X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=includes%2FMagicWord.php;h=563d3a5621f796a6a8794e8d676c93157159c343;hb=d6cf8c57b4f5b0fdab7010a2e58a4baaec56f42f;hp=511efab4cf54181abcecd7439dd2dc4579dce5c9;hpb=bf63ffaa2c7e472181d74829a8bb380ad2ee9735;p=lhc%2Fweb%2Fwiklou.git diff --git a/includes/MagicWord.php b/includes/MagicWord.php index 511efab4cf..563d3a5621 100644 --- a/includes/MagicWord.php +++ b/includes/MagicWord.php @@ -1,8 +1,11 @@ 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 = array(), $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 + * + * @param $id + * + * @return MagicWord */ static function &get( $id ) { - if (!array_key_exists( $id, self::$mObjects ) ) { + if ( !isset( self::$mObjects[$id] ) ) { $mw = new MagicWord(); $mw->load( $id ); self::$mObjects[$id] = $mw; @@ -133,6 +207,8 @@ class MagicWord { /** * Get an array of parser variable IDs + * + * @return array */ static function getVariableIDs() { if ( !self::$mVariableIDsInitialised ) { @@ -150,9 +226,56 @@ class MagicWord { return self::$mVariableIDs; } - # Initialises this object with an ID + /** + * Get an array of parser substitution modifier IDs + * @return array + */ + static function getSubstIDs() { + return self::$mSubstIDs; + } + + /** + * Allow external reads of TTL array + * + * @param $id int + * @return 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 + * + * @return MagicWordArray + */ + 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 + * + * @param $id + */ function load( $id ) { global $wgContLang; + wfProfileIn( __METHOD__ ); $this->mId = $id; $wgContLang->getMagic( $this ); if ( !$this->mSynonyms ) { @@ -160,6 +283,7 @@ class MagicWord { #throw new MWException( "Error: invalid magic word '$id'" ); wfDebugLog( 'exception', "Error: invalid magic word '$id'\n" ); } + wfProfileOut( __METHOD__ ); } /** @@ -167,18 +291,18 @@ class MagicWord { * @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 ? '' : 'i'; + + $case = $this->mCaseSensitive ? '' : 'iu'; $this->mRegex = "/{$this->mBaseRegex}/{$case}"; $this->mRegexStart = "/^(?:{$this->mBaseRegex})/{$case}"; $this->mVariableRegex = str_replace( "\\$1", "(.*?)", $this->mRegex ); @@ -186,8 +310,32 @@ class MagicWord { "/^(?:{$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. + * + * @param $s1 string + * @param $s2 string + * + * @return int + */ + function compareStringLength( $s1, $s2 ) { + $l1 = strlen( $s1 ); + $l2 = strlen( $s2 ); + if ( $l1 < $l2 ) { + return 1; + } elseif ( $l1 > $l2 ) { + return -1; + } else { + return 0; + } + } + /** * Gets a regex representing matching the word + * + * @return string */ function getRegex() { if ($this->mRegex == '' ) { @@ -200,16 +348,20 @@ class MagicWord { * 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 + * + * @return string */ function getRegexCase() { if ( $this->mRegex === '' ) $this->initRegex(); - return $this->mCaseSensitive ? '' : 'i'; + return $this->mCaseSensitive ? '' : 'iu'; } /** * Gets a regex matching the word, if it is at the string start + * + * @return string */ function getRegexStart() { if ($this->mRegex == '' ) { @@ -220,6 +372,8 @@ class MagicWord { /** * regex without the slashes and what not + * + * @return string */ function getBaseRegex() { if ($this->mRegex == '') { @@ -230,18 +384,24 @@ class MagicWord { /** * Returns true if the text contains the word + * + * @param $text string + * * @return bool */ function match( $text ) { - return preg_match( $this->getRegex(), $text ); + return (bool)preg_match( $this->getRegex(), $text ); } /** * Returns true if the text starts with the word + * + * @param $text string + * * @return bool */ function matchStart( $text ) { - return preg_match( $this->getRegexStart(), $text ); + return (bool)preg_match( $this->getRegexStart(), $text ); } /** @@ -249,12 +409,16 @@ class MagicWord { * 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. + * + * @param $text string + * + * @return string */ function matchVariableStartToEnd( $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 @@ -263,8 +427,11 @@ class MagicWord { $matches = array_values(array_filter($matches)); - if ( count($matches) == 1 ) { return $matches[0]; } - else { return $matches[1]; } + if ( count($matches) == 1 ) { + return $matches[0]; + } else { + return $matches[1]; + } } } @@ -272,6 +439,10 @@ class MagicWord { /** * Returns true if the text matches the word, and alters the * input string, removing all instances of the word + * + * @param $text string + * + * @return bool */ function matchAndRemove( &$text ) { $this->mFound = false; @@ -279,6 +450,10 @@ class MagicWord { return $this->mFound; } + /** + * @param $text + * @return bool + */ function matchStartAndRemove( &$text ) { $this->mFound = false; $text = preg_replace_callback( $this->getRegexStart(), array( &$this, 'pregRemoveAndRecord' ), $text ); @@ -287,18 +462,25 @@ class MagicWord { /** * Used in matchAndRemove() - * @private - **/ - function pregRemoveAndRecord( $match ) { + * + * @return string + */ + function pregRemoveAndRecord() { $this->mFound = true; return ''; } /** * Replaces the word with something else + * + * @param $replacement + * @param $subject + * @param $limit int + * + * @return string */ - function replace( $replacement, $subject, $limit=-1 ) { - $res = preg_replace( $this->getRegex(), wfRegexReplacement( $replacement ), $subject, $limit ); + function replace( $replacement, $subject, $limit = -1 ) { + $res = preg_replace( $this->getRegex(), StringUtils::escapeRegexReplacement( $replacement ), $subject, $limit ); $this->mModified = !($res === $subject); return $res; } @@ -307,6 +489,11 @@ class MagicWord { * Variable handling: {{SUBST:xxx}} style words * Calls back a function to determine what to replace xxx with * Input word must contain $1 + * + * @param $text string + * @param $callback + * + * @return string */ function substituteCallback( $text, $callback ) { $res = preg_replace_callback( $this->getVariableRegex(), $callback, $text ); @@ -316,6 +503,8 @@ class MagicWord { /** * Matches the word, where $1 is a wildcard + * + * @return string */ function getVariableRegex() { if ( $this->mVariableRegex == '' ) { @@ -326,6 +515,8 @@ class MagicWord { /** * Matches the entire string, where $1 is a wildcard + * + * @return string */ function getVariableStartToEndRegex() { if ( $this->mVariableStartToEndRegex == '' ) { @@ -336,11 +527,18 @@ class MagicWord { /** * Accesses the synonym list directly + * + * @param $i int + * + * @return string */ function getSynonym( $i ) { return $this->mSynonyms[$i]; } + /** + * @return array + */ function getSynonyms() { return $this->mSynonyms; } @@ -348,6 +546,8 @@ class MagicWord { /** * Returns true if the last call to replace() or substituteCallback() * returned a modified text, otherwise false. + * + * @return bool */ function getWasModified(){ return $this->mModified; @@ -358,8 +558,14 @@ class MagicWord { * 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. - * @static - **/ + * @todo Should this be static? It doesn't seem to be used at all + * + * @param $magicarr + * @param $subject + * @param $result + * + * @return bool + */ function replaceMultiple( $magicarr, $subject, &$result ){ $search = array(); $replace = array(); @@ -376,16 +582,293 @@ class MagicWord { /** * Adds all the synonyms of this MagicWord to an array, to allow quick * lookup in a list of magic words + * + * @param $array + * @param $value */ function addToArray( &$array, $value ) { + global $wgContLang; foreach ( $this->mSynonyms as $syn ) { - $array[$syn] = $value; + $array[$wgContLang->lc($syn)] = $value; } } + /** + * @return bool + */ function isCaseSensitive() { return $this->mCaseSensitive; } + + /** + * @return int + */ + 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 + * + * @param $name string + */ + public function add( $name ) { + $this->names[] = $name; + $this->hash = $this->baseRegex = $this->regex = null; + } + + /** + * Add a number of magic words by name + * + * @param $names array + */ + 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 + * + * @return string + */ + function getVariableRegex() { + return str_replace( "\\$1", "(.*?)", $this->getRegex() ); + } + + /** + * Get a regex anchored to the start of the string that does not match parameters + * + * @return array + */ + 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 + * + * @return array + */ + 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. + * + * @param $m array + * + * @return array + */ + 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. + * + * @param $text string + * + * @return array + */ + 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 + * + * @param $text string + * + * @return string|false + */ + 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) + * + * @param $text string + * + * @return array + */ + public function matchAndRemove( &$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. + * + * @param $text string + * + * @return int|false + */ + public function matchStartAndRemove( &$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; + } +}