MediaWiki  REL1_31
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 != '' ) {
90  $wgDiff = $bin;
91  }
92  }
93 
94  $user = new User();
96 
97  if ( $this->hasOption( 'tidy' ) ) {
99  if ( !$wgUseTidy ) {
100  $this->fatalError( 'Tidy was requested but $wgUseTidy is not set in LocalSettings.php' );
101  }
102  $this->options->setTidy( true );
103  }
104 
105  $this->failed = 0;
106  }
107 
108  public function conclusions() {
109  $this->error( "{$this->failed} failed revisions out of {$this->count}" );
110  if ( $this->count > 0 ) {
111  $this->output( " (" . ( $this->failed / $this->count ) . "%)\n" );
112  }
113  }
114 
115  function stripParameters( $text ) {
116  if ( !$this->stripParametersEnabled ) {
117  return $text;
118  }
119 
120  return preg_replace( '/(<a) [^>]+>/', '$1>', $text );
121  }
122 
127  public function processRevision( $rev ) {
128  $title = $rev->getTitle();
129 
130  $parser1Name = $this->getOption( 'parser1' );
131  $parser2Name = $this->getOption( 'parser2' );
132 
133  self::checkParserLocally( $parser1Name );
134  self::checkParserLocally( $parser2Name );
135 
136  $parser1 = new $parser1Name();
137  $parser2 = new $parser2Name();
138 
139  $content = $rev->getContent();
140 
141  if ( $content->getModel() !== CONTENT_MODEL_WIKITEXT ) {
142  $this->error( "Page {$title->getPrefixedText()} does not contain wikitext "
143  . "but {$content->getModel()}\n" );
144 
145  return;
146  }
147 
148  $text = strval( $content->getNativeData() );
149 
150  $output1 = $parser1->parse( $text, $title, $this->options );
151  $output2 = $parser2->parse( $text, $title, $this->options );
152 
153  if ( $output1->getText() != $output2->getText() ) {
154  $this->failed++;
155  $this->error( "Parsing for {$title->getPrefixedText()} differs\n" );
156 
157  if ( $this->saveFailed ) {
158  file_put_contents(
159  $this->saveFailed . '/' . rawurlencode( $title->getPrefixedText() ) . ".txt",
160  $text
161  );
162  }
163  if ( $this->showDiff ) {
164  $this->output( wfDiff(
165  $this->stripParameters( $output1->getText() ),
166  $this->stripParameters( $output2->getText() ),
167  ''
168  ) );
169  }
170  } else {
171  $this->output( $title->getPrefixedText() . "\tOK\n" );
172 
173  if ( $this->showParsedOutput ) {
174  $this->output( $this->stripParameters( $output1->getText() ) );
175  }
176  }
177  }
178 
179  private static function checkParserLocally( $parserName ) {
180  /* Look for the parser in a file appropiately named in the current folder */
181  if ( !class_exists( $parserName ) && file_exists( "$parserName.php" ) ) {
183  $wgAutoloadClasses[$parserName] = realpath( '.' ) . "/$parserName.php";
184  }
185  }
186 }
187 
189 require_once RUN_MAINTENANCE_IF_MAIN;
$user
please add to it if you re going to add events to the MediaWiki code where normally authentication against an external auth plugin would be creating a account $user
Definition: hooks.txt:247
CompareParsers\$count
$count
Definition: compareParsers.php:41
CompareParsers\checkOptions
checkOptions()
Definition: compareParsers.php:77
wfDiff
wfDiff( $before, $after, $params='-u')
Returns unified plain-text diff of two texts.
Definition: GlobalFunctions.php:2442
CompareParsers\stripParameters
stripParameters( $text)
Definition: compareParsers.php:115
CompareParsers\checkParserLocally
static checkParserLocally( $parserName)
Definition: compareParsers.php:179
Maintenance\fatalError
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
Definition: Maintenance.php:439
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:291
$wgDiff
$wgDiff
Path to the GNU diff utility.
Definition: DefaultSettings.php:6615
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
User
User
Definition: All_system_messages.txt:425
CONTENT_MODEL_WIKITEXT
const CONTENT_MODEL_WIKITEXT
Definition: Defines.php:245
php
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:37
CompareParsers\conclusions
conclusions()
Definition: compareParsers.php:108
$maintClass
$maintClass
Definition: compareParsers.php:188
CompareParsers\__construct
__construct()
Default constructor.
Definition: compareParsers.php:43
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:219
CompareParsers\processRevision
processRevision( $rev)
Callback function for each revision, parse with both parsers and compare.
Definition: compareParsers.php:127
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:964
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:95
options
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
$wgUseTidy
$wgUseTidy
Set this to true to use the deprecated tidy configuration parameters.
Definition: DefaultSettings.php:4303
$wgAutoloadClasses
$wgAutoloadClasses
Array mapping class names to filenames, for autoloading.
Definition: DefaultSettings.php:7350
DumpIterator
Base class for interating over a dump.
Definition: dumpIterator.php:36
$rev
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:1777
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:254
CompareParsers
Maintenance script to take page text out of an XML dump file and render basic HTML out to files.
Definition: compareParsers.php:39
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:416
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:388
class
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:56
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular param exists.
Definition: Maintenance.php:240
ParserOptions\newFromUser
static newFromUser( $user)
Get a ParserOptions object from a given user.
Definition: ParserOptions.php:978