MediaWiki  master
BackupDumper.php
Go to the documentation of this file.
1 <?php
28 require_once __DIR__ . '/../Maintenance.php';
29 require_once __DIR__ . '/../../includes/export/WikiExporter.php';
30 
34 
39 abstract class BackupDumper extends Maintenance {
40  public $reporting = true;
41  public $pages = null; // all pages
42  public $skipHeader = false; // don't output <mediawiki> and <siteinfo>
43  public $skipFooter = false; // don't output </mediawiki>
44  public $startId = 0;
45  public $endId = 0;
46  public $revStartId = 0;
47  public $revEndId = 0;
48  public $dumpUploads = false;
49  public $dumpUploadFileContents = false;
50  public $orderRevs = false;
51 
52  protected $reportingInterval = 100;
53  protected $pageCount = 0;
54  protected $revCount = 0;
55  protected $schemaVersion = null; // use default
56  protected $server = null; // use default
57  protected $sink = null; // Output filters
58  protected $lastTime = 0;
59  protected $pageCountLast = 0;
60  protected $revCountLast = 0;
61 
62  protected $outputTypes = [];
63  protected $filterTypes = [];
64 
65  protected $ID = 0;
66 
74  protected $forcedDb = null;
75 
77  protected $lb;
78 
82  function __construct( $args = null ) {
83  parent::__construct();
84  $this->stderr = fopen( "php://stderr", "wt" );
85 
86  // Built-in output and filter plugins
87  $this->registerOutput( 'file', DumpFileOutput::class );
88  $this->registerOutput( 'gzip', DumpGZipOutput::class );
89  $this->registerOutput( 'bzip2', DumpBZip2Output::class );
90  $this->registerOutput( 'dbzip2', DumpDBZip2Output::class );
91  $this->registerOutput( 'lbzip2', DumpLBZip2Output::class );
92  $this->registerOutput( '7zip', Dump7ZipOutput::class );
93 
94  $this->registerFilter( 'latest', DumpLatestFilter::class );
95  $this->registerFilter( 'notalk', DumpNotalkFilter::class );
96  $this->registerFilter( 'namespace', DumpNamespaceFilter::class );
97 
98  // These three can be specified multiple times
99  $this->addOption( 'plugin', 'Load a dump plugin class. Specify as <class>[:<file>].',
100  false, true, false, true );
101  $this->addOption( 'output', 'Begin a filtered output stream; Specify as <type>:<file>. ' .
102  '<type>s: file, gzip, bzip2, 7zip, dbzip2, lbzip2', false, true, false, true );
103  $this->addOption( 'filter', 'Add a filter on an output branch. Specify as ' .
104  '<type>[:<options>]. <types>s: latest, notalk, namespace', false, true, false, true );
105  $this->addOption( 'report', 'Report position and speed after every n pages processed. ' .
106  'Default: 100.', false, true );
107  $this->addOption( 'schema-version', 'Schema version to use for output. ' .
108  'Default: ' . WikiExporter::schemaVersion(), false, true );
109  $this->addOption( 'server', 'Force reading from MySQL server', false, true );
110  $this->addOption( '7ziplevel', '7zip compression level for all 7zip outputs. Used for ' .
111  '-mx option to 7za command.', false, true );
112 
113  if ( $args ) {
114  // Args should be loaded and processed so that dump() can be called directly
115  // instead of execute()
116  $this->loadWithArgv( $args );
117  $this->processOptions();
118  }
119  }
120 
125  function registerOutput( $name, $class ) {
126  $this->outputTypes[$name] = $class;
127  }
128 
133  function registerFilter( $name, $class ) {
134  $this->filterTypes[$name] = $class;
135  }
136 
144  function loadPlugin( $class, $file ) {
145  if ( $file != '' ) {
146  require_once $file;
147  }
148  $register = [ $class, 'register' ];
149  $register( $this );
150  }
151 
152  function execute() {
153  throw new MWException( 'execute() must be overridden in subclasses' );
154  }
155 
159  function processOptions() {
160  $sink = null;
161  $sinks = [];
162 
163  $this->schemaVersion = WikiExporter::schemaVersion();
164 
166  foreach ( $options as $arg ) {
167  list( $opt, $param ) = $arg;
168 
169  switch ( $opt ) {
170  case 'plugin':
171  $val = explode( ':', $param, 2 );
172 
173  if ( count( $val ) === 1 ) {
174  $this->loadPlugin( $val[0], '' );
175  } elseif ( count( $val ) === 2 ) {
176  $this->loadPlugin( $val[0], $val[1] );
177  }
178 
179  break;
180  case 'output':
181  $split = explode( ':', $param, 2 );
182  if ( count( $split ) !== 2 ) {
183  $this->fatalError( 'Invalid output parameter' );
184  }
185  list( $type, $file ) = $split;
186  if ( !is_null( $sink ) ) {
187  $sinks[] = $sink;
188  }
189  if ( !isset( $this->outputTypes[$type] ) ) {
190  $this->fatalError( "Unrecognized output sink type '$type'" );
191  }
192  $class = $this->outputTypes[$type];
193  if ( $type === "7zip" ) {
194  $sink = new $class( $file, intval( $this->getOption( '7ziplevel' ) ) );
195  } else {
196  $sink = new $class( $file );
197  }
198 
199  break;
200  case 'filter':
201  if ( is_null( $sink ) ) {
202  $sink = new DumpOutput();
203  }
204 
205  $split = explode( ':', $param, 2 );
206  $key = $split[0];
207 
208  if ( !isset( $this->filterTypes[$key] ) ) {
209  $this->fatalError( "Unrecognized filter type '$key'" );
210  }
211 
212  $type = $this->filterTypes[$key];
213 
214  if ( count( $split ) === 1 ) {
215  $filter = new $type( $sink );
216  } elseif ( count( $split ) === 2 ) {
217  $filter = new $type( $sink, $split[1] );
218  }
219 
220  // references are lame in php...
221  unset( $sink );
222  $sink = $filter;
223 
224  break;
225  case 'schema-version':
226  if ( !in_array( $param, XmlDumpWriter::$supportedSchemas ) ) {
227  $this->fatalError(
228  "Unsupported schema version $param. Supported versions: " .
229  implode( ', ', XmlDumpWriter::$supportedSchemas )
230  );
231  }
232  $this->schemaVersion = $param;
233  break;
234  }
235  }
236 
237  if ( $this->hasOption( 'report' ) ) {
238  $this->reportingInterval = intval( $this->getOption( 'report' ) );
239  }
240 
241  if ( $this->hasOption( 'server' ) ) {
242  $this->server = $this->getOption( 'server' );
243  }
244 
245  if ( is_null( $sink ) ) {
246  $sink = new DumpOutput();
247  }
248  $sinks[] = $sink;
249 
250  if ( count( $sinks ) > 1 ) {
251  $this->sink = new DumpMultiWriter( $sinks );
252  } else {
253  $this->sink = $sink;
254  }
255  }
256 
257  function dump( $history, $text = WikiExporter::TEXT ) {
258  # Notice messages will foul up your XML output even if they're
259  # relatively harmless.
260  if ( ini_get( 'display_errors' ) ) {
261  ini_set( 'display_errors', 'stderr' );
262  }
263 
264  $this->initProgress( $history );
265 
266  $db = $this->backupDb();
267  $exporter = new WikiExporter( $db, $history, $text );
268  $exporter->setSchemaVersion( $this->schemaVersion );
269  $exporter->dumpUploads = $this->dumpUploads;
270  $exporter->dumpUploadFileContents = $this->dumpUploadFileContents;
271 
272  $wrapper = new ExportProgressFilter( $this->sink, $this );
273  $exporter->setOutputSink( $wrapper );
274 
275  if ( !$this->skipHeader ) {
276  $exporter->openStream();
277  }
278  # Log item dumps: all or by range
279  if ( $history & WikiExporter::LOGS ) {
280  if ( $this->startId || $this->endId ) {
281  $exporter->logsByRange( $this->startId, $this->endId );
282  } else {
283  $exporter->allLogs();
284  }
285  } elseif ( is_null( $this->pages ) ) {
286  # Page dumps: all or by page ID range
287  if ( $this->startId || $this->endId ) {
288  $exporter->pagesByRange( $this->startId, $this->endId, $this->orderRevs );
289  } elseif ( $this->revStartId || $this->revEndId ) {
290  $exporter->revsByRange( $this->revStartId, $this->revEndId );
291  } else {
292  $exporter->allPages();
293  }
294  } else {
295  # Dump of specific pages
296  $exporter->pagesByName( $this->pages );
297  }
298 
299  if ( !$this->skipFooter ) {
300  $exporter->closeStream();
301  }
302 
303  $this->report( true );
304  }
305 
312  function initProgress( $history = WikiExporter::FULL ) {
313  $table = ( $history == WikiExporter::CURRENT ) ? 'page' : 'revision';
314  $field = ( $history == WikiExporter::CURRENT ) ? 'page_id' : 'rev_id';
315 
317  if ( $this->forcedDb === null ) {
318  $dbr = wfGetDB( DB_REPLICA );
319  }
320  $this->maxCount = $dbr->selectField( $table, "MAX($field)", '', __METHOD__ );
321  $this->startTime = microtime( true );
322  $this->lastTime = $this->startTime;
323  $this->ID = getmypid();
324  }
325 
332  function backupDb() {
333  if ( $this->forcedDb !== null ) {
334  return $this->forcedDb;
335  }
336 
337  $lbFactory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
338  $this->lb = $lbFactory->newMainLB();
339  $db = $this->lb->getConnection( DB_REPLICA, 'dump' );
340 
341  // Discourage the server from disconnecting us if it takes a long time
342  // to read out the big ol' batch query.
343  $db->setSessionOptions( [ 'connTimeout' => 3600 * 24 ] );
344 
345  return $db;
346  }
347 
355  function setDB( IDatabase $db = null ) {
356  parent::setDB( $db );
357  $this->forcedDb = $db;
358  }
359 
360  function __destruct() {
361  if ( isset( $this->lb ) ) {
362  $this->lb->closeAll();
363  }
364  }
365 
366  function backupServer() {
367  global $wgDBserver;
368 
369  return $this->server ?: $wgDBserver;
370  }
371 
372  function reportPage() {
373  $this->pageCount++;
374  }
375 
376  function revCount() {
377  $this->revCount++;
378  $this->report();
379  }
380 
381  function report( $final = false ) {
382  if ( $final xor ( $this->revCount % $this->reportingInterval == 0 ) ) {
383  $this->showReport();
384  }
385  }
386 
387  function showReport() {
388  if ( $this->reporting ) {
389  $now = wfTimestamp( TS_DB );
390  $nowts = microtime( true );
391  $deltaAll = $nowts - $this->startTime;
392  $deltaPart = $nowts - $this->lastTime;
393  $this->pageCountPart = $this->pageCount - $this->pageCountLast;
394  $this->revCountPart = $this->revCount - $this->revCountLast;
395 
396  if ( $deltaAll ) {
397  $portion = $this->revCount / $this->maxCount;
398  $eta = $this->startTime + $deltaAll / $portion;
399  $etats = wfTimestamp( TS_DB, intval( $eta ) );
400  $pageRate = $this->pageCount / $deltaAll;
401  $revRate = $this->revCount / $deltaAll;
402  } else {
403  $pageRate = '-';
404  $revRate = '-';
405  $etats = '-';
406  }
407  if ( $deltaPart ) {
408  $pageRatePart = $this->pageCountPart / $deltaPart;
409  $revRatePart = $this->revCountPart / $deltaPart;
410  } else {
411  $pageRatePart = '-';
412  $revRatePart = '-';
413  }
414  $this->progress( sprintf(
415  "%s: %s (ID %d) %d pages (%0.1f|%0.1f/sec all|curr), "
416  . "%d revs (%0.1f|%0.1f/sec all|curr), ETA %s [max %d]",
417  $now, wfWikiID(), $this->ID, $this->pageCount, $pageRate,
418  $pageRatePart, $this->revCount, $revRate, $revRatePart, $etats,
419  $this->maxCount
420  ) );
421  $this->lastTime = $nowts;
422  $this->revCountLast = $this->revCount;
423  }
424  }
425 
426  function progress( $string ) {
427  if ( $this->reporting ) {
428  fwrite( $this->stderr, $string . "\n" );
429  }
430  }
431 }
setDB(IDatabase $db=null)
Force the dump to use the provided database connection for database operations, wherever possible...
processOptions()
Processes arguments and sets $this->$sink accordingly.
deferred txt A few of the database updates required by various functions here can be deferred until after the result page is displayed to the user For updating the view updating the linked to tables after a etc PHP does not yet have any way to tell the server to actually return and disconnect while still running these but it might have such a feature in the future We handle these by creating a deferred update object and putting those objects on a global list
Definition: deferred.txt:11
dump( $history, $text=WikiExporter::TEXT)
LoadBalancer $lb
setSessionOptions(array $options)
Override database&#39;s default behavior.
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
getOption( $name, $default=null)
Get an option, or return the default.
if(PHP_SAPI !='cli-server') if(!isset( $_SERVER['SCRIPT_FILENAME'])) $file
Definition: router.php:42
progress( $string)
array $orderedOptions
Used to read the options in the order they were passed.
registerFilter( $name, $class)
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
__construct( $args=null)
wfGetDB( $db, $groups=[], $wiki=false)
Get a Database object.
$wgDBserver
Database host name or IP address.
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 MediaWikiServices
Definition: injection.txt:23
hasOption( $name)
Checks to see if a particular option exists.
loadWithArgv( $argv)
Load params and arguments from a given array of command-line arguments.
if( $line===false) $args
Definition: cdb.php:64
loadPlugin( $class, $file)
Load a plugin and register it.
initProgress( $history=WikiExporter::FULL)
Initialise starting time and maximum revision count.
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped & $options
Definition: hooks.txt:1982
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that When $user is not null
Definition: hooks.txt:780
$filter
wfWikiID()
Get an ASCII string identifying this wiki This is used as a prefix in memcached keys.
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
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
The ContentHandler facility adds support for arbitrary content types on wiki pages
Basic database interface for live and lazy-loaded relation database handles.
Definition: IDatabase.php:38
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
IDatabase null $forcedDb
The dependency-injected database to use.
report( $final=false)
static schemaVersion()
Returns the default export schema version, as defined by $wgXmlDumpSchemaVersion. ...
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
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 and we might be restricted by PHP settings such as safe mode or open_basedir We cannot assume that the software even has read access anywhere useful Many shared hosts run all users web applications under the same so they can t rely on Unix and must forbid reads to even standard directories like tmp lest users read each others files We cannot assume that the user has the ability to install or run any programs not written as web accessible PHP scripts Since anything that works on cheap shared hosting will work if you have shell or root access MediaWiki s design is based around catering to the lowest common denominator Although we support higher end setups as the way many things work by default is tailored toward shared hosting These defaults are unconventional from the point of view of and they certainly aren t ideal for someone who s installing MediaWiki as MediaWiki does not conform to normal Unix filesystem layout Hopefully we ll offer direct support for standard layouts in the but for now *any change to the location of files is unsupported *Moving things and leaving symlinks will *probably *not break but it is *strongly *advised not to try any more intrusive changes to get MediaWiki to conform more closely to your filesystem hierarchy Any such attempt will almost certainly result in unnecessary bugs The standard recommended location to install relative to the web is it should be possible to enable the appropriate rewrite rules by if you can reconfigure the web server
static string [] $supportedSchemas
the schema versions supported for output
Allows to change the fields on the form that will be generated $name
Definition: hooks.txt:271
const DB_REPLICA
Definition: defines.php:25
registerOutput( $name, $class)
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.