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         /**
  31          * Constructor.
  32          */
  33         public function __construct() {
  34                 $this->cache = ObjectCache::newAccelerator( 'hash' );
  35         }
  36
  37         /**
  38          * Get the singleton instance of this class.
  39          *
  40          * @return FileContentsHasher
  41          */
  42         public static function singleton() {
  43                 if ( !self::$instance ) {
  44                         self::$instance = new self;
  45                 }
  46
  47                 return self::$instance;
  48         }
  49
  50         /**
  51          * Get a hash of a file's contents, either by retrieving a previously-
  52          * computed hash from the cache, or by computing a hash from the file.
  53          *
  54          * @private
  55          * @param string $filePath Full path to the file.
  56          * @param string $algo Name of selected hashing algorithm.
  57          * @return string|bool Hash of file contents, or false if the file could not be read.
  58          */
  59         public function getFileContentsHashInternal( $filePath, $algo = 'md4' ) {
  60                 $mtime = MediaWiki\quietCall( 'filemtime', $filePath );
  61                 if ( $mtime === false ) {
  62                         return false;
  63                 }
  64
  65                 $cacheKey = wfGlobalCacheKey( __CLASS__, $filePath, $mtime, $algo );
  66                 $hash = $this->cache->get( $cacheKey );
  67
  68                 if ( $hash ) {
  69                         return $hash;
  70                 }
  71
  72                 $contents = MediaWiki\quietCall( 'file_get_contents', $filePath );
  73                 if ( $contents === false ) {
  74                         return false;
  75                 }
  76
  77                 $hash = hash( $algo, $contents );
  78                 $this->cache->set( $cacheKey, $hash, 60 * 60 * 24 );  // 24h
  79
  80                 return $hash;
  81         }
  82
  83         /**
  84          * Get a hash of the combined contents of one or more files, either by
  85          * retrieving a previously-computed hash from the cache, or by computing
  86          * a hash from the files.
  87          *
  88          * @param string|string[] $filePaths One or more file paths.
  89          * @param string $algo Name of selected hashing algorithm.
  90          * @return string|bool Hash of files' contents, or false if no file could not be read.
  91          */
  92         public static function getFileContentsHash( $filePaths, $algo = 'md4' ) {
  93                 $instance = self::singleton();
  94
  95                 if ( !is_array( $filePaths ) ) {
  96                         $filePaths = (array)$filePaths;
  97                 }
  98
  99                 if ( count( $filePaths ) === 1 ) {
 100                         return $instance->getFileContentsHashInternal( $filePaths[0], $algo );
 101                 }
 102
 103                 sort( $filePaths );
 104                 $hashes = array_map( function ( $filePath ) use ( $instance, $algo ) {
 105                         return $instance->getFileContentsHashInternal( $filePath, $algo ) ?: '';
 106                 }, $filePaths );
 107
 108                 $hashes = implode( '', $hashes );
 109                 return $hashes ? hash( $algo, $hashes ) : false;
 110         }
 111 }