-
Notifications
You must be signed in to change notification settings - Fork 12.4k
/
formatting.php
6262 lines (5673 loc) · 328 KB
/
formatting.php
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
<?php
/**
* Main WordPress Formatting API.
*
* Handles many functions for formatting output.
*
* @package WordPress
*/
/**
* Replaces common plain text characters with formatted entities.
*
* Returns given text with transformations of quotes into smart quotes, apostrophes,
* dashes, ellipses, the trademark symbol, and the multiplication symbol.
*
* As an example,
*
* 'cause today's effort makes it worth tomorrow's "holiday" ...
*
* Becomes:
*
* ’cause today’s effort makes it worth tomorrow’s “holiday” …
*
* Code within certain HTML blocks are skipped.
*
* Do not use this function before the {@see 'init'} action hook; everything will break.
*
* @since 0.71
*
* @global array $wp_cockneyreplace Array of formatted entities for certain common phrases.
* @global array $shortcode_tags
*
* @param string $text The text to be formatted.
* @param bool $reset Set to true for unit testing. Translated patterns will reset.
* @return string The string replaced with HTML entities.
*/
function wptexturize( $text, $reset = false ) {
global $wp_cockneyreplace, $shortcode_tags;
static $static_characters = null,
$static_replacements = null,
$dynamic_characters = null,
$dynamic_replacements = null,
$default_no_texturize_tags = null,
$default_no_texturize_shortcodes = null,
$run_texturize = true,
$apos = null,
$prime = null,
$double_prime = null,
$opening_quote = null,
$closing_quote = null,
$opening_single_quote = null,
$closing_single_quote = null,
$open_q_flag = '<!--oq-->',
$open_sq_flag = '<!--osq-->',
$apos_flag = '<!--apos-->';
// If there's nothing to do, just stop.
if ( empty( $text ) || false === $run_texturize ) {
return $text;
}
// Set up static variables. Run once only.
if ( $reset || ! isset( $static_characters ) ) {
/**
* Filters whether to skip running wptexturize().
*
* Returning false from the filter will effectively short-circuit wptexturize()
* and return the original text passed to the function instead.
*
* The filter runs only once, the first time wptexturize() is called.
*
* @since 4.0.0
*
* @see wptexturize()
*
* @param bool $run_texturize Whether to short-circuit wptexturize().
*/
$run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
if ( false === $run_texturize ) {
return $text;
}
/* translators: Opening curly double quote. */
$opening_quote = _x( '“', 'opening curly double quote' );
/* translators: Closing curly double quote. */
$closing_quote = _x( '”', 'closing curly double quote' );
/* translators: Apostrophe, for example in 'cause or can't. */
$apos = _x( '’', 'apostrophe' );
/* translators: Prime, for example in 9' (nine feet). */
$prime = _x( '′', 'prime' );
/* translators: Double prime, for example in 9" (nine inches). */
$double_prime = _x( '″', 'double prime' );
/* translators: Opening curly single quote. */
$opening_single_quote = _x( '‘', 'opening curly single quote' );
/* translators: Closing curly single quote. */
$closing_single_quote = _x( '’', 'closing curly single quote' );
/* translators: En dash. */
$en_dash = _x( '–', 'en dash' );
/* translators: Em dash. */
$em_dash = _x( '—', 'em dash' );
$default_no_texturize_tags = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' );
$default_no_texturize_shortcodes = array( 'code' );
// If a plugin has provided an autocorrect array, use it.
if ( isset( $wp_cockneyreplace ) ) {
$cockney = array_keys( $wp_cockneyreplace );
$cockneyreplace = array_values( $wp_cockneyreplace );
} else {
/*
* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
* for example... 'We do not have enough words yet'... is a typical quoted phrase. But when we write
* lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
*/
$cockney = explode(
',',
_x(
"'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
'Comma-separated list of words to texturize in your language'
)
);
$cockneyreplace = explode(
',',
_x(
'’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',
'Comma-separated list of replacement words in your language'
)
);
}
$static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
$static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
/*
* Pattern-based replacements of characters.
* Sort the remaining patterns into several arrays for performance tuning.
*/
$dynamic_characters = array(
'apos' => array(),
'quote' => array(),
'dash' => array(),
);
$dynamic_replacements = array(
'apos' => array(),
'quote' => array(),
'dash' => array(),
);
$dynamic = array();
$spaces = wp_spaces_regexp();
// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
if ( "'" !== $apos || "'" !== $closing_single_quote ) {
$dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
}
if ( "'" !== $apos || '"' !== $closing_quote ) {
$dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
}
// '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
if ( "'" !== $apos ) {
$dynamic['/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/'] = $apos_flag;
}
// Quoted numbers like '0.42'.
if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
$dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
}
// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
if ( "'" !== $opening_single_quote ) {
$dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $open_sq_flag;
}
// Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
if ( "'" !== $apos ) {
$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
}
$dynamic_characters['apos'] = array_keys( $dynamic );
$dynamic_replacements['apos'] = array_values( $dynamic );
$dynamic = array();
// Quoted numbers like "42".
if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
$dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
}
// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
if ( '"' !== $opening_quote ) {
$dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
}
$dynamic_characters['quote'] = array_keys( $dynamic );
$dynamic_replacements['quote'] = array_values( $dynamic );
$dynamic = array();
// Dashes and spaces.
$dynamic['/---/'] = $em_dash;
$dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
$dynamic['/(?<!xn)--/'] = $en_dash;
$dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash;
$dynamic_characters['dash'] = array_keys( $dynamic );
$dynamic_replacements['dash'] = array_values( $dynamic );
}
// Must do this every time in case plugins use these filters in a context sensitive manner.
/**
* Filters the list of HTML elements not to texturize.
*
* @since 2.8.0
*
* @param string[] $default_no_texturize_tags An array of HTML element names.
*/
$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
/**
* Filters the list of shortcodes not to texturize.
*
* @since 2.8.0
*
* @param string[] $default_no_texturize_shortcodes An array of shortcode names.
*/
$no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
$no_texturize_tags_stack = array();
$no_texturize_shortcodes_stack = array();
// Look for shortcodes and HTML elements.
preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
$tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
$found_shortcodes = ! empty( $tagnames );
$shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
$regex = _get_wptexturize_split_regex( $shortcode_regex );
$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
foreach ( $textarr as &$curl ) {
// Only call _wptexturize_pushpop_element if $curl is a delimiter.
$first = $curl[0];
if ( '<' === $first ) {
if ( str_starts_with( $curl, '<!--' ) ) {
// This is an HTML comment delimiter.
continue;
} else {
// This is an HTML element delimiter.
// Replace each & with & unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
_wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
}
} elseif ( '' === trim( $curl ) ) {
// This is a newline between delimiters. Performance improves when we check this.
continue;
} elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
// This is a shortcode delimiter.
if ( ! str_starts_with( $curl, '[[' ) && ! str_ends_with( $curl, ']]' ) ) {
// Looks like a normal shortcode.
_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
} else {
// Looks like an escaped shortcode.
continue;
}
} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
// This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
$curl = str_replace( $static_characters, $static_replacements, $curl );
if ( str_contains( $curl, "'" ) ) {
$curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
$curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
$curl = str_replace( $apos_flag, $apos, $curl );
$curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
}
if ( str_contains( $curl, '"' ) ) {
$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
$curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
$curl = str_replace( $open_q_flag, $opening_quote, $curl );
}
if ( str_contains( $curl, '-' ) ) {
$curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
}
// 9x9 (times), but never 0x9999.
if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
// Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
$curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl );
}
// Replace each & with & unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
}
}
return implode( '', $textarr );
}
/**
* Implements a logic tree to determine whether or not "7'." represents seven feet,
* then converts the special char into either a prime char or a closing quote char.
*
* @since 4.3.0
*
* @param string $haystack The plain text to be searched.
* @param string $needle The character to search for such as ' or ".
* @param string $prime The prime char to use for replacement.
* @param string $open_quote The opening quote char. Opening quote replacement must be
* accomplished already.
* @param string $close_quote The closing quote char to use for replacement.
* @return string The $haystack value after primes and quotes replacements.
*/
function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
$spaces = wp_spaces_regexp();
$flag = '<!--wp-prime-or-quote-->';
$quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ')/';
$prime_pattern = "/(?<=\\d)$needle/";
$flag_after_digit = "/(?<=\\d)$flag/";
$flag_no_digit = "/(?<!\\d)$flag/";
$sentences = explode( $open_quote, $haystack );
foreach ( $sentences as $key => &$sentence ) {
if ( ! str_contains( $sentence, $needle ) ) {
continue;
} elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
$sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
if ( $count > 1 ) {
// This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
$sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
if ( 0 === $count2 ) {
// Try looking for a quote followed by a period.
$count2 = substr_count( $sentence, "$flag." );
if ( $count2 > 0 ) {
// Assume the rightmost quote-period match is the end of quotation.
$pos = strrpos( $sentence, "$flag." );
} else {
/*
* When all else fails, make the rightmost candidate a closing quote.
* This is most likely to be problematic in the context of bug #18549.
*/
$pos = strrpos( $sentence, $flag );
}
$sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
}
// Use conventional replacement on any remaining primes and quotes.
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
$sentence = preg_replace( $flag_after_digit, $prime, $sentence );
$sentence = str_replace( $flag, $close_quote, $sentence );
} elseif ( 1 === $count ) {
// Found only one closing quote candidate, so give it priority over primes.
$sentence = str_replace( $flag, $close_quote, $sentence );
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
} else {
// No closing quotes found. Just run primes pattern.
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
}
} else {
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
$sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
}
if ( '"' === $needle && str_contains( $sentence, '"' ) ) {
$sentence = str_replace( '"', $close_quote, $sentence );
}
}
return implode( $open_quote, $sentences );
}
/**
* Searches for disabled element tags. Pushes element to stack on tag open
* and pops on tag close.
*
* Assumes first char of `$text` is tag opening and last char is tag closing.
* Assumes second char of `$text` is optionally `/` to indicate closing as in `</html>`.
*
* @since 2.9.0
* @access private
*
* @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
* @param string[] $stack Array of open tag elements.
* @param string[] $disabled_elements Array of tag names to match against. Spaces are not allowed in tag names.
*/
function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
// Is it an opening tag or closing tag?
if ( isset( $text[1] ) && '/' !== $text[1] ) {
$opening_tag = true;
$name_offset = 1;
} elseif ( 0 === count( $stack ) ) {
// Stack is empty. Just stop.
return;
} else {
$opening_tag = false;
$name_offset = 2;
}
// Parse out the tag name.
$space = strpos( $text, ' ' );
if ( false === $space ) {
$space = -1;
} else {
$space -= $name_offset;
}
$tag = substr( $text, $name_offset, $space );
// Handle disabled tags.
if ( in_array( $tag, $disabled_elements, true ) ) {
if ( $opening_tag ) {
/*
* This disables texturize until we find a closing tag of our type
* (e.g. <pre>) even if there was invalid nesting before that.
*
* Example: in the case <pre>sadsadasd</code>"baba"</pre>
* "baba" won't be texturized.
*/
array_push( $stack, $tag );
} elseif ( end( $stack ) === $tag ) {
array_pop( $stack );
}
}
}
/**
* Replaces double line breaks with paragraph elements.
*
* A group of regex replaces used to identify text formatted with newlines and
* replace double line breaks with HTML paragraph tags. The remaining line breaks
* after conversion become `<br />` tags, unless `$br` is set to '0' or 'false'.
*
* @since 0.71
*
* @param string $text The text which has to be formatted.
* @param bool $br Optional. If set, this will convert all remaining line breaks
* after paragraphing. Line breaks within `<script>`, `<style>`,
* and `<svg>` tags are not affected. Default true.
* @return string Text which has been converted into correct paragraph tags.
*/
function wpautop( $text, $br = true ) {
$pre_tags = array();
if ( trim( $text ) === '' ) {
return '';
}
// Just to make things a little easier, pad the end.
$text = $text . "\n";
/*
* Pre tags shouldn't be touched by autop.
* Replace pre tags with placeholders and bring them back after autop.
*/
if ( str_contains( $text, '<pre' ) ) {
$text_parts = explode( '</pre>', $text );
$last_part = array_pop( $text_parts );
$text = '';
$i = 0;
foreach ( $text_parts as $text_part ) {
$start = strpos( $text_part, '<pre' );
// Malformed HTML?
if ( false === $start ) {
$text .= $text_part;
continue;
}
$name = "<pre wp-pre-tag-$i></pre>";
$pre_tags[ $name ] = substr( $text_part, $start ) . '</pre>';
$text .= substr( $text_part, 0, $start ) . $name;
++$i;
}
$text .= $last_part;
}
// Change multiple <br>'s into two line breaks, which will turn into paragraphs.
$text = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $text );
$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
// Add a double line break above block-level opening tags.
$text = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $text );
// Add a double line break below block-level closing tags.
$text = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $text );
// Add a double line break after hr tags, which are self closing.
$text = preg_replace( '!(<hr\s*?/?>)!', "$1\n\n", $text );
// Standardize newline characters to "\n".
$text = str_replace( array( "\r\n", "\r" ), "\n", $text );
// Find newlines in all elements and add placeholders.
$text = wp_replace_in_html_tags( $text, array( "\n" => ' <!-- wpnl --> ' ) );
// Collapse line breaks before and after <option> elements so they don't get autop'd.
if ( str_contains( $text, '<option' ) ) {
$text = preg_replace( '|\s*<option|', '<option', $text );
$text = preg_replace( '|</option>\s*|', '</option>', $text );
}
/*
* Collapse line breaks inside <object> elements, before <param> and <embed> elements
* so they don't get autop'd.
*/
if ( str_contains( $text, '</object>' ) ) {
$text = preg_replace( '|(<object[^>]*>)\s*|', '$1', $text );
$text = preg_replace( '|\s*</object>|', '</object>', $text );
$text = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $text );
}
/*
* Collapse line breaks inside <audio> and <video> elements,
* before and after <source> and <track> elements.
*/
if ( str_contains( $text, '<source' ) || str_contains( $text, '<track' ) ) {
$text = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $text );
$text = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $text );
$text = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $text );
}
// Collapse line breaks before and after <figcaption> elements.
if ( str_contains( $text, '<figcaption' ) ) {
$text = preg_replace( '|\s*(<figcaption[^>]*>)|', '$1', $text );
$text = preg_replace( '|</figcaption>\s*|', '</figcaption>', $text );
}
// Remove more than two contiguous line breaks.
$text = preg_replace( "/\n\n+/", "\n\n", $text );
// Split up the contents into an array of strings, separated by double line breaks.
$paragraphs = preg_split( '/\n\s*\n/', $text, -1, PREG_SPLIT_NO_EMPTY );
// Reset $text prior to rebuilding.
$text = '';
// Rebuild the content as a string, wrapping every bit with a <p>.
foreach ( $paragraphs as $paragraph ) {
$text .= '<p>' . trim( $paragraph, "\n" ) . "</p>\n";
}
// Under certain strange conditions it could create a P of entirely whitespace.
$text = preg_replace( '|<p>\s*</p>|', '', $text );
// Add a closing <p> inside <div>, <address>, or <form> tag if missing.
$text = preg_replace( '!<p>([^<]+)</(div|address|form)>!', '<p>$1</p></$2>', $text );
// If an opening or closing block element tag is wrapped in a <p>, unwrap it.
$text = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $text );
// In some cases <li> may get wrapped in <p>, fix them.
$text = preg_replace( '|<p>(<li.+?)</p>|', '$1', $text );
// If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
$text = preg_replace( '|<p><blockquote([^>]*)>|i', '<blockquote$1><p>', $text );
$text = str_replace( '</blockquote></p>', '</p></blockquote>', $text );
// If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
$text = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)!', '$1', $text );
// If an opening or closing block element tag is followed by a closing <p> tag, remove it.
$text = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $text );
// Optionally insert line breaks.
if ( $br ) {
// Replace newlines that shouldn't be touched with a placeholder.
$text = preg_replace_callback( '/<(script|style|svg|math).*?<\/\\1>/s', '_autop_newline_preservation_helper', $text );
// Normalize <br>
$text = str_replace( array( '<br>', '<br/>' ), '<br />', $text );
// Replace any new line characters that aren't preceded by a <br /> with a <br />.
$text = preg_replace( '|(?<!<br />)\s*\n|', "<br />\n", $text );
// Replace newline placeholders with newlines.
$text = str_replace( '<WPPreserveNewline />', "\n", $text );
}
// If a <br /> tag is after an opening or closing block tag, remove it.
$text = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*<br />!', '$1', $text );
// If a <br /> tag is before a subset of opening or closing block tags, remove it.
$text = preg_replace( '!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $text );
$text = preg_replace( "|\n</p>$|", '</p>', $text );
// Replace placeholder <pre> tags with their original content.
if ( ! empty( $pre_tags ) ) {
$text = str_replace( array_keys( $pre_tags ), array_values( $pre_tags ), $text );
}
// Restore newlines in all elements.
if ( str_contains( $text, '<!-- wpnl -->' ) ) {
$text = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $text );
}
return $text;
}
/**
* Separates HTML elements and comments from the text.
*
* @since 4.2.4
*
* @param string $input The text which has to be formatted.
* @return string[] Array of the formatted text.
*/
function wp_html_split( $input ) {
return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
}
/**
* Retrieves the regular expression for an HTML element.
*
* @since 4.4.0
*
* @return string The regular expression
*/
function get_html_split_regex() {
static $regex;
if ( ! isset( $regex ) ) {
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$comments =
'!' // Start of comment, after the <.
. '(?:' // Unroll the loop: Consume everything until --> is found.
. '-(?!->)' // Dash not followed by end of comment.
. '[^\-]*+' // Consume non-dashes.
. ')*+' // Loop possessively.
. '(?:-->)?'; // End of comment. If not found, match all input.
$cdata =
'!\[CDATA\[' // Start of comment, after the <.
. '[^\]]*+' // Consume non-].
. '(?:' // Unroll the loop: Consume everything until ]]> is found.
. '](?!]>)' // One ] not followed by end of comment.
. '[^\]]*+' // Consume non-].
. ')*+' // Loop possessively.
. '(?:]]>)?'; // End of comment. If not found, match all input.
$escaped =
'(?=' // Is the element escaped?
. '!--'
. '|'
. '!\[CDATA\['
. ')'
. '(?(?=!-)' // If yes, which type?
. $comments
. '|'
. $cdata
. ')';
$regex =
'/(' // Capture the entire match.
. '<' // Find start of element.
. '(?' // Conditional expression follows.
. $escaped // Find end of escaped element.
. '|' // ...else...
. '[^>]*>?' // Find end of normal element.
. ')'
. ')/';
// phpcs:enable
}
return $regex;
}
/**
* Retrieves the combined regular expression for HTML and shortcodes.
*
* @access private
* @ignore
* @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
* @since 4.4.0
*
* @param string $shortcode_regex Optional. The result from _get_wptexturize_shortcode_regex().
* @return string The regular expression
*/
function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
static $html_regex;
if ( ! isset( $html_regex ) ) {
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$comment_regex =
'!' // Start of comment, after the <.
. '(?:' // Unroll the loop: Consume everything until --> is found.
. '-(?!->)' // Dash not followed by end of comment.
. '[^\-]*+' // Consume non-dashes.
. ')*+' // Loop possessively.
. '(?:-->)?'; // End of comment. If not found, match all input.
$html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
'<' // Find start of element.
. '(?(?=!--)' // Is this a comment?
. $comment_regex // Find end of comment.
. '|'
. '[^>]*>?' // Find end of element. If not found, match all input.
. ')';
// phpcs:enable
}
if ( empty( $shortcode_regex ) ) {
$regex = '/(' . $html_regex . ')/';
} else {
$regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
}
return $regex;
}
/**
* Retrieves the regular expression for shortcodes.
*
* @access private
* @ignore
* @since 4.4.0
*
* @param string[] $tagnames Array of shortcodes to find.
* @return string The regular expression
*/
function _get_wptexturize_shortcode_regex( $tagnames ) {
$tagregexp = implode( '|', array_map( 'preg_quote', $tagnames ) );
$tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$regex =
'\[' // Find start of shortcode.
. '[\/\[]?' // Shortcodes may begin with [/ or [[.
. $tagregexp // Only match registered shortcodes, because performance.
. '(?:'
. '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
. '|'
. '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
. ')*+' // Possessive critical.
. '\]' // Find end of shortcode.
. '\]?'; // Shortcodes may end with ]].
// phpcs:enable
return $regex;
}
/**
* Replaces characters or phrases within HTML elements only.
*
* @since 4.2.3
*
* @param string $haystack The text which has to be formatted.
* @param array $replace_pairs In the form array('from' => 'to', ...).
* @return string The formatted text.
*/
function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
// Find all elements.
$textarr = wp_html_split( $haystack );
$changed = false;
// Optimize when searching for one item.
if ( 1 === count( $replace_pairs ) ) {
// Extract $needle and $replace.
foreach ( $replace_pairs as $needle => $replace ) {
}
// Loop through delimiters (elements) only.
for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
if ( str_contains( $textarr[ $i ], $needle ) ) {
$textarr[ $i ] = str_replace( $needle, $replace, $textarr[ $i ] );
$changed = true;
}
}
} else {
// Extract all $needles.
$needles = array_keys( $replace_pairs );
// Loop through delimiters (elements) only.
for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
foreach ( $needles as $needle ) {
if ( str_contains( $textarr[ $i ], $needle ) ) {
$textarr[ $i ] = strtr( $textarr[ $i ], $replace_pairs );
$changed = true;
// After one strtr() break out of the foreach loop and look at next element.
break;
}
}
}
}
if ( $changed ) {
$haystack = implode( $textarr );
}
return $haystack;
}
/**
* Newline preservation help function for wpautop().
*
* @since 3.1.0
* @access private
*
* @param array $matches preg_replace_callback matches array
* @return string
*/
function _autop_newline_preservation_helper( $matches ) {
return str_replace( "\n", '<WPPreserveNewline />', $matches[0] );
}
/**
* Don't auto-p wrap shortcodes that stand alone.
*
* Ensures that shortcodes are not wrapped in `<p>...</p>`.
*
* @since 2.9.0
*
* @global array $shortcode_tags
*
* @param string $text The content.
* @return string The filtered content.
*/
function shortcode_unautop( $text ) {
global $shortcode_tags;
if ( empty( $shortcode_tags ) || ! is_array( $shortcode_tags ) ) {
return $text;
}
$tagregexp = implode( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
$spaces = wp_spaces_regexp();
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound,Universal.WhiteSpace.PrecisionAlignment.Found -- don't remove regex indentation
$pattern =
'/'
. '<p>' // Opening paragraph.
. '(?:' . $spaces . ')*+' // Optional leading whitespace.
. '(' // 1: The shortcode.
. '\\[' // Opening bracket.
. "($tagregexp)" // 2: Shortcode name.
. '(?![\\w-])' // Not followed by word character or hyphen.
// Unroll the loop: Inside the opening shortcode tag.
. '[^\\]\\/]*' // Not a closing bracket or forward slash.
. '(?:'
. '\\/(?!\\])' // A forward slash not followed by a closing bracket.
. '[^\\]\\/]*' // Not a closing bracket or forward slash.
. ')*?'
. '(?:'
. '\\/\\]' // Self closing tag and closing bracket.
. '|'
. '\\]' // Closing bracket.
. '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags.
. '[^\\[]*+' // Not an opening bracket.
. '(?:'
. '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag.
. '[^\\[]*+' // Not an opening bracket.
. ')*+'
. '\\[\\/\\2\\]' // Closing shortcode tag.
. ')?'
. ')'
. ')'
. '(?:' . $spaces . ')*+' // Optional trailing whitespace.
. '<\\/p>' // Closing paragraph.
. '/';
// phpcs:enable
return preg_replace( $pattern, '$1', $text );
}
/**
* Checks to see if a string is utf8 encoded.
*
* NOTE: This function checks for 5-Byte sequences, UTF8
* has Bytes Sequences with a maximum length of 4.
*
* @author bmorel at ssi dot fr (modified)
* @since 1.2.1
*
* @param string $str The string to be checked
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
function seems_utf8( $str ) {
mbstring_binary_safe_encoding();
$length = strlen( $str );
reset_mbstring_encoding();
for ( $i = 0; $i < $length; $i++ ) {
$c = ord( $str[ $i ] );
if ( $c < 0x80 ) {
$n = 0; // 0bbbbbbb
} elseif ( ( $c & 0xE0 ) === 0xC0 ) {
$n = 1; // 110bbbbb
} elseif ( ( $c & 0xF0 ) === 0xE0 ) {
$n = 2; // 1110bbbb
} elseif ( ( $c & 0xF8 ) === 0xF0 ) {
$n = 3; // 11110bbb
} elseif ( ( $c & 0xFC ) === 0xF8 ) {
$n = 4; // 111110bb
} elseif ( ( $c & 0xFE ) === 0xFC ) {
$n = 5; // 1111110b
} else {
return false; // Does not match any model.
}
for ( $j = 0; $j < $n; $j++ ) { // n bytes matching 10bbbbbb follow ?
if ( ( ++$i === $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) !== 0x80 ) ) {
return false;
}
}
}
return true;
}
/**
* Converts a number of special characters into their HTML entities.
*
* Specifically deals with: `&`, `<`, `>`, `"`, and `'`.
*
* `$quote_style` can be set to ENT_COMPAT to encode `"` to
* `"`, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
*
* @since 1.2.2
* @since 5.5.0 `$quote_style` also accepts `ENT_XML1`.
* @access private
*
* @param string $text The text which is to be encoded.
* @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
* both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
* Converts single and double quotes, as well as converting HTML
* named entities (that are not also XML named entities) to their
* code points if set to ENT_XML1. Also compatible with old values;
* converting single quotes if set to 'single',
* double if set to 'double' or both if otherwise set.
* Default is ENT_NOQUOTES.
* @param false|string $charset Optional. The character encoding of the string. Default false.
* @param bool $double_encode Optional. Whether to encode existing HTML entities. Default false.
* @return string The encoded text with HTML entities.
*/
function _wp_specialchars( $text, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$text = (string) $text;
if ( 0 === strlen( $text ) ) {
return '';
}
// Don't bother if there are no specialchars - saves some processing.
if ( ! preg_match( '/[&<>"\']/', $text ) ) {
return $text;
}
// Account for the previous behavior of the function when the $quote_style is not an accepted value.
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( ENT_XML1 === $quote_style ) {
$quote_style = ENT_QUOTES | ENT_XML1;
} elseif ( ! in_array( $quote_style, array( ENT_NOQUOTES, ENT_COMPAT, ENT_QUOTES, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
$charset = _canonical_charset( $charset ? $charset : get_option( 'blog_charset' ) );
$_quote_style = $quote_style;
if ( 'double' === $quote_style ) {
$quote_style = ENT_COMPAT;
$_quote_style = ENT_COMPAT;
} elseif ( 'single' === $quote_style ) {
$quote_style = ENT_NOQUOTES;
}
if ( ! $double_encode ) {
/*
* Guarantee every &entity; is valid, convert &garbage; into &garbage;
* This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
*/
$text = wp_kses_normalize_entities( $text, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' );
}
$text = htmlspecialchars( $text, $quote_style, $charset, $double_encode );
// Back-compat.
if ( 'single' === $_quote_style ) {
$text = str_replace( "'", ''', $text );
}
return $text;
}
/**
* Converts a number of HTML entities into their special characters.
*
* Specifically deals with: `&`, `<`, `>`, `"`, and `'`.
*
* `$quote_style` can be set to ENT_COMPAT to decode `"` entities,
* or ENT_QUOTES to do both `"` and `'`. Default is ENT_NOQUOTES where no quotes are decoded.
*
* @since 2.8.0