<?php
/**
* File for magic words
- * @package MediaWiki
- * @subpackage Parser
+ *
+ * See docs/magicword.txt
+ *
+ * @file
+ * @ingroup Parser
*/
/**
* 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.
*
- * To add magic words in an extension, use the LanguageGetMagic hook. For
+ * 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
+ * @ingroup Parser
*/
class MagicWord {
/**#@+
static public $mVariableIDsInitialised = false;
static public $mVariableIDs = array(
'currentmonth',
+ 'currentmonth1',
'currentmonthname',
'currentmonthnamegen',
'currentmonthabbrev',
'currenttime',
'currenthour',
'localmonth',
+ 'localmonth1',
'localmonthname',
'localmonthnamegen',
'localmonthabbrev',
'localhour',
'numberofarticles',
'numberoffiles',
+ 'numberofedits',
+ 'articlepath',
'sitename',
'server',
'servername',
'scriptpath',
+ 'stylepath',
'pagename',
'pagenamee',
'fullpagename',
'revisionday',
'revisionday2',
'revisionmonth',
+ 'revisionmonth1',
'revisionyear',
'revisiontimestamp',
+ 'revisionuser',
'subpagename',
'subpagenamee',
- 'displaytitle',
'talkspace',
'talkspacee',
'subjectspace',
'subjectpagename',
'subjectpagenamee',
'numberofusers',
- 'rawsuffix',
- 'newsectionlink',
+ 'numberofactiveusers',
'numberofpages',
'currentversion',
'basepagename',
'basepagenamee',
- 'urlencode',
'currenttimestamp',
'localtimestamp',
'directionmark',
- 'language',
'contentlanguage',
- 'pagesinnamespace',
'numberofadmins',
- 'defaultsort',
+ 'numberofviews',
+ );
+
+ /* Array of caching hints for ParserCache */
+ static public $mCacheTTLs = array (
+ 'currentmonth' => 86400,
+ 'currentmonth1' => 86400,
+ 'currentmonthname' => 86400,
+ 'currentmonthnamegen' => 86400,
+ 'currentmonthabbrev' => 86400,
+ 'currentday' => 3600,
+ 'currentday2' => 3600,
+ 'currentdayname' => 3600,
+ 'currentyear' => 86400,
+ 'currenttime' => 3600,
+ 'currenthour' => 3600,
+ 'localmonth' => 86400,
+ 'localmonth1' => 86400,
+ 'localmonthname' => 86400,
+ 'localmonthnamegen' => 86400,
+ 'localmonthabbrev' => 86400,
+ 'localday' => 3600,
+ 'localday2' => 3600,
+ 'localdayname' => 3600,
+ 'localyear' => 86400,
+ 'localtime' => 3600,
+ 'localhour' => 3600,
+ 'numberofarticles' => 3600,
+ 'numberoffiles' => 3600,
+ 'numberofedits' => 3600,
+ 'currentweek' => 3600,
+ 'currentdow' => 3600,
+ 'localweek' => 3600,
+ 'localdow' => 3600,
+ 'numberofusers' => 3600,
+ 'numberofactiveusers' => 3600,
+ 'numberofpages' => 3600,
+ 'currentversion' => 86400,
+ 'currenttimestamp' => 3600,
+ 'localtimestamp' => 3600,
+ 'pagesinnamespace' => 3600,
+ 'numberofadmins' => 3600,
+ 'numberofviews' => 3600,
+ 'numberingroup' => 3600,
+ );
+
+ static public $mDoubleUnderscoreIDs = array(
+ 'notoc',
+ 'nogallery',
+ 'forcetoc',
+ 'toc',
+ 'noeditsection',
+ 'newsectionlink',
+ 'nonewsectionlink',
+ 'hiddencat',
+ 'index',
+ 'noindex',
+ 'staticredirect',
+ 'notitleconvert',
+ 'nocontentconvert',
+ );
+
+ static public $mSubstIDs = array(
+ 'subst',
+ 'safesubst',
);
static public $mObjects = array();
+ static public $mDoubleUnderscoreArray = null;
/**#@-*/
- function MagicWord($id = 0, $syn = '', $cs = false) {
+ function __construct($id = 0, $syn = '', $cs = false) {
$this->mId = $id;
$this->mSynonyms = (array)$syn;
$this->mCaseSensitive = $cs;
/**
* Factory: creates an object representing an ID
* @static
+ * @return MagicWord
*/
static function &get( $id ) {
- if (!array_key_exists( $id, self::$mObjects ) ) {
+ wfProfileIn( __METHOD__ );
+ if ( !isset( self::$mObjects[$id] ) ) {
$mw = new MagicWord();
$mw->load( $id );
self::$mObjects[$id] = $mw;
}
+ wfProfileOut( __METHOD__ );
return self::$mObjects[$id];
}
return self::$mVariableIDs;
}
+ /**
+ * Get an array of parser substitution modifier IDs
+ */
+ static function getSubstIDs() {
+ return self::$mSubstIDs;
+ }
+
+ /* Allow external reads of TTL array */
+ static function getCacheTTL($id) {
+ if (array_key_exists($id,self::$mCacheTTLs)) {
+ return self::$mCacheTTLs[$id];
+ } else {
+ return -1;
+ }
+ }
+
+ /** Get a MagicWordArray of double-underscore entities */
+ static function getDoubleUnderscoreArray() {
+ if ( is_null( self::$mDoubleUnderscoreArray ) ) {
+ self::$mDoubleUnderscoreArray = new MagicWordArray( self::$mDoubleUnderscoreIDs );
+ }
+ return self::$mDoubleUnderscoreArray;
+ }
+
+ /**
+ * Clear the self::$mObjects variable
+ * For use in parser tests
+ */
+ public static function clearCache() {
+ self::$mObjects = array();
+ }
+
# Initialises this object with an ID
function load( $id ) {
global $wgContLang;
* @private
*/
function initRegex() {
- #$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
-
+ // Sort the synonyms by length, descending, so that the longest synonym
+ // matches in precedence to the shortest
+ $synonyms = $this->mSynonyms;
+ usort( $synonyms, array( $this, 'compareStringLength' ) );
+
$escSyn = array();
- foreach ( $this->mSynonyms as $synonym )
+ foreach ( $synonyms 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 ? '' : 'iu';
$this->mRegex = "/{$this->mBaseRegex}/{$case}";
$this->mRegexStart = "/^(?:{$this->mBaseRegex})/{$case}";
"/^(?:{$this->mBaseRegex})$/{$case}" );
}
+ /**
+ * A comparison function that returns -1, 0 or 1 depending on whether the
+ * first string is longer, the same length or shorter than the second
+ * string.
+ */
+ function compareStringLength( $s1, $s2 ) {
+ $l1 = strlen( $s1 );
+ $l2 = strlen( $s2 );
+ if ( $l1 < $l2 ) {
+ return 1;
+ } elseif ( $l1 > $l2 ) {
+ return -1;
+ } else {
+ return 0;
+ }
+ }
+
/**
* Gets a regex representing matching the word
*/
* @return bool
*/
function match( $text ) {
- return preg_match( $this->getRegex(), $text );
+ return (bool)preg_match( $this->getRegex(), $text );
}
/**
* @return bool
*/
function matchStart( $text ) {
- return preg_match( $this->getRegexStart(), $text );
+ return (bool)preg_match( $this->getRegexStart(), $text );
}
/**
$matches = array();
$matchcount = preg_match( $this->getVariableStartToEndRegex(), $text, $matches );
if ( $matchcount == 0 ) {
- return NULL;
+ return null;
} else {
# multiple matched parts (variable match); some will be empty because of
# synonyms. The variable will be the second non-empty one so remove any
function isCaseSensitive() {
return $this->mCaseSensitive;
}
+
+ function getId() {
+ return $this->mId;
+ }
}
-?>
+/**
+ * Class for handling an array of magic words
+ * @ingroup Parser
+ */
+class MagicWordArray {
+ var $names = array();
+ var $hash;
+ var $baseRegex, $regex;
+ var $matches;
+
+ function __construct( $names = array() ) {
+ $this->names = $names;
+ }
+
+ /**
+ * Add a magic word by name
+ */
+ public function add( $name ) {
+ $this->names[] = $name;
+ $this->hash = $this->baseRegex = $this->regex = null;
+ }
+
+ /**
+ * Add a number of magic words by name
+ */
+ public function addArray( $names ) {
+ $this->names = array_merge( $this->names, array_values( $names ) );
+ $this->hash = $this->baseRegex = $this->regex = null;
+ }
+
+ /**
+ * Get a 2-d hashtable for this array
+ */
+ function getHash() {
+ if ( is_null( $this->hash ) ) {
+ global $wgContLang;
+ $this->hash = array( 0 => array(), 1 => array() );
+ foreach ( $this->names as $name ) {
+ $magic = MagicWord::get( $name );
+ $case = intval( $magic->isCaseSensitive() );
+ foreach ( $magic->getSynonyms() as $syn ) {
+ if ( !$case ) {
+ $syn = $wgContLang->lc( $syn );
+ }
+ $this->hash[$case][$syn] = $name;
+ }
+ }
+ }
+ return $this->hash;
+ }
+
+ /**
+ * Get the base regex
+ */
+ function getBaseRegex() {
+ if ( is_null( $this->baseRegex ) ) {
+ $this->baseRegex = array( 0 => '', 1 => '' );
+ foreach ( $this->names as $name ) {
+ $magic = MagicWord::get( $name );
+ $case = intval( $magic->isCaseSensitive() );
+ foreach ( $magic->getSynonyms() as $i => $syn ) {
+ $group = "(?P<{$i}_{$name}>" . preg_quote( $syn, '/' ) . ')';
+ if ( $this->baseRegex[$case] === '' ) {
+ $this->baseRegex[$case] = $group;
+ } else {
+ $this->baseRegex[$case] .= '|' . $group;
+ }
+ }
+ }
+ }
+ return $this->baseRegex;
+ }
+
+ /**
+ * Get an unanchored regex that does not match parameters
+ */
+ function getRegex() {
+ if ( is_null( $this->regex ) ) {
+ $base = $this->getBaseRegex();
+ $this->regex = array( '', '' );
+ if ( $this->baseRegex[0] !== '' ) {
+ $this->regex[0] = "/{$base[0]}/iuS";
+ }
+ if ( $this->baseRegex[1] !== '' ) {
+ $this->regex[1] = "/{$base[1]}/S";
+ }
+ }
+ return $this->regex;
+ }
+
+ /**
+ * Get a regex for matching variables with parameters
+ */
+ function getVariableRegex() {
+ return str_replace( "\\$1", "(.*?)", $this->getRegex() );
+ }
+
+ /**
+ * Get a regex anchored to the start of the string that does not match parameters
+ */
+ function getRegexStart() {
+ $base = $this->getBaseRegex();
+ $newRegex = array( '', '' );
+ if ( $base[0] !== '' ) {
+ $newRegex[0] = "/^(?:{$base[0]})/iuS";
+ }
+ if ( $base[1] !== '' ) {
+ $newRegex[1] = "/^(?:{$base[1]})/S";
+ }
+ return $newRegex;
+ }
+
+ /**
+ * Get an anchored regex for matching variables with parameters
+ */
+ function getVariableStartToEndRegex() {
+ $base = $this->getBaseRegex();
+ $newRegex = array( '', '' );
+ if ( $base[0] !== '' ) {
+ $newRegex[0] = str_replace( "\\$1", "(.*?)", "/^(?:{$base[0]})$/iuS" );
+ }
+ if ( $base[1] !== '' ) {
+ $newRegex[1] = str_replace( "\\$1", "(.*?)", "/^(?:{$base[1]})$/S" );
+ }
+ return $newRegex;
+ }
+
+ /**
+ * Parse a match array from preg_match
+ * Returns array(magic word ID, parameter value)
+ * If there is no parameter value, that element will be false.
+ */
+ function parseMatch( $m ) {
+ reset( $m );
+ while ( list( $key, $value ) = each( $m ) ) {
+ if ( $key === 0 || $value === '' ) {
+ continue;
+ }
+ $parts = explode( '_', $key, 2 );
+ if ( count( $parts ) != 2 ) {
+ // This shouldn't happen
+ // continue;
+ throw new MWException( __METHOD__ . ': bad parameter name' );
+ }
+ list( /* $synIndex */, $magicName ) = $parts;
+ $paramValue = next( $m );
+ return array( $magicName, $paramValue );
+ }
+ // This shouldn't happen either
+ throw new MWException( __METHOD__.': parameter not found' );
+ }
+
+ /**
+ * Match some text, with parameter capture
+ * Returns an array with the magic word name in the first element and the
+ * parameter in the second element.
+ * Both elements are false if there was no match.
+ */
+ public function matchVariableStartToEnd( $text ) {
+ $regexes = $this->getVariableStartToEndRegex();
+ foreach ( $regexes as $regex ) {
+ if ( $regex !== '' ) {
+ $m = false;
+ if ( preg_match( $regex, $text, $m ) ) {
+ return $this->parseMatch( $m );
+ }
+ }
+ }
+ return array( false, false );
+ }
+
+ /**
+ * Match some text, without parameter capture
+ * Returns the magic word name, or false if there was no capture
+ */
+ public function matchStartToEnd( $text ) {
+ $hash = $this->getHash();
+ if ( isset( $hash[1][$text] ) ) {
+ return $hash[1][$text];
+ }
+ global $wgContLang;
+ $lc = $wgContLang->lc( $text );
+ if ( isset( $hash[0][$lc] ) ) {
+ return $hash[0][$lc];
+ }
+ return false;
+ }
+
+ /**
+ * Returns an associative array, ID => param value, for all items that match
+ * Removes the matched items from the input string (passed by reference)
+ */
+ public function matchAndRemove( &$text ) {
+ $found = array();
+ $regexes = $this->getRegex();
+ foreach ( $regexes as $regex ) {
+ if ( $regex === '' ) {
+ continue;
+ }
+ preg_match_all( $regex, $text, $matches, PREG_SET_ORDER );
+ foreach ( $matches as $m ) {
+ list( $name, $param ) = $this->parseMatch( $m );
+ $found[$name] = $param;
+ }
+ $text = preg_replace( $regex, '', $text );
+ }
+ return $found;
+ }
+
+ /**
+ * Return the ID of the magic word at the start of $text, and remove
+ * the prefix from $text.
+ * Return false if no match found and $text is not modified.
+ * Does not match parameters.
+ */
+ public function matchStartAndRemove( &$text ) {
+ $regexes = $this->getRegexStart();
+ foreach ( $regexes as $regex ) {
+ if ( $regex === '' ) {
+ continue;
+ }
+ if ( preg_match( $regex, $text, $m ) ) {
+ list( $id, ) = $this->parseMatch( $m );
+ if ( strlen( $m[0] ) >= strlen( $text ) ) {
+ $text = '';
+ } else {
+ $text = substr( $text, strlen( $m[0] ) );
+ }
+ return $id;
+ }
+ }
+ return false;
+ }
+}