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
  46                 list( $wordsBefore, $wordsBeforeStripped ) = $this->split( $linesBefore );
  47                 list( $wordsAfter, $wordsAfterStripped ) = $this->split( $linesAfter );
  48
  49                 try {
  50                         parent::__construct( $wordsBeforeStripped, $wordsAfterStripped );
  51                 } catch ( ComplexityException $ex ) {
  52                         // Too hard to diff, just show whole paragraph(s) as changed
  53                         $this->edits = [ new DiffOpChange( $linesBefore, $linesAfter ) ];
  54                 }
  55
  56                 $xi = $yi = 0;
  57                 $editCount = count( $this->edits );
  58                 for ( $i = 0; $i < $editCount; $i++ ) {
  59                         $orig = &$this->edits[$i]->orig;
  60                         if ( is_array( $orig ) ) {
  61                                 $orig = array_slice( $wordsBefore, $xi, count( $orig ) );
  62                                 $xi += count( $orig );
  63                         }
  64
  65                         $closing = &$this->edits[$i]->closing;
  66                         if ( is_array( $closing ) ) {
  67                                 $closing = array_slice( $wordsAfter, $yi, count( $closing ) );
  68                                 $yi += count( $closing );
  69                         }
  70                 }
  71
  72         }
  73
  74         /**
  75          * @param string[] $lines
  76          *
  77          * @return array[]
  78          */
  79         private function split( $lines ) {
  80
  81                 $words = [];
  82                 $stripped = [];
  83                 $first = true;
  84                 foreach ( $lines as $line ) {
  85                         if ( $first ) {
  86                                 $first = false;
  87                         } else {
  88                                 $words[] = "\n";
  89                                 $stripped[] = "\n";
  90                         }
  91                         $m = [];
  92                         if ( preg_match_all( '/ ( [^\S\n]+ | [0-9_A-Za-z\x80-\xff]+ | . ) (?: (?!< \n) [^\S\n])? /xs',
  93                                 $line, $m ) ) {
  94                                 foreach ( $m[0] as $word ) {
  95                                         $words[] = $word;
  96                                 }
  97                                 foreach ( $m[1] as $stripped_word ) {
  98                                         $stripped[] = $stripped_word;
  99                                 }
 100                         }
 101                 }
 102
 103                 return [ $words, $stripped ];
 104         }
 105
 106         /**
 107          * @return string[]
 108          */
 109         public function orig() {
 110                 $orig = new WordAccumulator;
 111
 112                 foreach ( $this->edits as $edit ) {
 113                         if ( $edit->type == 'copy' ) {
 114                                 $orig->addWords( $edit->orig );
 115                         } elseif ( $edit->orig ) {
 116                                 $orig->addWords( $edit->orig, 'del' );
 117                         }
 118                 }
 119                 $lines = $orig->getLines();
 120
 121                 return $lines;
 122         }
 123
 124         /**
 125          * @return string[]
 126          */
 127         public function closing() {
 128                 $closing = new WordAccumulator;
 129
 130                 foreach ( $this->edits as $edit ) {
 131                         if ( $edit->type == 'copy' ) {
 132                                 $closing->addWords( $edit->closing );
 133                         } elseif ( $edit->closing ) {
 134                                 $closing->addWords( $edit->closing, 'ins' );
 135                         }
 136                 }
 137                 $lines = $closing->getLines();
 138
 139                 return $lines;
 140         }
 141
 142 }