3 * File for magic words.
5 * See docs/magicword.txt.
7 * This program is free software; you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation; either version 2 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License along
18 * with this program; if not, write to the Free Software Foundation, Inc.,
19 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
20 * http://www.gnu.org/copyleft/gpl.html
27 * This class encapsulates "magic words" such as #redirect, __NOTOC__, etc.
31 * if (MagicWord::get( 'redirect' )->match( $text ) ) {
36 * Possible future improvements:
37 * * Simultaneous searching for a number of magic words
38 * * MagicWord::$mObjects in shared memory
40 * Please avoid reading the data out of one of these objects and then writing
41 * special case code. If possible, add another match()-like function here.
43 * To add magic words in an extension, use $magicWords in a file listed in
44 * $wgExtensionMessagesFiles[].
48 * $magicWords = array();
50 * $magicWords['en'] = array(
51 * 'magicwordkey' => array( 0, 'case_insensitive_magic_word' ),
52 * 'magicwordkey2' => array( 1, 'CASE_sensitive_magic_word2' ),
56 * For magic words which are also Parser variables, add a MagicWordwgVariableIDs
57 * hook. Use string keys.
65 var $mId, $mSynonyms, $mCaseSensitive;
67 var $mRegexStart = '';
69 var $mVariableRegex = '';
70 var $mVariableStartToEndRegex = '';
71 var $mModified = false;
74 static public $mVariableIDsInitialised = false;
75 static public $mVariableIDs = array(
79 'currentmonthnamegen',
138 'numberofactiveusers',
151 /* Array of caching hints for ParserCache */
152 static public $mCacheTTLs = array (
153 'currentmonth' => 86400,
154 'currentmonth1' => 86400,
155 'currentmonthname' => 86400,
156 'currentmonthnamegen' => 86400,
157 'currentmonthabbrev' => 86400,
158 'currentday' => 3600,
159 'currentday2' => 3600,
160 'currentdayname' => 3600,
161 'currentyear' => 86400,
162 'currenttime' => 3600,
163 'currenthour' => 3600,
164 'localmonth' => 86400,
165 'localmonth1' => 86400,
166 'localmonthname' => 86400,
167 'localmonthnamegen' => 86400,
168 'localmonthabbrev' => 86400,
171 'localdayname' => 3600,
172 'localyear' => 86400,
175 'numberofarticles' => 3600,
176 'numberoffiles' => 3600,
177 'numberofedits' => 3600,
178 'currentweek' => 3600,
179 'currentdow' => 3600,
182 'numberofusers' => 3600,
183 'numberofactiveusers' => 3600,
184 'numberofpages' => 3600,
185 'currentversion' => 86400,
186 'currenttimestamp' => 3600,
187 'localtimestamp' => 3600,
188 'pagesinnamespace' => 3600,
189 'numberofadmins' => 3600,
190 'numberofviews' => 3600,
191 'numberingroup' => 3600,
194 static public $mDoubleUnderscoreIDs = array(
210 static public $mSubstIDs = array(
215 static public $mObjects = array();
216 static public $mDoubleUnderscoreArray = null;
220 function __construct($id = 0, $syn = array(), $cs = false) {
222 $this->mSynonyms
= (array)$syn;
223 $this->mCaseSensitive
= $cs;
227 * Factory: creates an object representing an ID
233 static function &get( $id ) {
234 if ( !isset( self
::$mObjects[$id] ) ) {
235 $mw = new MagicWord();
237 self
::$mObjects[$id] = $mw;
239 return self
::$mObjects[$id];
243 * Get an array of parser variable IDs
247 static function getVariableIDs() {
248 if ( !self
::$mVariableIDsInitialised ) {
250 wfRunHooks( 'MagicWordwgVariableIDs', array( &self
::$mVariableIDs ) );
251 self
::$mVariableIDsInitialised = true;
253 return self
::$mVariableIDs;
257 * Get an array of parser substitution modifier IDs
260 static function getSubstIDs() {
261 return self
::$mSubstIDs;
265 * Allow external reads of TTL array
270 static function getCacheTTL( $id ) {
271 if ( array_key_exists( $id, self
::$mCacheTTLs ) ) {
272 return self
::$mCacheTTLs[$id];
279 * Get a MagicWordArray of double-underscore entities
281 * @return MagicWordArray
283 static function getDoubleUnderscoreArray() {
284 if ( is_null( self
::$mDoubleUnderscoreArray ) ) {
285 self
::$mDoubleUnderscoreArray = new MagicWordArray( self
::$mDoubleUnderscoreIDs );
287 return self
::$mDoubleUnderscoreArray;
291 * Clear the self::$mObjects variable
292 * For use in parser tests
294 public static function clearCache() {
295 self
::$mObjects = array();
299 * Initialises this object with an ID
303 function load( $id ) {
305 wfProfileIn( __METHOD__
);
307 $wgContLang->getMagic( $this );
308 if ( !$this->mSynonyms
) {
309 $this->mSynonyms
= array( 'dkjsagfjsgashfajsh' );
310 throw new MWException( "Error: invalid magic word '$id'" );
311 #wfDebugLog( 'exception', "Error: invalid magic word '$id'\n" );
313 wfProfileOut( __METHOD__
);
317 * Preliminary initialisation
320 function initRegex() {
321 // Sort the synonyms by length, descending, so that the longest synonym
322 // matches in precedence to the shortest
323 $synonyms = $this->mSynonyms
;
324 usort( $synonyms, array( $this, 'compareStringLength' ) );
327 foreach ( $synonyms as $synonym )
328 // In case a magic word contains /, like that's going to happen;)
329 $escSyn[] = preg_quote( $synonym, '/' );
330 $this->mBaseRegex
= implode( '|', $escSyn );
332 $case = $this->mCaseSensitive ?
'' : 'iu';
333 $this->mRegex
= "/{$this->mBaseRegex}/{$case}";
334 $this->mRegexStart
= "/^(?:{$this->mBaseRegex})/{$case}";
335 $this->mVariableRegex
= str_replace( "\\$1", "(.*?)", $this->mRegex
);
336 $this->mVariableStartToEndRegex
= str_replace( "\\$1", "(.*?)",
337 "/^(?:{$this->mBaseRegex})$/{$case}" );
341 * A comparison function that returns -1, 0 or 1 depending on whether the
342 * first string is longer, the same length or shorter than the second
350 function compareStringLength( $s1, $s2 ) {
355 } elseif ( $l1 > $l2 ) {
363 * Gets a regex representing matching the word
367 function getRegex() {
368 if ($this->mRegex
== '' ) {
371 return $this->mRegex
;
375 * Gets the regexp case modifier to use, i.e. i or nothing, to be used if
376 * one is using MagicWord::getBaseRegex(), otherwise it'll be included in
377 * the complete expression
381 function getRegexCase() {
382 if ( $this->mRegex
=== '' )
385 return $this->mCaseSensitive ?
'' : 'iu';
389 * Gets a regex matching the word, if it is at the string start
393 function getRegexStart() {
394 if ($this->mRegex
== '' ) {
397 return $this->mRegexStart
;
401 * regex without the slashes and what not
405 function getBaseRegex() {
406 if ($this->mRegex
== '') {
409 return $this->mBaseRegex
;
413 * Returns true if the text contains the word
415 * @param $text string
419 function match( $text ) {
420 return (bool)preg_match( $this->getRegex(), $text );
424 * Returns true if the text starts with the word
426 * @param $text string
430 function matchStart( $text ) {
431 return (bool)preg_match( $this->getRegexStart(), $text );
435 * Returns NULL if there's no match, the value of $1 otherwise
436 * The return code is the matched string, if there's no variable
437 * part in the regex and the matched variable part ($1) if there
440 * @param $text string
444 function matchVariableStartToEnd( $text ) {
446 $matchcount = preg_match( $this->getVariableStartToEndRegex(), $text, $matches );
447 if ( $matchcount == 0 ) {
450 # multiple matched parts (variable match); some will be empty because of
451 # synonyms. The variable will be the second non-empty one so remove any
452 # blank elements and re-sort the indices.
455 $matches = array_values(array_filter($matches));
457 if ( count($matches) == 1 ) {
467 * Returns true if the text matches the word, and alters the
468 * input string, removing all instances of the word
470 * @param $text string
474 function matchAndRemove( &$text ) {
475 $this->mFound
= false;
476 $text = preg_replace_callback( $this->getRegex(), array( &$this, 'pregRemoveAndRecord' ), $text );
477 return $this->mFound
;
484 function matchStartAndRemove( &$text ) {
485 $this->mFound
= false;
486 $text = preg_replace_callback( $this->getRegexStart(), array( &$this, 'pregRemoveAndRecord' ), $text );
487 return $this->mFound
;
491 * Used in matchAndRemove()
495 function pregRemoveAndRecord() {
496 $this->mFound
= true;
501 * Replaces the word with something else
503 * @param $replacement
509 function replace( $replacement, $subject, $limit = -1 ) {
510 $res = preg_replace( $this->getRegex(), StringUtils
::escapeRegexReplacement( $replacement ), $subject, $limit );
511 $this->mModified
= !($res === $subject);
516 * Variable handling: {{SUBST:xxx}} style words
517 * Calls back a function to determine what to replace xxx with
518 * Input word must contain $1
520 * @param $text string
525 function substituteCallback( $text, $callback ) {
526 $res = preg_replace_callback( $this->getVariableRegex(), $callback, $text );
527 $this->mModified
= !($res === $text);
532 * Matches the word, where $1 is a wildcard
536 function getVariableRegex() {
537 if ( $this->mVariableRegex
== '' ) {
540 return $this->mVariableRegex
;
544 * Matches the entire string, where $1 is a wildcard
548 function getVariableStartToEndRegex() {
549 if ( $this->mVariableStartToEndRegex
== '' ) {
552 return $this->mVariableStartToEndRegex
;
556 * Accesses the synonym list directly
562 function getSynonym( $i ) {
563 return $this->mSynonyms
[$i];
569 function getSynonyms() {
570 return $this->mSynonyms
;
574 * Returns true if the last call to replace() or substituteCallback()
575 * returned a modified text, otherwise false.
579 function getWasModified(){
580 return $this->mModified
;
584 * $magicarr is an associative array of (magic word ID => replacement)
585 * This method uses the php feature to do several replacements at the same time,
586 * thereby gaining some efficiency. The result is placed in the out variable
587 * $result. The return value is true if something was replaced.
588 * @todo Should this be static? It doesn't seem to be used at all
596 function replaceMultiple( $magicarr, $subject, &$result ){
599 foreach( $magicarr as $id => $replacement ){
600 $mw = MagicWord
::get( $id );
601 $search[] = $mw->getRegex();
602 $replace[] = $replacement;
605 $result = preg_replace( $search, $replace, $subject );
606 return !($result === $subject);
610 * Adds all the synonyms of this MagicWord to an array, to allow quick
611 * lookup in a list of magic words
616 function addToArray( &$array, $value ) {
618 foreach ( $this->mSynonyms
as $syn ) {
619 $array[$wgContLang->lc($syn)] = $value;
626 function isCaseSensitive() {
627 return $this->mCaseSensitive
;
639 * Class for handling an array of magic words
642 class MagicWordArray
{
643 var $names = array();
645 var $baseRegex, $regex;
648 function __construct( $names = array() ) {
649 $this->names
= $names;
653 * Add a magic word by name
655 * @param $name string
657 public function add( $name ) {
658 $this->names
[] = $name;
659 $this->hash
= $this->baseRegex
= $this->regex
= null;
663 * Add a number of magic words by name
665 * @param $names array
667 public function addArray( $names ) {
668 $this->names
= array_merge( $this->names
, array_values( $names ) );
669 $this->hash
= $this->baseRegex
= $this->regex
= null;
673 * Get a 2-d hashtable for this array
676 if ( is_null( $this->hash
) ) {
678 $this->hash
= array( 0 => array(), 1 => array() );
679 foreach ( $this->names
as $name ) {
680 $magic = MagicWord
::get( $name );
681 $case = intval( $magic->isCaseSensitive() );
682 foreach ( $magic->getSynonyms() as $syn ) {
684 $syn = $wgContLang->lc( $syn );
686 $this->hash
[$case][$syn] = $name;
696 function getBaseRegex() {
697 if ( is_null( $this->baseRegex
) ) {
698 $this->baseRegex
= array( 0 => '', 1 => '' );
699 foreach ( $this->names
as $name ) {
700 $magic = MagicWord
::get( $name );
701 $case = intval( $magic->isCaseSensitive() );
702 foreach ( $magic->getSynonyms() as $i => $syn ) {
703 $group = "(?P<{$i}_{$name}>" . preg_quote( $syn, '/' ) . ')';
704 if ( $this->baseRegex
[$case] === '' ) {
705 $this->baseRegex
[$case] = $group;
707 $this->baseRegex
[$case] .= '|' . $group;
712 return $this->baseRegex
;
716 * Get an unanchored regex that does not match parameters
718 function getRegex() {
719 if ( is_null( $this->regex
) ) {
720 $base = $this->getBaseRegex();
721 $this->regex
= array( '', '' );
722 if ( $this->baseRegex
[0] !== '' ) {
723 $this->regex
[0] = "/{$base[0]}/iuS";
725 if ( $this->baseRegex
[1] !== '' ) {
726 $this->regex
[1] = "/{$base[1]}/S";
733 * Get a regex for matching variables with parameters
737 function getVariableRegex() {
738 return str_replace( "\\$1", "(.*?)", $this->getRegex() );
742 * Get a regex anchored to the start of the string that does not match parameters
746 function getRegexStart() {
747 $base = $this->getBaseRegex();
748 $newRegex = array( '', '' );
749 if ( $base[0] !== '' ) {
750 $newRegex[0] = "/^(?:{$base[0]})/iuS";
752 if ( $base[1] !== '' ) {
753 $newRegex[1] = "/^(?:{$base[1]})/S";
759 * Get an anchored regex for matching variables with parameters
763 function getVariableStartToEndRegex() {
764 $base = $this->getBaseRegex();
765 $newRegex = array( '', '' );
766 if ( $base[0] !== '' ) {
767 $newRegex[0] = str_replace( "\\$1", "(.*?)", "/^(?:{$base[0]})$/iuS" );
769 if ( $base[1] !== '' ) {
770 $newRegex[1] = str_replace( "\\$1", "(.*?)", "/^(?:{$base[1]})$/S" );
776 * Parse a match array from preg_match
777 * Returns array(magic word ID, parameter value)
778 * If there is no parameter value, that element will be false.
784 function parseMatch( $m ) {
786 while ( list( $key, $value ) = each( $m ) ) {
787 if ( $key === 0 ||
$value === '' ) {
790 $parts = explode( '_', $key, 2 );
791 if ( count( $parts ) != 2 ) {
792 // This shouldn't happen
794 throw new MWException( __METHOD__
. ': bad parameter name' );
796 list( /* $synIndex */, $magicName ) = $parts;
797 $paramValue = next( $m );
798 return array( $magicName, $paramValue );
800 // This shouldn't happen either
801 throw new MWException( __METHOD__
.': parameter not found' );
805 * Match some text, with parameter capture
806 * Returns an array with the magic word name in the first element and the
807 * parameter in the second element.
808 * Both elements are false if there was no match.
810 * @param $text string
814 public function matchVariableStartToEnd( $text ) {
815 $regexes = $this->getVariableStartToEndRegex();
816 foreach ( $regexes as $regex ) {
817 if ( $regex !== '' ) {
819 if ( preg_match( $regex, $text, $m ) ) {
820 return $this->parseMatch( $m );
824 return array( false, false );
828 * Match some text, without parameter capture
829 * Returns the magic word name, or false if there was no capture
831 * @param $text string
833 * @return string|bool False on failure
835 public function matchStartToEnd( $text ) {
836 $hash = $this->getHash();
837 if ( isset( $hash[1][$text] ) ) {
838 return $hash[1][$text];
841 $lc = $wgContLang->lc( $text );
842 if ( isset( $hash[0][$lc] ) ) {
843 return $hash[0][$lc];
849 * Returns an associative array, ID => param value, for all items that match
850 * Removes the matched items from the input string (passed by reference)
852 * @param $text string
856 public function matchAndRemove( &$text ) {
858 $regexes = $this->getRegex();
859 foreach ( $regexes as $regex ) {
860 if ( $regex === '' ) {
863 preg_match_all( $regex, $text, $matches, PREG_SET_ORDER
);
864 foreach ( $matches as $m ) {
865 list( $name, $param ) = $this->parseMatch( $m );
866 $found[$name] = $param;
868 $text = preg_replace( $regex, '', $text );
874 * Return the ID of the magic word at the start of $text, and remove
875 * the prefix from $text.
876 * Return false if no match found and $text is not modified.
877 * Does not match parameters.
879 * @param $text string
881 * @return int|bool False on failure
883 public function matchStartAndRemove( &$text ) {
884 $regexes = $this->getRegexStart();
885 foreach ( $regexes as $regex ) {
886 if ( $regex === '' ) {
889 if ( preg_match( $regex, $text, $m ) ) {
890 list( $id, ) = $this->parseMatch( $m );
891 if ( strlen( $m[0] ) >= strlen( $text ) ) {
894 $text = substr( $text, strlen( $m[0] ) );