summaryrefslogtreecommitdiff
path: root/includes/StringUtils.php
blob: c1545e6ef5242fe850990eab5cedd73448ac1651 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
<?php
/**
 * Methods to play with strings.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 * http://www.gnu.org/copyleft/gpl.html
 *
 * @file
 */

/**
 * A collection of static methods to play with strings.
 */
class StringUtils {

	/**
	 * Test whether a string is valid UTF-8.
	 *
	 * The function check for invalid byte sequences, overlong encoding but
	 * not for different normalisations.
	 *
	 * This relies internally on the mbstring function mb_check_encoding()
	 * hardcoded to check against UTF-8. Whenever the function is not available
	 * we fallback to a pure PHP implementation. Setting $disableMbstring to
	 * true will skip the use of mb_check_encoding, this is mostly intended for
	 * unit testing our internal implementation.
	 *
	 * @since 1.21
	 * @note In MediaWiki 1.21, this function did not provide proper UTF-8 validation.
	 * In particular, the pure PHP code path did not in fact check for overlong forms.
	 * Beware of this when backporting code to that version of MediaWiki.
	 *
	 * @param string $value String to check
	 * @param boolean $disableMbstring Whether to use the pure PHP
	 * implementation instead of trying mb_check_encoding. Intended for unit
	 * testing. Default: false
	 *
	 * @return boolean Whether the given $value is a valid UTF-8 encoded string
	 */
	static function isUtf8( $value, $disableMbstring = false ) {
		$value = (string)$value;

		// If the mbstring extension is loaded, use it. However, before PHP 5.4, values above
		// U+10FFFF are incorrectly allowed, so we have to check for them separately.
		if ( !$disableMbstring && function_exists( 'mb_check_encoding' ) ) {
			static $newPHP;
			if ( $newPHP === null ) {
				$newPHP = !mb_check_encoding( "\xf4\x90\x80\x80", 'UTF-8' );
			}

			return mb_check_encoding( $value, 'UTF-8' ) &&
				( $newPHP || preg_match( "/\xf4[\x90-\xbf]|[\xf5-\xff]/S", $value ) === 0 );
		}

		if ( preg_match( "/[\x80-\xff]/S", $value ) === 0 ) {
			// String contains only ASCII characters, has to be valid
			return true;
		}

		// PCRE implements repetition using recursion; to avoid a stack overflow (and segfault)
		// for large input, we check for invalid sequences (<= 5 bytes) rather than valid
		// sequences, which can be as long as the input string is. Multiple short regexes are
		// used rather than a single long regex for performance.
		static $regexes;
		if ( $regexes === null ) {
			$cont = "[\x80-\xbf]";
			$after = "(?!$cont)"; // "(?:[^\x80-\xbf]|$)" would work here
			$regexes = array(
				// Continuation byte at the start
				"/^$cont/",

				// ASCII byte followed by a continuation byte
				"/[\\x00-\x7f]$cont/S",

				// Illegal byte
				"/[\xc0\xc1\xf5-\xff]/S",

				// Invalid 2-byte sequence, or valid one then an extra continuation byte
				"/[\xc2-\xdf](?!$cont$after)/S",

				// Invalid 3-byte sequence, or valid one then an extra continuation byte
				"/\xe0(?![\xa0-\xbf]$cont$after)/",
				"/[\xe1-\xec\xee\xef](?!$cont{2}$after)/S",
				"/\xed(?![\x80-\x9f]$cont$after)/",

				// Invalid 4-byte sequence, or valid one then an extra continuation byte
				"/\xf0(?![\x90-\xbf]$cont{2}$after)/",
				"/[\xf1-\xf3](?!$cont{3}$after)/S",
				"/\xf4(?![\x80-\x8f]$cont{2}$after)/",
			);
		}

		foreach ( $regexes as $regex ) {
			if ( preg_match( $regex, $value ) !== 0 ) {
				return false;
			}
		}
		return true;
	}

	/**
	 * Perform an operation equivalent to
	 *
	 *     preg_replace( "!$startDelim(.*?)$endDelim!", $replace, $subject );
	 *
	 * except that it's worst-case O(N) instead of O(N^2)
	 *
	 * Compared to delimiterReplace(), this implementation is fast but memory-
	 * hungry and inflexible. The memory requirements are such that I don't
	 * recommend using it on anything but guaranteed small chunks of text.
	 *
	 * @param $startDelim
	 * @param $endDelim
	 * @param $replace
	 * @param $subject
	 *
	 * @return string
	 */
	static function hungryDelimiterReplace( $startDelim, $endDelim, $replace, $subject ) {
		$segments = explode( $startDelim, $subject );
		$output = array_shift( $segments );
		foreach ( $segments as $s ) {
			$endDelimPos = strpos( $s, $endDelim );
			if ( $endDelimPos === false ) {
				$output .= $startDelim . $s;
			} else {
				$output .= $replace . substr( $s, $endDelimPos + strlen( $endDelim ) );
			}
		}
		return $output;
	}

	/**
	 * Perform an operation equivalent to
	 *
	 *   preg_replace_callback( "!$startDelim(.*)$endDelim!s$flags", $callback, $subject )
	 *
	 * This implementation is slower than hungryDelimiterReplace but uses far less
	 * memory. The delimiters are literal strings, not regular expressions.
	 *
	 * If the start delimiter ends with an initial substring of the end delimiter,
	 * e.g. in the case of C-style comments, the behavior differs from the model
	 * regex. In this implementation, the end must share no characters with the
	 * start, so e.g. /*\/ is not considered to be both the start and end of a
	 * comment. /*\/xy/*\/ is considered to be a single comment with contents /xy/.
	 *
	 * @param string $startDelim start delimiter
	 * @param string $endDelim end delimiter
	 * @param $callback Callback: function to call on each match
	 * @param $subject String
	 * @param string $flags regular expression flags
	 * @throws MWException
	 * @return string
	 */
	static function delimiterReplaceCallback( $startDelim, $endDelim, $callback, $subject, $flags = '' ) {
		$inputPos = 0;
		$outputPos = 0;
		$output = '';
		$foundStart = false;
		$encStart = preg_quote( $startDelim, '!' );
		$encEnd = preg_quote( $endDelim, '!' );
		$strcmp = strpos( $flags, 'i' ) === false ? 'strcmp' : 'strcasecmp';
		$endLength = strlen( $endDelim );
		$m = array();

		while ( $inputPos < strlen( $subject ) &&
			preg_match( "!($encStart)|($encEnd)!S$flags", $subject, $m, PREG_OFFSET_CAPTURE, $inputPos ) )
		{
			$tokenOffset = $m[0][1];
			if ( $m[1][0] != '' ) {
				if ( $foundStart &&
					$strcmp( $endDelim, substr( $subject, $tokenOffset, $endLength ) ) == 0 )
				{
					# An end match is present at the same location
					$tokenType = 'end';
					$tokenLength = $endLength;
				} else {
					$tokenType = 'start';
					$tokenLength = strlen( $m[0][0] );
				}
			} elseif ( $m[2][0] != '' ) {
				$tokenType = 'end';
				$tokenLength = strlen( $m[0][0] );
			} else {
				throw new MWException( 'Invalid delimiter given to ' . __METHOD__ );
			}

			if ( $tokenType == 'start' ) {
				# Only move the start position if we haven't already found a start
				# This means that START START END matches outer pair
				if ( !$foundStart ) {
					# Found start
					$inputPos = $tokenOffset + $tokenLength;
					# Write out the non-matching section
					$output .= substr( $subject, $outputPos, $tokenOffset - $outputPos );
					$outputPos = $tokenOffset;
					$contentPos = $inputPos;
					$foundStart = true;
				} else {
					# Move the input position past the *first character* of START,
					# to protect against missing END when it overlaps with START
					$inputPos = $tokenOffset + 1;
				}
			} elseif ( $tokenType == 'end' ) {
				if ( $foundStart ) {
					# Found match
					$output .= call_user_func( $callback, array(
						substr( $subject, $outputPos, $tokenOffset + $tokenLength - $outputPos ),
						substr( $subject, $contentPos, $tokenOffset - $contentPos )
					));
					$foundStart = false;
				} else {
					# Non-matching end, write it out
					$output .= substr( $subject, $inputPos, $tokenOffset + $tokenLength - $outputPos );
				}
				$inputPos = $outputPos = $tokenOffset + $tokenLength;
			} else {
				throw new MWException( 'Invalid delimiter given to ' . __METHOD__ );
			}
		}
		if ( $outputPos < strlen( $subject ) ) {
			$output .= substr( $subject, $outputPos );
		}
		return $output;
	}

	/**
	 * Perform an operation equivalent to
	 *
	 *   preg_replace( "!$startDelim(.*)$endDelim!$flags", $replace, $subject )
	 *
	 * @param string $startDelim start delimiter regular expression
	 * @param string $endDelim end delimiter regular expression
	 * @param string $replace replacement string. May contain $1, which will be
	 *                 replaced by the text between the delimiters
	 * @param string $subject to search
	 * @param string $flags regular expression flags
	 * @return String: The string with the matches replaced
	 */
	static function delimiterReplace( $startDelim, $endDelim, $replace, $subject, $flags = '' ) {
		$replacer = new RegexlikeReplacer( $replace );
		return self::delimiterReplaceCallback( $startDelim, $endDelim,
			$replacer->cb(), $subject, $flags );
	}

	/**
	 * More or less "markup-safe" explode()
	 * Ignores any instances of the separator inside <...>
	 * @param string $separator
	 * @param string $text
	 * @return array
	 */
	static function explodeMarkup( $separator, $text ) {
		$placeholder = "\x00";

		// Remove placeholder instances
		$text = str_replace( $placeholder, '', $text );

		// Replace instances of the separator inside HTML-like tags with the placeholder
		$replacer = new DoubleReplacer( $separator, $placeholder );
		$cleaned = StringUtils::delimiterReplaceCallback( '<', '>', $replacer->cb(), $text );

		// Explode, then put the replaced separators back in
		$items = explode( $separator, $cleaned );
		foreach ( $items as $i => $str ) {
			$items[$i] = str_replace( $placeholder, $separator, $str );
		}

		return $items;
	}

	/**
	 * Escape a string to make it suitable for inclusion in a preg_replace()
	 * replacement parameter.
	 *
	 * @param string $string
	 * @return string
	 */
	static function escapeRegexReplacement( $string ) {
		$string = str_replace( '\\', '\\\\', $string );
		$string = str_replace( '$', '\\$', $string );
		return $string;
	}

	/**
	 * Workalike for explode() with limited memory usage.
	 * Returns an Iterator
	 * @param string $separator
	 * @param string $subject
	 * @return ArrayIterator|ExplodeIterator
	 */
	static function explode( $separator, $subject ) {
		if ( substr_count( $subject, $separator ) > 1000 ) {
			return new ExplodeIterator( $separator, $subject );
		} else {
			return new ArrayIterator( explode( $separator, $subject ) );
		}
	}
}

/**
 * Base class for "replacers", objects used in preg_replace_callback() and
 * StringUtils::delimiterReplaceCallback()
 */
class Replacer {

	/**
	 * @return array
	 */
	function cb() {
		return array( &$this, 'replace' );
	}
}

/**
 * Class to replace regex matches with a string similar to that used in preg_replace()
 */
class RegexlikeReplacer extends Replacer {
	var $r;

	/**
	 * @param string $r
	 */
	function __construct( $r ) {
		$this->r = $r;
	}

	/**
	 * @param array $matches
	 * @return string
	 */
	function replace( $matches ) {
		$pairs = array();
		foreach ( $matches as $i => $match ) {
			$pairs["\$$i"] = $match;
		}
		return strtr( $this->r, $pairs );
	}

}

/**
 * Class to perform secondary replacement within each replacement string
 */
class DoubleReplacer extends Replacer {

	/**
	 * @param $from
	 * @param $to
	 * @param int $index
	 */
	function __construct( $from, $to, $index = 0 ) {
		$this->from = $from;
		$this->to = $to;
		$this->index = $index;
	}

	/**
	 * @param array $matches
	 * @return mixed
	 */
	function replace( $matches ) {
		return str_replace( $this->from, $this->to, $matches[$this->index] );
	}
}

/**
 * Class to perform replacement based on a simple hashtable lookup
 */
class HashtableReplacer extends Replacer {
	var $table, $index;

	/**
	 * @param $table
	 * @param int $index
	 */
	function __construct( $table, $index = 0 ) {
		$this->table = $table;
		$this->index = $index;
	}

	/**
	 * @param array $matches
	 * @return mixed
	 */
	function replace( $matches ) {
		return $this->table[$matches[$this->index]];
	}
}

/**
 * Replacement array for FSS with fallback to strtr()
 * Supports lazy initialisation of FSS resource
 */
class ReplacementArray {
	/*mostly private*/ var $data = false;
	/*mostly private*/ var $fss = false;

	/**
	 * Create an object with the specified replacement array
	 * The array should have the same form as the replacement array for strtr()
	 * @param array $data
	 */
	function __construct( $data = array() ) {
		$this->data = $data;
	}

	/**
	 * @return array
	 */
	function __sleep() {
		return array( 'data' );
	}

	function __wakeup() {
		$this->fss = false;
	}

	/**
	 * Set the whole replacement array at once
	 * @param array $data
	 */
	function setArray( $data ) {
		$this->data = $data;
		$this->fss = false;
	}

	/**
	 * @return array|bool
	 */
	function getArray() {
		return $this->data;
	}

	/**
	 * Set an element of the replacement array
	 * @param string $from
	 * @param string $to
	 */
	function setPair( $from, $to ) {
		$this->data[$from] = $to;
		$this->fss = false;
	}

	/**
	 * @param array $data
	 */
	function mergeArray( $data ) {
		$this->data = array_merge( $this->data, $data );
		$this->fss = false;
	}

	/**
	 * @param ReplacementArray $other
	 */
	function merge( $other ) {
		$this->data = array_merge( $this->data, $other->data );
		$this->fss = false;
	}

	/**
	 * @param string $from
	 */
	function removePair( $from ) {
		unset( $this->data[$from] );
		$this->fss = false;
	}

	/**
	 * @param array $data
	 */
	function removeArray( $data ) {
		foreach ( $data as $from => $to ) {
			$this->removePair( $from );
		}
		$this->fss = false;
	}

	/**
	 * @param string $subject
	 * @return string
	 */
	function replace( $subject ) {
		if ( function_exists( 'fss_prep_replace' ) ) {
			wfProfileIn( __METHOD__ . '-fss' );
			if ( $this->fss === false ) {
				$this->fss = fss_prep_replace( $this->data );
			}
			$result = fss_exec_replace( $this->fss, $subject );
			wfProfileOut( __METHOD__ . '-fss' );
		} else {
			wfProfileIn( __METHOD__ . '-strtr' );
			$result = strtr( $subject, $this->data );
			wfProfileOut( __METHOD__ . '-strtr' );
		}
		return $result;
	}
}

/**
 * An iterator which works exactly like:
 *
 * foreach ( explode( $delim, $s ) as $element ) {
 *    ...
 * }
 *
 * Except it doesn't use 193 byte per element
 */
class ExplodeIterator implements Iterator {
	// The subject string
	var $subject, $subjectLength;

	// The delimiter
	var $delim, $delimLength;

	// The position of the start of the line
	var $curPos;

	// The position after the end of the next delimiter
	var $endPos;

	// The current token
	var $current;

	/**
	 * Construct a DelimIterator
	 * @param string $delim
	 * @param string $subject
	 */
	function __construct( $delim, $subject ) {
		$this->subject = $subject;
		$this->delim = $delim;

		// Micro-optimisation (theoretical)
		$this->subjectLength = strlen( $subject );
		$this->delimLength = strlen( $delim );

		$this->rewind();
	}

	function rewind() {
		$this->curPos = 0;
		$this->endPos = strpos( $this->subject, $this->delim );
		$this->refreshCurrent();
	}

	function refreshCurrent() {
		if ( $this->curPos === false ) {
			$this->current = false;
		} elseif ( $this->curPos >= $this->subjectLength ) {
			$this->current = '';
		} elseif ( $this->endPos === false ) {
			$this->current = substr( $this->subject, $this->curPos );
		} else {
			$this->current = substr( $this->subject, $this->curPos, $this->endPos - $this->curPos );
		}
	}

	function current() {
		return $this->current;
	}

	/**
	 * @return int|bool Current position or boolean false if invalid
	 */
	function key() {
		return $this->curPos;
	}

	/**
	 * @return string
	 */
	function next() {
		if ( $this->endPos === false ) {
			$this->curPos = false;
		} else {
			$this->curPos = $this->endPos + $this->delimLength;
			if ( $this->curPos >= $this->subjectLength ) {
				$this->endPos = false;
			} else {
				$this->endPos = strpos( $this->subject, $this->delim, $this->curPos );
			}
		}
		$this->refreshCurrent();
		return $this->current;
	}

	/**
	 * @return bool
	 */
	function valid() {
		return $this->curPos !== false;
	}
}