includes/utils/FileContentsHasher.php

   1 <?php
   2 /**
   3  * Generate hash digests of file contents to help with cache invalidation.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  */
  22 class FileContentsHasher {
  23
  24         /** @var BagOStuff */
  25         protected $cache;
  26
  27         /** @var FileContentsHasher */
  28         private static $instance;
  29
  30         public function __construct() {
  31                 $this->cache = ObjectCache::getLocalServerInstance( 'hash' );
  32         }
  33
  34         /**
  35          * Get the singleton instance of this class.
  36          *
  37          * @return FileContentsHasher
  38          */
  39         public static function singleton() {
  40                 if ( !self::$instance ) {
  41                         self::$instance = new self;
  42                 }
  43
  44                 return self::$instance;
  45         }
  46
  47         /**
  48          * Get a hash of a file's contents, either by retrieving a previously-
  49          * computed hash from the cache, or by computing a hash from the file.
  50          *
  51          * @private
  52          * @param string $filePath Full path to the file.
  53          * @param string $algo Name of selected hashing algorithm.
  54          * @return string|bool Hash of file contents, or false if the file could not be read.
  55          */
  56         public function getFileContentsHashInternal( $filePath, $algo = 'md4' ) {
  57                 $mtime = filemtime( $filePath );
  58                 if ( $mtime === false ) {
  59                         return false;
  60                 }
  61
  62                 $cacheKey = $this->cache->makeGlobalKey( __CLASS__, $filePath, $mtime, $algo );
  63                 $hash = $this->cache->get( $cacheKey );
  64
  65                 if ( $hash ) {
  66                         return $hash;
  67                 }
  68
  69                 $contents = file_get_contents( $filePath );
  70                 if ( $contents === false ) {
  71                         return false;
  72                 }
  73
  74                 $hash = hash( $algo, $contents );
  75                 $this->cache->set( $cacheKey, $hash, 60 * 60 * 24 );  // 24h
  76
  77                 return $hash;
  78         }
  79
  80         /**
  81          * Get a hash of the combined contents of one or more files, either by
  82          * retrieving a previously-computed hash from the cache, or by computing
  83          * a hash from the files.
  84          *
  85          * @param string|string[] $filePaths One or more file paths.
  86          * @param string $algo Name of selected hashing algorithm.
  87          * @return string|bool Hash of files' contents, or false if no file could not be read.
  88          */
  89         public static function getFileContentsHash( $filePaths, $algo = 'md4' ) {
  90                 $instance = self::singleton();
  91
  92                 if ( !is_array( $filePaths ) ) {
  93                         $filePaths = (array)$filePaths;
  94                 }
  95
  96                 MediaWiki\suppressWarnings();
  97
  98                 if ( count( $filePaths ) === 1 ) {
  99                         $hash = $instance->getFileContentsHashInternal( $filePaths[0], $algo );
 100                         MediaWiki\restoreWarnings();
 101                         return $hash;
 102                 }
 103
 104                 sort( $filePaths );
 105                 $hashes = array_map( function ( $filePath ) use ( $instance, $algo ) {
 106                         return $instance->getFileContentsHashInternal( $filePath, $algo ) ?: '';
 107                 }, $filePaths );
 108
 109                 MediaWiki\restoreWarnings();
 110
 111                 $hashes = implode( '', $hashes );
 112                 return $hashes ? hash( $algo, $hashes ) : false;
 113         }
 114 }