Verzeichnisstruktur phpBB-3.2.0
- Veröffentlicht
- 06.01.2017
So funktioniert es
|
|
Auf das letzte Element klicken. Dies geht jeweils ein Schritt zurück |
Auf das Icon klicken, dies öffnet das Verzeichnis. Nochmal klicken schließt das Verzeichnis. |
|
|
(Beispiel Datei-Icons)
|
Auf das Icon klicken um den Quellcode anzuzeigen |
Mbstring.php
001 <?php
002
003 /*
004 * Copyright (C) 2016 Nicolas Grekas - p@tchwork.com
005 *
006 * This library is free software; you can redistribute it and/or modify it
007 * under the terms of the (at your option):
008 * Apache License v2.0 (http://apache.org/licenses/LICENSE-2.0.txt), or
009 * GNU General Public License v2.0 (http://gnu.org/licenses/gpl-2.0.txt).
010 */
011
012 namespace Patchwork\PHP\Shim;
013
014 /**
015 * Partial mbstring implementation in PHP, iconv based, UTF-8 centric.
016 *
017 * Implemented:
018 * - mb_convert_encoding - Convert character encoding
019 * - mb_convert_variables - Convert character code in variable(s)
020 * - mb_decode_mimeheader - Decode string in MIME header field
021 * - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED
022 * - mb_convert_case - Perform case folding on a string
023 * - mb_get_info - Get internal settings of mbstring
024 * - mb_http_input - Detect HTTP input character encoding
025 * - mb_http_output - Set/Get HTTP output character encoding
026 * - mb_internal_encoding - Set/Get internal character encoding
027 * - mb_list_encodings - Returns an array of all supported encodings
028 * - mb_output_handler - Callback function converts character encoding in output buffer
029 * - mb_strlen - Get string length
030 * - mb_strpos - Find position of first occurrence of string in a string
031 * - mb_strrpos - Find position of last occurrence of a string in a string
032 * - mb_strtolower - Make a string lowercase
033 * - mb_strtoupper - Make a string uppercase
034 * - mb_substitute_character - Set/Get substitution character
035 * - mb_substr - Get part of string
036 * - mb_stripos - Finds position of first occurrence of a string within another, case insensitive
037 * - mb_stristr - Finds first occurrence of a string within another, case insensitive
038 * - mb_strrchr - Finds the last occurrence of a character in a string within another
039 * - mb_strrichr - Finds the last occurrence of a character in a string within another, case insensitive
040 * - mb_strripos - Finds position of last occurrence of a string within another, case insensitive
041 * - mb_strstr - Finds first occurrence of a string within anothers
042 * - mb_strwidth - Return width of string
043 * - mb_substr_count - Count the number of substring occurrences
044 *
045 * Not implemented:
046 * - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more)
047 * - mb_decode_numericentity - Decode HTML numeric string reference to character
048 * - mb_encode_numericentity - Encode character to HTML numeric string reference
049 * - mb_ereg_* - Regular expression with multibyte support
050 * - mb_parse_str - Parse GET/POST/COOKIE data and set global variable
051 * - mb_preferred_mime_name - Get MIME charset string
052 * - mb_regex_encoding - Returns current encoding for multibyte regex as string
053 * - mb_regex_set_options - Set/Get the default options for mbregex functions
054 * - mb_send_mail - Send encoded mail
055 * - mb_split - Split multibyte string using regular expression
056 * - mb_strcut - Get part of string
057 * - mb_strimwidth - Get truncated string with specified width
058 *
059 * @internal
060 */
061 class Mbstring
062 {
063 const MB_CASE_FOLD = PHP_INT_MAX;
064
065 private static $encodingList = array('ASCII', 'UTF-8');
066 private static $language = 'neutral';
067 private static $internalEncoding = 'UTF-8';
068 private static $caseFold = array(
069 array('µ','ſ',"\xCD\x85",'ς',"\xCF\x90","\xCF\x91","\xCF\x95","\xCF\x96","\xCF\xB0","\xCF\xB1","\xCF\xB5","\xE1\xBA\x9B","\xE1\xBE\xBE"),
070 array('μ','s','ι', 'σ','β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1",'ι'),
071 );
072
073 public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null)
074 {
075 if (is_array($fromEncoding) || false !== strpos($fromEncoding, ',')) {
076 $fromEncoding = self::mb_detect_encoding($s, $fromEncoding);
077 } else {
078 $fromEncoding = self::getEncoding($fromEncoding);
079 }
080
081 $toEncoding = self::getEncoding($toEncoding);
082
083 if ('BASE64' === $fromEncoding) {
084 $s = base64_decode($s);
085 $fromEncoding = $toEncoding;
086 }
087
088 if ('BASE64' === $toEncoding) {
089 return base64_encode($s);
090 }
091
092 if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) {
093 if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) {
094 $fromEncoding = 'Windows-1252';
095 }
096 if ('UTF-8' !== $fromEncoding) {
097 $s = iconv($fromEncoding, 'UTF-8', $s);
098 }
099
100 return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s);
101 }
102
103 if ('HTML-ENTITIES' === $fromEncoding) {
104 $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8');
105 $fromEncoding = 'UTF-8';
106 }
107
108 return iconv($fromEncoding, $toEncoding, $s);
109 }
110
111 public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null)
112 {
113 $vars = array(&$a, &$b, &$c, &$d, &$e, &$f);
114
115 $ok = true;
116 array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) {
117 if (false === $v = Mbstring::mb_convert_encoding($v, $toEncoding, $fromEncoding)) {
118 $ok = false;
119 }
120 });
121
122 return $ok ? $fromEncoding : false;
123 }
124
125 public static function mb_decode_mimeheader($s)
126 {
127 return iconv_mime_decode($s, 2, self::$internalEncoding);
128 }
129
130 public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null)
131 {
132 trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING);
133 }
134
135 public static function mb_convert_case($s, $mode, $encoding = null)
136 {
137 if ('' === $s .= '') {
138 return '';
139 }
140
141 $encoding = self::getEncoding($encoding);
142
143 if ('UTF-8' === $encoding) {
144 $encoding = null;
145 } else {
146 $s = iconv($encoding, 'UTF-8', $s);
147 }
148
149 if (MB_CASE_TITLE == $mode) {
150 $s = preg_replace_callback('/\b\p{Ll}/u', array(__CLASS__, 'title_case_upper'), $s);
151 $s = preg_replace_callback('/\B[\p{Lu}\p{Lt}]+/u', array(__CLASS__, 'title_case_lower'), $s);
152 } else {
153 if (MB_CASE_UPPER == $mode) {
154 static $upper = null;
155 if (null === $upper) {
156 $upper = self::getData('upperCase');
157 }
158 $map = $upper;
159 } else {
160 if (self::MB_CASE_FOLD === $mode) {
161 $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s);
162 }
163
164 static $lower = null;
165 if (null === $lower) {
166 $lower = self::getData('lowerCase');
167 }
168 $map = $lower;
169 }
170
171 static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);
172
173 $i = 0;
174 $len = strlen($s);
175
176 while ($i < $len) {
177 $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
178 $uchr = substr($s, $i, $ulen);
179 $i += $ulen;
180
181 if (isset($map[$uchr])) {
182 $uchr = $map[$uchr];
183 $nlen = strlen($uchr);
184
185 if ($nlen == $ulen) {
186 $nlen = $i;
187 do {
188 $s[--$nlen] = $uchr[--$ulen];
189 } while ($ulen);
190 } else {
191 $s = substr_replace($s, $uchr, $i - $ulen, $ulen);
192 $len += $nlen - $ulen;
193 $i += $nlen - $ulen;
194 }
195 }
196 }
197 }
198
199 if (null === $encoding) {
200 return $s;
201 }
202
203 return iconv('UTF-8', $encoding, $s);
204 }
205
206 public static function mb_internal_encoding($encoding = null)
207 {
208 if (null === $encoding) {
209 return self::$internalEncoding;
210 }
211
212 $encoding = self::getEncoding($encoding);
213
214 if ('UTF-8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) {
215 self::$internalEncoding = $encoding;
216
217 return true;
218 }
219
220 return false;
221 }
222
223 public static function mb_language($lang = null)
224 {
225 if (null === $lang) {
226 return self::$language;
227 }
228
229 switch ($lang = strtolower($lang)) {
230 case 'uni':
231 case 'neutral':
232 self::$language = $lang;
233
234 return true;
235 }
236
237 return false;
238 }
239
240 public static function mb_list_encodings()
241 {
242 return array('UTF-8');
243 }
244
245 public static function mb_encoding_aliases($encoding)
246 {
247 switch (strtoupper($encoding)) {
248 case 'UTF8':
249 case 'UTF-8':
250 return array('utf8');
251 }
252
253 return false;
254 }
255
256 public static function mb_check_encoding($var = null, $encoding = null)
257 {
258 if (null === $encoding) {
259 if (null === $var) {
260 return false;
261 }
262 $encoding = self::$internalEncoding;
263 }
264
265 return self::mb_detect_encoding($var, array($encoding)) || false !== @iconv($encoding, $encoding, $var);
266 }
267
268 public static function mb_detect_encoding($str, $encodingList = null, $strict = false)
269 {
270 if (null === $encodingList) {
271 $encodingList = self::$encodingList;
272 } else {
273 if (!is_array($encodingList)) {
274 $encodingList = array_map('trim', explode(',', $encodingList));
275 }
276 $encodingList = array_map('strtoupper', $encodingList);
277 }
278
279 foreach ($encodingList as $enc) {
280 switch ($enc) {
281 case 'ASCII':
282 if (!preg_match('/[\x80-\xFF]/', $str)) {
283 return $enc;
284 }
285 break;
286
287 case 'UTF8':
288 case 'UTF-8':
289 if (preg_match('//u', $str)) {
290 return 'UTF-8';
291 }
292 break;
293
294 default:
295 if (0 === strncmp($enc, 'ISO-8859-', 9)) {
296 return $enc;
297 }
298 }
299 }
300
301 return false;
302 }
303
304 public static function mb_detect_order($encodingList = null)
305 {
306 if (null === $encodingList) {
307 return self::$encodingList;
308 }
309
310 if (!is_array($encodingList)) {
311 $encodingList = array_map('trim', explode(',', $encodingList));
312 }
313 $encodingList = array_map('strtoupper', $encodingList);
314
315 foreach ($encodingList as $enc) {
316 switch ($enc) {
317 default:
318 if (strncmp($enc, 'ISO-8859-', 9)) {
319 return false;
320 }
321 case 'ASCII':
322 case 'UTF8':
323 case 'UTF-8':
324 }
325 }
326
327 self::$encodingList = $encodingList;
328
329 return true;
330 }
331
332 public static function mb_strlen($s, $encoding = null)
333 {
334 $encoding = self::getEncoding($encoding);
335
336 return iconv_strlen($s, $encoding);
337 }
338
339 public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null)
340 {
341 $encoding = self::getEncoding($encoding);
342
343 if ('' === $needle .= '') {
344 trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING);
345
346 return false;
347 }
348
349 return iconv_strpos($haystack, $needle, $offset, $encoding);
350 }
351
352 public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null)
353 {
354 $encoding = self::getEncoding($encoding);
355
356 if ($offset != (int) $offset) {
357 $offset = 0;
358 } elseif ($offset = (int) $offset) {
359 if ($offset < 0) {
360 $haystack = self::mb_substr($haystack, 0, $offset, $encoding);
361 $offset = 0;
362 } else {
363 $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding);
364 }
365 }
366
367 $pos = iconv_strrpos($haystack, $needle, $encoding);
368
369 return false !== $pos ? $offset + $pos : false;
370 }
371
372 public static function mb_strtolower($s, $encoding = null)
373 {
374 return self::mb_convert_case($s, MB_CASE_LOWER, $encoding);
375 }
376
377 public static function mb_strtoupper($s, $encoding = null)
378 {
379 return self::mb_convert_case($s, MB_CASE_UPPER, $encoding);
380 }
381
382 public static function mb_substitute_character($c = null)
383 {
384 if (0 === strcasecmp($c, 'none')) {
385 return true;
386 }
387
388 return null !== $c ? false : 'none';
389 }
390
391 public static function mb_substr($s, $start, $length = null, $encoding = null)
392 {
393 $encoding = self::getEncoding($encoding);
394
395 if ($start < 0) {
396 $start = iconv_strlen($s, $encoding) + $start;
397 if ($start < 0) {
398 $start = 0;
399 }
400 }
401
402 if (null === $length) {
403 $length = 2147483647;
404 } elseif ($length < 0) {
405 $length = iconv_strlen($s, $encoding) + $length - $start;
406 if ($length < 0) {
407 return '';
408 }
409 }
410
411 return iconv_substr($s, $start, $length, $encoding).'';
412 }
413
414 public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null)
415 {
416 $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
417 $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
418
419 return self::mb_strpos($haystack, $needle, $offset, $encoding);
420 }
421
422 public static function mb_stristr($haystack, $needle, $part = false, $encoding = null)
423 {
424 $pos = self::mb_stripos($haystack, $needle, 0, $encoding);
425
426 return self::getSubpart($pos, $part, $haystack, $encoding);
427 }
428
429 public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null)
430 {
431 $encoding = self::getEncoding($encoding);
432 $needle = self::mb_substr($needle, 0, 1, $encoding);
433 $pos = iconv_strrpos($haystack, $needle, $encoding);
434
435 return self::getSubpart($pos, $part, $haystack, $encoding);
436 }
437
438 public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null)
439 {
440 $needle = self::mb_substr($needle, 0, 1, $encoding);
441 $pos = self::mb_strripos($haystack, $needle, $encoding);
442
443 return self::getSubpart($pos, $part, $haystack, $encoding);
444 }
445
446 public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null)
447 {
448 $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
449 $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
450
451 return self::mb_strrpos($haystack, $needle, $offset, $encoding);
452 }
453
454 public static function mb_strstr($haystack, $needle, $part = false, $encoding = null)
455 {
456 $pos = strpos($haystack, $needle);
457 if (false === $pos) {
458 return false;
459 }
460 if ($part) {
461 return substr($haystack, 0, $pos);
462 }
463
464 return substr($haystack, $pos);
465 }
466
467 public static function mb_get_info($type = 'all')
468 {
469 $info = array(
470 'internal_encoding' => self::$internalEncoding,
471 'http_output' => 'pass',
472 'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)',
473 'func_overload' => 0,
474 'func_overload_list' => 'no overload',
475 'mail_charset' => 'UTF-8',
476 'mail_header_encoding' => 'BASE64',
477 'mail_body_encoding' => 'BASE64',
478 'illegal_chars' => 0,
479 'encoding_translation' => 'Off',
480 'language' => self::$language,
481 'detect_order' => self::$encodingList,
482 'substitute_character' => 'none',
483 'strict_detection' => 'Off',
484 );
485
486 if ('all' === $type) {
487 return $info;
488 }
489 if (isset($info[$type])) {
490 return $info[$type];
491 }
492
493 return false;
494 }
495
496 public static function mb_http_input($type = '')
497 {
498 return false;
499 }
500
501 public static function mb_http_output($encoding = null)
502 {
503 return null !== $encoding ? 'pass' === $encoding : 'pass';
504 }
505
506 public static function mb_strwidth($s, $encoding = null)
507 {
508 $encoding = self::getEncoding($encoding);
509
510 if ('UTF-8' !== $encoding) {
511 $s = iconv($encoding, 'UTF-8', $s);
512 }
513
514 $s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide);
515
516 return ($wide << 1) + iconv_strlen($s, 'UTF-8');
517 }
518
519 public static function mb_substr_count($haystack, $needle, $encoding = null)
520 {
521 return substr_count($haystack, $needle);
522 }
523
524 public static function mb_output_handler($contents, $status)
525 {
526 return $contents;
527 }
528
529 private static function getSubpart($pos, $part, $haystack, $encoding)
530 {
531 if (false === $pos) {
532 return false;
533 }
534 if ($part) {
535 return self::mb_substr($haystack, 0, $pos, $encoding);
536 }
537
538 return self::mb_substr($haystack, $pos, null, $encoding);
539 }
540
541 private static function html_encoding_callback($m)
542 {
543 $i = 1;
544 $entities = '';
545 $m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8'));
546
547 while (isset($m[$i])) {
548 if (0x80 > $m[$i]) {
549 $entities .= chr($m[$i++]);
550 continue;
551 }
552 if (0xF0 <= $m[$i]) {
553 $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
554 } elseif (0xE0 <= $m[$i]) {
555 $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
556 } else {
557 $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
558 }
559
560 $entities .= '&#'.$c.';';
561 }
562
563 return $entities;
564 }
565
566 private static function title_case_lower($s)
567 {
568 return self::mb_convert_case($s[0], MB_CASE_LOWER, 'UTF-8');
569 }
570
571 private static function title_case_upper($s)
572 {
573 return self::mb_convert_case($s[0], MB_CASE_UPPER, 'UTF-8');
574 }
575
576 private static function getData($file)
577 {
578 if (file_exists($file = __DIR__.'/unidata/'.$file.'.ser')) {
579 return unserialize(file_get_contents($file));
580 }
581
582 return false;
583 }
584
585 private static function getEncoding($encoding)
586 {
587 if (null === $encoding) {
588 return self::$internalEncoding;
589 }
590
591 $encoding = strtoupper($encoding);
592
593 if ('8BIT' === $encoding || 'BINARY' === $encoding) {
594 return 'CP850';
595 }
596 if ('UTF8' === $encoding) {
597 return 'UTF-8';
598 }
599
600 return $encoding;
601 }
602 }
603