fork(2) download
copy 
  1. <?php
  2.  
  3. function sentence_split($text) {
  4.     $before_regexes = array('/(?:(?:[\'\"„][\.!?…][\'\"”]\s)|(?:[^\.]\s[A-Z]\.\s)|(?:\b(?:St|Gen|Hon|Vol|Prof|Dr|Mr|Ms|Mrs|[JS]r|Col|Maj|Brig|Sgt|Capt|Cmnd|Sen|Rev|Rep|Revd)\.\s)|(?:\b(?:St|Gen|Hon|Prof|Dr|Mr|Ms|Mrs|[JS]r|Col|Maj|Brig|Sgt|Capt|Cmnd|Sen|Rev|Rep|Revd)\.\s[A-Z]\.\s)|(?:\bApr\.\s)|(?:\bAug\.\s)|(?:\bBros\.\s)|(?:\bCo\.\s)|(?:\bCorp\.\s)|(?:\bDec\.\s)|(?:\bDist\.\s)|(?:\bFeb\.\s)|(?:\bInc\.\s)|(?:\bJan\.\s)|(?:\bJul\.\s)|(?:\bJun\.\s)|(?:\bMar\.\s)|(?:\bNov\.\s)|(?:\bOct\.\s)|(?:\bPh\.?D\.\s)|(?:\bSept?\.\s)|(?:\b\p{Lu}\.\p{Lu}\.\s)|(?:\b\p{Lu}\.\s\p{Lu}\.\s)|(?:\bcf\.\s)|(?:\be\.g\.\s)|(?:\besp\.\s)|(?:\bet\b\s\bal\.\s)|(?:\bvs\.\s)|(?:\p{Ps}[!?]+\p{Pe} ))\Z/mu',
  5.         '/(?:(?:[\.\s]\p{L}{1,2}\.\s))\Z/mu',
  6.         '/(?:(?:[\[\(]*\.\.\.[\]\)]* ))\Z/mu',
  7.         '/(?:(?:\b(?:pp|[Vv]iz|i\.?\s*e|[Vvol]|[Rr]col|maj|Lt|[Ff]ig|[Ff]igs|[Vv]iz|[Vv]ols|[Aa]pprox|[Ii]ncl|Pres|[Dd]ept|min|max|[Gg]ovt|lb|ft|c\.?\s*f|vs)\.\s))\Z/mu',
  8.         '/(?:(?:\b[Ee]tc\.\s))\Z/mu',
  9.         '/(?:(?:[\.!?…]+\p{Pe} )|(?:[\[\(]*…[\]\)]* ))\Z/mu',
  10.         '/(?:(?:\b\p{L}\.))\Z/mu',
  11.         '/(?:(?:\b\p{L}\.\s))\Z/mu',
  12.         '/(?:(?:\b[Ff]igs?\.\s)|(?:\b[nN]o\.\s))\Z/mu',
  13.         '/(?:(?:[\"”\']\s*))\Z/mu',
  14.         '/(?:(?:[\.!?…][\x{00BB}\x{2019}\x{201D}\x{203A}\"\'\p{Pe}\x{0002}]*\s)|(?:\r?\n))\Z/mu',
  15.         '/(?:(?:[\.!?…][\'\"\x{00BB}\x{2019}\x{201D}\x{203A}\p{Pe}\x{0002}]*))\Z/mu',
  16.         '/(?:(?:\s\p{L}[\.!?…]\s))\Z/mu');
  17.     $after_regexes = array('/\A(?:)/mu',
  18.         '/\A(?:[\p{N}\p{Ll}])/mu',
  19.         '/\A(?:[^\p{Lu}])/mu',
  20.         '/\A(?:[^\p{Lu}]|I)/mu',
  21.         '/\A(?:[^p{Lu}])/mu',
  22.         '/\A(?:\p{Ll})/mu',
  23.         '/\A(?:\p{L}\.)/mu',
  24.         '/\A(?:\p{L}\.\s)/mu',
  25.         '/\A(?:\p{N})/mu',
  26.         '/\A(?:\s*\p{Ll})/mu',
  27.         '/\A(?:)/mu',
  28.         '/\A(?:\p{Lu}[^\p{Lu}])/mu',
  29.         '/\A(?:\p{Lu}\p{Ll})/mu');
  30.     $is_sentence_boundary = array(false, false, false, false, false, false, false, false, false, false, true, true, true);
  31.     $count = 13;
  32.  
  33.     $sentences = array();
  34.     $sentence = '';
  35.     $before = '';
  36.     $after = substr($text, 0, 10);
  37.     $text = substr($text, 10);
  38.  
  39.     while($text != '') {
  40.         for($i = 0; $i < $count; $i++) {
  41.             if(preg_match($before_regexes[$i], $before) && preg_match($after_regexes[$i], $after)) {
  42.                 if($is_sentence_boundary[$i]) {
  43.                     array_push($sentences, $sentence);
  44.                     $sentence = '';
  45.                 }
  46.                 break;
  47.             }
  48.         }
  49.  
  50.         $first_from_text = $text[0];
  51.         $text = substr($text, 1);
  52.         $first_from_after = $after[0];
  53.         $after = substr($after, 1);
  54.         $before .= $first_from_after;
  55.         $sentence .= $first_from_after;
  56.         $after .= $first_from_text;
  57.     }
  58.  
  59.     if($sentence != '' && $after != '') {
  60.         array_push($sentences, $sentence.$after);
  61.     }
  62.  
  63.     return $sentences;
  64. }
  65.  
  66. $text = "Entertainment media properties.&Acirc;&nbsp; Fairy Tail and Tokyo Ghoul.";
  67. print_r(sentence_split($text));
  68.  
  69.  
  70.  
  71.  
Success #stdin #stdout 0.03s 52472KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Array
(
    [0] => Entertainment media properties.&Acirc;&nbsp; Fairy Tail and Tokyo Ghoul.
)
https://ideone.com/epdpxO
language:
PHP (php 7.3.5)
created:
8 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!