Sākums Izpētīt Palīdzība
Reģistrēties Pierakstīties
oleg
/
pixelfed
spogulis no https://github.com/pixelfed/pixelfed.git
1
0
Atdalīts 0
Faili Problēmas 0 Vikivietne
Koks: a0e15d89e2
Atzari Tagi
pixelfed
/
app
/
Util
/
Lexer
/
Regex.php

Regex.php 23 KB
Vēsture Neapstrādāts

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336 
  1. <?php
    2. 

  2. 

  3. /**
    4. 

  4.  * @author     Mike Cochrane <mikec@mikenz.geek.nz>
    5. 

  5.  * @author     Nick Pope <nick@nickpope.me.uk>
    6. 

  6.  * @copyright  Copyright © 2010, Mike Cochrane, Nick Pope
    7. 

  7.  * @license    http://www.apache.org/licenses/LICENSE-2.0  Apache License v2.0
    8. 

  8.  */
    9. 

  9. 

  10. namespace App\Util\Lexer;
    11. 

  11. 

  12. /**
    13. 

  13.  * Twitter Regex Abstract Class.
    14. 

  14.  *
    15. 

  15.  * Used by subclasses that need to parse tweets.
    16. 

  16.  *
    17. 

  17.  * Originally written by {@link http://github.com/mikenz Mike Cochrane}, this
    18. 

  18.  * is based on code by {@link http://github.com/mzsanford Matt Sanford} and
    19. 

  19.  * heavily modified by {@link http://github.com/ngnpope Nick Pope}.
    20. 

  20.  *
    21. 

  21.  * @author     Mike Cochrane <mikec@mikenz.geek.nz>
    22. 

  22.  * @author     Nick Pope <nick@nickpope.me.uk>
    23. 

  23.  * @copyright  Copyright © 2010, Mike Cochrane, Nick Pope
    24. 

  24.  * @license    http://www.apache.org/licenses/LICENSE-2.0  Apache License v2.0
    25. 

  25.  */
    26. 

  26. abstract class Regex
    27. 

  27. {
    28. 

  28.     /**
    29. 

  29.      * Contains all generated regular expressions.
    30. 

  30.      *
    31. 

  31.      * @var string The regex patterns.
    32. 

  32.      */
    33. 

  33.     protected static $patterns = [];
    34. 

  34. 

  35.     /**
    36. 

  36.      * The tweet to be used in parsing.  This should be populated by the
    37. 

  37.      * constructor of all subclasses.
    38. 

  38.      *
    39. 

  39.      * @var string
    40. 

  40.      */
    41. 

  41.     protected $tweet = '';
    42. 

  42. 

  43.     /**
    44. 

  44.      * This constructor is used to populate some variables.
    45. 

  45.      *
    46. 

  46.      * @param string $tweet The tweet to parse.
    47. 

  47.      */
    48. 

  48.     protected function __construct($tweet = null)
    49. 

  49.     {
    50. 

  50.         $this->tweet = $tweet;
    51. 

  51.     }
    52. 

  52. 

  53.     /**
    54. 

  54.      * Emulate a static initialiser while PHP doesn't have one.
    55. 

  55.      */
    56. 

  56.     public static function __static()
    57. 

  57.     {
    58. 

  58.         // Check whether we have initialized the regular expressions:
    59. 

  59.         static $initialized = false;
    60. 

  60.         if ($initialized) {
    61. 

  61.             return;
    62. 

  62.         }
    63. 

  63.         // Get a shorter reference to the regular expression array:
    64. 

  64.         $re = &self::$patterns;
    65. 

  65.         // Initialise local storage arrays:
    66. 

  66.         $tmp = [];
    67. 

  67. 

  68.         // Expression to match whitespace characters.
    69. 

  69.         //
    70. 

  70.         //   0x0009-0x000D  Cc # <control-0009>..<control-000D>
    71. 

  71.         //   0x0020         Zs # SPACE
    72. 

  72.         //   0x0085         Cc # <control-0085>
    73. 

  73.         //   0x00A0         Zs # NO-BREAK SPACE
    74. 

  74.         //   0x1680         Zs # OGHAM SPACE MARK
    75. 

  75.         //   0x180E         Zs # MONGOLIAN VOWEL SEPARATOR
    76. 

  76.         //   0x2000-0x200A  Zs # EN QUAD..HAIR SPACE
    77. 

  77.         //   0x2028         Zl # LINE SEPARATOR
    78. 

  78.         //   0x2029         Zp # PARAGRAPH SEPARATOR
    79. 

  79.         //   0x202F         Zs # NARROW NO-BREAK SPACE
    80. 

  80.         //   0x205F         Zs # MEDIUM MATHEMATICAL SPACE
    81. 

  81.         //   0x3000         Zs # IDEOGRAPHIC SPACE
    82. 

  82.         $tmp['spaces'] = '\x{0009}-\x{000D}\x{0020}\x{0085}\x{00a0}\x{1680}\x{180E}\x{2000}-\x{200a}\x{2028}\x{2029}\x{202f}\x{205f}\x{3000}';
    83. 

  83. 

  84.         // Invalid Characters:
    85. 

  85.         //   0xFFFE,0xFEFF # BOM
    86. 

  86.         //   0xFFFF        # Special
    87. 

  87.         //   0x202A-0x202E # Directional change
    88. 

  88.         $tmp['invalid_characters'] = '\x{202a}-\x{202e}\x{feff}\x{fffe}\x{ffff}';
    89. 

  89. 

  90.         // Expression to match at and hash sign characters:
    91. 

  91.         $tmp['at_signs'] = '@＠';
    92. 

  92.         $tmp['hash_signs'] = '#＃';
    93. 

  93. 

  94.         // Expression to match latin accented characters.
    95. 

  95.         //
    96. 

  96.         //   0x00C0-0x00D6
    97. 

  97.         //   0x00D8-0x00F6
    98. 

  98.         //   0x00F8-0x00FF
    99. 

  99.         //   0x0100-0x024f
    100. 

  100.         //   0x0253-0x0254
    101. 

  101.         //   0x0256-0x0257
    102. 

  102.         //   0x0259
    103. 

  103.         //   0x025b
    104. 

  104.         //   0x0263
    105. 

  105.         //   0x0268
    106. 

  106.         //   0x026f
    107. 

  107.         //   0x0272
    108. 

  108.         //   0x0289
    109. 

  109.         //   0x028b
    110. 

  110.         //   0x02bb
    111. 

  111.         //   0x0300-0x036f
    112. 

  112.         //   0x1e00-0x1eff
    113. 

  113.         //
    114. 

  114.         // Excludes 0x00D7 - multiplication sign (confusable with 'x').
    115. 

  115.         // Excludes 0x00F7 - division sign.
    116. 

  116.         $tmp['latin_accents'] = '\x{00c0}-\x{00d6}\x{00d8}-\x{00f6}\x{00f8}-\x{00ff}';
    117. 

  117.         $tmp['latin_accents'] .= '\x{0100}-\x{024f}\x{0253}-\x{0254}\x{0256}-\x{0257}';
    118. 

  118.         $tmp['latin_accents'] .= '\x{0259}\x{025b}\x{0263}\x{0268}\x{026f}\x{0272}\x{0289}\x{028b}\x{02bb}\x{0300}-\x{036f}\x{1e00}-\x{1eff}';
    119. 

  119. 

  120.         // Expression to match RTL characters.
    121. 

  121.         //
    122. 

  122.         //   0x0600-0x06FF Arabic
    123. 

  123.         //   0x0750-0x077F Arabic Supplement
    124. 

  124.         //   0x08A0-0x08FF Arabic Extended-A
    125. 

  125.         //   0x0590-0x05FF Hebrew
    126. 

  126.         //   0xFB50-0xFDFF Arabic Presentation Forms-A
    127. 

  127.         //   0xFE70-0xFEFF Arabic Presentation Forms-B
    128. 

  128.         $tmp['rtl_chars'] = '\x{0600}-\x{06ff}\x{0750}-\x{077f}\x{08a0}-\x{08ff}\x{0590}-\x{05ff}\x{fb50}-\x{fdff}\x{fe70}-\x{feff}';
    129. 

  129. 

  130.         $tmp['hashtag_letters'] = '\p{L}\p{M}';
    131. 

  131.         $tmp['hashtag_numerals'] = '\p{Nd}';
    132. 

  132.         // Hashtag special chars
    133. 

  133.         //
    134. 

  134.         //   _      underscore
    135. 

  135.         //   0x200c ZERO WIDTH NON-JOINER (ZWNJ)
    136. 

  136.         //   0x200d ZERO WIDTH JOINER (ZWJ)
    137. 

  137.         //   0xa67e CYRILLIC KAVYKA
    138. 

  138.         //   0x05be HEBREW PUNCTUATION MAQAF
    139. 

  139.         //   0x05f3 HEBREW PUNCTUATION GERESH
    140. 

  140.         //   0x05f4 HEBREW PUNCTUATION GERSHAYIM
    141. 

  141.         //   0xff5e FULLWIDTH TILDE
    142. 

  142.         //   0x301c WAVE DASH
    143. 

  143.         //   0x309b KATAKANA-HIRAGANA VOICED SOUND MARK
    144. 

  144.         //   0x309c KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
    145. 

  145.         //   0x30a0 KATAKANA-HIRAGANA DOUBLE HYPHEN
    146. 

  146.         //   0x30fb KATAKANA MIDDLE DOT
    147. 

  147.         //   0x3003 DITTO MARK
    148. 

  148.         //   0x0f0b TIBETAN MARK INTERSYLLABIC TSHEG
    149. 

  149.         //   0x0f0c TIBETAN MARK DELIMITER TSHEG BSTAR
    150. 

  150.         //   0x00b7 MIDDLE DOT
    151. 

  151.         $tmp['hashtag_special_chars'] = '_\x{200c}\x{200d}\x{a67e}\x{05be}\x{05f3}\x{05f4}\x{ff5e}\x{301c}\x{309b}\x{309c}\x{30a0}\x{30fb}\x{3003}\x{0f0b}\x{0f0c}\x{00b7}';
    152. 

  152.         $tmp['hashtag_letters_numerals_set'] = '['.$tmp['hashtag_letters'].$tmp['hashtag_numerals'].$tmp['hashtag_special_chars'].']';
    153. 

  153.         $tmp['hashtag_letters_set'] = '['.$tmp['hashtag_letters'].']';
    154. 

  154.         $tmp['hashtag_boundary'] = '(?:\A|\x{fe0e}|\x{fe0f}|[^&'.$tmp['hashtag_letters'].$tmp['hashtag_numerals'].$tmp['hashtag_special_chars'].'])';
    155. 

  155.         $tmp['hashtag'] = '('.$tmp['hashtag_boundary'].')(#|\x{ff03})(?!\x{fe0f}|\x{20e3})('.$tmp['hashtag_letters_numerals_set'].'*'.$tmp['hashtag_letters_set'].$tmp['hashtag_letters_numerals_set'].'*)';
    156. 

  156. 

  157.         $re['valid_hashtag'] = '/'.$tmp['hashtag'].'(?=(.*|$))/iu';
    158. 

  158.         $re['end_hashtag_match'] = '/\A(?:['.$tmp['hash_signs'].']|:\/\/)/u';
    159. 

  159. 

  160.         // XXX: PHP doesn't have Ruby's $' (dollar apostrophe) so we have to capture
    161. 

  161.         //      $after in the following regular expression.  Note that we only use a
    162. 

  162.         //      look-ahead capture here and don't append $after when we return.
    163. 

  163.         $tmp['valid_mention_preceding_chars'] = '([^a-zA-Z0-9_!#\$%&*@＠\/]|^|(?:^|[^a-z0-9_+~.-])RT:?)';
    164. 

  164. 

  165.         $re['valid_mentions_or_lists'] = '/'.$tmp['valid_mention_preceding_chars'].'(['.$tmp['at_signs'].'])([a-z0-9_\-.]{1,20})((\/[a-z][a-z0-9_\-]{0,24})?(?=(.*|$))(?:@[a-z0-9\.\-]+[a-z0-9]+)?)/i';
    166. 

  166. 

  167.         $re['valid_reply'] = '/^(?:['.$tmp['spaces'].'])*['.$tmp['at_signs'].']([a-z0-9_\-.]{1,20})(?=(.*|$))/iu';
    168. 

  168.         $re['end_mention_match'] = '/\A(?:['.$tmp['at_signs'].']|['.$tmp['latin_accents'].']|:\/\/)/iu';
    169. 

  169. 

  170.         // URL related hash regex collection
    171. 

  171. 

  172.         $tmp['valid_url_preceding_chars'] = '(?:[^A-Z0-9_@＠\$#＃\.'.$tmp['invalid_characters'].']|^)';
    173. 

  173. 

  174.         $tmp['domain_valid_chars'] = '0-9a-z'.$tmp['latin_accents'];
    175. 

  175.         $tmp['valid_subdomain'] = '(?>(?:['.$tmp['domain_valid_chars'].']['.$tmp['domain_valid_chars'].'\-_]*)?['.$tmp['domain_valid_chars'].']\.)';
    176. 

  176.         $tmp['valid_domain_name'] = '(?:(?:['.$tmp['domain_valid_chars'].']['.$tmp['domain_valid_chars'].'\-]*)?['.$tmp['domain_valid_chars'].']\.)';
    177. 

  177.         $tmp['domain_valid_unicode_chars'] = '[^\p{P}\p{Z}\p{C}'.$tmp['invalid_characters'].$tmp['spaces'].']';
    178. 

  178. 

  179.         $gTLD = 'abb|abbott|abogado|academy|accenture|accountant|accountants|aco|active|actor|ads|adult|aeg|aero|afl|agency|aig|airforce|airtel|allfinanz|alsace|amsterdam|android|apartments|app|aquarelle|archi|army|arpa|asia|associates|attorney|auction|audio|auto|autos|axa|azure|band|bank|bar|barcelona|barclaycard|barclays|bargains|bauhaus|bayern|bbc|bbva|bcn|beer|bentley|berlin|best|bet|bharti|bible|bid|bike|bing|bingo|bio|biz|black|blackfriday|bloomberg|blue|bmw|bnl|bnpparibas|boats|bond|boo|boots|boutique|bradesco|bridgestone|broker|brother|brussels|budapest|build|builders|business|buzz|bzh|cab|cafe|cal|camera|camp|cancerresearch|canon|capetown|capital|caravan|cards|care|career|careers|cars|cartier|casa|cash|casino|cat|catering|cba|cbn|ceb|center|ceo|cern|cfa|cfd|chanel|channel|chat|cheap|chloe|christmas|chrome|church|cisco|citic|city|claims|cleaning|click|clinic|clothing|cloud|club|coach|codes|coffee|college|cologne|com|commbank|community|company|computer|condos|construction|consulting|contractors|cooking|cool|coop|corsica|country|coupons|courses|credit|creditcard|cricket|crown|crs|cruises|cuisinella|cymru|cyou|dabur|dad|dance|date|dating|datsun|day|dclk|deals|degree|delivery|delta|democrat|dental|dentist|desi|design|dev|diamonds|diet|digital|direct|directory|discount|dnp|docs|dog|doha|domains|doosan|download|drive|durban|dvag|earth|eat|edu|education|email|emerck|energy|engineer|engineering|enterprises|epson|equipment|erni|esq|estate|eurovision|eus|events|everbank|exchange|expert|exposed|express|fage|fail|faith|family|fan|fans|farm|fashion|feedback|film|finance|financial|firmdale|fish|fishing|fit|fitness|flights|florist|flowers|flsmidth|fly|foo|football|forex|forsale|forum|foundation|frl|frogans|fund|furniture|futbol|fyi|gal|gallery|game|garden|gbiz|gdn|gent|genting|ggee|gift|gifts|gives|giving|glass|gle|global|globo|gmail|gmo|gmx|gold|goldpoint|golf|goo|goog|google|gop|gov|graphics|gratis|green|gripe|group|guge|guide|guitars|guru|hamburg|hangout|haus|healthcare|help|here|hermes|hiphop|hitachi|hiv|hockey|holdings|holiday|homedepot|homes|honda|horse|host|hosting|hoteles|hotmail|house|how|hsbc|ibm|icbc|ice|icu|ifm|iinet|immo|immobilien|industries|infiniti|info|ing|ink|institute|insure|int|international|investments|ipiranga|irish|ist|istanbul|itau|iwc|java|jcb|jetzt|jewelry|jlc|jll|jobs|joburg|jprs|juegos|kaufen|kddi|kim|kitchen|kiwi|koeln|komatsu|krd|kred|kyoto|lacaixa|lancaster|land|lasalle|lat|latrobe|law|lawyer|lds|lease|leclerc|legal|lexus|lgbt|liaison|lidl|life|lighting|limited|limo|link|live|lixil|loan|loans|lol|london|lotte|lotto|love|ltda|lupin|luxe|luxury|madrid|maif|maison|man|management|mango|market|marketing|markets|marriott|mba|media|meet|melbourne|meme|memorial|men|menu|miami|microsoft|mil|mini|mma|mobi|moda|moe|mom|monash|money|montblanc|mormon|mortgage|moscow|motorcycles|mov|movie|movistar|mtn|mtpc|museum|nadex|nagoya|name|navy|nec|net|netbank|network|neustar|new|news|nexus|ngo|nhk|nico|ninja|nissan|nokia|nra|nrw|ntt|nyc|office|okinawa|omega|one|ong|onl|online|ooo|oracle|orange|org|organic|osaka|otsuka|ovh|page|panerai|paris|partners|parts|party|pet|pharmacy|philips|photo|photography|photos|physio|piaget|pics|pictet|pictures|pink|pizza|place|play|plumbing|plus|pohl|poker|porn|post|praxi|press|pro|prod|productions|prof|properties|property|pub|qpon|quebec|racing|realtor|realty|recipes|red|redstone|rehab|reise|reisen|reit|ren|rent|rentals|repair|report|republican|rest|restaurant|review|reviews|rich|ricoh|rio|rip|rocks|rodeo|rsvp|ruhr|run|ryukyu|saarland|sakura|sale|samsung|sandvik|sandvikcoromant|sanofi|sap|sarl|saxo|sca|scb|schmidt|scholarships|school|schule|schwarz|science|scor|scot|seat|seek|sener|services|sew|sex|sexy|shiksha|shoes|show|shriram|singles|site|ski|sky|skype|sncf|soccer|social|software|sohu|solar|solutions|sony|soy|space|spiegel|spreadbetting|srl|starhub|statoil|studio|study|style|sucks|supplies|supply|support|surf|surgery|suzuki|swatch|swiss|sydney|systems|taipei|tatamotors|tatar|tattoo|tax|taxi|team|tech|technology|tel|telefonica|temasek|tennis|thd|theater|tickets|tienda|tips|tires|tirol|today|tokyo|tools|top|toray|toshiba|tours|town|toyota|toys|trade|trading|training|travel|trust|tui|ubs|university|uno|uol|vacations|vegas|ventures|vermögensberater|vermögensberatung|versicherung|vet|viajes|video|villas|vin|vision|vista|vistaprint|vlaanderen|vodka|vote|voting|voto|voyage|wales|walter|wang|watch|webcam|website|wed|wedding|weir|whoswho|wien|wiki|williamhill|win|windows|wine|wme|work|works|world|wtc|wtf|xbox|xerox|xin|xperia|xxx|xyz|yachts|yandex|yodobashi|yoga|yokohama|youtube|zip|zone|zuerich|дети|ком|москва|онлайн|орг|рус|сайт|קום|بازار|شبكة|كوم|موقع|कॉम|नेट|संगठन|คอม|みんな|グーグル|コム|世界|中信|中文网|企业|佛山|信息|健康|八卦|公司|公益|商城|商店|商标|在线|大拿|娱乐|工行|广东|慈善|我爱你|手机|政务|政府|新闻|时尚|机构|淡马锡|游戏|点看|移动|组织机构|网址|网店|网络|谷歌|集团|飞利浦|餐厅|닷넷|닷컴|삼성|onion';
    180. 

  180.         $ccTLD = '한국|香港|澳門|新加坡|台灣|台湾|中國|中国|გე|ไทย|ලංකා|ഭാരതം|ಭಾರತ|భారత్|சிங்கப்பூர்|இலங்கை|இந்தியா|ଭାରତ|ભારત|ਭਾਰਤ|ভাৰত|ভারত|বাংলা|भारोत|भारतम्|भारत|ڀارت|پاکستان|مليسيا|مصر|قطر|فلسطين|عمان|عراق|سورية|سودان|تونس|بھارت|بارت|ایران|امارات|المغرب|السعودية|الجزائر|الاردن|հայ|қаз|укр|срб|рф|мон|мкд|ею|бел|бг|ελ|zw|zm|za|yt|ye|ws|wf|vu|vn|vi|vg|ve|vc|va|uz|uy|us|um|uk|ug|ua|tz|tw|tv|tt|tr|tp|to|tn|tm|tl|tk|tj|th|tg|tf|td|tc|sz|sy|sx|sv|su|st|ss|sr|so|sn|sm|sl|sk|sj|si|sh|sg|se|sd|sc|sb|sa|rw|ru|rs|ro|re|qa|py|pw|pt|ps|pr|pn|pm|pl|pk|ph|pg|pf|pe|pa|om|nz|nu|nr|np|no|nl|ni|ng|nf|ne|nc|na|mz|my|mx|mw|mv|mu|mt|ms|mr|mq|mp|mo|mn|mm|ml|mk|mh|mg|mf|me|md|mc|ma|ly|lv|lu|lt|ls|lr|lk|li|lc|lb|la|kz|ky|kw|kr|kp|kn|km|ki|kh|kg|ke|jp|jo|jm|je|it|is|ir|iq|io|in|im|il|ie|id|hu|ht|hr|hn|hm|hk|gy|gw|gu|gt|gs|gr|gq|gp|gn|gm|gl|gi|gh|gg|gf|ge|gd|gb|ga|fr|fo|fm|fk|fj|fi|eu|et|es|er|eh|eg|ee|ec|dz|do|dm|dk|dj|de|cz|cy|cx|cw|cv|cu|cr|co|cn|cm|cl|ck|ci|ch|cg|cf|cd|cc|ca|bz|by|bw|bv|bt|bs|br|bq|bo|bn|bm|bl|bj|bi|bh|bg|bf|be|bd|bb|ba|az|ax|aw|au|at|as|ar|aq|ao|an|am|al|ai|ag|af|ae|ad|ac';
    181. 

  181. 

  182.         $tmp['valid_gTLD'] = '(?:(?:'.$gTLD.')(?=[^0-9a-z@]|$))';
    183. 

  183.         $tmp['valid_ccTLD'] = '(?:(?:'.$ccTLD.')(?=[^0-9a-z@]|$))';
    184. 

  184.         $tmp['valid_special_ccTLD'] = '(?:(?:'.'co|tv'.')(?=[^0-9a-z@]|$))';
    185. 

  185.         $tmp['valid_punycode'] = '(?:xn--[0-9a-z]+)';
    186. 

  186. 

  187.         $tmp['valid_domain'] = '(?:'                                            // subdomains + domain + TLD
    188. 

  188.             .$tmp['valid_subdomain'].'+'.$tmp['valid_domain_name']         // e.g. www.twitter.com, foo.co.jp, bar.co.uk
    189. 

  189.             .'(?:'.$tmp['valid_gTLD'].'|'.$tmp['valid_ccTLD'].'|'.$tmp['valid_punycode'].'))'
    190. 

  190.             .'|(?:'                                                                // domain + gTLD | some ccTLD
    191. 

  191.             .$tmp['valid_domain_name']                                         // e.g. twitter.com
    192. 

  192.             .'(?:'.$tmp['valid_gTLD'].'|'.$tmp['valid_punycode'].'|'.$tmp['valid_special_ccTLD'].')'
    193. 

  193.             .')'
    194. 

  194.             .'|(?:(?:(?<=http:\/\/)|(?<=https:\/\/))'
    195. 

  195.             .'(?:'
    196. 

  196.             .'(?:'.$tmp['valid_domain_name'].$tmp['valid_ccTLD'].')' // protocol + domain + ccTLD
    197. 

  197.             .'|(?:'                                                                // protocol + unicode domain + TLD
    198. 

  198.             .$tmp['domain_valid_unicode_chars'].'+\.'
    199. 

  199.             .'(?:'.$tmp['valid_gTLD'].'|'.$tmp['valid_ccTLD'].')'
    200. 

  200.             .')'
    201. 

  201.             .')'
    202. 

  202.             .')'
    203. 

  203.             .'|(?:'                                                                // domain + ccTLD + '/'
    204. 

  204.             .$tmp['valid_domain_name'].$tmp['valid_ccTLD'].'(?=\/)'            // e.g. t.co/
    205. 

  205.             .')';
    206. 

  206.         // Used by the extractor:
    207. 

  207.         $re['valid_ascii_domain'] = '/'.$tmp['valid_subdomain'].'*'.$tmp['valid_domain_name'].'(?:'.$tmp['valid_gTLD'].'|'.$tmp['valid_ccTLD'].'|'.$tmp['valid_punycode'].')/iu';
    208. 

  208. 

  209.         // Used by the extractor for stricter t.co URL extraction:
    210. 

  210.         $re['valid_tco_url'] = '/^https?:\/\/t\.co\/[a-z0-9]+/iu';
    211. 

  211. 

  212.         // Used by the extractor to filter out unwanted URLs:
    213. 

  213.         $re['invalid_short_domain'] = '/\A'.$tmp['valid_domain_name'].$tmp['valid_ccTLD'].'\Z/iu';
    214. 

  214.         $re['valid_special_short_domain'] = '/\A'.$tmp['valid_domain_name'].$tmp['valid_special_ccTLD'].'\Z/iu';
    215. 

  215.         $re['invalid_url_without_protocol_preceding_chars'] = '/[\-_.\/]\z/iu';
    216. 

  216. 

  217.         $tmp['valid_port_number'] = '[0-9]+';
    218. 

  218. 

  219.         $tmp['valid_general_url_path_chars'] = '[a-z\p{Cyrillic}0-9!\*;:=\+\,\.\$\/%#\[\]\-_~&|@'.$tmp['latin_accents'].']';
    220. 

  220.         // Allow URL paths to contain up to two nested levels of balanced parentheses:
    221. 

  221.         // 1. Used in Wikipedia URLs, e.g. /Primer_(film)
    222. 

  222.         // 2. Used in IIS sessions, e.g. /S(dfd346)/
    223. 

  223.         // 3. Used in Rdio URLs like /track/We_Up_(Album_Version_(Edited))/
    224. 

  224.         $tmp['valid_url_balanced_parens'] = '(?:\('
    225. 

  225.             .'(?:'.$tmp['valid_general_url_path_chars'].'+'
    226. 

  226.             .'|'
    227. 

  227.             // allow one nested level of balanced parentheses
    228. 

  228.             .'(?:'
    229. 

  229.             .$tmp['valid_general_url_path_chars'].'*'
    230. 

  230.             .'\('.$tmp['valid_general_url_path_chars'].'+'.'\)'
    231. 

  231.             .$tmp['valid_general_url_path_chars'].'*'
    232. 

  232.             .')'
    233. 

  233.             .')'
    234. 

  234.             .'\))';
    235. 

  235.         // Valid end-of-path characters (so /foo. does not gobble the period).
    236. 

  236.         // 1. Allow =&# for empty URL parameters and other URL-join artifacts.
    237. 

  237.         $tmp['valid_url_path_ending_chars'] = '[a-z\p{Cyrillic}0-9=_#\/\+\-'.$tmp['latin_accents'].']|(?:'.$tmp['valid_url_balanced_parens'].')';
    238. 

  238.         $tmp['valid_url_path'] = '(?:(?:'
    239. 

  239.             .$tmp['valid_general_url_path_chars'].'*(?:'
    240. 

  240.             .$tmp['valid_url_balanced_parens'].' '
    241. 

  241.             .$tmp['valid_general_url_path_chars'].'*)*'
    242. 

  242.             .$tmp['valid_url_path_ending_chars'].')|(?:@'
    243. 

  243.             .$tmp['valid_general_url_path_chars'].'+\/))';
    244. 

  244. 

  245.         $tmp['valid_url_query_chars'] = '[a-z0-9!?\*\'\(\);:&=\+\$\/%#\[\]\-_\.,~|@]';
    246. 

  246.         $tmp['valid_url_query_ending_chars'] = '[a-z0-9_&=#\/\-]';
    247. 

  247. 

  248.         $re['valid_url'] = '/(?:'                           // $1 Complete match (preg_match() already matches everything.)
    249. 

  249.             .'('.$tmp['valid_url_preceding_chars'].')' // $2 Preceding characters
    250. 

  250.             .'('                                           // $3 Complete URL
    251. 

  251.             .'(https?:\/\/)?'                              // $4 Protocol (optional)
    252. 

  252.             .'('.$tmp['valid_domain'].')'              // $5 Domain(s)
    253. 

  253.             .'(?::('.$tmp['valid_port_number'].'))?'   // $6 Port number (optional)
    254. 

  254.             .'(\/'.$tmp['valid_url_path'].'*)?'        // $7 URL Path
    255. 

  255.             .'(\?'.$tmp['valid_url_query_chars'].'*'.$tmp['valid_url_query_ending_chars'].')?' // $8 Query String
    256. 

  256.             .')'
    257. 

  257.             .')/iux';
    258. 

  258. 

  259.         $tmp['cash_signs'] = '\$';
    260. 

  260.         $tmp['cashtag'] = '[a-z]{1,6}(?:[._][a-z]{1,2})?';
    261. 

  261.         $re['valid_cashtag'] = '/(^|['.$tmp['spaces'].'])(['.$tmp['cash_signs'].'])('.$tmp['cashtag'].')(?=($|\s|[[:punct:]]))/iu';
    262. 

  262.         $re['end_cashtag_match'] = '/\A(?:['.$tmp['cash_signs'].']|:\/\/)/u';
    263. 

  263. 

  264.         // These URL validation pattern strings are based on the ABNF from RFC 3986
    265. 

  265.         $tmp['validate_url_unreserved'] = '[a-z\p{Cyrillic}0-9\-._~]';
    266. 

  266.         $tmp['validate_url_pct_encoded'] = '(?:%[0-9a-f]{2})';
    267. 

  267.         $tmp['validate_url_sub_delims'] = '[!$&\'()*+,;=]';
    268. 

  268.         $tmp['validate_url_pchar'] = '(?:'.$tmp['validate_url_unreserved'].'|'.$tmp['validate_url_pct_encoded'].'|'.$tmp['validate_url_sub_delims'].'|[:\|@])'; ///iox
    269. 

  269. 

  270.         $tmp['validate_url_userinfo'] = '(?:'.$tmp['validate_url_unreserved'].'|'.$tmp['validate_url_pct_encoded'].'|'.$tmp['validate_url_sub_delims'].'|:)*'; ///iox
    271. 

  271. 

  272.         $tmp['validate_url_dec_octet'] = '(?:[0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])'; ///i
    273. 

  273.         $tmp['validate_url_ipv4'] = '(?:'.$tmp['validate_url_dec_octet'].'(?:\.'.$tmp['validate_url_dec_octet'].'){3})'; ///iox
    274. 

  274.         // Punting on real IPv6 validation for now
    275. 

  275.         $tmp['validate_url_ipv6'] = '(?:\[[a-f0-9:\.]+\])'; ///i
    276. 

  276.         // Also punting on IPvFuture for now
    277. 

  277.         $tmp['validate_url_ip'] = '(?:'.$tmp['validate_url_ipv4'].'|'.$tmp['validate_url_ipv6'].')'; ///iox
    278. 

  278.         // This is more strict than the rfc specifies
    279. 

  279.         $tmp['validate_url_subdomain_segment'] = '(?:[a-z0-9](?:[a-z0-9_\-]*[a-z0-9])?)'; ///i
    280. 

  280.         $tmp['validate_url_domain_segment'] = '(?:[a-z0-9](?:[a-z0-9\-]*[a-z0-9])?)'; ///i
    281. 

  281.         $tmp['validate_url_domain_tld'] = '(?:[a-z](?:[a-z0-9\-]*[a-z0-9])?)'; ///i
    282. 

  282.         $tmp['validate_url_domain'] = '(?:(?:'.$tmp['validate_url_subdomain_segment'].'\.)*(?:'.$tmp['validate_url_domain_segment'].'\.)'.$tmp['validate_url_domain_tld'].')'; ///iox
    283. 

  283. 

  284.         $tmp['validate_url_host'] = '(?:'.$tmp['validate_url_ip'].'|'.$tmp['validate_url_domain'].')'; ///iox
    285. 

  285.         // Unencoded internationalized domains - this doesn't check for invalid UTF-8 sequences
    286. 

  286.         $tmp['validate_url_unicode_subdomain_segment'] = '(?:(?:[a-z0-9]|[^\x00-\x7f])(?:(?:[a-z0-9_\-]|[^\x00-\x7f])*(?:[a-z0-9]|[^\x00-\x7f]))?)'; ///ix
    287. 

  287.         $tmp['validate_url_unicode_domain_segment'] = '(?:(?:[a-z0-9]|[^\x00-\x7f])(?:(?:[a-z0-9\-]|[^\x00-\x7f])*(?:[a-z0-9]|[^\x00-\x7f]))?)'; ///ix
    288. 

  288.         $tmp['validate_url_unicode_domain_tld'] = '(?:(?:[a-z]|[^\x00-\x7f])(?:(?:[a-z0-9\-]|[^\x00-\x7f])*(?:[a-z0-9]|[^\x00-\x7f]))?)'; ///ix
    289. 

  289.         $tmp['validate_url_unicode_domain'] = '(?:(?:'.$tmp['validate_url_unicode_subdomain_segment'].'\.)*(?:'.$tmp['validate_url_unicode_domain_segment'].'\.)'.$tmp['validate_url_unicode_domain_tld'].')'; ///iox
    290. 

  290. 

  291.         $tmp['validate_url_unicode_host'] = '(?:'.$tmp['validate_url_ip'].'|'.$tmp['validate_url_unicode_domain'].')'; ///iox
    292. 

  292. 

  293.         $tmp['validate_url_port'] = '[0-9]{1,5}';
    294. 

  294. 

  295.         $re['validate_url_unicode_authority'] = '/'
    296. 

  296.             .'(?:('.$tmp['validate_url_userinfo'].')@)?' //  $1 userinfo
    297. 

  297.             .'('.$tmp['validate_url_unicode_host'].')'   //  $2 host
    298. 

  298.             .'(?::('.$tmp['validate_url_port'].'))?'     //  $3 port
    299. 

  299.             .'/iux';
    300. 

  300. 

  301.         $re['validate_url_authority'] = '/'
    302. 

  302.             .'(?:('.$tmp['validate_url_userinfo'].')@)?' //  $1 userinfo
    303. 

  303.             .'('.$tmp['validate_url_host'].')'           //  $2 host
    304. 

  304.             .'(?::('.$tmp['validate_url_port'].'))?'     //  $3 port
    305. 

  305.             .'/ix';
    306. 

  306. 

  307.         $re['validate_url_scheme'] = '/(?:[a-z][a-z0-9+\-.]*)/i';
    308. 

  308.         $re['validate_url_path'] = '/(\/'.$tmp['validate_url_pchar'].'*)*/iu';
    309. 

  309.         $re['validate_url_query'] = '/('.$tmp['validate_url_pchar'].'|\/|\?)*/iu';
    310. 

  310.         $re['validate_url_fragment'] = '/('.$tmp['validate_url_pchar'].'|\/|\?)*/iu';
    311. 

  311. 

  312.         // Modified version of RFC 3986 Appendix B
    313. 

  313.         $re['validate_url_unencoded'] = '/^' //  Full URL
    314. 

  314.             .'(?:'
    315. 

  315.             .'([^:\/?#]+):\/\/' //  $1 Scheme
    316. 

  316.             .')?'
    317. 

  317.             .'([^\/?#]*)'       //  $2 Authority
    318. 

  318.             .'([^?#]*)'         //  $3 Path
    319. 

  319.             .'(?:'
    320. 

  320.             .'\?([^#]*)'        //  $4 Query
    321. 

  321.             .')?'
    322. 

  322.             .'(?:'
    323. 

  323.             .'\#(.*)'           //  $5 Fragment
    324. 

  324.             .')?$/iux';
    325. 

  325. 

  326.         $re['invalid_characters'] = '/['.$tmp['invalid_characters'].']/u';
    327. 

  327. 

  328.         $re['rtl_chars'] = '/['.$tmp['rtl_chars'].']/iu';
    329. 

  329. 

  330.         // Flag that initialization is complete:
    331. 

  331.         $initialized = true;
    332. 

  332.     }
    333. 

  333. }
    334. 

  334. 

  335. // Cause regular expressions to be initialized as soon as this file is loaded:
    336. 

  336. Regex::__static();
    337.