includes/diff/WordLevelDiff.php

   1 <?php
   2 /**
   3  * Copyright © 2000, 2001 Geoffrey T. Dairiki <dairiki@dairiki.org>
   4  * You may copy this code freely under the conditions of the GPL.
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License along
  17  * with this program; if not, write to the Free Software Foundation, Inc.,
  18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19  * http://www.gnu.org/copyleft/gpl.html
  20  *
  21  * @file
  22  * @ingroup DifferenceEngine
  23  * @defgroup DifferenceEngine DifferenceEngine
  24  */
  25
  26 use MediaWiki\Diff\ComplexityException;
  27 use MediaWiki\Diff\WordAccumulator;
  28
  29 /**
  30  * Performs a word-level diff on several lines
  31  *
  32  * @ingroup DifferenceEngine
  33  */
  34 class WordLevelDiff extends \Diff {
  35         /**
  36          * @inheritdoc
  37          */
  38         protected $bailoutComplexity = 40000000; // Roughly 6K x 6K words changed
  39
  40         /**
  41          * @param string[] $linesBefore
  42          * @param string[] $linesAfter
  43          */
  44         public function __construct( $linesBefore, $linesAfter ) {
  45                 list( $wordsBefore, $wordsBeforeStripped ) = $this->split( $linesBefore );
  46                 list( $wordsAfter, $wordsAfterStripped ) = $this->split( $linesAfter );
  47
  48                 try {
  49                         parent::__construct( $wordsBeforeStripped, $wordsAfterStripped );
  50                 } catch ( ComplexityException $ex ) {
  51                         // Too hard to diff, just show whole paragraph(s) as changed
  52                         $this->edits = [ new DiffOpChange( $linesBefore, $linesAfter ) ];
  53                 }
  54
  55                 $xi = $yi = 0;
  56                 $editCount = count( $this->edits );
  57                 for ( $i = 0; $i < $editCount; $i++ ) {
  58                         $orig = &$this->edits[$i]->orig;
  59                         if ( is_array( $orig ) ) {
  60                                 $orig = array_slice( $wordsBefore, $xi, count( $orig ) );
  61                                 $xi += count( $orig );
  62                         }
  63
  64                         $closing = &$this->edits[$i]->closing;
  65                         if ( is_array( $closing ) ) {
  66                                 $closing = array_slice( $wordsAfter, $yi, count( $closing ) );
  67                                 $yi += count( $closing );
  68                         }
  69                 }
  70         }
  71
  72         /**
  73          * @param string[] $lines
  74          *
  75          * @return array[]
  76          */
  77         private function split( $lines ) {
  78                 $words = [];
  79                 $stripped = [];
  80                 $first = true;
  81                 foreach ( $lines as $line ) {
  82                         if ( $first ) {
  83                                 $first = false;
  84                         } else {
  85                                 $words[] = "\n";
  86                                 $stripped[] = "\n";
  87                         }
  88                         $m = [];
  89                         if ( preg_match_all( '/ ( [^\S\n]+ | [0-9_A-Za-z\x80-\xff]+ | . ) (?: (?!< \n) [^\S\n])? /xs',
  90                                 $line, $m ) ) {
  91                                 foreach ( $m[0] as $word ) {
  92                                         $words[] = $word;
  93                                 }
  94                                 foreach ( $m[1] as $stripped_word ) {
  95                                         $stripped[] = $stripped_word;
  96                                 }
  97                         }
  98                 }
  99
 100                 return [ $words, $stripped ];
 101         }
 102
 103         /**
 104          * @return string[]
 105          */
 106         public function orig() {
 107                 $orig = new WordAccumulator;
 108
 109                 foreach ( $this->edits as $edit ) {
 110                         if ( $edit->type == 'copy' ) {
 111                                 $orig->addWords( $edit->orig );
 112                         } elseif ( $edit->orig ) {
 113                                 $orig->addWords( $edit->orig, 'del' );
 114                         }
 115                 }
 116                 $lines = $orig->getLines();
 117
 118                 return $lines;
 119         }
 120
 121         /**
 122          * @return string[]
 123          */
 124         public function closing() {
 125                 $closing = new WordAccumulator;
 126
 127                 foreach ( $this->edits as $edit ) {
 128                         if ( $edit->type == 'copy' ) {
 129                                 $closing->addWords( $edit->closing );
 130                         } elseif ( $edit->closing ) {
 131                                 $closing->addWords( $edit->closing, 'ins' );
 132                         }
 133                 }
 134                 $lines = $closing->getLines();
 135
 136                 return $lines;
 137         }
 138
 139 }