手始めに、私は自分の PHP スキルが哀れであることを認めなければなりません (これを 3 日間行っています)。
この 3 日間で、mediawiki で編集したばかりのページを解析する拡張機能を大幅に変更しました。当初の目的は、データベース内の他のページの名前と一致するテキストのページを解析し、それらを自動リンクすることでした。ただし、この機能は「メイン」名前空間 (名前空間 0) でのみ実行されます。名前空間の加重ホワイトリストを使用して、名前空間全体のリンクを解析するように変更しました。(ホワイトリストの場所に基づいて、先着順で重み付けされます。ホワイトリストがDevelopment, Rules 開発に勝るルールの場合。)
拡張機能をさらに変更して、現在のページの名前空間をホワイト リスト配列の先頭にプッシュすることで優先順位を付け、現在のユーザー グループの所属を特定して、優先リストをさらに変更したいと考えています。
- ユーザー グループの所属を特定する
- 現在のページの名前空間を決定する 解決済み $var=$article->getTitle()->getNamespace();
- 値を配列の先頭にプッシュする 解決済み array_unshift($hastack, $needle);
誰かが、少なくとも最初の 2 つのことを説明しているサイトを教えてくれれば、非常にありがたいです。(メディアウィキ コミュニティはこれまであまり役に立たなかった)
コード例を提供する場合は、愚かさを保つようにしてください。私はこの{{shrug}}に慣れていません（コードサンプルphpをシンプルに保つことを意味します...拡張可能であるため、常により良い方法がありますが、私はそうではありません追加のモジュールに精通しています。)
問題の MediaWiki のバージョンは 1.21 です (2013 年 7 月現在の安定版)
注: 何らかの理由でコードが正しく表示されませんが、行が失われることはありません。
ホワイトリストの配列は次のように定義されます。
$wgLinkTitlesNamespaceWhitelist = array(5000, 5002, 5004, 5006,0);
メインファイル LinkTitles5000_body,php
if ( !defined( 'MEDIAWIKI' ) ) {
die( 'Not an entry point.' );
}
/*
function dump($var) {
error_log(print_r($var, TRUE) . "\n", 3, 'php://stderr');
};
*/
class LinkTitles_5000 {
static $safeTitle;
/// Setup function, hooks the extension's functions to MediaWiki events.
public static function setup() {
global $wgLinkTitlesParseOnEdit;
global $wgLinkTitlesParseOnRender;
global $wgHooks;
if ( $wgLinkTitlesParseOnEdit ) {
$wgHooks['ArticleSave'][] = 'LinkTitles_5000::onArticleSave';
};
if ( $wgLinkTitlesParseOnRender ) {
$wgHooks['ArticleAfterFetchContent'][] = 'LinkTitles_5000::onArticleAfterFetchContent';
};
$wgHooks['ParserBeforeTidy'][] = 'LinkTitles_5000::removeMagicWord';
}
/// This function is hooked to the ArticleSave event.
/// It will be called whenever a page is about to be
/// saved.
public static function onArticleSave( &$article, &$user, &$text, &$summary,
$minor, $watchthis, $sectionanchor, &$flags, &$status ) {
// To prevent time-consuming parsing of the page whenever
// it is edited and saved, we only parse it if the flag
// 'minor edits' is not set.
return $minor or self::parseContent( $article, $text );
}
/// Called when an ArticleAfterFetchContent event occurs; this requires the
/// $wgLinkTitlesParseOnRender option to be set to 'true'
public static function onArticleAfterFetchContent( &$article, &$content ) {
// The ArticleAfterFetchContent event is triggered whenever page content
// is retrieved from the database, i.e. also for editing etc.
// Therefore we access the global $action variabl to only parse the
// content when the page is viewed.
global $action;
if ( in_array( $action, array('view', 'render', 'purge') ) ) {
self::parseContent( $article, $content );
};
return true;
}
/// This function performs the actual parsing of the content.
static function parseContent( &$article, &$text ) {
// If the page contains the magic word '__NOAUTOLINKS__', do not parse
// the content.
$mw = MagicWord::get('MAG_LINKTITLES_TERMINOLOGY_NOAUTOLINKS');
if ( $mw -> match( $text ) ) {
return true;
}
// Configuration variables need to be defined here as globals.
global $wgLinkTitlesPreferShortTitles;
global $wgLinkTitlesMinimumTitleLength;
global $wgLinkTitlesParseHeadings;
global $wgLinkTitlesBlackList;
global $wgLinkTitlesSkipTemplates;
global $wgLinkTitlesFirstOnly;
global $wgLinkTitlesWordStartOnly;
global $wgLinkTitlesWordEndOnly;
// global $wgLinkTitlesIgnoreCase;
global $wgLinkTitlesSmartMode;
global $wgCapitalLinks;
global $wgLinkTitlesNamespaceWhitelist;
global $wgExtraNamespaces;
( $wgLinkTitlesWordStartOnly ) ? $wordStartDelim = '\b' : $wordStartDelim = '';
( $wgLinkTitlesWordEndOnly ) ? $wordEndDelim = '\b' : $wordEndDelim = '';
// ( $wgLinkTitlesIgnoreCase ) ? $regexModifier = 'i' : $regexModifier = '';
// To prevent adding self-references, we now
// extract the current page's title.
$myTitle = $article->getTitle()->getText();
( $wgLinkTitlesPreferShortTitles ) ? $sort_order = 'ASC' : $sort_order = 'DESC';
( $wgLinkTitlesFirstOnly ) ? $limit = 1 : $limit = -1;
if ( $wgLinkTitlesSkipTemplates )
{
$templatesDelimiter = '{{.+}}';
} else {
$templatesDelimiter = '{{[^|]+?}}|{{.+\|';
};
// Build a regular expression that will capture existing wiki links ("[[...]]"),
// wiki headings ("= ... =", "== ... ==" etc.),
// urls ("http://example.com", "[http://example.com]", "[http://example.com Description]",
// and email addresses ("mail@example.com").
// Since there is a user option to skip headings, we make this part of the expression
// optional. Note that in order to use preg_split(), it is important to have only one
// capturing subpattern (which precludes the use of conditional subpatterns).
( $wgLinkTitlesParseHeadings ) ? $delimiter = '' : $delimiter = '=+.+?=+|';
$urlPattern = '[a-z]+?\:\/\/(?:\S+\.)+\S+(?:\/.*)?';
$delimiter = '/(' . $delimiter . '\[\[.*?\]\]|' . $templatesDelimiter .
'|\[' . $urlPattern . '\s.+?\]|'. $urlPattern .
'(?=\s|$)|(?<=\b)\S+\@(?:\S+\.)+\S+(?=\b))/i';
$black_list = str_replace( '_', ' ',
'("' . implode( '", "',$wgLinkTitlesBlackList ) . '")' );
// Depending on the global setting $wgCapitalLinks, we need
// different callback functions further down.
if ( $wgCapitalLinks ) {
$callBack = "LinkTitles_5000::CallBackCaseInsensitive";
} else {
$callBack = "LinkTitles_5000::CallBackCaseSensitive";
}
# Added to suuport $wgLinkTitlesNamespaceWhitelist
foreach ($wgLinkTitlesNamespaceWhitelist as $LT_namespace){
# Create the link part reflecting NameSpace:
# if namespace is main (0) set to empty string
if ($LT_namespace === 0){
$LT_namespacePart = "";
} else {
$LT_namespacePart = str_replace('_', ' ', $wgExtraNamespaces[(int)$LT_namespace]);
$LT_namespacePart = $LT_namespacePart . ":";
}
# ===
// Build an SQL query and fetch all page titles ordered
// by length from shortest to longest.
// Only titles from 'normal' pages (namespace uid = 0)
// are returned.
$dbr = wfGetDB( DB_SLAVE );
# modified to suuport $wgLinkTitlesNamespaceWhitelist
# 'page_namespace = 0' becomes 'page_namespace = ' . $LT_namespace,
# ===
$res = $dbr->select(
$wgDBprefix . 'page',
'page_title, page_namespace',
array(
'page_namespace = ' . strval($LT_namespace),
'CHAR_LENGTH(page_title) >= ' . $wgLinkTitlesMinimumTitleLength,
'page_title NOT IN ' . $black_list,
),
__METHOD__,
array( 'ORDER BY' => 'CHAR_LENGTH(page_title) ' . $sort_order )
);
// Iterate through the page titles
foreach( $res as $row ) {
// Page titles are stored in the database with spaces
// replaced by underscores. Therefore we now convert
// the underscores back to spaces.
$title = str_replace('_', ' ', $row->page_title);
if ( $title != $myTitle ) {
LinkTitles_5000::$safeTitle = str_replace( '/', '\/', $title );
# add this to skip the function if more than 1 level of sub pages
# Thus if 0 or 1 "\/" is found we continue and process the entry
# if two or more are found we go AARRRRRGGGGHHHHH and skip it!
if (substr_count(LinkTitles_5000::$safeTitle, '\/') >1) {
continue;
}
# adding this to allow for sub pages to be broken into their parts
$LT5000_pos = strpos(LinkTitles_5000::$safeTitle, "\/");
if ($LT5000_pos !== false){
$LT5000_front = substr(LinkTitles_5000::$safeTitle, 0, $LT5000_pos);
$LT5000_back = substr(LinkTitles_5000::$safeTitle, $LT5000_pos+1);
LinkTitles_5000::$safeTitle = substr($title, $LT5000_pos+1);
} else {
$LT5000_back = '';
$LT5000_front = LinkTitles_5000::$safeTitle;;
}
// split the string by [[...]] groups
// credits to inhan @ StackOverflow for suggesting preg_split
// see http://stackoverflow.com/questions/10672286
$arr = preg_split( $delimiter, $text, -1, PREG_SPLIT_DELIM_CAPTURE );
// Depending on the global configuration setting $wgCapitalLinks,
// 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
// be either case.
if ( $wgCapitalLinks ) {
$searchTerm = '((?i)' . LinkTitles_5000::$safeTitle[0] . '(?-i)' .
substr(LinkTitles_5000::$safeTitle, 1) . ')';
} else {
$searchTerm = '(' . LinkTitles_5000::$safeTitle . ')';
}
$LT5000_out = "[[" . $LT_namespacePart . $title . "|";
for ( $i = 0; $i < count( $arr ); $i+=2 ) {
// even indexes will point to text that is not enclosed by brackets
$arr[$i] = preg_replace( '/(?<![\:\.\@\/\?\&])' .
$wordStartDelim . $searchTerm . $wordEndDelim . '/',
$LT5000_out.'$1]]', $arr[$i], $limit, $count );
if (( $limit >= 0 ) && ( $count > 0 )) {
break;
};
};
$text = implode( '', $arr );
// If smart mode is turned on, the extension will perform a second
// pass on the page and add links with aliases where the case does
// not match.
if ($wgLinkTitlesSmartMode) {
// split the string by [[...]] groups
// credits to inhan @ StackOverflow for suggesting preg_split
// see http://stackoverflow.com/questions/10672286
$arr = preg_split( $delimiter, $text, -1, PREG_SPLIT_DELIM_CAPTURE );
for ( $i = 0; $i < count( $arr ); $i+=2 ) {
// even indexes will point to text that is not enclosed by brackets
$arr[$i] = preg_replace_callback( '/(?<![\:\.\@\/\?\&])' .
$wordStartDelim . '(' . LinkTitles_5000::$safeTitle . ')' .
$wordEndDelim . '/i', $callBack, $arr[$i], $limit, $count );
if (( $limit >= 0 ) && ( $count > 0 )) {
break;
};
};
$text = implode( '', $arr );
}
}; // if $title != $myTitle
}; // foreach $res as $row
}; // foreach $wgLinkTitlesNamespaceWhitelist as $LT_namespace
return true;
}
static function CallBackCaseInsensitive($matches) {
if ($LT5000_pos !== false){
# this if a / was found in the first place
$LT5000_call_out = $LT_namespacePart . $LT5000_front . '/' . $LT5000_back;
} else {
# this if there was no slash
$LT5000_call_out = $LT_namespacePart . $matches[0];
}
if ( strcmp(substr(LinkTitles_5000::$safeTitle, 1), substr($matches[0], 1)) == 0 ) {
return '[[' . $LT5000_call_out . '|]]';
} else {
return '[[' . $LT5000_call_out . '|' . $matches[0] . ']]';
}
}
static function CallBackCaseSensitive($matches) {
if ($LT5000_pos !== false){
# this if a / was found in the first place
$LT5000_call_out = $LT_namespacePart . $LT5000_front . '/' . $LT5000_back;
} else {
# this if there was no slash
$LT5000_call_out = $LT_namespacePart . $matches[0];
}
if ( strcmp(substr(LinkTitles_5000::$safeTitle, 0), substr($matches[0], 0)) == 0 ) {
return '[['. $LT5000_call_out . '|]]';
} else {
return '[[' . $LT5000_call_out . '|' . $matches[0] . ']]';
}
}
static function removeMagicWord( &$parser, &$text ) {
$mw = MagicWord::get('MAG_LINKTITLES_TERMINOLOGY_NOAUTOLINKS');
$mw -> matchAndRemove( $text );
return true;
}
}
モジュール ローダー関数 LinkTitles_5000.php:
if ( !defined( 'MEDIAWIKI' ) ) {
die( 'Not an entry point.' );
}
/*
error_reporting(E_ALL);
ini_set('display_errors', 'On');
ini_set('error_log', 'php://stderr');
$wgMainCacheType = CACHE_NONE;
$wgCacheDirectory = false;
*/
// Configuration variables
$wgLinkTitlesPreferShortTitles = false;
$wgLinkTitlesMinimumTitleLength = 3;
$wgLinkTitlesParseHeadings = false;
$wgLinkTitlesParseOnEdit = true;
$wgLinkTitlesParseOnRender = false;
$wgLinkTitlesSkipTemplates = false;
$wgLinkTitlesBlackList = array();
$wgLinkTitlesFirstOnly = false;
$wgLinkTitlesWordStartOnly = true;
$wgLinkTitlesWordEndOnly = true;
$wgLinkTitlesSmartMode = true;
$wgLinkTitlesNamespaceWhitelist = array();
$wgExtensionCredits['parserhook'][] = array(
'path' => FILE,
'name' => 'LinkTitles_5000',
'author' => '[https://www.mediawiki.org/wiki/User:Bovender Daniel Kraus]',
'url' => 'https://www.mediawiki.org/wiki/Extension:LinkTitles',
'version' => '2.2.0',
'descriptionmsg' => 'linktitles-desc'
);
$wgExtensionMessagesFiles['LinkTitles_5000'] = dirname( FILE ) . '/LinkTitles_5000.i18n.php';
$wgExtensionMessagesFiles['LinkTitlesMagic_5000'] = dirname( FILE ) . '/LinkTitles_5000.i18n.magic.php';
$wgAutoloadClasses['LinkTitles_5000'] = dirname( FILE ) . '/LinkTitles_5000.body.php';
$wgExtensionFunctions[] = 'LinkTitles_5000::setup';
// vim: ts=2:sw=2:noet