MediaWiki  master
grep.php
Go to the documentation of this file.
1 <?php
2 // phpcs:disable MediaWiki.Files.ClassMatchesFilename.NotMatch
7 
8 require_once __DIR__ . '/Maintenance.php';
9 
15 class GrepPages extends Maintenance {
17  private $contLang;
18 
20  private $wikiPageFactory;
21 
22  public function __construct() {
23  parent::__construct();
24  $this->addDescription( 'Search the source text of pages for lines matching ' .
25  'a given regex, and print the lines.' );
26  $this->addOption( 'prefix',
27  'Title prefix. Can be specified more than once. ' .
28  'Use e.g. --prefix=Talk: to search an entire namespace.',
29  false, true, false, true );
30  $this->addOption( 'show-wiki', 'Add the wiki ID to the output' );
31  $this->addOption( 'pages-with-matches',
32  'Suppress normal output; instead print the title of each page ' .
33  'from which output would normally have been printed.',
34  false, false, 'l' );
35  $this->addArg( 'regex', 'The regex to search for' );
36  }
37 
38  private function init() {
39  $services = $this->getServiceContainer();
40  $this->contLang = $services->getContentLanguage();
41  $this->wikiPageFactory = $services->getWikiPageFactory();
42  }
43 
44  public function execute() {
45  $this->init();
46 
47  $showWiki = $this->getOption( 'show-wiki' );
48  $wikiId = WikiMap::getCurrentWikiId();
49  $prefix = $this->getOption( 'prefix' );
50  $regex = $this->getArg( 0 );
51  $titleOnly = $this->hasOption( 'pages-with-matches' );
52 
53  if ( ( $regex[0] ?? '' ) === '/' ) {
54  $delimRegex = $regex[0];
55  } else {
56  $delimRegex = '{' . $regex . '}';
57  }
58 
59  foreach ( $this->findPages( $prefix ) as $page ) {
60  $content = $page->getContent( RevisionRecord::RAW );
61  $titleText = $page->getTitle()->getPrefixedDBkey();
62  if ( !$content ) {
63  $this->error( "Page has no content: $titleText" );
64  continue;
65  }
66  if ( !$content instanceof TextContent ) {
67  $this->error( "Page has a non-text content model: $titleText" );
68  continue;
69  }
70 
71  $text = $content->getText();
72 
73  if ( $titleOnly ) {
74  if ( preg_match( $delimRegex, $text ) ) {
75  if ( $showWiki ) {
76  echo "$wikiId\t$titleText\n";
77  } else {
78  echo "$titleText\n";
79  }
80  }
81  } else {
82  foreach ( StringUtils::explode( "\n", $text ) as $lineNum => $line ) {
83  $lineNum++;
84  if ( preg_match( $delimRegex, $line ) ) {
85  if ( $showWiki ) {
86  echo "$wikiId\t$titleText:$lineNum:$line\n";
87  } else {
88  echo "$titleText:$lineNum:$line\n";
89  }
90  }
91  }
92  }
93  }
94  }
95 
96  public function findPages( $prefixes = null ) {
97  $dbr = $this->getDB( DB_REPLICA );
98  $orConds = [];
99  if ( $prefixes !== null ) {
100  foreach ( $prefixes as $prefix ) {
101  $colonPos = strpos( $prefix, ':' );
102  if ( $colonPos !== false ) {
103  $ns = $this->contLang->getNsIndex( substr( $prefix, 0, $colonPos ) );
104  $prefixDBkey = substr( $prefix, $colonPos + 1 );
105  } else {
106  $ns = NS_MAIN;
107  $prefixDBkey = $prefix;
108  }
109  $prefixCond = [ 'page_namespace' => $ns ];
110  if ( $prefixDBkey !== '' ) {
111  $prefixCond[] = 'page_title ' . $dbr->buildLike( $prefixDBkey, $dbr->anyString() );
112  }
113  $orConds[] = $dbr->makeList( $prefixCond, LIST_AND );
114  }
115  }
116 
117  $conds = $orConds ? $dbr->makeList( $orConds, LIST_OR ) : [];
118  $pageQuery = WikiPage::getQueryInfo();
119 
120  $res = $dbr->newSelectQueryBuilder()
121  ->queryInfo( $pageQuery )
122  ->where( $conds )
123  ->caller( __METHOD__ )
124  ->fetchResultSet();
125  foreach ( $res as $row ) {
126  $title = Title::newFromRow( $row );
127  yield $this->wikiPageFactory->newFromTitle( $title );
128  }
129  }
130 }
131 
132 $maintClass = GrepPages::class;
133 require_once RUN_MAINTENANCE_IF_MAIN;
const NS_MAIN
Definition: Defines.php:64
const LIST_OR
Definition: Defines.php:46
const LIST_AND
Definition: Defines.php:43
Search pages for a given regex.
Definition: grep.php:15
execute()
Do the actual work.
Definition: grep.php:44
findPages( $prefixes=null)
Definition: grep.php:96
__construct()
Default constructor.
Definition: grep.php:22
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: Maintenance.php:66
getDB( $db, $groups=[], $dbDomain=false)
Returns a database to be used by current maintenance script.
error( $err, $die=0)
Throw an error to the user.
addArg( $arg, $description, $required=true, $multi=false)
Add some args that are needed.
hasOption( $name)
Checks to see if a particular option was set.
getServiceContainer()
Returns the main service container.
getArg( $argId=0, $default=null)
Get an argument.
addDescription( $text)
Set the description text.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
getOption( $name, $default=null)
Get an option, or return the default.
Service for creating WikiPage objects.
Page revision base class.
Represents a title within MediaWiki.
Definition: Title.php:76
Tools for dealing with other locally-hosted wikis.
Definition: WikiMap.php:31
static explode( $separator, $subject)
Workalike for explode() with limited memory usage.
Content object implementation for representing flat text.
Definition: TextContent.php:41
static getQueryInfo()
Return the tables, fields, and join conditions to be selected to create a new page object.
Definition: WikiPage.php:316
$maintClass
Definition: grep.php:132
const DB_REPLICA
Definition: defines.php:26
$content
Definition: router.php:76