REL1_32/php/renderDump_8php_source.html

<?php

require_once __DIR__ . '/Maintenance.php';


class DumpRenderer extends Maintenance {


    private $count = 0;

    private $outputDirectory, $startTime;


    public function __construct() {

        parent::__construct();

        $this->addDescription(

            'Take page text out of an XML dump file and render basic HTML out to files' );

        $this->addOption( 'output-dir', 'The directory to output the HTML files to', true, true );

        $this->addOption( 'prefix', 'Prefix for the rendered files (defaults to wiki)', false, true );

        $this->addOption( 'parser', 'Use an alternative parser class', false, true );

    }


    public function execute() {

        $this->outputDirectory = $this->getOption( 'output-dir' );

        $this->prefix = $this->getOption( 'prefix', 'wiki' );

        $this->startTime = microtime( true );


        if ( $this->hasOption( 'parser' ) ) {

            global $wgParserConf;

            $wgParserConf['class'] = $this->getOption( 'parser' );

            $this->prefix .= "-{$wgParserConf['class']}";

        }


        $source = new ImportStreamSource( $this->getStdin() );

        $importer = new WikiImporter( $source, $this->getConfig() );


        $importer->setRevisionCallback(

            [ $this, 'handleRevision' ] );

        $importer->setNoticeCallback( function ( $msg, $params ) {

            echo wfMessage( $msg, $params )->text() . "\n";

        } );


        $importer->doImport();


        $delta = microtime( true ) - $this->startTime;

        $this->error( "Rendered {$this->count} pages in " . round( $delta, 2 ) . " seconds " );

        if ( $delta > 0 ) {

            $this->error( round( $this->count / $delta, 2 ) . " pages/sec" );

        }

        $this->error( "\n" );

    }


    public function handleRevision( $rev ) {

        $title = $rev->getTitle();

        if ( !$title ) {

            $this->error( "Got bogus revision with null title!" );


            return;

        }

        $display = $title->getPrefixedText();


        $this->count++;


        $sanitized = rawurlencode( $display );

        $filename = sprintf( "%s/%s-%07d-%s.html",

            $this->outputDirectory,

            $this->prefix,

            $this->count,

            $sanitized );

        $this->output( sprintf( "%s\n", $filename, $display ) );


        $user = new User();

        $options = ParserOptions::newFromUser( $user );


        $content = $rev->getContent();

        $output = $content->getParserOutput( $title, null, $options );


        file_put_contents( $filename,

            "<!DOCTYPE html>\n" .

            "<html lang=\"en\" dir=\"ltr\">\n" .

            "<head>\n" .

            "<meta charset=\"UTF-8\" />\n" .

            "<title>" . htmlspecialchars( $display ) . "</title>\n" .

            "</head>\n" .

            "<body>\n" .

            $output->getText() .

            "</body>\n" .

            "</html>" );

    }


}


$maintClass = DumpRenderer::class;

require_once RUN_MAINTENANCE_IF_MAIN;

$wgParserConf
$wgParserConf
Parser configuration.
Definition DefaultSettings.php:4158

DumpRenderer
Maintenance script that takes page text out of an XML dump file and render basic HTML out to files.
Definition renderDump.php:39

DumpRenderer\$outputDirectory
$outputDirectory
Definition renderDump.php:42

DumpRenderer\$count
$count
Definition renderDump.php:41

DumpRenderer\handleRevision
handleRevision( $rev)
Callback function for each revision, turn into HTML and save.
Definition renderDump.php:87

DumpRenderer\__construct
__construct()
Default constructor.
Definition renderDump.php:44

DumpRenderer\$startTime
$startTime
Definition renderDump.php:42

DumpRenderer\execute
execute()
Do the actual work.
Definition renderDump.php:53

ImportStreamSource
Imports a XML dump from a file (either from file upload, files on disk, or HTTP)
Definition ImportStreamSource.php:32

Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition maintenance.txt:39

Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition Maintenance.php:414

Maintenance\getStdin
getStdin( $len=null)
Return input from stdin.
Definition Maintenance.php:387

Maintenance\hasOption
hasOption( $name)
Checks to see if a particular option exists.
Definition Maintenance.php:257

Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition Maintenance.php:317

Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition Maintenance.php:236

Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition Maintenance.php:271

Maintenance\getConfig
getConfig()
Definition Maintenance.php:574

User
The User object encapsulates all of the user-specific settings (user_id, name, rights,...
Definition User.php:47

WikiImporter
XML file reader for the page data importer.
Definition WikiImporter.php:35

error
do that in ParserLimitReportFormat instead use this to modify the parameters of the image all existing parser cache entries will be invalid To avoid you ll need to handle that somehow(e.g. with the RejectParserCacheValue hook) because MediaWiki won 't do it for you. & $defaults error
Definition hooks.txt:2683

$options
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:2050

wfMessage
either a unescaped string or a HtmlArmor object after in associative array form externallinks including delete and has completed for all link tables whether this was an auto creation use $formDescriptor instead default is conds Array Extra conditions for the No matching items in log is displayed if loglist is empty msgKey Array If you want a nice box with a set this to the key of the message First element is the message additional optional elements are parameters for the key that are processed with wfMessage() -> params() ->parseAsBlock() - offset Set to overwrite offset parameter in $wgRequest set to '' to unset offset - wrap String Wrap the message in html(usually something like "&lt;div ...>$1&lt;/div>"). - flags Integer display flags(NO_ACTION_LINK, NO_EXTRA_USER_LINKS) 'LogException':Called before an exception(or PHP error) is logged. This is meant for integration with external error aggregation services

$output
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title e g db for database replication lag or jobqueue for job queue size converted to pseudo seconds It is possible to add more fields and they will be returned to the user in the API response after the basic globals have been set but before ordinary actions take place $output
Definition hooks.txt:2317

$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:1818

RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition maintenance.txt:50

$source
$source
Definition mwdoc-filter.php:46

$content
$content
Definition pageupdater.txt:72

$maintClass
$maintClass
Definition renderDump.php:126

$params
$params
Definition styleTest.css.php:44