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  $res = $this->db->select(
231  [ 'page', 'revision' ],
232  [ 'DISTINCT rev_user_text', 'rev_user' ],
233  [
234  $this->db->bitAnd( 'rev_deleted', Revision::DELETED_USER ) . ' = 0',
235  $cond,
236  'page_id = rev_id',
237  ],
238  __METHOD__
239  );
240 
241  foreach ( $res as $row ) {
242  $this->author_list .= "<contributor>" .
243  "<username>" .
244  htmlentities( $row->rev_user_text ) .
245  "</username>" .
246  "<id>" .
247  $row->rev_user .
248  "</id>" .
249  "</contributor>";
250  }
251  $this->author_list .= "</contributors>";
252  }
253 
260  protected function dumpFrom( $cond = '', $orderRevs = false ) {
261  # For logging dumps...
262  if ( $this->history & self::LOGS ) {
263  $where = [];
264  # Hide private logs
265  $hideLogs = LogEventsList::getExcludeClause( $this->db );
266  if ( $hideLogs ) {
267  $where[] = $hideLogs;
268  }
269  # Add on any caller specified conditions
270  if ( $cond ) {
271  $where[] = $cond;
272  }
273  # Get logging table name for logging.* clause
274  $logging = $this->db->tableName( 'logging' );
275 
276  if ( $this->buffer == self::STREAM ) {
277  $prev = $this->db->bufferResults( false );
278  }
279  $result = null; // Assuring $result is not undefined, if exception occurs early
280 
281  $commentQuery = CommentStore::newKey( 'log_comment' )->getJoin();
282 
283  try {
284  $result = $this->db->select( [ 'logging', 'user' ] + $commentQuery['tables'],
285  [ "{$logging}.*", 'user_name' ] + $commentQuery['fields'], // grab the user name
286  $where,
287  __METHOD__,
288  [ 'ORDER BY' => 'log_id', 'USE INDEX' => [ 'logging' => 'PRIMARY' ] ],
289  [ 'user' => [ 'JOIN', 'user_id = log_user' ] ] + $commentQuery['joins']
290  );
291  $this->outputLogStream( $result );
292  if ( $this->buffer == self::STREAM ) {
293  $this->db->bufferResults( $prev );
294  }
295  } catch ( Exception $e ) {
296  // Throwing the exception does not reliably free the resultset, and
297  // would also leave the connection in unbuffered mode.
298 
299  // Freeing result
300  try {
301  if ( $result ) {
302  $result->free();
303  }
304  } catch ( Exception $e2 ) {
305  // Already in panic mode -> ignoring $e2 as $e has
306  // higher priority
307  }
308 
309  // Putting database back in previous buffer mode
310  try {
311  if ( $this->buffer == self::STREAM ) {
312  $this->db->bufferResults( $prev );
313  }
314  } catch ( Exception $e2 ) {
315  // Already in panic mode -> ignoring $e2 as $e has
316  // higher priority
317  }
318 
319  // Inform caller about problem
320  throw $e;
321  }
322  # For page dumps...
323  } else {
324  $tables = [ 'page', 'revision' ];
325  $opts = [ 'ORDER BY' => 'page_id ASC' ];
326  $opts['USE INDEX'] = [];
327  $join = [];
328  if ( is_array( $this->history ) ) {
329  # Time offset/limit for all pages/history...
330  $revJoin = 'page_id=rev_page';
331  # Set time order
332  if ( $this->history['dir'] == 'asc' ) {
333  $op = '>';
334  $opts['ORDER BY'] = 'rev_timestamp ASC';
335  } else {
336  $op = '<';
337  $opts['ORDER BY'] = 'rev_timestamp DESC';
338  }
339  # Set offset
340  if ( !empty( $this->history['offset'] ) ) {
341  $revJoin .= " AND rev_timestamp $op " .
342  $this->db->addQuotes( $this->db->timestamp( $this->history['offset'] ) );
343  }
344  $join['revision'] = [ 'INNER JOIN', $revJoin ];
345  # Set query limit
346  if ( !empty( $this->history['limit'] ) ) {
347  $opts['LIMIT'] = intval( $this->history['limit'] );
348  }
349  } elseif ( $this->history & self::FULL ) {
350  # Full history dumps...
351  # query optimization for history stub dumps
352  if ( $this->text == self::STUB && $orderRevs ) {
353  $tables = [ 'revision', 'page' ];
354  $opts[] = 'STRAIGHT_JOIN';
355  $opts['ORDER BY'] = [ 'rev_page ASC', 'rev_id ASC' ];
356  $opts['USE INDEX']['revision'] = 'rev_page_id';
357  $join['page'] = [ 'INNER JOIN', 'rev_page=page_id' ];
358  } else {
359  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page' ];
360  }
361  } elseif ( $this->history & self::CURRENT ) {
362  # Latest revision dumps...
363  if ( $this->list_authors && $cond != '' ) { // List authors, if so desired
364  $this->do_list_authors( $cond );
365  }
366  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page AND page_latest=rev_id' ];
367  } elseif ( $this->history & self::STABLE ) {
368  # "Stable" revision dumps...
369  # Default JOIN, to be overridden...
370  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page AND page_latest=rev_id' ];
371  # One, and only one hook should set this, and return false
372  if ( Hooks::run( 'WikiExporter::dumpStableQuery', [ &$tables, &$opts, &$join ] ) ) {
373  throw new MWException( __METHOD__ . " given invalid history dump type." );
374  }
375  } elseif ( $this->history & self::RANGE ) {
376  # Dump of revisions within a specified range
377  $join['revision'] = [ 'INNER JOIN', 'page_id=rev_page' ];
378  $opts['ORDER BY'] = [ 'rev_page ASC', 'rev_id ASC' ];
379  } else {
380  # Unknown history specification parameter?
381  throw new MWException( __METHOD__ . " given invalid history dump type." );
382  }
383  # Query optimization hacks
384  if ( $cond == '' ) {
385  $opts[] = 'STRAIGHT_JOIN';
386  $opts['USE INDEX']['page'] = 'PRIMARY';
387  }
388  # Build text join options
389  if ( $this->text != self::STUB ) { // 1-pass
390  $tables[] = 'text';
391  $join['text'] = [ 'INNER JOIN', 'rev_text_id=old_id' ];
392  }
393 
394  if ( $this->buffer == self::STREAM ) {
395  $prev = $this->db->bufferResults( false );
396  }
397  $result = null; // Assuring $result is not undefined, if exception occurs early
398  try {
399  Hooks::run( 'ModifyExportQuery',
400  [ $this->db, &$tables, &$cond, &$opts, &$join ] );
401 
402  $commentQuery = CommentStore::newKey( 'rev_comment' )->getJoin();
403 
404  # Do the query!
405  $result = $this->db->select(
406  $tables + $commentQuery['tables'],
407  [ '*' ] + $commentQuery['fields'],
408  $cond,
409  __METHOD__,
410  $opts,
411  $join + $commentQuery['joins']
412  );
413  # Output dump results
414  $this->outputPageStream( $result );
415 
416  if ( $this->buffer == self::STREAM ) {
417  $this->db->bufferResults( $prev );
418  }
419  } catch ( Exception $e ) {
420  // Throwing the exception does not reliably free the resultset, and
421  // would also leave the connection in unbuffered mode.
422 
423  // Freeing result
424  try {
425  if ( $result ) {
426  $result->free();
427  }
428  } catch ( Exception $e2 ) {
429  // Already in panic mode -> ignoring $e2 as $e has
430  // higher priority
431  }
432 
433  // Putting database back in previous buffer mode
434  try {
435  if ( $this->buffer == self::STREAM ) {
436  $this->db->bufferResults( $prev );
437  }
438  } catch ( Exception $e2 ) {
439  // Already in panic mode -> ignoring $e2 as $e has
440  // higher priority
441  }
442 
443  // Inform caller about problem
444  throw $e;
445  }
446  }
447  }
448 
461  protected function outputPageStream( $resultset ) {
462  $last = null;
463  foreach ( $resultset as $row ) {
464  if ( $last === null ||
465  $last->page_namespace != $row->page_namespace ||
466  $last->page_title != $row->page_title ) {
467  if ( $last !== null ) {
468  $output = '';
469  if ( $this->dumpUploads ) {
470  $output .= $this->writer->writeUploads( $last, $this->dumpUploadFileContents );
471  }
472  $output .= $this->writer->closePage();
473  $this->sink->writeClosePage( $output );
474  }
475  $output = $this->writer->openPage( $row );
476  $this->sink->writeOpenPage( $row, $output );
477  $last = $row;
478  }
479  $output = $this->writer->writeRevision( $row );
480  $this->sink->writeRevision( $row, $output );
481  }
482  if ( $last !== null ) {
483  $output = '';
484  if ( $this->dumpUploads ) {
485  $output .= $this->writer->writeUploads( $last, $this->dumpUploadFileContents );
486  }
488  $output .= $this->writer->closePage();
489  $this->sink->writeClosePage( $output );
490  }
491  }
492 
496  protected function outputLogStream( $resultset ) {
497  foreach ( $resultset as $row ) {
498  $output = $this->writer->writeLogItem( $row );
499  $this->sink->writeLogItem( $row, $output );
500  }
501  }
502 }
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 $e
Definition: hooks.txt:2142
setOutputSink(&$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 $output
Definition: hooks.txt:2199
outputPageStream($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:268
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 '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:1964
$last
__construct($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 $title
Definition: hooks.txt:933
static run($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:1751
const DELETED_USER
Definition: Revision.php:92
bool $dumpUploadFileContents
An extension writer
Definition: hooks.txt:51
static schemaVersion()
Returns the export schema version.
do_list_authors($cond)
Generates the distinct list of authors of an article Not called by default (depends on $this->list_au...
static newKey($key)
Static constructor for easier chaining.
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 & $tables
Definition: hooks.txt:989
logsByRange($start, $end)
pageByTitle($title)
static getExcludeClause($db, $audience= 'public', User $user=null)
SQL clause to skip forbidden log types for this user.
outputLogStream($resultset)