MediaWiki  1.33.0
importTextFiles.php
Go to the documentation of this file.
1 <?php
25 
26 require_once __DIR__ . '/Maintenance.php';
27 
35  public function __construct() {
36  parent::__construct();
37  $this->addDescription( 'Reads in text files and imports their content to pages of the wiki' );
38  $this->addOption( 'user', 'Username to which edits should be attributed. ' .
39  'Default: "Maintenance script"', false, true, 'u' );
40  $this->addOption( 'summary', 'Specify edit summary for the edits', false, true, 's' );
41  $this->addOption( 'use-timestamp', 'Use the modification date of the text file ' .
42  'as the timestamp for the edit' );
43  $this->addOption( 'overwrite', 'Overwrite existing pages. If --use-timestamp is passed, this ' .
44  'will only overwrite pages if the file has been modified since the page was last modified.' );
45  $this->addOption( 'prefix', 'A string to place in front of the file name', false, true, 'p' );
46  $this->addOption( 'bot', 'Mark edits as bot edits in the recent changes list.' );
47  $this->addOption( 'rc', 'Place revisions in RecentChanges.' );
48  $this->addArg( 'files', 'Files to import' );
49  }
50 
51  public function execute() {
52  $userName = $this->getOption( 'user', false );
53  $summary = $this->getOption( 'summary', 'Imported from text file' );
54  $useTimestamp = $this->hasOption( 'use-timestamp' );
55  $rc = $this->hasOption( 'rc' );
56  $bot = $this->hasOption( 'bot' );
57  $overwrite = $this->hasOption( 'overwrite' );
58  $prefix = $this->getOption( 'prefix', '' );
59 
60  // Get all the arguments. A loop is required since Maintenance doesn't
61  // support an arbitrary number of arguments.
62  $files = [];
63  $i = 0;
64  while ( $arg = $this->getArg( $i++ ) ) {
65  if ( file_exists( $arg ) ) {
66  $files[$arg] = file_get_contents( $arg );
67  } else {
68  // use glob to support the Windows shell, which doesn't automatically
69  // expand wildcards
70  $found = false;
71  foreach ( glob( $arg ) as $filename ) {
72  $found = true;
73  $files[$filename] = file_get_contents( $filename );
74  }
75  if ( !$found ) {
76  $this->fatalError( "Fatal error: The file '$arg' does not exist!" );
77  }
78  }
79  };
80 
81  $count = count( $files );
82  $this->output( "Importing $count pages...\n" );
83 
84  if ( $userName === false ) {
85  $user = User::newSystemUser( 'Maintenance script', [ 'steal' => true ] );
86  } else {
87  $user = User::newFromName( $userName );
88  }
89 
90  if ( !$user ) {
91  $this->fatalError( "Invalid username\n" );
92  }
93  if ( $user->isAnon() ) {
94  $user->addToDatabase();
95  }
96 
97  $exit = 0;
98 
99  $successCount = 0;
100  $failCount = 0;
101  $skipCount = 0;
102 
103  foreach ( $files as $file => $text ) {
104  $pageName = $prefix . pathinfo( $file, PATHINFO_FILENAME );
105  $timestamp = $useTimestamp ? wfTimestamp( TS_UNIX, filemtime( $file ) ) : wfTimestampNow();
106 
107  $title = Title::newFromText( $pageName );
108  // Have to check for # manually, since it gets interpreted as a fragment
109  if ( !$title || $title->hasFragment() ) {
110  $this->error( "Invalid title $pageName. Skipping.\n" );
111  $skipCount++;
112  continue;
113  }
114 
115  $exists = $title->exists();
116  $oldRevID = $title->getLatestRevID();
117  $oldRev = $oldRevID ? Revision::newFromId( $oldRevID ) : null;
118  $actualTitle = $title->getPrefixedText();
119 
120  if ( $exists ) {
121  $touched = wfTimestamp( TS_UNIX, $title->getTouched() );
122  if ( !$overwrite ) {
123  $this->output( "Title $actualTitle already exists. Skipping.\n" );
124  $skipCount++;
125  continue;
126  } elseif ( $useTimestamp && intval( $touched ) >= intval( $timestamp ) ) {
127  $this->output( "File for title $actualTitle has not been modified since the " .
128  "destination page was touched. Skipping.\n" );
129  $skipCount++;
130  continue;
131  }
132  }
133 
134  $rev = new WikiRevision( MediaWikiServices::getInstance()->getMainConfig() );
135  $rev->setText( rtrim( $text ) );
136  $rev->setTitle( $title );
137  $rev->setUserObj( $user );
138  $rev->setComment( $summary );
139  $rev->setTimestamp( $timestamp );
140 
141  if ( $exists && $overwrite && $rev->getContent()->equals( $oldRev->getContent() ) ) {
142  $this->output( "File for title $actualTitle contains no changes from the current " .
143  "revision. Skipping.\n" );
144  $skipCount++;
145  continue;
146  }
147 
148  $status = $rev->importOldRevision();
149  $newId = $title->getLatestRevID();
150 
151  if ( $status ) {
152  $action = $exists ? 'updated' : 'created';
153  $this->output( "Successfully $action $actualTitle\n" );
154  $successCount++;
155  } else {
156  $action = $exists ? 'update' : 'create';
157  $this->output( "Failed to $action $actualTitle\n" );
158  $failCount++;
159  $exit = 1;
160  }
161 
162  // Create the RecentChanges entry if necessary
163  if ( $rc && $status ) {
164  if ( $exists ) {
165  if ( is_object( $oldRev ) ) {
166  $oldContent = $oldRev->getContent();
168  $timestamp,
169  $title,
170  $rev->getMinor(),
171  $user,
172  $summary,
173  $oldRevID,
174  $oldRev->getTimestamp(),
175  $bot,
176  '',
177  $oldContent ? $oldContent->getSize() : 0,
178  $rev->getContent()->getSize(),
179  $newId,
180  1 /* the pages don't need to be patrolled */
181  );
182  }
183  } else {
185  $timestamp,
186  $title,
187  $rev->getMinor(),
188  $user,
189  $summary,
190  $bot,
191  '',
192  $rev->getContent()->getSize(),
193  $newId,
194  1
195  );
196  }
197  }
198  }
199 
200  $this->output( "Done! $successCount succeeded, $skipCount skipped.\n" );
201  if ( $exit ) {
202  $this->fatalError( "Import failed with $failCount failed pages.\n", $exit );
203  }
204  }
205 }
206 
208 require_once RUN_MAINTENANCE_IF_MAIN;
$maintClass
$maintClass
Definition: importTextFiles.php:207
$status
Status::newGood()` to allow deletion, and then `return false` from the hook function. Ensure you consume the 'ChangeTagAfterDelete' hook to carry out custom deletion actions. $tag:name of the tag $user:user initiating the action & $status:Status object. See above. 'ChangeTagsListActive':Allows you to nominate which of the tags your extension uses are in active use. & $tags:list of all active tags. Append to this array. 'ChangeTagsAfterUpdateTags':Called after tags have been updated with the ChangeTags::updateTags function. Params:$addedTags:tags effectively added in the update $removedTags:tags effectively removed in the update $prevTags:tags that were present prior to the update $rc_id:recentchanges table id $rev_id:revision table id $log_id:logging table id $params:tag params $rc:RecentChange being tagged when the tagging accompanies the action, or null $user:User who performed the tagging when the tagging is subsequent to the action, or null 'ChangeTagsAllowedAdd':Called when checking if a user can add tags to a change. & $allowedTags:List of all the tags the user is allowed to add. Any tags the user wants to add( $addTags) that are not in this array will cause it to fail. You may add or remove tags to this array as required. $addTags:List of tags user intends to add. $user:User who is adding the tags. 'ChangeUserGroups':Called before user groups are changed. $performer:The User who will perform the change $user:The User whose groups will be changed & $add:The groups that will be added & $remove:The groups that will be removed 'Collation::factory':Called if $wgCategoryCollation is an unknown collation. $collationName:Name of the collation in question & $collationObject:Null. Replace with a subclass of the Collation class that implements the collation given in $collationName. 'ConfirmEmailComplete':Called after a user 's email has been confirmed successfully. $user:user(object) whose email is being confirmed 'ContentAlterParserOutput':Modify parser output for a given content object. Called by Content::getParserOutput after parsing has finished. Can be used for changes that depend on the result of the parsing but have to be done before LinksUpdate is called(such as adding tracking categories based on the rendered HTML). $content:The Content to render $title:Title of the page, as context $parserOutput:ParserOutput to manipulate 'ContentGetParserOutput':Customize parser output for a given content object, called by AbstractContent::getParserOutput. May be used to override the normal model-specific rendering of page content. $content:The Content to render $title:Title of the page, as context $revId:The revision ID, as context $options:ParserOptions for rendering. To avoid confusing the parser cache, the output can only depend on parameters provided to this hook function, not on global state. $generateHtml:boolean, indicating whether full HTML should be generated. If false, generation of HTML may be skipped, but other information should still be present in the ParserOutput object. & $output:ParserOutput, to manipulate or replace 'ContentHandlerDefaultModelFor':Called when the default content model is determined for a given title. May be used to assign a different model for that title. $title:the Title in question & $model:the model name. Use with CONTENT_MODEL_XXX constants. 'ContentHandlerForModelID':Called when a ContentHandler is requested for a given content model name, but no entry for that model exists in $wgContentHandlers. Note:if your extension implements additional models via this hook, please use GetContentModels hook to make them known to core. $modeName:the requested content model name & $handler:set this to a ContentHandler object, if desired. 'ContentModelCanBeUsedOn':Called to determine whether that content model can be used on a given page. This is especially useful to prevent some content models to be used in some special location. $contentModel:ID of the content model in question $title:the Title in question. & $ok:Output parameter, whether it is OK to use $contentModel on $title. Handler functions that modify $ok should generally return false to prevent further hooks from further modifying $ok. 'ContribsPager::getQueryInfo':Before the contributions query is about to run & $pager:Pager object for contributions & $queryInfo:The query for the contribs Pager 'ContribsPager::reallyDoQuery':Called before really executing the query for My Contributions & $data:an array of results of all contribs queries $pager:The ContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'ContributionsLineEnding':Called before a contributions HTML line is finished $page:SpecialPage object for contributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'ContributionsToolLinks':Change tool links above Special:Contributions $id:User identifier $title:User page title & $tools:Array of tool links $specialPage:SpecialPage instance for context and services. Can be either SpecialContributions or DeletedContributionsPage. Extensions should type hint against a generic SpecialPage though. 'ConvertContent':Called by AbstractContent::convert when a conversion to another content model is requested. Handler functions that modify $result should generally return false to disable further attempts at conversion. $content:The Content object to be converted. $toModel:The ID of the content model to convert to. $lossy:boolean indicating whether lossy conversion is allowed. & $result:Output parameter, in case the handler function wants to provide a converted Content object. Note that $result->getContentModel() must return $toModel. 'ContentSecurityPolicyDefaultSource':Modify the allowed CSP load sources. This affects all directives except for the script directive. If you want to add a script source, see ContentSecurityPolicyScriptSource hook. & $defaultSrc:Array of Content-Security-Policy allowed sources $policyConfig:Current configuration for the Content-Security-Policy header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyDirectives':Modify the content security policy directives. Use this only if ContentSecurityPolicyDefaultSource and ContentSecurityPolicyScriptSource do not meet your needs. & $directives:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyScriptSource':Modify the allowed CSP script sources. Note that you also have to use ContentSecurityPolicyDefaultSource if you want non-script sources to be loaded from whatever you add. & $scriptSrc:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'CustomEditor':When invoking the page editor Return true to allow the normal editor to be used, or false if implementing a custom editor, e.g. for a special namespace, etc. $article:Article being edited $user:User performing the edit 'DatabaseOraclePostInit':Called after initialising an Oracle database $db:the DatabaseOracle object 'DeletedContribsPager::reallyDoQuery':Called before really executing the query for Special:DeletedContributions Similar to ContribsPager::reallyDoQuery & $data:an array of results of all contribs queries $pager:The DeletedContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'DeletedContributionsLineEnding':Called before a DeletedContributions HTML line is finished. Similar to ContributionsLineEnding $page:SpecialPage object for DeletedContributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'DeleteUnknownPreferences':Called by the cleanupPreferences.php maintenance script to build a WHERE clause with which to delete preferences that are not known about. This hook is used by extensions that have dynamically-named preferences that should not be deleted in the usual cleanup process. For example, the Gadgets extension creates preferences prefixed with 'gadget-', and so anything with that prefix is excluded from the deletion. &where:An array that will be passed as the $cond parameter to IDatabase::select() to determine what will be deleted from the user_properties table. $db:The IDatabase object, useful for accessing $db->buildLike() etc. 'DifferenceEngineAfterLoadNewText':called in DifferenceEngine::loadNewText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before returning true from this function. $differenceEngine:DifferenceEngine object 'DifferenceEngineLoadTextAfterNewContentIsLoaded':called in DifferenceEngine::loadText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before checking if the variable 's value is null. This hook can be used to inject content into said class member variable. $differenceEngine:DifferenceEngine object 'DifferenceEngineMarkPatrolledLink':Allows extensions to change the "mark as patrolled" link which is shown both on the diff header as well as on the bottom of a page, usually wrapped in a span element which has class="patrollink". $differenceEngine:DifferenceEngine object & $markAsPatrolledLink:The "mark as patrolled" link HTML(string) $rcid:Recent change ID(rc_id) for this change(int) 'DifferenceEngineMarkPatrolledRCID':Allows extensions to possibly change the rcid parameter. For example the rcid might be set to zero due to the user being the same as the performer of the change but an extension might still want to show it under certain conditions. & $rcid:rc_id(int) of the change or 0 $differenceEngine:DifferenceEngine object $change:RecentChange object $user:User object representing the current user 'DifferenceEngineNewHeader':Allows extensions to change the $newHeader variable, which contains information about the new revision, such as the revision 's author, whether the revision was marked as a minor edit or not, etc. $differenceEngine:DifferenceEngine object & $newHeader:The string containing the various #mw-diff-otitle[1-5] divs, which include things like revision author info, revision comment, RevisionDelete link and more $formattedRevisionTools:Array containing revision tools, some of which may have been injected with the DiffRevisionTools hook $nextlink:String containing the link to the next revision(if any) $status
Definition: hooks.txt:1266
$user
return true to allow those checks to and false if checking is done & $user
Definition: hooks.txt:1476
Title\newFromText
static newFromText( $text, $defaultNamespace=NS_MAIN)
Create a new Title from text, such as what one would find in a link.
Definition: Title.php:306
$file
if(PHP_SAPI !='cli-server') if(!isset( $_SERVER['SCRIPT_FILENAME'])) $file
Definition: router.php:42
Revision\newFromId
static newFromId( $id, $flags=0)
Load a page revision from a given revision ID number.
Definition: Revision.php:118
Maintenance\fatalError
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
Definition: Maintenance.php:485
captcha-old.count
count
Definition: captcha-old.py:249
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:329
wfTimestamp
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
Definition: GlobalFunctions.php:1912
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
User\newFromName
static newFromName( $name, $validate='valid')
Static factory method for creation from username.
Definition: User.php:585
Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
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:35
User\newSystemUser
static newSystemUser( $name, $options=[])
Static factory method for creation of a "system" user from username.
Definition: User.php:813
ImportTextFiles\__construct
__construct()
Default constructor.
Definition: importTextFiles.php:35
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:925
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:248
RecentChange\notifyEdit
static notifyEdit( $timestamp, $title, $minor, $user, $comment, $oldId, $lastTimestamp, $bot, $ip='', $oldSize=0, $newSize=0, $newId=0, $patrol=0, $tags=[])
Makes an entry in the database corresponding to an edit.
Definition: RecentChange.php:685
use
as see the revision history and available at free of to any person obtaining a copy of this software and associated documentation to deal in the Software without including without limitation the rights to use
Definition: MIT-LICENSE.txt:10
wfTimestampNow
wfTimestampNow()
Convenience function; returns MediaWiki timestamp for the present time.
Definition: GlobalFunctions.php:1941
ImportTextFiles
Maintenance script which reads in text files and imports their content to a page of the wiki.
Definition: importTextFiles.php:34
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:283
WikiRevision
Represents a revision, log entry or upload during the import process.
Definition: WikiRevision.php:37
RecentChange\notifyNew
static notifyNew( $timestamp, $title, $minor, $user, $comment, $bot, $ip='', $size=0, $newId=0, $patrol=0, $tags=[])
Makes an entry in the database corresponding to page creation Note: the title object must be loaded w...
Definition: RecentChange.php:759
Maintenance\addArg
addArg( $arg, $description, $required=true)
Add some args that are needed.
Definition: Maintenance.php:300
$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:1769
as
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
ImportTextFiles\execute
execute()
Do the actual work.
Definition: importTextFiles.php:51
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:462
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:434
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:52
MediaWikiServices
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
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular option exists.
Definition: Maintenance.php:269
Maintenance\getArg
getArg( $argId=0, $default=null)
Get an argument.
Definition: Maintenance.php:352