wiki.techinc.nl/includes/MagicWord.php

382 lines
9.1 KiB
PHP
Raw Normal View History

<?php
/**
* File for magic words
* @package MediaWiki
2005-04-28 20:46:11 +00:00
* @subpackage Parser
*/
/**
* This class encapsulates "magic words" such as #redirect, __NOTOC__, etc.
* Usage:
* if (MagicWord::get( 'redirect' )->match( $text ) )
2006-01-07 13:09:30 +00:00
*
* Possible future improvements:
* * Simultaneous searching for a number of magic words
2006-07-14 16:36:35 +00:00
* * MagicWord::$mObjects in shared memory
*
2006-01-07 13:09:30 +00:00
* Please avoid reading the data out of one of these objects and then writing
* special case code. If possible, add another match()-like function here.
*
2006-07-14 16:36:35 +00:00
* To add magic words in an extension, use the LanguageGetMagic hook. For
* magic words which are also Parser variables, add a MagicWordwgVariableIDs
* hook. Use string keys.
*
* @package MediaWiki
*/
class MagicWord {
/**#@+
2006-06-10 18:28:50 +00:00
* @private
*/
var $mId, $mSynonyms, $mCaseSensitive, $mRegex;
var $mRegexStart, $mBaseRegex, $mVariableRegex;
2006-07-14 16:36:35 +00:00
var $mModified, $mFound;
static public $mVariableIDsInitialised = false;
static public $mVariableIDs = array(
'currentmonth',
'currentmonthname',
'currentmonthnamegen',
'currentmonthabbrev',
'currentday',
'currentday2',
'currentdayname',
'currentyear',
'currenttime',
2006-08-14 22:43:50 +00:00
'currenthour',
'localmonth',
'localmonthname',
'localmonthnamegen',
'localmonthabbrev',
'localday',
'localday2',
'localdayname',
'localyear',
'localtime',
'localhour',
2006-07-14 16:36:35 +00:00
'numberofarticles',
'numberoffiles',
'sitename',
'server',
'servername',
'scriptpath',
'pagename',
'pagenamee',
'fullpagename',
'fullpagenamee',
'namespace',
'namespacee',
'currentweek',
'currentdow',
'localweek',
'localdow',
2006-07-14 16:36:35 +00:00
'revisionid',
'subpagename',
'subpagenamee',
'displaytitle',
'talkspace',
'talkspacee',
'subjectspace',
'subjectspacee',
'talkpagename',
'talkpagenamee',
'subjectpagename',
'subjectpagenamee',
'numberofusers',
'rawsuffix',
'newsectionlink',
'numberofpages',
'currentversion',
'basepagename',
'basepagenamee',
'urlencode',
'currenttimestamp',
'localtimestamp',
2006-07-14 16:36:35 +00:00
'directionmark',
'language',
'contentlanguage',
'pagesinnamespace',
'numberofadmins',
);
static public $mObjects = array();
/**#@-*/
function MagicWord($id = 0, $syn = '', $cs = false) {
$this->mId = $id;
$this->mSynonyms = (array)$syn;
$this->mCaseSensitive = $cs;
$this->mRegex = '';
$this->mRegexStart = '';
$this->mVariableRegex = '';
$this->mVariableStartToEndRegex = '';
$this->mModified = false;
}
/**
* Factory: creates an object representing an ID
* @static
*/
static function &get( $id ) {
2006-07-14 16:36:35 +00:00
if (!array_key_exists( $id, self::$mObjects ) ) {
$mw = new MagicWord();
$mw->load( $id );
2006-07-14 16:36:35 +00:00
self::$mObjects[$id] = $mw;
}
2006-07-14 16:36:35 +00:00
return self::$mObjects[$id];
}
/**
* Get an array of parser variable IDs
*/
static function getVariableIDs() {
if ( !self::$mVariableIDsInitialised ) {
# Deprecated constant definition hook, available for extensions that need it
$magicWords = array();
wfRunHooks( 'MagicWordMagicWords', array( &$magicWords ) );
foreach ( $magicWords as $word ) {
define( $word, $word );
}
# Get variable IDs
wfRunHooks( 'MagicWordwgVariableIDs', array( &self::$mVariableIDs ) );
self::$mVariableIDsInitialised = true;
}
return self::$mVariableIDs;
}
2006-01-07 13:31:29 +00:00
2003-12-14 14:25:44 +00:00
# Initialises this object with an ID
function load( $id ) {
2006-01-07 13:31:29 +00:00
global $wgContLang;
$this->mId = $id;
$wgContLang->getMagic( $this );
}
2006-01-07 13:31:29 +00:00
/**
* Preliminary initialisation
2006-06-10 18:28:50 +00:00
* @private
*/
function initRegex() {
#$variableClass = Title::legalChars();
# This was used for matching "$1" variables, but different uses of the feature will have
# different restrictions, which should be checked *after* the MagicWord has been matched,
# not here. - IMSoP
$escSyn = array();
foreach ( $this->mSynonyms as $synonym )
// In case a magic word contains /, like that's going to happen;)
$escSyn[] = preg_quote( $synonym, '/' );
$this->mBaseRegex = implode( '|', $escSyn );
$case = $this->mCaseSensitive ? '' : 'i';
$this->mRegex = "/{$this->mBaseRegex}/{$case}";
$this->mRegexStart = "/^(?:{$this->mBaseRegex})/{$case}";
$this->mVariableRegex = str_replace( "\\$1", "(.*?)", $this->mRegex );
2006-01-07 13:09:30 +00:00
$this->mVariableStartToEndRegex = str_replace( "\\$1", "(.*?)",
"/^(?:{$this->mBaseRegex})$/{$case}" );
}
2006-01-07 13:31:29 +00:00
/**
* Gets a regex representing matching the word
*/
function getRegex() {
if ($this->mRegex == '' ) {
$this->initRegex();
}
return $this->mRegex;
}
/**
* Gets the regexp case modifier to use, i.e. i or nothing, to be used if
* one is using MagicWord::getBaseRegex(), otherwise it'll be included in
* the complete expression
*/
function getRegexCase() {
if ( $this->mRegex === '' )
$this->initRegex();
return $this->mCaseSensitive ? '' : 'i';
}
/**
* Gets a regex matching the word, if it is at the string start
*/
function getRegexStart() {
if ($this->mRegex == '' ) {
$this->initRegex();
}
return $this->mRegexStart;
}
2004-01-12 00:55:01 +00:00
/**
* regex without the slashes and what not
*/
function getBaseRegex() {
if ($this->mRegex == '') {
$this->initRegex();
}
return $this->mBaseRegex;
}
2006-01-07 13:31:29 +00:00
/**
* Returns true if the text contains the word
* @return bool
*/
function match( $text ) {
return preg_match( $this->getRegex(), $text );
}
/**
* Returns true if the text starts with the word
* @return bool
*/
function matchStart( $text ) {
return preg_match( $this->getRegexStart(), $text );
}
/**
* Returns NULL if there's no match, the value of $1 otherwise
* The return code is the matched string, if there's no variable
* part in the regex and the matched variable part ($1) if there
* is one.
*/
2004-01-12 00:55:01 +00:00
function matchVariableStartToEnd( $text ) {
$matches = array();
2004-01-12 00:55:01 +00:00
$matchcount = preg_match( $this->getVariableStartToEndRegex(), $text, $matches );
if ( $matchcount == 0 ) {
return NULL;
} else {
2006-07-05 18:25:39 +00:00
# multiple matched parts (variable match); some will be empty because of
# synonyms. The variable will be the second non-empty one so remove any
# blank elements and re-sort the indices.
# See also bug 6526
$matches = array_values(array_filter($matches));
if ( count($matches) == 1 ) { return $matches[0]; }
else { return $matches[1]; }
2004-01-12 00:55:01 +00:00
}
}
/**
* Returns true if the text matches the word, and alters the
* input string, removing all instances of the word
*/
function matchAndRemove( &$text ) {
2006-07-14 16:36:35 +00:00
$this->mFound = false;
$text = preg_replace_callback( $this->getRegex(), array( &$this, 'pregRemoveAndRecord' ), $text );
return $this->mFound;
}
function matchStartAndRemove( &$text ) {
2006-07-14 16:36:35 +00:00
$this->mFound = false;
$text = preg_replace_callback( $this->getRegexStart(), array( &$this, 'pregRemoveAndRecord' ), $text );
return $this->mFound;
2006-01-07 13:31:29 +00:00
}
2006-07-14 16:36:35 +00:00
/**
* Used in matchAndRemove()
* @private
**/
function pregRemoveAndRecord( $match ) {
$this->mFound = true;
return '';
}
/**
* Replaces the word with something else
*/
function replace( $replacement, $subject, $limit=-1 ) {
$res = preg_replace( $this->getRegex(), wfRegexReplacement( $replacement ), $subject, $limit );
$this->mModified = !($res === $subject);
return $res;
}
2003-09-21 13:10:10 +00:00
/**
* Variable handling: {{SUBST:xxx}} style words
* Calls back a function to determine what to replace xxx with
* Input word must contain $1
*/
2003-09-21 13:10:10 +00:00
function substituteCallback( $text, $callback ) {
$res = preg_replace_callback( $this->getVariableRegex(), $callback, $text );
$this->mModified = !($res === $text);
return $res;
2003-09-21 13:10:10 +00:00
}
/**
* Matches the word, where $1 is a wildcard
*/
function getVariableRegex() {
if ( $this->mVariableRegex == '' ) {
2003-09-21 13:10:10 +00:00
$this->initRegex();
2006-01-07 13:09:30 +00:00
}
2003-09-21 13:10:10 +00:00
return $this->mVariableRegex;
}
/**
* Matches the entire string, where $1 is a wildcard
*/
function getVariableStartToEndRegex() {
if ( $this->mVariableStartToEndRegex == '' ) {
2004-01-12 00:55:01 +00:00
$this->initRegex();
2006-01-07 13:09:30 +00:00
}
2004-01-12 00:55:01 +00:00
return $this->mVariableStartToEndRegex;
}
/**
* Accesses the synonym list directly
*/
2003-09-21 13:10:10 +00:00
function getSynonym( $i ) {
return $this->mSynonyms[$i];
}
2006-07-02 17:47:24 +00:00
function getSynonyms() {
return $this->mSynonyms;
}
/**
2006-01-07 13:09:30 +00:00
* Returns true if the last call to replace() or substituteCallback()
* returned a modified text, otherwise false.
*/
function getWasModified(){
return $this->mModified;
}
/**
* $magicarr is an associative array of (magic word ID => replacement)
* This method uses the php feature to do several replacements at the same time,
* thereby gaining some efficiency. The result is placed in the out variable
* $result. The return value is true if something was replaced.
2006-01-07 13:09:30 +00:00
* @static
**/
function replaceMultiple( $magicarr, $subject, &$result ){
$search = array();
$replace = array();
foreach( $magicarr as $id => $replacement ){
$mw = MagicWord::get( $id );
$search[] = $mw->getRegex();
$replace[] = $replacement;
}
$result = preg_replace( $search, $replace, $subject );
return !($result === $subject);
}
/**
* Adds all the synonyms of this MagicWord to an array, to allow quick
* lookup in a list of magic words
*/
function addToArray( &$array, $value ) {
foreach ( $this->mSynonyms as $syn ) {
$array[$syn] = $value;
}
}
function isCaseSensitive() {
return $this->mCaseSensitive;
}
}
?>