diocloid/LinkTitles
1
0
Fork 0
mirror of https://github.com/diocloid/LinkTitles.git synced 2025-07-13 01:39:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Use PageContentSave rather than ArticleSave hook.

Browse Source 
This commit also contains some refactoring which should lend itself to
increased performance.
This commit is contained in:
Daniel Kraus
2014-06-08 19:08:19 +02:00
parent 5745621366
commit adbc1ea5cd
3 changed files with 38 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
LinkTitles.body.php
View File

@ -28,7 +28,6 @@
/// Central class of the extension. Sets up parser hooks. /// Central class of the extension. Sets up parser hooks.
/// This class contains only static functions; do not instantiate. /// This class contains only static functions; do not instantiate.
/// @todo Use the current PageContentSave hook rather than the deprecated ArticleSave hook.
class LinkTitles { class LinkTitles {
/// Setup function, hooks the extension's functions to MediaWiki events. /// Setup function, hooks the extension's functions to MediaWiki events.
public static function setup() { public static function setup() {
@ -36,7 +35,7 @@
global $wgLinkTitlesParseOnRender; global $wgLinkTitlesParseOnRender;
global $wgHooks; global $wgHooks;
if ( $wgLinkTitlesParseOnEdit ) { if ( $wgLinkTitlesParseOnEdit ) {
$wgHooks['ArticleSave'][] = 'LinkTitles::onArticleSave'; $wgHooks['PageContentSave'][] = 'LinkTitles::onPageContentSave';
}; };
if ( $wgLinkTitlesParseOnRender ) { if ( $wgLinkTitlesParseOnRender ) {
$wgHooks['ArticleAfterFetchContent'][] = 'LinkTitles::onArticleAfterFetchContent'; $wgHooks['ArticleAfterFetchContent'][] = 'LinkTitles::onArticleAfterFetchContent';
@ -45,18 +44,18 @@
} }
/// Event handler that is hooked to the ArticleSave event. /// Event handler that is hooked to the ArticleSave event.
public static function onArticleSave( &$article, &$user, &$text, &$summary, public static function onPageContentSave( &$wikiPage, &$user, &$content, &$summary,
$minor, $watchthis, $sectionanchor, &$flags, &$status ) { $isMinor, $isWatch, $section, &$flags, &$status ) {
// To prevent time-consuming parsing of the page whenever // To prevent time-consuming parsing of the page whenever
// it is edited and saved, we only parse it if the flag // it is edited and saved, we only parse it if the flag
// 'minor edits' is not set. // 'minor edits' is not set.
return $minor or self::parseContent( $article, $text ); return $isMinor or self::parseContent( $wikiPage, $content );
} }
/// Event handler that is hooked to the ArticleAfterFetchContent event. /// Event handler that is hooked to the ArticleAfterFetchContent event.
/// @param $article Article object /// @param $article Article object
/// @param $content String that holds the article content /// @param $content Content object that holds the article content
public static function onArticleAfterFetchContent( &$article, &$content ) { public static function onArticleAfterFetchContent( &$article, &$content ) {
// The ArticleAfterFetchContent event is triggered whenever page content // The ArticleAfterFetchContent event is triggered whenever page content
// is retrieved from the database, i.e. also for editing etc. // is retrieved from the database, i.e. also for editing etc.
@ -71,17 +70,16 @@
/// Core function of the extension, performs the actual parsing of the content. /// Core function of the extension, performs the actual parsing of the content.
/// @param $article Article object /// @param $article Article object
/// @param $text String that holds the article content /// @param $content Content object that holds the article content
/// @returns true /// @returns true
static function parseContent( &$article, &$text ) { static function parseContent( &$article, &$content ) {
// If the page contains the magic word '__NOAUTOLINKS__', do not parse // If the page contains the magic word '__NOAUTOLINKS__', do not parse
// the content. // the content.
$noAutoLinks = MagicWord::get('MAG_LINKTITLES_NOAUTOLINKS'); if ( $content->matchMagicWord(
if ( $noAutoLinks -> match( $text ) ) { MagicWord::get('MAG_LINKTITLES_NOAUTOLINKS') ) ) {
return true; return true;
} }
$noAutoLinkTarget = MagicWord::get('MAG_LINKTITLES_NOTARGET');
// Configuration variables need to be defined here as globals. // Configuration variables need to be defined here as globals.
global $wgLinkTitlesPreferShortTitles; global $wgLinkTitlesPreferShortTitles;
@ -138,8 +136,11 @@
'(?<=\b)\S+\@(?:\S+\.)+\S+(?=\b)' . // email addresses '(?<=\b)\S+\@(?:\S+\.)+\S+(?=\b)' . // email addresses
')/i'; ')/i';
// Build a blacklist of pages that are not supposed to be link
// targets. This includes the current page.
$black_list = str_replace( '_', ' ', $black_list = str_replace( '_', ' ',
'("' . implode( '", "',$wgLinkTitlesBlackList ) . '")' ); '("' . implode( '", "',$wgLinkTitlesBlackList ) .
$myTitle->getDbKey() . '")' );
// Build an SQL query and fetch all page titles ordered by length from // Build an SQL query and fetch all page titles ordered by length from
@ -175,6 +176,8 @@
); );
} }
$text = $content->getContentHandler()->serializeContent($content);
// Iterate through the page titles // Iterate through the page titles
foreach( $res as $row ) { foreach( $res as $row ) {
// Obtain an instance of a Title class for the current database // Obtain an instance of a Title class for the current database
@ -190,41 +193,33 @@
// To prevent linking to pages that redirect to the current page, // To prevent linking to pages that redirect to the current page,
// obtain the title that the target page redirects to. Will be null // obtain the title that the target page redirects to. Will be null
// if there is no redirect. // if there is no redirect.
$redirectTitle = $targetPage->getRedirectTarget(); $redirectTitle = $targetPage->getContent()->getUltimateRedirectTarget();
if ( $redirectTitle ) {
// If the target page redirects to the current page, exit the
// function.
if ( $redirectTitle->equals($myTitle) ) {
continue;
}
}
if ( $noAutoLinkTarget->match($targetText) ) { // Proceed only if the currently examined page does not redirect to
continue; // our page and does not contain the no-target magic word
} if (
!( $redirectTitle && $redirectTitle->equals($myTitle) ) &&
!( $targetPage->getContent()->matchMagicWord(
MagicWord::get('MAG_LINKTITLES_NOTARGET') ) ) ) {
// Only proceed if we're not operating on the very same page, if the // split the page content by [[...]] groups
// target page does not have the __NOAUTOLINKTARGET__ magic word in
// it, and if the target page does not redirect to the current page.
if ( ! $myTitle->equals($targetTitle) ) {
// split the string by [[...]] groups
// credits to inhan @ StackOverflow for suggesting preg_split // credits to inhan @ StackOverflow for suggesting preg_split
// see http://stackoverflow.com/questions/10672286 // see http://stackoverflow.com/questions/10672286
$arr = preg_split( $delimiter, $text, -1, PREG_SPLIT_DELIM_CAPTURE ); $arr = preg_split( $delimiter, $text, -1, PREG_SPLIT_DELIM_CAPTURE );
// Escape certain special characters in the page title to prevent // Escape certain special characters in the page title to prevent
// regexp compilation errors // regexp compilation errors
$escapedTitle = preg_quote($targetTitleText, '/'); $quotedTitle = preg_quote($targetTitleText, '/');
// Depending on the global configuration setting $wgCapitalLinks, // Depending on the global configuration setting $wgCapitalLinks,
// the title has to be searched for either in a strictly case-sensitive // the title has to be searched for either in a strictly case-sensitive
// way, or in a 'fuzzy' way where the first letter of the title may // way, or in a 'fuzzy' way where the first letter of the title may
// be either case. // be either case.
if ( $wgCapitalLinks && ( $escapedTitle[0] != '\\' )) { if ( $wgCapitalLinks && ( $quotedTitle[0] != '\\' )) {
$searchTerm = '((?i)' . $escapedTitle[0] . '(?-i)' . $searchTerm = '((?i)' . $quotedTitle[0] . '(?-i)' .
substr($escapedTitle, 1) . ')'; substr($quotedTitle, 1) . ')';
} else { } else {
$searchTerm = '(' . $escapedTitle . ')'; $searchTerm = '(' . $quotedTitle . ')';
} }
for ( $i = 0; $i < count( $arr ); $i+=2 ) { for ( $i = 0; $i < count( $arr ); $i+=2 ) {
@ -286,15 +281,17 @@
for ( $i = 0; $i < count( $arr ); $i+=2 ) { for ( $i = 0; $i < count( $arr ); $i+=2 ) {
// even indexes will point to text that is not enclosed by brackets // even indexes will point to text that is not enclosed by brackets
$arr[$i] = preg_replace_callback( '/(?<![\:\.\@\/\?\&])' . $arr[$i] = preg_replace_callback( '/(?<![\:\.\@\/\?\&])' .
$wordStartDelim . '(' . $escapedTitle . ')' . $wordStartDelim . '(' . $quotedTitle . ')' .
$wordEndDelim . '/i', $callback, $arr[$i], $limit, $count ); $wordEndDelim . '/i', $callback, $arr[$i], $limit, $count );
if (( $limit >= 0 ) && ( $count > 0 )) { if (( $limit >= 0 ) && ( $count > 0 )) {
break; break;
}; };
}; };
$text = implode( '', $arr ); $text = implode( '', $arr );
} // @todo check if text was changed
}; // if ! $myTitle.equals($targetTitle) $content = $content->getContentHandler()->unserializeContent( $text );
} // $wgLinkTitlesSmartMode
}
}; // foreach $res as $row }; // foreach $res as $row
return true; return true;
} }
@ -311,10 +308,9 @@
// TODO: make this namespace-aware // TODO: make this namespace-aware
$titleObj = Title::makeTitle(0, $title); $titleObj = Title::makeTitle(0, $title);
$page = WikiPage::factory($titleObj); $page = WikiPage::factory($titleObj);
$content = $page->getContent();
$article = Article::newFromWikiPage($page, $context); $article = Article::newFromWikiPage($page, $context);
$text = $article->getContent(); LinkTitles::parseContent($article, $content);
LinkTitles::parseContent($article, $text);
$content = new WikitextContent($text);
$page->doEditContent($content, $page->doEditContent($content,
"Links to existing pages added by LinkTitles bot.", "Links to existing pages added by LinkTitles bot.",
EDIT_MINOR | EDIT_FORCE_BOT, EDIT_MINOR | EDIT_FORCE_BOT,

2
LinkTitles.php
View File

@ -155,7 +155,7 @@
'name' => 'LinkTitles', 'name' => 'LinkTitles',
'author' => '[https://www.mediawiki.org/wiki/User:Bovender Daniel Kraus]', 'author' => '[https://www.mediawiki.org/wiki/User:Bovender Daniel Kraus]',
'url' => 'https://www.mediawiki.org/wiki/Extension:LinkTitles', 'url' => 'https://www.mediawiki.org/wiki/Extension:LinkTitles',
'version' => '2.4.0', 'version' => '2.4.2',
'descriptionmsg' => 'linktitles-desc' 'descriptionmsg' => 'linktitles-desc'
); );

2
README.md
View File

@ -5,6 +5,8 @@ MediaWiki extension that automatically adds links to words that match titles of
For more information, see http://www.mediawiki.org/wiki/Extension:LinkTitles For more information, see http://www.mediawiki.org/wiki/Extension:LinkTitles
Minimum requirements: MediaWiki 1.21+, PHP 5.3
Source code documentation can be found at the [Github project Source code documentation can be found at the [Github project
pages](http://bovender.github.io/LinkTitles). pages](http://bovender.github.io/LinkTitles).