MediaWiki  master
compareParsers.php
Go to the documentation of this file.
1 <?php
31 require_once __DIR__ . '/dumpIterator.php';
32 
40 
41  private $count = 0;
42 
43  public function __construct() {
44  parent::__construct();
45  $this->saveFailed = false;
46  $this->addDescription( 'Run a file or dump with several parsers' );
47  $this->addOption( 'parser1', 'The first parser to compare.', true, true );
48  $this->addOption( 'parser2', 'The second parser to compare.', true, true );
49  $this->addOption( 'tidy', 'Run tidy on the articles.', false, false );
50  $this->addOption(
51  'save-failed',
52  'Folder in which articles which differ will be stored.',
53  false,
54  true
55  );
56  $this->addOption( 'show-diff', 'Show a diff of the two renderings.', false, false );
57  $this->addOption(
58  'diff-bin',
59  'Binary to use for diffing (can also be provided by DIFF env var).',
60  false,
61  false
62  );
63  $this->addOption(
64  'strip-parameters',
65  'Remove parameters of html tags to increase readability.',
66  false,
67  false
68  );
69  $this->addOption(
70  'show-parsed-output',
71  'Show the parsed html if both Parsers give the same output.',
72  false,
73  false
74  );
75  }
76 
77  public function checkOptions() {
78  if ( $this->hasOption( 'save-failed' ) ) {
79  $this->saveFailed = $this->getOption( 'save-failed' );
80  }
81 
82  $this->stripParametersEnabled = $this->hasOption( 'strip-parameters' );
83  $this->showParsedOutput = $this->hasOption( 'show-parsed-output' );
84 
85  $this->showDiff = $this->hasOption( 'show-diff' );
86  if ( $this->showDiff ) {
87  $bin = $this->getOption( 'diff-bin', getenv( 'DIFF' ) );
88  if ( $bin != '' ) {
89  global $wgDiff;
90  $wgDiff = $bin;
91  }
92  }
93 
94  $user = new User();
96 
97  if ( $this->hasOption( 'tidy' ) ) {
98  if ( !MWTidy::isEnabled() ) {
99  $this->fatalError( 'Tidy was requested but $wgTidyConfig is not set in LocalSettings.php' );
100  }
101  $this->options->setTidy( true );
102  }
103 
104  $this->failed = 0;
105  }
106 
107  public function conclusions() {
108  $this->error( "{$this->failed} failed revisions out of {$this->count}" );
109  if ( $this->count > 0 ) {
110  $this->output( " (" . ( $this->failed / $this->count ) . "%)\n" );
111  }
112  }
113 
114  function stripParameters( $text ) {
115  if ( !$this->stripParametersEnabled ) {
116  return $text;
117  }
118 
119  return preg_replace( '/(<a) [^>]+>/', '$1>', $text );
120  }
121 
126  public function processRevision( $rev ) {
127  $title = $rev->getTitle();
128 
129  $parser1Name = $this->getOption( 'parser1' );
130  $parser2Name = $this->getOption( 'parser2' );
131 
132  self::checkParserLocally( $parser1Name );
133  self::checkParserLocally( $parser2Name );
134 
135  $parser1 = new $parser1Name();
136  $parser2 = new $parser2Name();
137 
138  $content = $rev->getContent();
139 
140  if ( $content->getModel() !== CONTENT_MODEL_WIKITEXT ) {
141  $this->error( "Page {$title->getPrefixedText()} does not contain wikitext "
142  . "but {$content->getModel()}\n" );
143 
144  return;
145  }
146 
147  $text = strval( $content->getText() );
148 
149  $output1 = $parser1->parse( $text, $title, $this->options );
150  $output2 = $parser2->parse( $text, $title, $this->options );
151 
152  if ( $output1->getText() != $output2->getText() ) {
153  $this->failed++;
154  $this->error( "Parsing for {$title->getPrefixedText()} differs\n" );
155 
156  if ( $this->saveFailed ) {
157  file_put_contents(
158  $this->saveFailed . '/' . rawurlencode( $title->getPrefixedText() ) . ".txt",
159  $text
160  );
161  }
162  if ( $this->showDiff ) {
163  $this->output( wfDiff(
164  $this->stripParameters( $output1->getText() ),
165  $this->stripParameters( $output2->getText() ),
166  ''
167  ) );
168  }
169  } else {
170  $this->output( $title->getPrefixedText() . "\tOK\n" );
171 
172  if ( $this->showParsedOutput ) {
173  $this->output( $this->stripParameters( $output1->getText() ) );
174  }
175  }
176  }
177 
178  private static function checkParserLocally( $parserName ) {
179  /* Look for the parser in a file appropiately named in the current folder */
180  if ( !class_exists( $parserName ) && file_exists( "$parserName.php" ) ) {
181  global $wgAutoloadClasses;
182  $wgAutoloadClasses[$parserName] = realpath( '.' ) . "/$parserName.php";
183  }
184  }
185 }
186 
188 require_once RUN_MAINTENANCE_IF_MAIN;
const CONTENT_MODEL_WIKITEXT
Definition: Defines.php:231
error( $err, $die=0)
Throw an error to the user.
processRevision( $rev)
Callback function for each revision, parse with both parsers and compare.
getOption( $name, $default=null)
Get an option, or return the default.
static checkParserLocally( $parserName)
static isEnabled()
Definition: MWTidy.php:54
Maintenance script to take page text out of an XML dump file and render basic HTML out to files...
hasOption( $name)
Checks to see if a particular option exists.
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
$maintClass
addDescription( $text)
Set the description text.
wfDiff( $before, $after, $params='-u')
Returns unified plain-text diff of two texts.
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:925
output( $out, $channel=null)
Throw some output to the user.
Base class for interating over a dump.
presenting them properly to the user as errors is done by the caller return true use this to change the list i e etc $rev
Definition: hooks.txt:1766
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
Using a hook running we can avoid having all this option specific stuff in our mainline code Using the function We ve cleaned up the code here by removing clumps of infrequently used code and moving them off somewhere else It s much easier for someone working with this code to see what s _really_ going and make changes or fix bugs In we can take all the code that deals with the little used title reversing options(say) and put it in one place. Instead of having little title-reversing if-blocks spread all over the codebase in showAnArticle
stripParameters( $text)
you have access to all of the normal MediaWiki so you can get a DB use the etc For full docs on the Maintenance class
Definition: maintenance.txt:52
static newFromUser( $user)
Get a ParserOptions object from a given user.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
$wgAutoloadClasses
Array mapping class names to filenames, for autoloading.
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
$content
Definition: pageupdater.txt:72
$wgDiff
Path to the GNU diff utility.
return true to allow those checks to and false if checking is done & $user
Definition: hooks.txt:1473