MediaWiki  master
WikiExporter.php
Go to the documentation of this file.
1 <?php
32 
36 class WikiExporter {
38  public $list_authors = false;
39 
41  public $dumpUploads = false;
42 
44  public $dumpUploadFileContents = false;
45 
47  public $author_list = "";
48 
49  const FULL = 1;
50  const CURRENT = 2;
51  const STABLE = 4; // extension defined
52  const LOGS = 8;
53  const RANGE = 16;
54 
55  const BUFFER = 0;
56  const STREAM = 1;
57 
58  const TEXT = 0;
59  const STUB = 1;
60 
62  public $buffer;
63 
65  public $text;
66 
68  public $sink;
69 
74  public static function schemaVersion() {
75  return "0.10";
76  }
77 
94  function __construct( $db, $history = self::CURRENT,
95  $buffer = self::BUFFER, $text = self::TEXT ) {
96  $this->db = $db;
97  $this->history = $history;
98  $this->buffer = $buffer;
99  $this->writer = new XmlDumpWriter();
100  $this->sink = new DumpOutput();
101  $this->text = $text;
102  }
103 
111  public function setOutputSink( &$sink ) {
112  $this->sink =& $sink;
113  }
114 
115  public function openStream() {
116  $output = $this->writer->openStream();
117  $this->sink->writeOpenStream( $output );
118  }
119 
120  public function closeStream() {
121  $output = $this->writer->closeStream();
122  $this->sink->writeCloseStream( $output );
123  }
124 
130  public function allPages() {
131  $this->dumpFrom( '' );
132  }
133 
142  public function pagesByRange( $start, $end, $orderRevs ) {
143  if ( $orderRevs ) {
144  $condition = 'rev_page >= ' . intval( $start );
145  if ( $end ) {
146  $condition .= ' AND rev_page < ' . intval( $end );
147  }
148  } else {
149  $condition = 'page_id >= ' . intval( $start );
150  if ( $end ) {
151  $condition .= ' AND page_id < ' . intval( $end );
152  }
153  }
154  $this->dumpFrom( $condition, $orderRevs );
155  }
156 
164  public function revsByRange( $start, $end ) {
165  $condition = 'rev_id >= ' . intval( $start );
166  if ( $end ) {
167  $condition .= ' AND rev_id < ' . intval( $end );
168  }
169  $this->dumpFrom( $condition );
170  }
171 
175  public function pageByTitle( $title ) {
176  $this->dumpFrom(
177  'page_namespace=' . $title->getNamespace() .
178  ' AND page_title=' . $this->db->addQuotes( $title->getDBkey() ) );
179  }
180 
185  public function pageByName( $name ) {
187  if ( is_null( $title ) ) {
188  throw new MWException( "Can't export invalid title" );
189  } else {
190  $this->pageByTitle( $title );
191  }
192  }
193 
197  public function pagesByName( $names ) {
198  foreach ( $names as $name ) {
199  $this->pageByName( $name );
200  }
201  }
202 
203  public function allLogs() {
204  $this->dumpFrom( '' );
205  }
206 
211  public function logsByRange( $start, $end ) {
212  $condition = 'log_id >= ' . intval( $start );
213  if ( $end ) {
214  $condition .= ' AND log_id < ' . intval( $end );
215  }
216  $this->dumpFrom( $condition );
217  }
218 
226  protected function do_list_authors( $cond ) {
227  $this->author_list = "<contributors>";
228  // rev_deleted
229 
230  $revQuery = Revision::getQueryInfo( [ 'page' ] );
231  $res = $this->db->select(
232  $revQuery['tables'],
233  [
234  'rev_user_text' => $revQuery['fields']['rev_user_text'],
235  'rev_user' => $revQuery['fields']['rev_user'],
236  ],
237  [
238  $this->db->bitAnd( 'rev_deleted', Revision::DELETED_USER ) . ' = 0',
239  $cond,
240  ],
241  __METHOD__,
242  [ 'DISTINCT' ],
243  $revQuery['joins']
244  );
245 
246  foreach ( $res as $row ) {
247  $this->author_list .= "<contributor>" .
248  "<username>" .
249  htmlentities( $row->rev_user_text ) .
250  "</username>" .
251  "<id>" .
252  $row->rev_user .
253  "</id>" .
254  "</contributor>";
255  }
256  $this->author_list .= "</contributors>";
257  }
258 
265  protected function dumpFrom( $cond = '', $orderRevs = false ) {
266  # For logging dumps...
267  if ( $this->history & self::LOGS ) {
268  $where = [];
269  # Hide private logs
270  $hideLogs = LogEventsList::getExcludeClause( $this->db );
271  if ( $hideLogs ) {
272  $where[] = $hideLogs;
273  }
274  # Add on any caller specified conditions
275  if ( $cond ) {
276  $where[] = $cond;
277  }
278  # Get logging table name for logging.* clause
279  $logging = $this->db->tableName( 'logging' );
280 
281  if ( $this->buffer == self::STREAM ) {
282  $prev = $this->db->bufferResults( false );
283  }
284  $result = null; // Assuring $result is not undefined, if exception occurs early
285 
286  $commentQuery = CommentStore::getStore()->getJoin( 'log_comment' );
287  $actorQuery = ActorMigration::newMigration()->getJoin( 'log_user' );
288 
289  try {
290  $result = $this->db->select(
291  array_merge( [ 'logging' ], $commentQuery['tables'], $actorQuery['tables'], [ 'user' ] ),
292  [ "{$logging}.*", 'user_name' ] + $commentQuery['fields'] + $actorQuery['fields'],
293  $where,
294  __METHOD__,
295  [ 'ORDER BY' => 'log_id', 'USE INDEX' => [ 'logging' => 'PRIMARY' ] ],
296  [
297  'user' => [ 'JOIN', 'user_id = ' . $actorQuery['fields']['log_user'] ]
298  ] + $commentQuery['joins'] + $actorQuery['joins']
299  );
300  $this->outputLogStream( $result );
301  if ( $this->buffer == self::STREAM ) {
302  $this->db->bufferResults( $prev );
303  }
304  } catch ( Exception $e ) {
305  // Throwing the exception does not reliably free the resultset, and
306  // would also leave the connection in unbuffered mode.
307 
308  // Freeing result
309  try {
310  if ( $result ) {
311  $result->free();
312  }
313  } catch ( Exception $e2 ) {
314  // Already in panic mode -> ignoring $e2 as $e has
315  // higher priority
316  }
317 
318  // Putting database back in previous buffer mode
319  try {
320  if ( $this->buffer == self::STREAM ) {
321  $this->db->bufferResults( $prev );
322  }
323  } catch ( Exception $e2 ) {
324  // Already in panic mode -> ignoring $e2 as $e has
325  // higher priority
326  }
327 
328  // Inform caller about problem
329  throw $e;
330  }
331  # For page dumps...
332  } else {
333  $revOpts = [ 'page' ];
334  if ( $this->text != self::STUB ) {
335  $revOpts[] = 'text';
336  }
337  $revQuery = Revision::getQueryInfo( $revOpts );
338 
339  // We want page primary rather than revision
340  $tables = array_merge( [ 'page' ], array_diff( $revQuery['tables'], [ 'page' ] ) );
341  $join = $revQuery['joins'] + [
342  'revision' => $revQuery['joins']['page']
343  ];
344  unset( $join['page'] );
345 
346  $fields = array_merge( $revQuery['fields'], [ 'page_restrictions' ] );
347 
348  $conds = [];
349  if ( $cond !== '' ) {
350  $conds[] = $cond;
351  }
352  $opts = [ 'ORDER BY' => 'page_id ASC' ];
353  $opts['USE INDEX'] = [];
354  if ( is_array( $this->history ) ) {
355  # Time offset/limit for all pages/history...
356  # Set time order
357  if ( $this->history['dir'] == 'asc' ) {
358  $op = '>';
359  $opts['ORDER BY'] = 'rev_timestamp ASC';
360  } else {
361  $op = '<';
362  $opts['ORDER BY'] = 'rev_timestamp DESC';
363  }
364  # Set offset
365  if ( !empty( $this->history['offset'] ) ) {
366  $conds[] = "rev_timestamp $op " .
367  $this->db->addQuotes( $this->db->timestamp( $this->history['offset'] ) );
368  }
369  # Set query limit
370  if ( !empty( $this->history['limit'] ) ) {
371  $opts['LIMIT'] = intval( $this->history['limit'] );
372  }
373  } elseif ( $this->history & self::FULL ) {
374  # Full history dumps...
375  # query optimization for history stub dumps
376  if ( $this->text == self::STUB && $orderRevs ) {
377  $tables = $revQuery['tables'];
378  $opts['ORDER BY'] = [ 'rev_page ASC', 'rev_id ASC' ];
379  $opts['USE INDEX']['revision'] = 'rev_page_id';
380  unset( $join['revision'] );
381  $join['page'] = [ 'INNER JOIN', 'rev_page=page_id' ];
382  }
383  } elseif ( $this->history & self::CURRENT ) {
384  # Latest revision dumps...
385  if ( $this->list_authors && $cond != '' ) { // List authors, if so desired
386  $this->do_list_authors( $cond );
387  }
388  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page AND page_latest=rev_id' ];
389  } elseif ( $this->history & self::STABLE ) {
390  # "Stable" revision dumps...
391  # Default JOIN, to be overridden...
392  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page AND page_latest=rev_id' ];
393  # One, and only one hook should set this, and return false
394  if ( Hooks::run( 'WikiExporter::dumpStableQuery', [ &$tables, &$opts, &$join ] ) ) {
395  throw new MWException( __METHOD__ . " given invalid history dump type." );
396  }
397  } elseif ( $this->history & self::RANGE ) {
398  # Dump of revisions within a specified range
399  $opts['ORDER BY'] = [ 'rev_page ASC', 'rev_id ASC' ];
400  } else {
401  # Unknown history specification parameter?
402  throw new MWException( __METHOD__ . " given invalid history dump type." );
403  }
404 
405  if ( $this->buffer == self::STREAM ) {
406  $prev = $this->db->bufferResults( false );
407  }
408  $result = null; // Assuring $result is not undefined, if exception occurs early
409  try {
410  Hooks::run( 'ModifyExportQuery',
411  [ $this->db, &$tables, &$cond, &$opts, &$join ] );
412 
413  # Do the query!
414  $result = $this->db->select(
415  $tables,
416  $fields,
417  $conds,
418  __METHOD__,
419  $opts,
420  $join
421  );
422  # Output dump results
423  $this->outputPageStream( $result );
424 
425  if ( $this->buffer == self::STREAM ) {
426  $this->db->bufferResults( $prev );
427  }
428  } catch ( Exception $e ) {
429  // Throwing the exception does not reliably free the resultset, and
430  // would also leave the connection in unbuffered mode.
431 
432  // Freeing result
433  try {
434  if ( $result ) {
435  $result->free();
436  }
437  } catch ( Exception $e2 ) {
438  // Already in panic mode -> ignoring $e2 as $e has
439  // higher priority
440  }
441 
442  // Putting database back in previous buffer mode
443  try {
444  if ( $this->buffer == self::STREAM ) {
445  $this->db->bufferResults( $prev );
446  }
447  } catch ( Exception $e2 ) {
448  // Already in panic mode -> ignoring $e2 as $e has
449  // higher priority
450  }
451 
452  // Inform caller about problem
453  throw $e;
454  }
455  }
456  }
457 
470  protected function outputPageStream( $resultset ) {
471  $last = null;
472  foreach ( $resultset as $row ) {
473  if ( $last === null ||
474  $last->page_namespace != $row->page_namespace ||
475  $last->page_title != $row->page_title ) {
476  if ( $last !== null ) {
477  $output = '';
478  if ( $this->dumpUploads ) {
479  $output .= $this->writer->writeUploads( $last, $this->dumpUploadFileContents );
480  }
481  $output .= $this->writer->closePage();
482  $this->sink->writeClosePage( $output );
483  }
484  $output = $this->writer->openPage( $row );
485  $this->sink->writeOpenPage( $row, $output );
486  $last = $row;
487  }
488  $output = $this->writer->writeRevision( $row );
489  $this->sink->writeRevision( $row, $output );
490  }
491  if ( $last !== null ) {
492  $output = '';
493  if ( $this->dumpUploads ) {
494  $output .= $this->writer->writeUploads( $last, $this->dumpUploadFileContents );
495  }
497  $output .= $this->writer->closePage();
498  $this->sink->writeClosePage( $output );
499  }
500  }
501 
505  protected function outputLogStream( $resultset ) {
506  foreach ( $resultset as $row ) {
507  $output = $this->writer->writeLogItem( $row );
508  $this->sink->writeLogItem( $row, $output );
509  }
510  }
511 }
DumpOutput $sink
bool $list_authors
Return distinct author list (when not returning full history)
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
div flags Integer display flags(NO_ACTION_LINK, NO_EXTRA_USER_LINKS) 'LogException'returning false will NOT prevent logging $e
Definition: hooks.txt:2164
setOutputSink(&$sink)
Set the DumpOutput or DumpFilter object which will receive various row objects and XML output for fil...
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title after the basic globals have been set but before ordinary actions take place $output
Definition: hooks.txt:2221
outputPageStream($resultset)
Runs through a query result set dumping page and revision records.
static newFromText($text, $defaultNamespace=NS_MAIN)
Create a new Title from text, such as what one would find in a link.
Definition: Title.php:273
allPages()
Dumps a series of page and revision records for all pages in the database, either including complete ...
string $author_list
The index of the header message $result[1]=The index of the body text message $result[2 through n]=Parameters passed to body text message.Please note the header message cannot receive/use parameters. 'ImportHandleLogItemXMLTag':When parsing a XML tag in a log item.Return false to stop further processing of the tag $reader:XMLReader object $logInfo:Array of information 'ImportHandlePageXMLTag':When parsing a XML tag in a page.Return false to stop further processing of the tag $reader:XMLReader object &$pageInfo:Array of information 'ImportHandleRevisionXMLTag':When parsing a XML tag in a page revision.Return false to stop further processing of the tag $reader:XMLReader object $pageInfo:Array of page information $revisionInfo:Array of revision information 'ImportHandleToplevelXMLTag':When parsing a top level XML tag.Return false to stop further processing of the tag $reader:XMLReader object 'ImportHandleUnknownUser':When a user doesn't exist locally, this hook is called to give extensions an opportunity to auto-create it.If the auto-creation is successful, return false.$name:User name 'ImportHandleUploadXMLTag':When parsing a XML tag in a file upload.Return false to stop further processing of the tag $reader:XMLReader object $revisionInfo:Array of information 'ImportLogInterwikiLink':Hook to change the interwiki link used in log entries and edit summaries for transwiki imports.&$fullInterwikiPrefix:Interwiki prefix, may contain colons.&$pageTitle:String that contains page title. 'ImportSources':Called when reading from the $wgImportSources configuration variable.Can be used to lazy-load the import sources list.&$importSources:The value of $wgImportSources.Modify as necessary.See the comment in DefaultSettings.php for the detail of how to structure this array. 'InfoAction':When building information to display on the action=info page.$context:IContextSource object &$pageInfo:Array of information 'InitializeArticleMaybeRedirect':MediaWiki check to see if title is a redirect.&$title:Title object for the current page &$request:WebRequest &$ignoreRedirect:boolean to skip redirect check &$target:Title/string of redirect target &$article:Article object 'InternalParseBeforeLinks':during Parser's internalParse method before links but after nowiki/noinclude/includeonly/onlyinclude and other processings.&$parser:Parser object &$text:string containing partially parsed text &$stripState:Parser's internal StripState object 'InternalParseBeforeSanitize':during Parser's internalParse method just before the parser removes unwanted/dangerous HTML tags and after nowiki/noinclude/includeonly/onlyinclude and other processings.Ideal for syntax-extensions after template/parser function execution which respect nowiki and HTML-comments.&$parser:Parser object &$text:string containing partially parsed text &$stripState:Parser's internal StripState object 'InterwikiLoadPrefix':When resolving if a given prefix is an interwiki or not.Return true without providing an interwiki to continue interwiki search.$prefix:interwiki prefix we are looking for.&$iwData:output array describing the interwiki with keys iw_url, iw_local, iw_trans and optionally iw_api and iw_wikiid. 'InvalidateEmailComplete':Called after a user's email has been invalidated successfully.$user:user(object) whose email is being invalidated 'IRCLineURL':When constructing the URL to use in an IRC notification.Callee may modify $url and $query, URL will be constructed as $url.$query &$url:URL to index.php &$query:Query string $rc:RecentChange object that triggered url generation 'IsFileCacheable':Override the result of Article::isFileCacheable()(if true) &$article:article(object) being checked 'IsTrustedProxy':Override the result of IP::isTrustedProxy() &$ip:IP being check &$result:Change this value to override the result of IP::isTrustedProxy() 'IsUploadAllowedFromUrl':Override the result of UploadFromUrl::isAllowedUrl() $url:URL used to upload from &$allowed:Boolean indicating if uploading is allowed for given URL 'isValidEmailAddr':Override the result of Sanitizer::validateEmail(), for instance to return false if the domain name doesn't match your organization.$addr:The e-mail address entered by the user &$result:Set this and return false to override the internal checks 'isValidPassword':Override the result of User::isValidPassword() $password:The password entered by the user &$result:Set this and return false to override the internal checks $user:User the password is being validated for 'Language::getMessagesFileName':$code:The language code or the language we're looking for a messages file for &$file:The messages file path, you can override this to change the location. 'LanguageGetMagic':DEPRECATED!Use $magicWords in a file listed in $wgExtensionMessagesFiles instead.Use this to define synonyms of magic words depending of the language &$magicExtensions:associative array of magic words synonyms $lang:language code(string) 'LanguageGetNamespaces':Provide custom ordering for namespaces or remove namespaces.Do not use this hook to add namespaces.Use CanonicalNamespaces for that.&$namespaces:Array of namespaces indexed by their numbers 'LanguageGetSpecialPageAliases':DEPRECATED!Use $specialPageAliases in a file listed in $wgExtensionMessagesFiles instead.Use to define aliases of special pages names depending of the language &$specialPageAliases:associative array of magic words synonyms $lang:language code(string) 'LanguageGetTranslatedLanguageNames':Provide translated language names.&$names:array of language code=> language name $code:language of the preferred translations 'LanguageLinks':Manipulate a page's language links.This is called in various places to allow extensions to define the effective language links for a page.$title:The page's Title.&$links:Array with elements of the form"language:title"in the order that they will be output.&$linkFlags:Associative array mapping prefixed links to arrays of flags.Currently unused, but planned to provide support for marking individual language links in the UI, e.g.for featured articles. 'LanguageSelector':Hook to change the language selector available on a page.$out:The output page.$cssClassName:CSS class name of the language selector. 'LinkBegin':DEPRECATED!Use HtmlPageLinkRendererBegin instead.Used when generating internal and interwiki links in Linker::link(), before processing starts.Return false to skip default processing and return $ret.See documentation for Linker::link() for details on the expected meanings of parameters.$skin:the Skin object $target:the Title that the link is pointing to &$html:the contents that the< a > tag should have(raw HTML) $result
Definition: hooks.txt:1986
static getQueryInfo($options=[])
Return the tables, fields, and join conditions to be selected to create a new revision object...
Definition: Revision.php:493
$last
static newMigration()
Static constructor.
__construct($db, $history=self::CURRENT, $buffer=self::BUFFER, $text=self::TEXT)
If using WikiExporter::STREAM to stream a large amount of data, provide a database connection which i...
pageByName($name)
revsByRange($start, $end)
Dumps a series of page and revision records for those pages in the database with revisions falling wi...
pagesByName($names)
$res
Definition: database.txt:21
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:935
static run($event, array $args=[], $deprecatedVersion=null)
Call hook functions defined in Hooks::register and $wgHooks.
Definition: Hooks.php:203
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add text
Definition: design.txt:12
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:9
pagesByRange($start, $end, $orderRevs)
Dumps a series of page and revision records for those pages in the database falling within the page_i...
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
presenting them properly to the user as errors is done by the caller return true use this to change the list i e etc next in line in page history
Definition: hooks.txt:1768
const DELETED_USER
Definition: Revision.php:49
static getStore()
bool $dumpUploadFileContents
An extension writer
Definition: hooks.txt:51
static schemaVersion()
Returns the export schema version.
$revQuery
do_list_authors($cond)
Generates the distinct list of authors of an article Not called by default (depends on $this->list_au...
Allows to change the fields on the form that will be generated $name
Definition: hooks.txt:302
dumpFrom($cond= '', $orderRevs=false)
this hook is for auditing only RecentChangesLinked and Watchlist RecentChangesLinked and Watchlist Do not use this to implement individual filters if they are compatible with the ChangesListFilter and ChangesListFilterGroup structure use sub classes of those in conjunction with the ChangesListSpecialPageStructuredFilters hook This hook can be used to implement filters that do not implement that or custom behavior that is not an individual filter e g Watchlist & $tables
Definition: hooks.txt:991
logsByRange($start, $end)
pageByTitle($title)
static getExcludeClause($db, $audience= 'public', User $user=null)
SQL clause to skip forbidden log types for this user.
outputLogStream($resultset)