_decoding_encoding_ctx {
/* We can skip some conversion if the input and output encoding are both UTF-8,
* we only have to validate and substitute replacement characters */
bool fast_path; /* Put first, near the encode & decode structures, for cache locality */
lxb_encoding_encode_t encode;
lxb_encoding_decode_t decode;
const lxb_encoding_data_t *encode_data;
const lxb_encoding_data_t *decode_data;
lxb_char_t encoding_output[4096];
lxb_codepoint_t codepoints[4096];
} dom_decoding_encoding_ctx;
static void dom_decoding_encoding_ctx_init(dom_decoding_encoding_ctx *ctx)
{
ctx->encode_data = lxb_encoding_data(LXB_ENCODING_UTF_8);
ctx->decode_data = NULL;
/* Set fast path on by default so that the decoder finishing is skipped if this was never initialised properly. */
ctx->fast_path = true;
(void) lxb_encoding_encode_init(
&ctx->encode,
ctx->encode_data,
ctx->encoding_output,
sizeof(ctx->encoding_output) / sizeof(*ctx->encoding_output)
);
(void) lxb_encoding_encode_replace_set(&ctx->encode, LXB_ENCODING_REPLACEMENT_BYTES, LXB_ENCODING_REPLACEMENT_SIZE);
}
static const char *dom_lexbor_tokenizer_error_code_to_string(lxb_html_tokenizer_error_id_t id)
{
switch (id) {
case LXB_HTML_TOKENIZER_ERROR_ABCLOFEMCO: return "abrupt-closing-of-empty-comment";
case LXB_HTML_TOKENIZER_ERROR_ABDOPUID: return "abrupt-doctype-public-identifier";
case LXB_HTML_TOKENIZER_ERROR_ABDOSYID: return "abrupt-doctype-system-identifier";
case LXB_HTML_TOKENIZER_ERROR_ABOFDIINNUCHRE: return "absence-of-digits-in-numeric-character-reference";
case LXB_HTML_TOKENIZER_ERROR_CDINHTCO: return "cdata-in-html-content";
case LXB_HTML_TOKENIZER_ERROR_CHREOUUNRA: return "character-reference-outside-unicode-range";
case LXB_HTML_TOKENIZER_ERROR_COCHININST: return "control-character-in-input-stream";
case LXB_HTML_TOKENIZER_ERROR_COCHRE: return "control-character-reference";
case LXB_HTML_TOKENIZER_ERROR_ENTAWIAT: return "end-tag-with-attributes";
case LXB_HTML_TOKENIZER_ERROR_DUAT: return "duplicate-attribute";
case LXB_HTML_TOKENIZER_ERROR_ENTAWITRSO: return "end-tag-with-trailing-solidus";
case LXB_HTML_TOKENIZER_ERROR_EOBETANA: return "eof-before-tag-name";
case LXB_HTML_TOKENIZER_ERROR_EOINCD: return "eof-in-cdata";
case LXB_HTML_TOKENIZER_ERROR_EOINCO: return "eof-in-comment";
case LXB_HTML_TOKENIZER_ERROR_EOINDO: return "eof-in-doctype";
case LXB_HTML_TOKENIZER_ERROR_EOINSCHTCOLITE: return "eof-in-script-html-comment-like-text";
case LXB_HTML_TOKENIZER_ERROR_EOINTA: return "eof-in-tag";
case LXB_HTML_TOKENIZER_ERROR_INCLCO: return "incorrectly-closed-comment";
case LXB_HTML_TOKENIZER_ERROR_INOPCO: return "incorrectly-opened-comment";
case LXB_HTML_TOKENIZER_ERROR_INCHSEAFDONA: return "invalid-character-sequence-after-doctype-name";
case LXB_HTML_TOKENIZER_ERROR_INFICHOFTANA: return "invalid-first-character-of-tag-name";
case LXB_HTML_TOKENIZER_ERROR_MIATVA: return "missing-attribute-value";
case LXB_HTML_TOKENIZER_ERROR_MIDONA: return "missing-doctype-name";
case LXB_HTML_TOKENIZER_ERROR_MIDOPUID: return "missing-doctype-public-identifier";
case LXB_HTML_TOKENIZER_ERROR_MIDOSYID: return "missing-doctype-system-identifier";
case LXB_HTML_TOKENIZER_ERROR_MIENTANA: return "missing-end-tag-name";
case LXB_HTML_TOKENIZER_ERROR_MIQUBEDOPUID: return "missing-quote-before-doctype-public-identifier";
case LXB_HTML_TOKENIZER_ERROR_MIQUBEDOSYID: return "missing-quote-before-doctype-system-identifier";
case LXB_HTML_TOKENIZER_ERROR_MISEAFCHRE: return "missing-semicolon-after-character-reference";
case LXB_HTML_TOKENIZER_ERROR_MIWHAFDOPUKE: return "missing-whitespace-after-doctype-public-keyword";
case LXB_HTML_TOKENIZER_ERROR_MIWHAFDOSYKE: return "missing-whitespace-after-doctype-system-keyword";
case LXB_HTML_TOKENIZER_ERROR_MIWHBEDONA: return "missing-whitespace-before-doctype-name";
case LXB_HTML_TOKENIZER_ERROR_MIWHBEAT: return "missing-whitespace-between-attributes";
case LXB_HTML_TOKENIZER_ERROR_MIWHBEDOPUANSYID: return "missing-whitespace-between-doctype-public-and-system-identifiers";
case LXB_HTML_TOKENIZER_ERROR_NECO: return "nested-comment";
case LXB_HTML_TOKENIZER_ERROR_NOCHRE: return "noncharacter-character-reference";
case LXB_HTML_TOKENIZER_ERROR_NOININST: return "noncharacter-in-input-stream";
case LXB_HTML_TOKENIZER_ERROR_NOVOHTELSTTAWITRSO: return "non-void-html-element-start-tag-with-trailing-solidus";
case LXB_HTML_TOKENIZER_ERROR_NUCHRE: return "null-character-reference";
case LXB_HTML_TOKENIZER_ERROR_SUCHRE: return "surrogate-character-reference";
case LXB_HTML_TOKENIZER_ERROR_SUININST: return "surrogate-in-input-stream";
case LXB_HTML_TOKENIZER_ERROR_UNCHAFDOSYID: return "unexpected-character-after-doctype-system-identifier";
case LXB_HTML_TOKENIZER_ERROR_UNCHINATNA: return "unexpected-character-in-attribute-name";
case LXB_HTML_TOKENIZER_ERROR_UNCHINUNATVA: return "unexpected-character-in-unquoted-attribute-value";
case LXB_HTML_TOKENIZER_ERROR_UNEQSIBEATNA: return "unexpected-equals-sign-before-attribute-name";
case LXB_HTML_TOKENIZER_ERROR_UNNUCH: return "unexpected-null-character";
case LXB_HTML_TOKENIZER_ERROR_UNQUMAINOFTANA: return "unexpected-question-mark-instead-of-tag-name";
case LXB_HTML_TOKENIZER_ERROR_UNSOINTA: return "unexpected-solidus-in-tag";
case LXB_HTML_TOKENIZER_ERROR_UNNACHRE: return "unknown-named-character-reference";
default: return "unknown error";
}
}
static const char *dom_lexbor_tree_error_code_to_string(lxb_html_tree_error_id_t id)
{
switch (id) {
case LXB_HTML_RULES_ERROR_UNTO: return "unexpected-token";
case LXB_HTML_RULES_ERROR_UNCLTO: return "unexpected-closed-token";
case LXB_HTML_RULES_ERROR_NUCH: return "null-character";
case LXB_HTML_RULES_ERROR_UNCHTO: return "unexpected-character-token";
case LXB_HTML_RULES_ERROR_UNTOININMO: return "unexpected-token-in-initial-mode";
case LXB_HTML_RULES_ERROR_BADOTOININMO: return "bad-doctype-token-in-initial-mode";
case LXB_HTML_RULES_ERROR_DOTOINBEHTMO: return "doctype-token-in-before-html-mode";
case LXB_HTML_RULES_ERROR_UNCLTOINBEHTMO: return "unexpected-closed-token-in-before-html-mode";
case LXB_HTML_RULES_ERROR_DOTOINBEHEMO: return "doctype-token-in-before-head-mode";
case LXB_HTML_RULES_ERROR_UNCLTOINBEHEMO: return "unexpected-closed_token-in-before-head-mode";
case LXB_HTML_RULES_ERROR_DOTOINHEMO: return "doctype-token-in-head-mode";
case LXB_HTML_RULES_ERROR_NOVOHTELSTTAWITRSO: return "non-void-html-element-start-tag-with-trailing-solidus";
case LXB_HTML_RULES_ERROR_HETOINHEMO: return "head-token-in-head-mode";
case LXB_HTML_RULES_ERROR_UNCLTOINHEMO: return "unexpected-closed-token-in-head-mode";
case LXB_HTML_RULES_ERROR_TECLTOWIOPINHEMO: return "template-closed-token-without-opening-in-head-mode";
case LXB_HTML_RULES_ERROR_TEELISNOCUINHEMO: return "template-element-is-not-current-in-head-mode";
case LXB_HTML_RULES_ERROR_DOTOINHENOMO: return "doctype-token-in-head-noscript-mode";
case LXB_HTML_RULES_ERROR_DOTOAFHEMO: return "doctype-token-after-head-mode";
case LXB_HTML_RULES_ERROR_HETOAFHEMO: return "head-token-after-head-mode";
case LXB_HTML_RULES_ERROR_DOTOINBOMO: return "doctype-token-in-body-mode";
case LXB_HTML_RULES_ERROR_BAENOPELISWR: return "bad-ending-open-elements-is-wrong";
case LXB_HTML_RULES_ERROR_OPELISWR: return "open-elements-is-wrong";
case LXB_HTML_RULES_ERROR_UNELINOPELST: return "unexpected-element-in-open-elements-stack";
case LXB_HTML_RULES_ERROR_MIELINOPELST: return "missing-element-in-open-elements-stack";
case LXB_HTML_RULES_ERROR_NOBOELINSC: return "no-body-element-in-scope";
case LXB_HTML_RULES_ERROR_MIELINSC: return "missing-element-in-scope";
case LXB_HTML_RULES_ERROR_UNELINSC: return "unexpected-element-in-scope";
case LXB_HTML_RULES_ERROR_UNELINACFOST: return "unexpected-element-in-active-formatting-stack";
case LXB_HTML_RULES_ERROR_UNENOFFI: return "unexpected-end-of-file";
case LXB_HTML_RULES_ERROR_CHINTATE: return "characters-in-table-text";
case LXB_HTML_RULES_ERROR_DOTOINTAMO: return "doctype-token-in-table-mode";
case LXB_HTML_RULES_ERROR_DOTOINSEMO: return "doctype-token-in-select-mode";
case LXB_HTML_RULES_ERROR_DOTOAFBOMO: return "doctype-token-after-body-mode";
case LXB_HTML_RULES_ERROR_DOTOINFRMO: return "doctype-token-in-frameset-mode";
case LXB_HTML_RULES_ERROR_DOTOAFFRMO: return "doctype-token-after-frameset-mode";
case LXB_HTML_RULES_ERROR_DOTOFOCOMO: return "doctype-token-foreign-content-mode";
default: return "unknown error";
}
}
static const char *dom_lexbor_libxml2_bridge_status_code_to_string(lexbor_libxml2_bridge_status status)
{
switch (status) {
case LEXBOR_LIBXML2_BRIDGE_STATUS_CANNOT_INIT: return "cannot initialize data structures";
case LEXBOR_LIBXML2_BRIDGE_STATUS_FATAL_PARSE: return "fatal error in parsing";
case LEXBOR_LIBXML2_BRIDGE_STATUS_OVERFLOW: return "string length overflow";
case LEXBOR_LIBXML2_BRIDGE_STATUS_OOM: return "out of memory";
default: return "unknown error";
}
}
static void dom_reset_line_column_cache(dom_line_column_cache *cache)
{
cache->last_line = 1;
cache->last_column = 1;
cache->last_offset = 0;
}
static void dom_find_line_and_column_using_cache(
const dom_lexbor_libxml2_bridge_application_data *application_data,
dom_line_column_cache *cache,
size_t offset
)
{
offset -= application_data->current_total_offset;
if (offset > application_data->current_input_length) {
/* Possible with empty input, also just good for general safety */
offset = application_data->current_input_length;
}
/* Either unicode or UTF-8 data */
if (application_data->current_input_codepoints != NULL) {
while (cache->last_offset < offset) {
if (application_data->current_input_codepoints[cache->last_offset] == 0x000A /* Unicode codepoint for line feed */) {
cache->last_line++;
cache->last_column = 1;
} else {
cache->last_column++;
}
cache->last_offset++;
}
} else {
while (cache->last_offset < offset) {
const lxb_char_t current = application_data->current_input_characters[cache->last_offset];
if (current == '\n') {
cache->last_line++;
cache->last_column = 1;
cache->last_offset++;
} else {
/* See Lexbor tokenizer patch
* Note for future self: branchlessly computing the length and jumping by the length would be nice,
* however it takes so many instructions to do so that it is slower than this naive method. */
if ((current & 0b11000000) != 0b10000000) {
cache->last_column++;
}
cache->last_offset++;
}
}
}
}
static void dom_lexbor_libxml2_bridge_tokenizer_error_reporter(
void *application_data_voidptr,
lxb_html_tokenizer_error_t *error,
size_t offset
)
{
dom_lexbor_libxml2_bridge_application_data *application_data = application_data_voidptr;
dom_find_line_and_column_using_cache(application_data, &application_data->cache_tokenizer, offset);
php_libxml_pretend_ctx_error_ex(application_data->input_name, application_data->cache_tokenizer.last_line, application_data->cache_tokenizer.last_column, "tokenizer error %s in %s, line: %zu, column: %zu\n", dom_lexbor_tokenizer_error_code_to_string(error->id), application_data->input_name, application_data->cache_tokenizer.last_line, application_data->cache_tokenizer.last_column);
}
static void dom_lexbor_libxml2_bridge_tree_error_reporter(
void *application_data_voidptr,
lxb_html_tree_error_t *error,
size_t line,
size_t column,
size_t len
)
{
dom_lexbor_libxml2_bridge_application_data *application_data = application_data_voidptr;
if (line == 1 && application_data->html_no_implied && error->id == LXB_HTML_RULES_ERROR_UNTOININMO) {
/* For no implied mode, we want to mimick libxml's behaviour of not reporting an error for a lacking doctype. */
return;
}
if (UNEXPECTED(len <= 1)) {
/* Possible with EOF, or single-character tokens, don't use a range in the error display in this case */
php_libxml_pretend_ctx_error_ex(
application_data->input_name,
line,
column,
"tree error %s in %s, line: %zu, column: %zu\n",
dom_lexbor_tree_error_code_to_string(error->id),
application_data->input_name,
line,
column
);
} else {
php_libxml_pretend_ctx_error_ex(
application_data->input_name,
line,
column,
"tree error %s in %s, line: %zu, column: %zu-%zu\n",
dom_lexbor_tree_error_code_to_string(error->id),
application_data->input_name,
line,
column,
column + len - 1
);
}
}
static xmlNodePtr dom_search_child(xmlNodePtr parent, const char *searching_for)
{
xmlNodePtr node = parent->children;
while (node != NULL) {
if (node->type == XML_ELEMENT_NODE && strcmp((const char *) node->name, searching_for) == 0) {
return node;
}
node = node->next;
}
return NULL;
}
static void dom_place_remove_element_and_hoist_children(xmlNodePtr parent, const char *searching_for)
{
xmlNodePtr node = dom_search_child(parent, searching_for);
if (node != NULL) {
xmlUnlinkNode(node);
xmlNodePtr child = node->children;
while (child != NULL) {
xmlUnlinkNode(child);
xmlAddChild(parent, child);
child = node->children;
}
xmlFreeNode(node);
}
}
static void dom_post_process_html5_loading(
xmlDocPtr lxml_doc,
zend_long options,
const lexbor_libxml2_bridge_extracted_observations *observations
)
{
if (options & HTML_PARSE_NOIMPLIED) {
xmlNodePtr html_node = dom_search_child((xmlNodePtr) lxml_doc, "html");
if (!observations->has_explicit_head_tag) {
dom_place_remove_element_and_hoist_children(html_node, "head");
}
if (!observations->has_explicit_body_tag) {
dom_place_remove_element_and_hoist_children(html_node, "body");
}
if (!observations->has_explicit_html_tag) {
/* The HTML node has a single namespace declaration, that we must preserve after removing the node.
* However, it's possible the namespace is NULL if DOM\HTML_NO_DEFAULT_NS was set. */
if (!(options & DOM_HTML_NO_DEFAULT_NS)) {
php_libxml_set_old_ns(lxml_doc, html_node->nsDef);
html_node->nsDef = NULL;
}
dom_place_remove_element_and_hoist_children((xmlNodePtr) lxml_doc, "html");
if (!(options & DOM_HTML_NO_DEFAULT_NS) && EXPECTED(lxml_doc->children != NULL)) {
xmlNodePtr node = lxml_doc->children;
while (node) {
/* Fine to use the DOM wrap reconciliation here because it's the "modern" world of DOM,
* and no user manipulation happened yet. */
xmlDOMWrapCtxt dummy_ctxt = {0};
xmlDOMWrapReconcileNamespaces(&dummy_ctxt, node, /* options */ 0);
node = node->next;
}
}
}
}
}
/* https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding */
static dom_character_encoding_data dom_determine_encoding(const char *source, size_t source_len)
{
dom_character_encoding_data result;
/* BOM sniffing */
if (source_len >= 3 && source[0] == '\xEF' && source[1] == '\xBB' && source[2] == '\xBF') {
result.encoding_data = lxb_encoding_data(LXB_ENCODING_UTF_8);
result.bom_shift = 3;
return result;
} else if (source_len >= 2) {
if (source[0] == '\xFE' && source[1] == '\xFF') {
result.encoding_data = lxb_encoding_data(LXB_ENCODING_UTF_16BE);
result.bom_shift = 2;
return result;
} else if (source[0] == '\xFF' && source[1] == '\xFE') {
result.encoding_data = lxb_encoding_data(LXB_ENCODING_UTF_16LE);
result.bom_shift = 2;
return result;
}
}
/* Perform prescan */
lxb_html_encoding_t encoding;
lxb_status_t status = lxb_html_encoding_init(&encoding);
if (status != LXB_STATUS_OK) {
goto fallback_uninit;
}
/* This is the "wait either for 1024 bytes or 500ms" part */
if (source_len > 1024) {
source_len = 1024;
}
status = lxb_html_encoding_determine(&encoding, (const lxb_char_t *) source, (const lxb_char_t *) source + source_len);
if (status != LXB_STATUS_OK) {
goto fallback;
}
lxb_html_encoding_entry_t *entry = lxb_html_encoding_meta_entry(&encoding, 0);
if (entry == NULL) {
goto fallback;
}
result.encoding_data = lxb_encoding_data_by_pre_name(entry->name, entry->end - entry->name);
if (!result.encoding_data) {
goto fallback;
}
result.bom_shift = 0;
lxb_html_encoding_destroy(&encoding, false);
return result;
fallback:
lxb_html_encoding_destroy(&encoding, false);
fallback_uninit:
result.encoding_data = lxb_encoding_data(DOM_FALLBACK_ENCODING_ID);
result.bom_shift = 0;
return result;
}
static void dom_setup_parser_encoding_manually(const lxb_char_t *buf_start, const lxb_encoding_data_t *encoding_data, dom_decoding_encoding_ctx *decoding_encoding_ctx, dom_lexbor_libxml2_bridge_application_data *application_data)
{
static const lxb_codepoint_t replacement_codepoint = LXB_ENCODING_REPLACEMENT_CODEPOINT;
decoding_encoding_ctx->decode_data = encoding_data;
(void) lxb_encoding_decode_init(
&decoding_encoding_ctx->decode,
decoding_encoding_ctx->decode_data,
decoding_encoding_ctx->codepoints,
sizeof(decoding_encoding_ctx->codepoints) / sizeof(*decoding_encoding_ctx->codepoints)
);
(void) lxb_encoding_decode_replace_set(
&decoding_encoding_ctx->decode,
&replacement_codepoint,
LXB_ENCODING_REPLACEMENT_BUFFER_LEN
);
/* Note: encode_data is for UTF-8 */
decoding_encoding_ctx->fast_path = decoding_encoding_ctx->decode_data == decoding_encoding_ctx->encode_data;
if (decoding_encoding_ctx->fast_path) {
application_data->current_input_codepoints = NULL;
application_data->current_input_characters = (const char *) buf_start;
} else {
application_data->current_input_codepoints = decoding_encoding_ctx->codepoints;
application_data->current_input_characters = NULL;
}
}
static void dom_setup_parser_encoding_implicitly(
const lxb_char_t **buf_ref,
size_t *read,
dom_decoding_encoding_ctx *decoding_encoding_ctx,
dom_lexbor_libxml2_bridge_application_data *application_data
)
{
const char *buf_start = (const char *) *buf_ref;
dom_character_encoding_data dom_encoding_data = dom_determine_encoding(buf_start, *read);
*buf_ref += dom_encoding_data.bom_shift;
*read -= dom_encoding_data.bom_shift;
dom_setup_parser_encoding_manually((const lxb_char_t *) buf_start, dom_encoding_data.encoding_data, decoding_encoding_ctx, application_data);
}
static bool dom_process_parse_chunk(
lexbor_libxml2_bridge_parse_context *ctx,
lxb_html_document_t *document,
lxb_html_parser_t *parser,
size_t encoded_length,
const lxb_char_t *encoding_output,
size_t input_buffer_length,
size_t *tokenizer_error_offset,
size_t *tree_error_offset
)
{
dom_lexbor_libxml2_bridge_application_data *application_data = ctx->application_data;
application_data->current_input_length = input_buffer_length;
lexbor_status_t lexbor_status = lxb_html_document_parse_chunk(document, encoding_output, encoded_length);
if (UNEXPECTED(lexbor_status != LXB_STATUS_OK)) {
return false;
}
if (ctx->tokenizer_error_reporter || ctx->tree_error_reporter) {
lexbor_libxml2_bridge_report_errors(ctx, parser, encoding_output, application_data->current_total_offset, tokenizer_error_offset, tree_error_offset);
dom_find_line_and_column_using_cache(application_data, &application_data->cache_tokenizer, application_data->current_total_offset + input_buffer_length);
}
application_data->current_total_offset += input_buffer_length;
application_data->cache_tokenizer.last_offset = 0;
return true;
}
static bool dom_decode_encode_fast_path(
lexbor_libxml2_bridge_parse_context *ctx,
lxb_html_document_t *document,
lxb_html_parser_t *parser,
const lxb_char_t **buf_ref_ref,
const lxb_char_t *buf_end,
dom_decoding_encoding_ctx *decoding_encoding_ctx,
size_t *tokenizer_error_offset,
size_t *tree_error_offset
)
{
const lxb_char_t *buf_ref = *buf_ref_ref;
const lxb_char_t *last_output = buf_ref;
while (buf_ref != buf_end) {
const lxb_char_t *buf_ref_backup = buf_ref;
/* Fast path converts non-validated UTF-8 -> validated UTF-8 */
lxb_codepoint_t codepoint = lxb_encoding_decode_utf_8_single(&decoding_encoding_ctx->decode, &buf_ref, buf_end);
if (UNEXPECTED(codepoint > LXB_ENCODING_MAX_CODEPOINT)) {
size_t skip = buf_ref - buf_ref_backup; /* Skip invalid data, it's replaced by the UTF-8 replacement bytes */
if (!dom_process_parse_chunk(
ctx,
document,
parser,
buf_ref - last_output - skip,
last_output,
buf_ref - last_output,
tokenizer_error_offset,
tree_error_offset
)) {
goto fail_oom;
}
if (!dom_process_parse_chunk(
ctx,
document,
parser,
LXB_ENCODING_REPLACEMENT_SIZE,
LXB_ENCODING_REPLACEMENT_BYTES,
0,
tokenizer_error_offset,
tree_error_offset
)) {
goto fail_oom;
}
last_output = buf_ref;
}
}
if (buf_ref != last_output
&& !dom_process_parse_chunk(
ctx,
document,
parser,
buf_ref - last_output,
last_output,
buf_ref - last_output,
tokenizer_error_offset,
tree_error_offset
)) {
goto fail_oom;
}
*buf_ref_ref = buf_ref;
return true;
fail_oom:
*buf_ref_ref = buf_ref;
return false;
}
static bool dom_decode_encode_slow_path(
lexbor_libxml2_bridge_parse_context *ctx,
lxb_html_document_t *document,
lxb_html_parser_t *parser,
const lxb_char_t **buf_ref_ref,
const lxb_char_t *buf_end,
dom_decoding_encoding_ctx *decoding_encoding_ctx,
size_t *tokenizer_error_offset,
size_t *tree_error_offset
)
{
const lxb_char_t *buf_ref = *buf_ref_ref;
lexbor_status_t decode_status, encode_status;
do {
decode_status = decoding_encoding_ctx->decode_data->decode(&decoding_encoding_ctx->decode, &buf_ref, buf_end);
const lxb_codepoint_t *codepoints_ref = (const lxb_codepoint_t *) decoding_encoding_ctx->codepoints;
size_t decoding_buffer_used = lxb_encoding_decode_buf_used(&decoding_encoding_ctx->decode);
const lxb_codepoint_t *codepoints_end = decoding_encoding_ctx->codepoints + decoding_buffer_used;
do {
encode_status = decoding_encoding_ctx->encode_data->encode(&decoding_encoding_ctx->encode, &codepoints_ref, codepoints_end);
ZEND_ASSERT(encode_status != LXB_STATUS_ERROR && "parameters and replacements should be valid");
if (!dom_process_parse_chunk(
ctx,
document,
parser,
lxb_encoding_encode_buf_used(&decoding_encoding_ctx->encode),
decoding_encoding_ctx->encoding_output,
decoding_buffer_used,
tokenizer_error_offset,
tree_error_offset
)) {
goto fail_oom;
}
lxb_encoding_encode_buf_used_set(&decoding_encoding_ctx->encode, 0);
} while (encode_status == LXB_STATUS_SMALL_BUFFER);
lxb_encoding_decode_buf_used_set(&decoding_encoding_ctx->decode, 0);
} while (decode_status == LXB_STATUS_SMALL_BUFFER);
*buf_ref_ref = buf_ref;
return true;
fail_oom:
*buf_ref_ref = buf_ref;
return false;
}
static bool dom_parse_decode_encode_step(
lexbor_libxml2_bridge_parse_context *ctx,
lxb_html_document_t *document,
lxb_html_parser_t *parser,
const lxb_char_t **buf_ref_ref,
const lxb_char_t *buf_end,
dom_decoding_encoding_ctx *decoding_encoding_ctx,
size_t *tokenizer_error_offset,
size_t *tree_error_offset
)
{
if (decoding_encoding_ctx->fast_path) {
return dom_decode_encode_fast_path(
ctx,
document,
parser,
buf_ref_ref,
buf_end,
decoding_encoding_ctx,
tokenizer_error_offset,
tree_error_offset
);
} else {
return dom_decode_encode_slow_path(
ctx,
document,
parser,
buf_ref_ref,
buf_end,
decoding_encoding_ctx,
tokenizer_error_offset,
tree_error_offset
);
}
}
static bool dom_parse_decode_encode_finish(
lexbor_libxml2_bridge_parse_context *ctx,
lxb_html_document_t *document,
lxb_html_parser_t *parser,
dom_decoding_encoding_ctx *decoding_encoding_ctx,
size_t *tokenizer_error_offset,
size_t *tree_error_offset
)
{
if (!decoding_encoding_ctx->fast_path) {
/* Fast path handles codepoints one by one, so this part is not applicable in that case */
(void) lxb_encoding_decode_finish(&decoding_encoding_ctx->decode);
size_t decoding_buffer_size = lxb_encoding_decode_buf_used(&decoding_encoding_ctx->decode);
if (decoding_buffer_size > 0) {
const lxb_codepoint_t *codepoints_ref = (const lxb_codepoint_t *) decoding_encoding_ctx->codepoints;
const lxb_codepoint_t *codepoints_end = codepoints_ref + decoding_buffer_size;
(void) decoding_encoding_ctx->encode_data->encode(&decoding_encoding_ctx->encode, &codepoints_ref, codepoints_end);
if (!dom_process_parse_chunk(
ctx,
document,
parser,
lxb_encoding_encode_buf_used(&decoding_encoding_ctx->encode),
decoding_encoding_ctx->encoding_output,
decoding_buffer_size,
tokenizer_error_offset,
tree_error_offset
)) {
return false;
}
}
}
(void) lxb_encoding_encode_finish(&decoding_encoding_ctx->encode);
if (lxb_encoding_encode_buf_used(&decoding_encoding_ctx->encode)
&& !dom_process_parse_chunk(
ctx,
document,
parser,
lxb_encoding_encode_buf_used(&decoding_encoding_ctx->encode),
decoding_encoding_ctx->encoding_output,
lxb_encoding_decode_buf_used(&decoding_encoding_ctx->decode),
tokenizer_error_offset,
tree_error_offset
)) {
return false;
}
return true;
}
static bool check_options_validity(uint32_t arg_num, zend_long options)
{
const zend_long VALID_OPTIONS = XML_PARSE_NOERROR | XML_PARSE_COMPACT | HTML_PARSE_NOIMPLIED | DOM_HTML_NO_DEFAULT_NS;
if ((options & ~VALID_OPTIONS) != 0) {
zend_argument_value_error(arg_num, "contains invalid flags (allowed flags: "
"LIBXML_NOERROR, "
"LIBXML_COMPACT, "
"LIBXML_HTML_NOIMPLIED, "
"DOM\\NO_DEFAULT_NS)");
return false;
}
return true;
}
PHP_METHOD(DOM_HTMLDocument, createEmpty)
{
const char *encoding = "UTF-8";
size_t encoding_len = strlen("UTF-8");
if (zend_parse_parameters(ZEND_NUM_ARGS(), "|p", &encoding, &encoding_len) == FAILURE) {
RETURN_THROWS();
}
const lxb_encoding_data_t *encoding_data = lxb_encoding_data_by_name((const lxb_char_t *) encoding, encoding_len);
if (encoding_data == NULL) {
zend_argument_value_error(1, "must be a valid document encoding");
RETURN_THROWS();
}
#ifdef LIBXML_HTML_ENABLED
xmlDocPtr lxml_doc = htmlNewDocNoDtD(NULL, NULL);
if (UNEXPECTED(lxml_doc == NULL)) {
goto oom;
}
#else
xmlDocPtr lxml_doc = xmlNewDoc((const xmlChar *) "1.0");
if (UNEXPECTED(lxml_doc == NULL)) {
goto oom;
}
lxml_doc->type = XML_HTML_DOCUMENT_NODE;
#endif
lxml_doc->encoding = xmlStrdup((const xmlChar *) encoding);
dom_object *intern = php_dom_instantiate_object_helper(
return_value,
dom_html_document_class_entry,
(xmlNodePtr) lxml_doc,
NULL
);
intern->document->is_modern_api_class = true;
return;
oom:
php_dom_throw_error(INVALID_STATE_ERR, 1);
RETURN_THROWS();
}
PHP_METHOD(DOM_HTMLDocument, createFromString)
{
const char *source, *override_encoding = NULL;
size_t source_len, override_encoding_len;
zend_long options = 0;
if (zend_parse_parameters(
ZEND_NUM_ARGS(),
"s|lp!",
&source,
&source_len,
&options,
&override_encoding,
&override_encoding_len
) == FAILURE) {
RETURN_THROWS();
}
if (!check_options_validity(2, options)) {
RETURN_THROWS();
}
dom_lexbor_libxml2_bridge_application_data application_data;
application_data.input_name = "Entity";
application_data.current_total_offset = 0;
application_data.html_no_implied = options & HTML_PARSE_NOIMPLIED;
dom_reset_line_column_cache(&application_data.cache_tokenizer);
lexbor_libxml2_bridge_parse_context ctx;
lexbor_libxml2_bridge_parse_context_init(&ctx);
if (!(options & XML_PARSE_NOERROR)) {
lexbor_libxml2_bridge_parse_set_error_callbacks(
&ctx,
dom_lexbor_libxml2_bridge_tokenizer_error_reporter,
dom_lexbor_libxml2_bridge_tree_error_reporter
);
}
ctx.application_data = &application_data;
size_t tokenizer_error_offset = 0;
size_t tree_error_offset = 0;
/* Setup everything encoding & decoding related */
const lxb_char_t *buf_ref = (const lxb_char_t *) source;
dom_decoding_encoding_ctx decoding_encoding_ctx;
dom_decoding_encoding_ctx_init(&decoding_encoding_ctx);
if (override_encoding != NULL) {
const lxb_encoding_data_t *encoding_data = lxb_encoding_data_by_name(
(const lxb_char_t *) override_encoding,
override_encoding_len
);
if (!encoding_data) {
zend_argument_value_error(3, "must be a valid document encoding");
RETURN_THROWS();
}
dom_setup_parser_encoding_manually(buf_ref, encoding_data, &decoding_encoding_ctx, &application_data);
} else {
dom_setup_parser_encoding_implicitly(&buf_ref, &source_len, &decoding_encoding_ctx, &application_data);
}
lxb_html_document_t *document = lxb_html_document_create();
if (UNEXPECTED(document == NULL)) {
goto fail_oom;
}
lxb_status_t lexbor_status = lxb_html_document_parse_chunk_begin(document);
if (UNEXPECTED(lexbor_status != LXB_STATUS_OK)) {
goto fail_oom;
}
lxb_html_parser_t *parser = document->dom_document.parser;
while (source_len > 0) {
size_t chunk_size = source_len;
const size_t MAX_CHUNK_SIZE = sizeof(decoding_encoding_ctx.encoding_output) / sizeof(*decoding_encoding_ctx.encoding_output);
if (chunk_size > MAX_CHUNK_SIZE) {
chunk_size = MAX_CHUNK_SIZE;
}
source_len -= chunk_size;
const lxb_char_t *buf_end = buf_ref + chunk_size;
bool result = dom_parse_decode_encode_step(
&ctx,
document,
parser,
&buf_ref,
buf_end,
&decoding_encoding_ctx,
&tokenizer_error_offset,
&tree_error_offset
);
if (!result) {
goto fail_oom;
}
}
if (!dom_parse_decode_encode_finish(&ctx, document, parser, &decoding_encoding_ctx, &tokenizer_error_offset, &tree_error_offset)) {
goto fail_oom;
}
lexbor_status = lxb_html_document_parse_chunk_end(document);
if (lexbor_status != LXB_STATUS_OK) {
goto fail_oom;
}
xmlDocPtr lxml_doc;
lexbor_libxml2_bridge_status bridge_status = lexbor_libxml2_bridge_convert_document(
document,
&lxml_doc,
options & XML_PARSE_COMPACT,
!(options & DOM_HTML_NO_DEFAULT_NS)
);
lexbor_libxml2_bridge_copy_observations(parser->tree, &ctx.observations);
if (UNEXPECTED(bridge_status != LEXBOR_LIBXML2_BRIDGE_STATUS_OK)) {
php_libxml_ctx_error(
NULL,
"%s in %s",
dom_lexbor_libxml2_bridge_status_code_to_string(bridge_status),
application_data.input_name
);
lxb_html_document_destroy(document);
RETURN_FALSE;
}
lxb_html_document_destroy(document);
dom_post_process_html5_loading(lxml_doc, options, &ctx.observations);
if (decoding_encoding_ctx.decode_data) {
lxml_doc->encoding = xmlStrdup((const xmlChar *) decoding_encoding_ctx.decode_data->name);
} else {
lxml_doc->encoding = xmlStrdup((const xmlChar *) "UTF-8");
}
dom_object *intern = php_dom_instantiate_object_helper(
return_value,
dom_html_document_class_entry,
(xmlNodePtr) lxml_doc,
NULL
);
intern->document->is_modern_api_class = true;
return;
fail_oom:
lxb_html_document_destroy(document);
php_dom_throw_error(INVALID_STATE_ERR, 1);
RETURN_THROWS();
}
PHP_METHOD(DOM_HTMLDocument, createFromFile)
{
const char *filename, *override_encoding = NULL;
size_t filename_len, override_encoding_len;
zend_long options = 0;
php_stream *stream = NULL;
if (zend_parse_parameters(
ZEND_NUM_ARGS(),
"p|lp!",
&filename,
&filename_len,
&options,
&override_encoding,
&override_encoding_len
) == FAILURE) {
RETURN_THROWS();
}
/* See php_libxml_streams_IO_open_wrapper(), apparently this caused issues in the past. */
if (strstr(filename, "%00")) {
zend_argument_value_error(1, "must not contain percent-encoded NUL bytes");
RETURN_THROWS();
}
if (!check_options_validity(2, options)) {
RETURN_THROWS();
}
dom_lexbor_libxml2_bridge_application_data application_data;
application_data.input_name = filename;
application_data.current_total_offset = 0;
application_data.html_no_implied = options & HTML_PARSE_NOIMPLIED;
dom_reset_line_column_cache(&application_data.cache_tokenizer);
lexbor_libxml2_bridge_parse_context ctx;
lexbor_libxml2_bridge_parse_context_init(&ctx);
if (!(options & XML_PARSE_NOERROR)) {
lexbor_libxml2_bridge_parse_set_error_callbacks(
&ctx,
dom_lexbor_libxml2_bridge_tokenizer_error_reporter,
dom_lexbor_libxml2_bridge_tree_error_reporter
);
}
ctx.application_data = &application_data;
char buf[4096];
/* Setup everything encoding & decoding related */
dom_decoding_encoding_ctx decoding_encoding_ctx;
dom_decoding_encoding_ctx_init(&decoding_encoding_ctx);
bool should_determine_encoding_implicitly = true; /* First read => determine encoding implicitly */
if (override_encoding != NULL) {
const lxb_encoding_data_t *encoding_data = lxb_encoding_data_by_name(
(const lxb_char_t *) override_encoding,
override_encoding_len
);
if (!encoding_data) {
zend_argument_value_error(3, "must be a valid document encoding");
RETURN_THROWS();
}
should_determine_encoding_implicitly = false;
dom_setup_parser_encoding_manually((const lxb_char_t *) buf, encoding_data, &decoding_encoding_ctx, &application_data);
}
stream = php_stream_open_wrapper_ex(filename, "rb", REPORT_ERRORS, /* opened_path */ NULL, php_libxml_get_stream_context());
if (!stream) {
if (!EG(exception)) {
zend_throw_exception_ex(NULL, 0, "Cannot open file '%s'", filename);
}
RETURN_THROWS();
}
/* MIME sniff */
if (should_determine_encoding_implicitly) {
zend_string *charset = php_libxml_sniff_charset_from_stream(stream);
if (charset != NULL) {
const lxb_encoding_data_t *encoding_data = lxb_encoding_data_by_name(
(const lxb_char_t *) ZSTR_VAL(charset),
ZSTR_LEN(charset)
);
if (encoding_data != NULL) {
should_determine_encoding_implicitly = false;
dom_setup_parser_encoding_manually(
(const lxb_char_t *) buf,
encoding_data,
&decoding_encoding_ctx,
&application_data
);
}
zend_string_release_ex(charset, false);
}
}
lxb_html_document_t *document = lxb_html_document_create();
if (UNEXPECTED(document == NULL)) {
goto fail_oom;
}
lxb_status_t lexbor_status = lxb_html_document_parse_chunk_begin(document);
if (UNEXPECTED(lexbor_status != LXB_STATUS_OK)) {
goto fail_oom;
}
size_t tokenizer_error_offset = 0;