includes/parser/MWTidy.php

   1 <?php
   2 /**
   3  * HTML validation and correction
   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  * @ingroup Parser
  22  */
  23
  24 /**
  25  * Class to interact with HTML tidy
  26  *
  27  * Either the external tidy program or the in-process tidy extension
  28  * will be used depending on availability. Override the default
  29  * $wgTidyInternal setting to disable the internal if it's not working.
  30  *
  31  * @ingroup Parser
  32  */
  33 class MWTidy {
  34         private static $instance;
  35
  36         /**
  37          * Interface with html tidy.
  38          * If tidy isn't able to correct the markup, the original will be
  39          * returned in all its glory with a warning comment appended.
  40          *
  41          * @param string $text HTML input fragment. This should not contain a
  42          *                     <body> or <html> tag.
  43          * @return string Corrected HTML output
  44          */
  45         public static function tidy( $text ) {
  46                 $driver = self::singleton();
  47                 if ( !$driver ) {
  48                         throw new MWException( __METHOD__ .
  49                                 ': tidy is disabled, caller should have checked MWTidy::isEnabled()' );
  50                 }
  51                 return $driver->tidy( $text );
  52         }
  53
  54         /**
  55          * Check HTML for errors, used if $wgValidateAllHtml = true.
  56          *
  57          * @param string $text
  58          * @param string &$errorStr Return the error string
  59          * @return bool Whether the HTML is valid
  60          */
  61         public static function checkErrors( $text, &$errorStr = null ) {
  62                 $driver = self::singleton();
  63                 if ( !$driver ) {
  64                         throw new MWException( __METHOD__ .
  65                                 ': tidy is disabled, caller should have checked MWTidy::isEnabled()' );
  66                 }
  67                 if ( $driver->supportsValidate() ) {
  68                         return $driver->validate( $text, $errorStr );
  69                 } else {
  70                         throw new MWException( __METHOD__ . ": error text return from HHVM tidy is not supported" );
  71                 }
  72         }
  73
  74         public static function isEnabled() {
  75                 return self::singleton() !== false;
  76         }
  77
  78         protected static function singleton() {
  79                 global $wgUseTidy, $wgTidyInternal, $wgTidyConf, $wgDebugTidy, $wgTidyConfig,
  80                         $wgTidyBin, $wgTidyOpts;
  81
  82                 if ( self::$instance === null ) {
  83                         if ( $wgTidyConfig !== null ) {
  84                                 $config = $wgTidyConfig;
  85                         } elseif ( $wgUseTidy ) {
  86                                 // b/c configuration
  87                                 $config = [
  88                                         'tidyConfigFile' => $wgTidyConf,
  89                                         'debugComment' => $wgDebugTidy,
  90                                         'tidyBin' => $wgTidyBin,
  91                                         'tidyCommandLine' => $wgTidyOpts ];
  92                                 if ( $wgTidyInternal ) {
  93                                         if ( wfIsHHVM() ) {
  94                                                 $config['driver'] = 'RaggettInternalHHVM';
  95                                         } else {
  96                                                 $config['driver'] = 'RaggettInternalPHP';
  97                                         }
  98                                 } else {
  99                                         $config['driver'] = 'RaggettExternal';
 100                                 }
 101                         } else {
 102                                 return false;
 103                         }
 104                         self::$instance = self::factory( $config );
 105                 }
 106                 return self::$instance;
 107         }
 108
 109         /**
 110          * Create a new Tidy driver object from configuration.
 111          * @see $wgTidyConfig
 112          * @param array $config
 113          * @return TidyDriverBase
 114          */
 115         public static function factory( array $config ) {
 116                 switch ( $config['driver'] ) {
 117                         case 'RaggettInternalHHVM':
 118                                 $instance = new MediaWiki\Tidy\RaggettInternalHHVM( $config );
 119                                 break;
 120                         case 'RaggettInternalPHP':
 121                                 $instance = new MediaWiki\Tidy\RaggettInternalPHP( $config );
 122                                 break;
 123                         case 'RaggettExternal':
 124                                 $instance = new MediaWiki\Tidy\RaggettExternal( $config );
 125                                 break;
 126                         case 'Html5Depurate':
 127                                 $instance = new MediaWiki\Tidy\Html5Depurate( $config );
 128                                 break;
 129                         case 'Html5Internal':
 130                                 $instance = new MediaWiki\Tidy\Html5Internal( $config );
 131                                 break;
 132                         case 'disabled':
 133                                 return false;
 134                         default:
 135                                 throw new MWException( "Invalid tidy driver: \"{$config['driver']}\"" );
 136                 }
 137                 return $instance;
 138         }
 139
 140         /**
 141          * Set the driver to be used. This is for testing.
 142          * @param TidyDriverBase|false|null $instance
 143          */
 144         public static function setInstance( $instance ) {
 145                 self::$instance = $instance;
 146         }
 147
 148         /**
 149          * Destroy the current singleton instance
 150          */
 151         public static function destroySingleton() {
 152                 self::$instance = null;
 153         }
 154 }