joomus /libraries/joomla/string/string.php

Language PHP Lines 959
MD5 Hash bd6188ac66970eb72a3387d2f8c995a0 Estimated Cost $11,410 (why?)
Repository https://bitbucket.org/eternaware/joomus.git View Raw File View Project SPDX
  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
<?php
/**
 * @package     Joomla.Platform
 * @subpackage  String
 *
 * @copyright   Copyright (C) 2005 - 2012 Open Source Matters, Inc. All rights reserved.
 * @license     GNU General Public License version 2 or later; see LICENSE
 */

defined('JPATH_PLATFORM') or die;

// PHP mbstring and iconv local configuration

// Check if mbstring extension is loaded and attempt to load it if not present except for windows
if (extension_loaded('mbstring'))
{
	// Make sure to suppress the output in case ini_set is disabled
	@ini_set('mbstring.internal_encoding', 'UTF-8');
	@ini_set('mbstring.http_input', 'UTF-8');
	@ini_set('mbstring.http_output', 'UTF-8');
}

// Same for iconv
if (function_exists('iconv'))
{
	// These are settings that can be set inside code
	iconv_set_encoding("internal_encoding", "UTF-8");
	iconv_set_encoding("input_encoding", "UTF-8");
	iconv_set_encoding("output_encoding", "UTF-8");
}

/**
 * Include the utf8 package
 */
jimport('phputf8.utf8');
jimport('phputf8.strcasecmp');

/**
 * String handling class for utf-8 data
 * Wraps the phputf8 library
 * All functions assume the validity of utf-8 strings.
 *
 * @package     Joomla.Platform
 * @subpackage  String
 * @since       11.1
 */
abstract class JString
{
	/**
	 * Increment styles.
	 *
	 * @var    array
	 * @since  11.3
	 */
	protected static $incrementStyles = array(
		'dash' => array(
			'#-(\d+)$#',
			'-%d'
		),
		'default' => array(
			array('#\((\d+)\)$#', '#\(\d+\)$#'),
			array(' (%d)', '(%d)'),
		),
	);

	/**
	 * Split a string in camel case format
	 *
	 * "FooBarABCDef"            becomes  array("Foo", "Bar", "ABC", "Def");
	 * "JFooBar"                 becomes  array("J", "Foo", "Bar");
	 * "J001FooBar002"           becomes  array("J001", "Foo", "Bar002");
	 * "abcDef"                  becomes  array("abc", "Def");
	 * "abc_defGhi_Jkl"          becomes  array("abc_def", "Ghi_Jkl");
	 * "ThisIsA_NASAAstronaut"   becomes  array("This", "Is", "A_NASA", "Astronaut")),
	 * "JohnFitzgerald_Kennedy"  becomes  array("John", "Fitzgerald_Kennedy")),
	 *
	 * @param   string  $string  The source string.
	 *
	 * @return  array   The splitted string.
	 *
	 * @deprecated  12.3 Use JStringNormalise::fromCamelCase()
	 * @since   11.3
	 */
	public static function splitCamelCase($string)
	{
		JLog::add('JString::splitCamelCase has been deprecated. Use JStringNormalise::fromCamelCase.', JLog::WARNING, 'deprecated');

		return JStringNormalise::fromCamelCase($string, true);
	}

	/**
	 * Increments a trailing number in a string.
	 *
	 * Used to easily create distinct labels when copying objects. The method has the following styles:
	 *
	 * default: "Label" becomes "Label (2)"
	 * dash:    "Label" becomes "Label-2"
	 *
	 * @param   string   $string  The source string.
	 * @param   string   $style   The the style (default|dash).
	 * @param   integer  $n       If supplied, this number is used for the copy, otherwise it is the 'next' number.
	 *
	 * @return  string  The incremented string.
	 *
	 * @since   11.3
	 */
	public static function increment($string, $style = 'default', $n = 0)
	{
		$styleSpec = isset(self::$incrementStyles[$style]) ? self::$incrementStyles[$style] : self::$incrementStyles['default'];

		// Regular expression search and replace patterns.
		if (is_array($styleSpec[0]))
		{
			$rxSearch = $styleSpec[0][0];
			$rxReplace = $styleSpec[0][1];
		}
		else
		{
			$rxSearch = $rxReplace = $styleSpec[0];
		}

		// New and old (existing) sprintf formats.
		if (is_array($styleSpec[1]))
		{
			$newFormat = $styleSpec[1][0];
			$oldFormat = $styleSpec[1][1];
		}
		else
		{
			$newFormat = $oldFormat = $styleSpec[1];
		}

		// Check if we are incrementing an existing pattern, or appending a new one.
		if (preg_match($rxSearch, $string, $matches))
		{
			$n = empty($n) ? ($matches[1] + 1) : $n;
			$string = preg_replace($rxReplace, sprintf($oldFormat, $n), $string);
		}
		else
		{
			$n = empty($n) ? 2 : $n;
			$string .= sprintf($newFormat, $n);
		}

		return $string;
	}

	/**
	 * UTF-8 aware alternative to strpos.
	 *
	 * Find position of first occurrence of a string.
	 *
	 * @param   string   $str     String being examined
	 * @param   string   $search  String being searched for
	 * @param   integer  $offset  Optional, specifies the position from which the search should be performed
	 *
	 * @return  mixed  Number of characters before the first match or FALSE on failure
	 *
	 * @see     http://www.php.net/strpos
	 * @since   11.1
	 */
	public static function strpos($str, $search, $offset = false)
	{
		if ($offset === false)
		{
			return utf8_strpos($str, $search);
		}
		else
		{
			return utf8_strpos($str, $search, $offset);
		}
	}

	/**
	 * UTF-8 aware alternative to strrpos
	 * Finds position of last occurrence of a string
	 *
	 * @param   string   $str     String being examined.
	 * @param   string   $search  String being searched for.
	 * @param   integer  $offset  Offset from the left of the string.
	 *
	 * @return  mixed  Number of characters before the last match or false on failure
	 *
	 * @see     http://www.php.net/strrpos
	 * @since   11.1
	 */
	public static function strrpos($str, $search, $offset = 0)
	{
		return utf8_strrpos($str, $search, $offset);
	}

	/**
	 * UTF-8 aware alternative to substr
	 * Return part of a string given character offset (and optionally length)
	 *
	 * @param   string   $str     String being processed
	 * @param   integer  $offset  Number of UTF-8 characters offset (from left)
	 * @param   integer  $length  Optional length in UTF-8 characters from offset
	 *
	 * @return  mixed string or FALSE if failure
	 *
	 * @see     http://www.php.net/substr
	 * @since   11.1
	 */
	public static function substr($str, $offset, $length = false)
	{
		if ($length === false)
		{
			return utf8_substr($str, $offset);
		}
		else
		{
			return utf8_substr($str, $offset, $length);
		}
	}

	/**
	 * UTF-8 aware alternative to strtlower
	 *
	 * Make a string lowercase
	 * Note: The concept of a characters "case" only exists is some alphabets
	 * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
	 * not exist in the Chinese alphabet, for example. See Unicode Standard
	 * Annex #21: Case Mappings
	 *
	 * @param   string  $str  String being processed
	 *
	 * @return  mixed  Either string in lowercase or FALSE is UTF-8 invalid
	 *
	 * @see http://www.php.net/strtolower
	 * @since   11.1
	 */
	public static function strtolower($str)
	{
		return utf8_strtolower($str);
	}

	/**
	 * UTF-8 aware alternative to strtoupper
	 * Make a string uppercase
	 * Note: The concept of a characters "case" only exists is some alphabets
	 * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
	 * not exist in the Chinese alphabet, for example. See Unicode Standard
	 * Annex #21: Case Mappings
	 *
	 * @param   string  $str  String being processed
	 *
	 * @return  mixed  Either string in uppercase or FALSE is UTF-8 invalid
	 *
	 * @see     http://www.php.net/strtoupper
	 * @since   11.1
	 */
	public static function strtoupper($str)
	{
		return utf8_strtoupper($str);
	}

	/**
	 * UTF-8 aware alternative to strlen.
	 *
	 * Returns the number of characters in the string (NOT THE NUMBER OF BYTES),
	 *
	 * @param   string  $str  UTF-8 string.
	 *
	 * @return  integer  Number of UTF-8 characters in string.
	 *
	 * @see http://www.php.net/strlen
	 * @since   11.1
	 */
	public static function strlen($str)
	{
		return utf8_strlen($str);
	}

	/**
	 * UTF-8 aware alternative to str_ireplace
	 * Case-insensitive version of str_replace
	 *
	 * @param   string   $search   String to search
	 * @param   string   $replace  Existing string to replace
	 * @param   string   $str      New string to replace with
	 * @param   integer  $count    Optional count value to be passed by referene
	 *
	 * @return  string  UTF-8 String
	 *
	 * @see     http://www.php.net/str_ireplace
	 * @since   11.1
	 */
	public static function str_ireplace($search, $replace, $str, $count = null)
	{
		jimport('phputf8.str_ireplace');
		if ($count === false)
		{
			return utf8_ireplace($search, $replace, $str);
		}
		else
		{
			return utf8_ireplace($search, $replace, $str, $count);
		}
	}

	/**
	 * UTF-8 aware alternative to str_split
	 * Convert a string to an array
	 *
	 * @param   string   $str        UTF-8 encoded string to process
	 * @param   integer  $split_len  Number to characters to split string by
	 *
	 * @return  array
	 *
	 * @see     http://www.php.net/str_split
	 * @since   11.1
	 */
	public static function str_split($str, $split_len = 1)
	{
		jimport('phputf8.str_split');

		return utf8_str_split($str, $split_len);
	}

	/**
	 * UTF-8/LOCALE aware alternative to strcasecmp
	 * A case insensitive string comparison
	 *
	 * @param   string  $str1    string 1 to compare
	 * @param   string  $str2    string 2 to compare
	 * @param   mixed   $locale  The locale used by strcoll or false to use classical comparison
	 *
	 * @return  integer   < 0 if str1 is less than str2; > 0 if str1 is greater than str2, and 0 if they are equal.
	 *
	 * @see     http://www.php.net/strcasecmp
	 * @see     http://www.php.net/strcoll
	 * @see     http://www.php.net/setlocale
	 * @since   11.1
	 */
	public static function strcasecmp($str1, $str2, $locale = false)
	{
		if ($locale)
		{
			// Get current locale
			$locale0 = setlocale(LC_COLLATE, 0);
			if (!$locale = setlocale(LC_COLLATE, $locale))
			{
				$locale = $locale0;
			}

			// See if we have successfully set locale to UTF-8
			if (!stristr($locale, 'UTF-8') && stristr($locale, '_') && preg_match('~\.(\d+)$~', $locale, $m))
			{
				$encoding = 'CP' . $m[1];
			}
			elseif (stristr($locale, 'UTF-8') || stristr($locale, 'utf8'))
			{
				$encoding = 'UTF-8';
			}
			else
			{
				$encoding = 'nonrecodable';
			}

			// If we successfully set encoding it to utf-8 or encoding is sth weird don't recode
			if ($encoding == 'UTF-8' || $encoding == 'nonrecodable')
			{
				return strcoll(utf8_strtolower($str1), utf8_strtolower($str2));
			}
			else
			{
				return strcoll(
					self::transcode(utf8_strtolower($str1), 'UTF-8', $encoding),
					self::transcode(utf8_strtolower($str2), 'UTF-8', $encoding)
				);
			}
		}
		else
		{
			return utf8_strcasecmp($str1, $str2);
		}
	}

	/**
	 * UTF-8/LOCALE aware alternative to strcmp
	 * A case sensitive string comparison
	 *
	 * @param   string  $str1    string 1 to compare
	 * @param   string  $str2    string 2 to compare
	 * @param   mixed   $locale  The locale used by strcoll or false to use classical comparison
	 *
	 * @return  integer  < 0 if str1 is less than str2; > 0 if str1 is greater than str2, and 0 if they are equal.
	 *
	 * @see     http://www.php.net/strcmp
	 * @see     http://www.php.net/strcoll
	 * @see     http://www.php.net/setlocale
	 * @since   11.1
	 */
	public static function strcmp($str1, $str2, $locale = false)
	{
		if ($locale)
		{
			// Get current locale
			$locale0 = setlocale(LC_COLLATE, 0);
			if (!$locale = setlocale(LC_COLLATE, $locale))
			{
				$locale = $locale0;
			}

			// See if we have successfully set locale to UTF-8
			if (!stristr($locale, 'UTF-8') && stristr($locale, '_') && preg_match('~\.(\d+)$~', $locale, $m))
			{
				$encoding = 'CP' . $m[1];
			}
			elseif (stristr($locale, 'UTF-8') || stristr($locale, 'utf8'))
			{
				$encoding = 'UTF-8';
			}
			else
			{
				$encoding = 'nonrecodable';
			}

			// If we successfully set encoding it to utf-8 or encoding is sth weird don't recode
			if ($encoding == 'UTF-8' || $encoding == 'nonrecodable')
			{
				return strcoll($str1, $str2);
			}
			else
			{
				return strcoll(self::transcode($str1, 'UTF-8', $encoding), self::transcode($str2, 'UTF-8', $encoding));
			}
		}
		else
		{
			return strcmp($str1, $str2);
		}
	}

	/**
	 * UTF-8 aware alternative to strcspn
	 * Find length of initial segment not matching mask
	 *
	 * @param   string   $str     The string to process
	 * @param   string   $mask    The mask
	 * @param   integer  $start   Optional starting character position (in characters)
	 * @param   integer  $length  Optional length
	 *
	 * @return  integer  The length of the initial segment of str1 which does not contain any of the characters in str2
	 *
	 * @see     http://www.php.net/strcspn
	 * @since   11.1
	 */
	public static function strcspn($str, $mask, $start = null, $length = null)
	{
		jimport('phputf8.strcspn');
		if ($start === false && $length === false)
		{
			return utf8_strcspn($str, $mask);
		}
		elseif ($length === false)
		{
			return utf8_strcspn($str, $mask, $start);
		}
		else
		{
			return utf8_strcspn($str, $mask, $start, $length);
		}
	}

	/**
	 * UTF-8 aware alternative to stristr
	 * Returns all of haystack from the first occurrence of needle to the end.
	 * needle and haystack are examined in a case-insensitive manner
	 * Find first occurrence of a string using case insensitive comparison
	 *
	 * @param   string  $str     The haystack
	 * @param   string  $search  The needle
	 *
	 * @return string the sub string
	 *
	 * @see     http://www.php.net/stristr
	 * @since   11.1
	 */
	public static function stristr($str, $search)
	{
		jimport('phputf8.stristr');
		return utf8_stristr($str, $search);
	}

	/**
	 * UTF-8 aware alternative to strrev
	 * Reverse a string
	 *
	 * @param   string  $str  String to be reversed
	 *
	 * @return  string   The string in reverse character order
	 *
	 * @see     http://www.php.net/strrev
	 * @since   11.1
	 */
	public static function strrev($str)
	{
		jimport('phputf8.strrev');

		return utf8_strrev($str);
	}

	/**
	 * UTF-8 aware alternative to strspn
	 * Find length of initial segment matching mask
	 *
	 * @param   string   $str     The haystack
	 * @param   string   $mask    The mask
	 * @param   integer  $start   Start optional
	 * @param   integer  $length  Length optional
	 *
	 * @return  integer
	 *
	 * @see     http://www.php.net/strspn
	 * @since   11.1
	 */
	public static function strspn($str, $mask, $start = null, $length = null)
	{
		jimport('phputf8.strspn');
		if ($start === null && $length === null)
		{
			return utf8_strspn($str, $mask);
		}
		elseif ($length === null)
		{
			return utf8_strspn($str, $mask, $start);
		}
		else
		{
			return utf8_strspn($str, $mask, $start, $length);
		}
	}

	/**
	 * UTF-8 aware substr_replace
	 * Replace text within a portion of a string
	 *
	 * @param   string   $str     The haystack
	 * @param   string   $repl    The replacement string
	 * @param   integer  $start   Start
	 * @param   integer  $length  Length (optional)
	 *
	 * @return  string
	 *
	 * @see     http://www.php.net/substr_replace
	 * @since   11.1
	 */
	public static function substr_replace($str, $repl, $start, $length = null)
	{
		// Loaded by library loader
		if ($length === false)
		{
			return utf8_substr_replace($str, $repl, $start);
		}
		else
		{
			return utf8_substr_replace($str, $repl, $start, $length);
		}
	}

	/**
	 * UTF-8 aware replacement for ltrim()
	 *
	 * Strip whitespace (or other characters) from the beginning of a string
	 * You only need to use this if you are supplying the charlist
	 * optional arg and it contains UTF-8 characters. Otherwise ltrim will
	 * work normally on a UTF-8 string
	 *
	 * @param   string  $str       The string to be trimmed
	 * @param   string  $charlist  The optional charlist of additional characters to trim
	 *
	 * @return  string  The trimmed string
	 *
	 * @see     http://www.php.net/ltrim
	 * @since   11.1
	 */
	public static function ltrim($str, $charlist = false)
	{
		if (empty($charlist) && $charlist !== false)
		{
			return $str;
		}

		jimport('phputf8.trim');
		if ($charlist === false)
		{
			return utf8_ltrim($str);
		}
		else
		{
			return utf8_ltrim($str, $charlist);
		}
	}

	/**
	 * UTF-8 aware replacement for rtrim()
	 * Strip whitespace (or other characters) from the end of a string
	 * You only need to use this if you are supplying the charlist
	 * optional arg and it contains UTF-8 characters. Otherwise rtrim will
	 * work normally on a UTF-8 string
	 *
	 * @param   string  $str       The string to be trimmed
	 * @param   string  $charlist  The optional charlist of additional characters to trim
	 *
	 * @return  string  The trimmed string
	 *
	 * @see     http://www.php.net/rtrim
	 * @since   11.1
	 */
	public static function rtrim($str, $charlist = false)
	{
		if (empty($charlist) && $charlist !== false)
		{
			return $str;
		}

		jimport('phputf8.trim');
		if ($charlist === false)
		{
			return utf8_rtrim($str);
		}
		else
		{
			return utf8_rtrim($str, $charlist);
		}
	}

	/**
	 * UTF-8 aware replacement for trim()
	 * Strip whitespace (or other characters) from the beginning and end of a string
	 * Note: you only need to use this if you are supplying the charlist
	 * optional arg and it contains UTF-8 characters. Otherwise trim will
	 * work normally on a UTF-8 string
	 *
	 * @param   string  $str       The string to be trimmed
	 * @param   string  $charlist  The optional charlist of additional characters to trim
	 *
	 * @return  string  The trimmed string
	 *
	 * @see     http://www.php.net/trim
	 * @since   11.1
	 */
	public static function trim($str, $charlist = false)
	{
		if (empty($charlist) && $charlist !== false)
		{
			return $str;
		}

		jimport('phputf8.trim');
		if ($charlist === false)
		{
			return utf8_trim($str);
		}
		else
		{
			return utf8_trim($str, $charlist);
		}
	}

	/**
	 * UTF-8 aware alternative to ucfirst
	 * Make a string's first character uppercase or all words' first character uppercase
	 *
	 * @param   string  $str           String to be processed
	 * @param   string  $delimiter     The words delimiter (null means do not split the string)
	 * @param   string  $newDelimiter  The new words delimiter (null means equal to $delimiter)
	 *
	 * @return  string  If $delimiter is null, return the string with first character as upper case (if applicable)
	 *                  else consider the string of words separated by the delimiter, apply the ucfirst to each words
	 *                  and return the string with the new delimiter
	 *
	 * @see     http://www.php.net/ucfirst
	 * @since   11.1
	 */
	public static function ucfirst($str, $delimiter = null, $newDelimiter = null)
	{
		jimport('phputf8.ucfirst');
		if ($delimiter === null)
		{
			return utf8_ucfirst($str);
		}
		else
		{
			if ($newDelimiter === null)
			{
				$newDelimiter = $delimiter;
			}
			return implode($newDelimiter, array_map('utf8_ucfirst', explode($delimiter, $str)));
		}
	}

	/**
	 * UTF-8 aware alternative to ucwords
	 * Uppercase the first character of each word in a string
	 *
	 * @param   string  $str  String to be processed
	 *
	 * @return  string  String with first char of each word uppercase
	 *
	 * @see     http://www.php.net/ucwords
	 * @since   11.1
	 */
	public static function ucwords($str)
	{
		jimport('phputf8.ucwords');
		return utf8_ucwords($str);
	}

	/**
	 * Transcode a string.
	 *
	 * @param   string  $source         The string to transcode.
	 * @param   string  $from_encoding  The source encoding.
	 * @param   string  $to_encoding    The target encoding.
	 *
	 * @return  mixed  The transcoded string, or null if the source was not a string.
	 *
	 * @link    https://bugs.php.net/bug.php?id=48147
	 *
	 * @since   11.1
	 */
	public static function transcode($source, $from_encoding, $to_encoding)
	{
		if (is_string($source))
		{
			switch (ICONV_IMPL)
			{
				case 'glibc':
				return @iconv($from_encoding, $to_encoding . '//TRANSLIT,IGNORE', $source);
				case 'libiconv':
				default:
				return iconv($from_encoding, $to_encoding . '//IGNORE//TRANSLIT', $source);
			}
		}

		return null;
	}

	/**
	 * Tests a string as to whether it's valid UTF-8 and supported by the Unicode standard.
	 *
	 * Note: this function has been modified to simple return true or false.
	 *
	 * @param   string  $str  UTF-8 encoded string.
	 *
	 * @return  boolean  true if valid
	 *
	 * @author  <hsivonen@iki.fi>
	 * @see     http://hsivonen.iki.fi/php-utf8/
	 * @see     compliant
	 * @since   11.1
	 */
	public static function valid($str)
	{
		// Cached expected number of octets after the current octet
		// until the beginning of the next UTF8 character sequence
		$mState = 0;

		// Cached Unicode character
		$mUcs4 = 0;

		// Cached expected number of octets in the current sequence
		$mBytes = 1;

		$len = strlen($str);

		for ($i = 0; $i < $len; $i++)
		{
			$in = ord($str{$i});

			if ($mState == 0)
			{
				// When mState is zero we expect either a US-ASCII character or a
				// multi-octet sequence.
				if (0 == (0x80 & ($in)))
				{
					// US-ASCII, pass straight through.
					$mBytes = 1;
				}
				elseif (0xC0 == (0xE0 & ($in)))
				{
					// First octet of 2 octet sequence
					$mUcs4 = ($in);
					$mUcs4 = ($mUcs4 & 0x1F) << 6;
					$mState = 1;
					$mBytes = 2;
				}
				elseif (0xE0 == (0xF0 & ($in)))
				{
					// First octet of 3 octet sequence
					$mUcs4 = ($in);
					$mUcs4 = ($mUcs4 & 0x0F) << 12;
					$mState = 2;
					$mBytes = 3;
				}
				elseif (0xF0 == (0xF8 & ($in)))
				{
					// First octet of 4 octet sequence
					$mUcs4 = ($in);
					$mUcs4 = ($mUcs4 & 0x07) << 18;
					$mState = 3;
					$mBytes = 4;
				}
				elseif (0xF8 == (0xFC & ($in)))
				{
					/* First octet of 5 octet sequence.
					 *
					 * This is illegal because the encoded codepoint must be either
					 * (a) not the shortest form or
					 * (b) outside the Unicode range of 0-0x10FFFF.
					 * Rather than trying to resynchronize, we will carry on until the end
					 * of the sequence and let the later error handling code catch it.
					 */
					$mUcs4 = ($in);
					$mUcs4 = ($mUcs4 & 0x03) << 24;
					$mState = 4;
					$mBytes = 5;
				}
				elseif (0xFC == (0xFE & ($in)))
				{
					// First octet of 6 octet sequence, see comments for 5 octet sequence.
					$mUcs4 = ($in);
					$mUcs4 = ($mUcs4 & 1) << 30;
					$mState = 5;
					$mBytes = 6;

				}
				else
				{
					/* Current octet is neither in the US-ASCII range nor a legal first
					 * octet of a multi-octet sequence.
					 */
					return false;
				}
			}
			else
			{
				// When mState is non-zero, we expect a continuation of the multi-octet
				// sequence
				if (0x80 == (0xC0 & ($in)))
				{
					// Legal continuation.
					$shift = ($mState - 1) * 6;
					$tmp = $in;
					$tmp = ($tmp & 0x0000003F) << $shift;
					$mUcs4 |= $tmp;

					/**
					 * End of the multi-octet sequence. mUcs4 now contains the final
					 * Unicode codepoint to be output
					 */
					if (0 == --$mState)
					{
						/*
						 * Check for illegal sequences and codepoints.
						 */
						// From Unicode 3.1, non-shortest form is illegal
						if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || ((4 == $mBytes) && ($mUcs4 < 0x10000))
							|| (4 < $mBytes)
							|| (($mUcs4 & 0xFFFFF800) == 0xD800) // From Unicode 3.2, surrogate characters are illegal
							|| ($mUcs4 > 0x10FFFF)) // Codepoints outside the Unicode range are illegal
						{
							return false;
						}

						// Initialize UTF8 cache.
						$mState = 0;
						$mUcs4 = 0;
						$mBytes = 1;
					}
				}
				else
				{
					/**
					 *((0xC0 & (*in) != 0x80) && (mState != 0))
					 * Incomplete multi-octet sequence.
					 */
					return false;
				}
			}
		}
		return true;
	}

	/**
	 * Tests whether a string complies as UTF-8. This will be much
	 * faster than utf8_is_valid but will pass five and six octet
	 * UTF-8 sequences, which are not supported by Unicode and
	 * so cannot be displayed correctly in a browser. In other words
	 * it is not as strict as utf8_is_valid but it's faster. If you use
	 * it to validate user input, you place yourself at the risk that
	 * attackers will be able to inject 5 and 6 byte sequences (which
	 * may or may not be a significant risk, depending on what you are
	 * are doing)
	 *
	 * @param   string  $str  UTF-8 string to check
	 *
	 * @return  boolean  TRUE if string is valid UTF-8
	 *
	 * @see     valid
	 * @see     http://www.php.net/manual/en/reference.pcre.pattern.modifiers.php#54805
	 * @since   11.1
	 */
	public static function compliant($str)
	{
		if (strlen($str) == 0)
		{
			return true;
		}

		/*
		 * If even just the first character can be matched, when the /u
		 * modifier is used, then it's valid UTF-8. If the UTF-8 is somehow
		 * invalid, nothing at all will match, even if the string contains
		 * some valid sequences
		 */
		return (preg_match('/^.{1}/us', $str, $ar) == 1);
	}

	/**
	 * Does a UTF-8 safe version of PHP parse_url function
	 *
	 * @param   string  $url  URL to parse
	 *
	 * @return  mixed  Associative array or false if badly formed URL.
	 *
	 * @see     http://us3.php.net/manual/en/function.parse-url.php
	 * @since   11.1
	 */
	public static function parse_url($url)
	{
		$result = false;

		// Build arrays of values we need to decode before parsing
		$entities = array('%21', '%2A', '%27', '%28', '%29', '%3B', '%3A', '%40', '%26', '%3D', '%24', '%2C', '%2F', '%3F', '%23', '%5B', '%5D');
		$replacements = array('!', '*', "'", "(", ")", ";", ":", "@", "&", "=", "$", ",", "/", "?", "#", "[", "]");

		// Create encoded URL with special URL characters decoded so it can be parsed
		// All other characters will be encoded
		$encodedURL = str_replace($entities, $replacements, urlencode($url));

		// Parse the encoded URL
		$encodedParts = parse_url($encodedURL);

		// Now, decode each value of the resulting array
		if ($encodedParts)
		{
			foreach ($encodedParts as $key => $value)
			{
				$result[$key] = urldecode(str_replace($replacements, $entities, $value));
			}
		}
		return $result;
	}
}
Back to Top