X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=maintenance%2FgenerateSitemap.php;h=80d31f970f03720cef664459d8bd81b531858146;hb=63f9ffedd27f426b9fb8dd585ea484381aa2af00;hp=8ca7934123d4aa18fa5abac55f25821f53a3b5cb;hpb=4833675caae9bfdb8bc2dc193c88a155be720b06;p=lhc%2Fweb%2Fwiklou.git diff --git a/maintenance/generateSitemap.php b/maintenance/generateSitemap.php index 8ca7934123..80d31f970f 100644 --- a/maintenance/generateSitemap.php +++ b/maintenance/generateSitemap.php @@ -1,9 +1,10 @@ and + * Brion Vibber + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -19,21 +20,18 @@ define( 'GS_TALK', -1 ); * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. * http://www.gnu.org/copyleft/gpl.html * + * @file * @ingroup Maintenance - * - * @copyright Copyright © 2005, Ævar Arnfjörð Bjarmason - * @copyright Copyright © 2005, Jens Frank - * @copyright Copyright © 2005, Brion Vibber - * * @see http://www.sitemaps.org/ * @see http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd - * - * @license http://www.gnu.org/copyleft/gpl.html GNU General Public License 2.0 or later */ -require_once( dirname(__FILE__) . '/Maintenance.php' ); +require_once( dirname( __FILE__ ) . '/Maintenance.php' ); class GenerateSitemap extends Maintenance { + const GS_MAIN = -2; + const GS_TALK = -1; + /** * The maximum amount of urls in a sitemap file * @@ -60,11 +58,11 @@ class GenerateSitemap extends Maintenance { var $fspath; /** - * The path to append to the domain name + * The URL path to prepend to filenames in the index; should resolve to the same directory as $fspath * * @var string */ - var $path; + var $urlpath; /** * Whether or not to use compression @@ -123,42 +121,53 @@ class GenerateSitemap extends Maintenance { */ var $file; + /** + * Identifier to use in filenames, default $wgDBname + * + * @var string + */ + private $identifier; + /** * Constructor */ public function __construct() { parent::__construct(); $this->mDescription = "Creates a sitemap for the site"; - $this->addOption( 'fspath', 'The file system path to save to, e.g. /tmp/sitemap' . - "\n\t\tdefaults to current directory", false, true ); - $this->addOption( 'server', "The protocol and server name to use in URLs, e.g.\n" . - "\t\thttp://en.wikipedia.org. This is sometimes necessary because\n" . - "\t\tserver name detection may fail in command line scripts.", false, true ); + $this->addOption( 'fspath', 'The file system path to save to, e.g. /tmp/sitemap; defaults to current directory', false, true ); + $this->addOption( 'urlpath', 'The URL path corresponding to --fspath, prepended to filenames in the index; defaults to an empty string', false, true ); $this->addOption( 'compress', 'Compress the sitemap files, can take value yes|no, default yes', false, true ); + $this->addOption( 'identifier', 'What site identifier to use for the wiki, defaults to $wgDBname', false, true ); } /** * Execute */ public function execute() { - global $wgScriptPath; $this->setNamespacePriorities(); $this->url_limit = 50000; $this->size_limit = pow( 2, 20 ) * 10; $this->fspath = self::init_path( $this->getOption( 'fspath', getcwd() ) ); + $this->urlpath = $this->getOption( 'urlpath', "" ); + if ( $this->urlpath !== "" && substr( $this->urlpath, -1 ) !== '/' ) { + $this->urlpath .= '/'; + } + $this->identifier = $this->getOption( 'identifier', wfWikiID() ); $this->compress = $this->getOption( 'compress', 'yes' ) !== 'no'; $this->dbr = wfGetDB( DB_SLAVE ); $this->generateNamespaces(); $this->timestamp = wfTimestamp( TS_ISO_8601, wfTimestampNow() ); - $this->findex = fopen( "{$this->fspath}sitemap-index-" . wfWikiID() . ".xml", 'wb' ); + $this->findex = fopen( "{$this->fspath}sitemap-index-{$this->identifier}.xml", 'wb' ); $this->main(); } private function setNamespacePriorities() { + global $wgSitemapNamespacesPriorities; + // Custom main namespaces - $this->priorities[GS_MAIN] = '0.5'; + $this->priorities[self::GS_MAIN] = '0.5'; // Custom talk namesspaces - $this->priorities[GS_TALK] = '0.1'; + $this->priorities[self::GS_TALK] = '0.1'; // MediaWiki standard namespaces $this->priorities[NS_MAIN] = '1.0'; $this->priorities[NS_TALK] = '0.1'; @@ -176,21 +185,39 @@ class GenerateSitemap extends Maintenance { $this->priorities[NS_HELP_TALK] = '0.1'; $this->priorities[NS_CATEGORY] = '0.5'; $this->priorities[NS_CATEGORY_TALK] = '0.1'; + + // Custom priorities + if ( $wgSitemapNamespacesPriorities !== false ) { + /** + * @var $wgSitemapNamespacesPriorities array + */ + foreach ( $wgSitemapNamespacesPriorities as $namespace => $priority ) { + $float = floatval( $priority ); + if ( $float > 1.0 ) { + $priority = '1.0'; + } elseif ( $float < 0.0 ) { + $priority = '0.0'; + } + $this->priorities[$namespace] = $priority; + } + } } /** * Create directory if it does not exist and return pathname with a trailing slash + * @param $fspath string + * @return null|string */ private static function init_path( $fspath ) { - if( !isset( $fspath ) ) { + if ( !isset( $fspath ) ) { return null; } # Create directory if needed - if( $fspath && !is_dir( $fspath ) ) { - wfMkdirParents( $fspath ) or die("Can not create directory $fspath.\n"); + if ( $fspath && !is_dir( $fspath ) ) { + wfMkdirParents( $fspath, null, __METHOD__ ) or die( "Can not create directory $fspath.\n" ); } - return realpath( $fspath ). DIRECTORY_SEPARATOR ; + return realpath( $fspath ) . DIRECTORY_SEPARATOR ; } /** @@ -199,7 +226,7 @@ class GenerateSitemap extends Maintenance { function generateNamespaces() { // Only generate for specific namespaces if $wgSitemapNamespaces is an array. global $wgSitemapNamespaces; - if( is_array( $wgSitemapNamespaces ) ) { + if ( is_array( $wgSitemapNamespaces ) ) { $this->namespaces = $wgSitemapNamespaces; return; } @@ -221,11 +248,9 @@ class GenerateSitemap extends Maintenance { /** * Get the priority of a given namespace * - * @param int $namespace The namespace to get the priority for - + - * @return string + * @param $namespace Integer: the namespace to get the priority for + * @return String */ - function priority( $namespace ) { return isset( $this->priorities[$namespace] ) ? $this->priorities[$namespace] : $this->guessPriority( $namespace ); } @@ -235,20 +260,18 @@ class GenerateSitemap extends Maintenance { * default priority for the namespace, varies depending on whether it's * a talkpage or not. * - * @param int $namespace The namespace to get the priority for - * - * @return string + * @param $namespace Integer: the namespace to get the priority for + * @return String */ function guessPriority( $namespace ) { - return MWNamespace::isMain( $namespace ) ? $this->priorities[GS_MAIN] : $this->priorities[GS_TALK]; + return MWNamespace::isMain( $namespace ) ? $this->priorities[self::GS_MAIN] : $this->priorities[self::GS_TALK]; } /** * Return a database resolution of all the pages in a given namespace * - * @param int $namespace Limit the query to this namespace - * - * @return resource + * @param $namespace Integer: limit the query to this namespace + * @return Resource */ function getPageRes( $namespace ) { return $this->dbr->select( 'page', @@ -264,10 +287,8 @@ class GenerateSitemap extends Maintenance { /** * Main loop - * - * @access public */ - function main() { + public function main() { global $wgContLang; fwrite( $this->findex, $this->openIndex() ); @@ -280,7 +301,7 @@ class GenerateSitemap extends Maintenance { $i = $smcount = 0; $fns = $wgContLang->getFormattedNsText( $namespace ); - $this->output( "$namespace ($fns)" ); + $this->output( "$namespace ($fns)\n" ); foreach ( $res as $row ) { if ( $i++ === 0 || $i === $this->url_limit + 1 || $length + $this->limit[1] + $this->limit[2] > $this->size_limit ) { if ( $this->file !== false ) { @@ -297,15 +318,15 @@ class GenerateSitemap extends Maintenance { } $title = Title::makeTitle( $row->page_namespace, $row->page_title ); $date = wfTimestamp( TS_ISO_8601, $row->page_touched ); - $entry = $this->fileEntry( $title->getFullURL(), $date, $this->priority( $namespace ) ); + $entry = $this->fileEntry( $title->getCanonicalURL(), $date, $this->priority( $namespace ) ); $length += strlen( $entry ); $this->write( $this->file, $entry ); // generate pages for language variants - if($wgContLang->hasVariants()){ + if ( $wgContLang->hasVariants() ) { $variants = $wgContLang->getVariants(); - foreach($variants as $vCode){ - if($vCode==$wgContLang->getCode()) continue; // we don't want default variant - $entry = $this->fileEntry( $title->getFullURL('',$vCode), $date, $this->priority( $namespace ) ); + foreach ( $variants as $vCode ) { + if ( $vCode == $wgContLang->getCode() ) continue; // we don't want default variant + $entry = $this->fileEntry( $title->getCanonicalURL( '', $vCode ), $date, $this->priority( $namespace ) ); $length += strlen( $entry ); $this->write( $this->file, $entry ); } @@ -323,16 +344,23 @@ class GenerateSitemap extends Maintenance { /** * gzopen() / fopen() wrapper * - * @return resource + * @return Resource */ function open( $file, $flags ) { - return $this->compress ? gzopen( $file, $flags ) : fopen( $file, $flags ); + $resource = $this->compress ? gzopen( $file, $flags ) : fopen( $file, $flags ); + if( $resource === false ) { + wfDebugDieBacktrace( __METHOD__ . " error opening file $file with flags $flags. Check permissions?" ); + } + return $resource; } /** * gzwrite() / fwrite() wrapper */ function write( &$handle, $str ) { + if( $handle === true || $handle === false ) { + wfDebugDieBacktrace( __METHOD__ . " was passed a boolean as a file handle.\n" ); + } if ( $this->compress ) gzwrite( $handle, $str ); else @@ -352,23 +380,18 @@ class GenerateSitemap extends Maintenance { /** * Get a sitemap filename * - * @static - * - * @param int $namespace The namespace - * @param int $count The count - * - * @return string + * @param $namespace Integer: the namespace + * @param $count Integer: the count + * @return String */ function sitemapFilename( $namespace, $count ) { $ext = $this->compress ? '.gz' : ''; - return "sitemap-".wfWikiID()."-NS_$namespace-$count.xml$ext"; + return "sitemap-{$this->identifier}-NS_$namespace-$count.xml$ext"; } /** * Return the XML required to open an XML file * - * @static - * * @return string */ function xmlHead() { @@ -378,9 +401,7 @@ class GenerateSitemap extends Maintenance { /** * Return the XML schema being used * - * @static - * - * @returns string + * @return String */ function xmlSchema() { return 'http://www.sitemaps.org/schemas/sitemap/0.9'; @@ -389,7 +410,7 @@ class GenerateSitemap extends Maintenance { /** * Return the XML required to open a sitemap index file * - * @return string + * @return String */ function openIndex() { return $this->xmlHead() . '' . "\n"; @@ -398,16 +419,13 @@ class GenerateSitemap extends Maintenance { /** * Return the XML for a single sitemap indexfile entry * - * @static - * - * @param string $filename The filename of the sitemap file - * - * @return string + * @param $filename String: the filename of the sitemap file + * @return String */ function indexEntry( $filename ) { return "\t\n" . - "\t\t$filename\n" . + "\t\t{$this->urlpath}$filename\n" . "\t\t{$this->timestamp}\n" . "\t\n"; } @@ -415,9 +433,7 @@ class GenerateSitemap extends Maintenance { /** * Return the XML required to close a sitemap index file * - * @static - * - * @return string + * @return String */ function closeIndex() { return "\n"; @@ -426,7 +442,7 @@ class GenerateSitemap extends Maintenance { /** * Return the XML required to open a sitemap file * - * @return string + * @return String */ function openFile() { return $this->xmlHead() . '' . "\n"; @@ -435,13 +451,10 @@ class GenerateSitemap extends Maintenance { /** * Return the XML for a single sitemap entry * - * @static - * - * @param string $url An RFC 2396 compliant URL - * @param string $date A ISO 8601 date - * @param string $priority A priority indicator, 0.0 - 1.0 inclusive with a 0.1 stepsize - * - * @return string + * @param $url String: an RFC 2396 compliant URL + * @param $date String: a ISO 8601 date + * @param $priority String: a priority indicator, 0.0 - 1.0 inclusive with a 0.1 stepsize + * @return String */ function fileEntry( $url, $date, $priority ) { return @@ -455,8 +468,7 @@ class GenerateSitemap extends Maintenance { /** * Return the XML required to close sitemap file * - * @static - * @return string + * @return String */ function closeFile() { return "\n"; @@ -466,15 +478,16 @@ class GenerateSitemap extends Maintenance { * Populate $this->limit */ function generateLimit( $namespace ) { + // bug 17961: make a title with the longest possible URL in this namespace $title = Title::makeTitle( $namespace, str_repeat( "\xf0\xa8\xae\x81", 63 ) . "\xe5\x96\x83" ); $this->limit = array( strlen( $this->openFile() ), - strlen( $this->fileEntry( $title->getFullUrl(), wfTimestamp( TS_ISO_8601, wfTimestamp() ), $this->priority( $namespace ) ) ), + strlen( $this->fileEntry( $title->getCanonicalURL(), wfTimestamp( TS_ISO_8601, wfTimestamp() ), $this->priority( $namespace ) ) ), strlen( $this->closeFile() ) ); } } $maintClass = "GenerateSitemap"; -require_once( DO_MAINTENANCE ); +require_once( RUN_MAINTENANCE_IF_MAIN );