From: addshore Date: Mon, 21 Mar 2016 11:51:16 +0000 (+0000) Subject: Split LocalisationCache.php classes into own files X-Git-Tag: 1.31.0-rc.0~7488^2 X-Git-Url: http://git.cyclocoop.org/%7B%7B%20url_for%28%27admin_vote_del%27%2C%20idvote=vote.voteid%29%20%7D%7D?a=commitdiff_plain;h=b8ca311a1cf0a15c6261db07a3f3b48a45641b71;p=lhc%2Fweb%2Fwiklou.git Split LocalisationCache.php classes into own files Change-Id: I1b88081e6b082fcad73990550a3ffbf58e11d97e --- diff --git a/autoload.php b/autoload.php index e74df0aa1f..1bab501566 100644 --- a/autoload.php +++ b/autoload.php @@ -634,11 +634,11 @@ $wgAutoloadLocalClasses = [ 'LBFactoryMulti' => __DIR__ . '/includes/db/loadbalancer/LBFactoryMulti.php', 'LBFactorySimple' => __DIR__ . '/includes/db/loadbalancer/LBFactorySimple.php', 'LBFactorySingle' => __DIR__ . '/includes/db/loadbalancer/LBFactorySingle.php', - 'LCStore' => __DIR__ . '/includes/cache/LocalisationCache.php', - 'LCStoreCDB' => __DIR__ . '/includes/cache/LocalisationCache.php', - 'LCStoreDB' => __DIR__ . '/includes/cache/LocalisationCache.php', - 'LCStoreNull' => __DIR__ . '/includes/cache/LocalisationCache.php', - 'LCStoreStaticArray' => __DIR__ . '/includes/cache/LCStoreStaticArray.php', + 'LCStore' => __DIR__ . '/includes/cache/localisation/LCStore.php', + 'LCStoreCDB' => __DIR__ . '/includes/cache/localisation/LCStoreCDB.php', + 'LCStoreDB' => __DIR__ . '/includes/cache/localisation/LCStoreDB.php', + 'LCStoreNull' => __DIR__ . '/includes/cache/localisation/LCStoreNull.php', + 'LCStoreStaticArray' => __DIR__ . '/includes/cache/localisation/LCStoreStaticArray.php', 'LangMemUsage' => __DIR__ . '/maintenance/language/langmemusage.php', 'Language' => __DIR__ . '/languages/Language.php', 'LanguageAr' => __DIR__ . '/languages/classes/LanguageAr.php', @@ -718,8 +718,9 @@ $wgAutoloadLocalClasses = [ 'LocalIdLookup' => __DIR__ . '/includes/user/LocalIdLookup.php', 'LocalRepo' => __DIR__ . '/includes/filerepo/LocalRepo.php', 'LocalSettingsGenerator' => __DIR__ . '/includes/installer/LocalSettingsGenerator.php', - 'LocalisationCache' => __DIR__ . '/includes/cache/LocalisationCache.php', - 'LocalisationCacheBulkLoad' => __DIR__ . '/includes/cache/LocalisationCache.php', + 'LocalisationCache' => __DIR__ . '/includes/cache/localisation/LocalisationCache.php', + 'LocalisationCacheBulkLoad' => __DIR__ . + '/includes/cache/localisation/LocalisationCacheBulkLoad.php', 'LockManager' => __DIR__ . '/includes/filebackend/lockmanager/LockManager.php', 'LockManagerGroup' => __DIR__ . '/includes/filebackend/lockmanager/LockManagerGroup.php', 'LogEntry' => __DIR__ . '/includes/logging/LogEntry.php', diff --git a/includes/cache/LCStoreStaticArray.php b/includes/cache/LCStoreStaticArray.php deleted file mode 100644 index 1e20082f16..0000000000 --- a/includes/cache/LCStoreStaticArray.php +++ /dev/null @@ -1,140 +0,0 @@ -directory = $conf['directory']; - } else { - $this->directory = $wgCacheDirectory; - } - } - - public function startWrite( $code ) { - $this->currentLang = $code; - $this->fname = $this->directory . '/' . $code . '.l10n.php'; - $this->data[$code] = []; - if ( file_exists( $this->fname ) ) { - $this->data[$code] = require $this->fname; - } - } - - public function set( $key, $value ) { - $this->data[$this->currentLang][$key] = self::encode( $value ); - } - - /** - * Encodes a value into an array format - * - * @param mixed $value - * @return array - * @throws RuntimeException - */ - public static function encode( $value ) { - if ( is_scalar( $value ) || $value === null ) { - // [V]alue - return [ 'v', $value ]; - } - if ( is_object( $value ) ) { - // [S]erialized - return [ 's', serialize( $value ) ]; - } - if ( is_array( $value ) ) { - // [A]rray - return [ 'a', array_map( function ( $v ) { - return LCStoreStaticArray::encode( $v ); - }, $value ) ]; - } - - throw new RuntimeException( 'Cannot encode ' . var_export( $value, true ) ); - } - - /** - * Decode something that was encoded with encode - * - * @param array $encoded - * @return array|mixed - * @throws RuntimeException - */ - public static function decode( array $encoded ) { - $type = $encoded[0]; - $data = $encoded[1]; - - switch ( $type ) { - case 'v': - return $data; - case 's': - return unserialize( $data ); - case 'a': - return array_map( function ( $v ) { - return LCStoreStaticArray::decode( $v ); - }, $data ); - default: - throw new RuntimeException( - 'Unable to decode ' . var_export( $encoded, true ) ); - } - } - - public function finishWrite() { - file_put_contents( - $this->fname, - "data[$this->currentLang], true ) . ';' - ); - $this->currentLang = null; - $this->fname = null; - } - - public function get( $code, $key ) { - if ( !array_key_exists( $code, $this->data ) ) { - $fname = $this->directory . '/' . $code . '.l10n.php'; - if ( !file_exists( $fname ) ) { - return null; - } - $this->data[$code] = require $fname; - } - $data = $this->data[$code]; - if ( array_key_exists( $key, $data ) ) { - return self::decode( $data[$key] ); - } - return null; - } -} diff --git a/includes/cache/LocalisationCache.php b/includes/cache/LocalisationCache.php deleted file mode 100644 index 6efeabef4a..0000000000 --- a/includes/cache/LocalisationCache.php +++ /dev/null @@ -1,1479 +0,0 @@ - - * zh-hans -> en ). Some common errors are corrected, for example namespace - * names with spaces instead of underscores, but heavyweight processing, such - * as grammatical transformation, is done by the caller. - */ -class LocalisationCache { - const VERSION = 4; - - /** Configuration associative array */ - private $conf; - - /** - * True if recaching should only be done on an explicit call to recache(). - * Setting this reduces the overhead of cache freshness checking, which - * requires doing a stat() for every extension i18n file. - */ - private $manualRecache = false; - - /** - * True to treat all files as expired until they are regenerated by this object. - */ - private $forceRecache = false; - - /** - * The cache data. 3-d array, where the first key is the language code, - * the second key is the item key e.g. 'messages', and the third key is - * an item specific subkey index. Some items are not arrays and so for those - * items, there are no subkeys. - */ - protected $data = []; - - /** - * The persistent store object. An instance of LCStore. - * - * @var LCStore - */ - private $store; - - /** - * A 2-d associative array, code/key, where presence indicates that the item - * is loaded. Value arbitrary. - * - * For split items, if set, this indicates that all of the subitems have been - * loaded. - */ - private $loadedItems = []; - - /** - * A 3-d associative array, code/key/subkey, where presence indicates that - * the subitem is loaded. Only used for the split items, i.e. messages. - */ - private $loadedSubitems = []; - - /** - * An array where presence of a key indicates that that language has been - * initialised. Initialisation includes checking for cache expiry and doing - * any necessary updates. - */ - private $initialisedLangs = []; - - /** - * An array mapping non-existent pseudo-languages to fallback languages. This - * is filled by initShallowFallback() when data is requested from a language - * that lacks a Messages*.php file. - */ - private $shallowFallbacks = []; - - /** - * An array where the keys are codes that have been recached by this instance. - */ - private $recachedLangs = []; - - /** - * All item keys - */ - static public $allKeys = [ - 'fallback', 'namespaceNames', 'bookstoreList', - 'magicWords', 'messages', 'rtl', 'capitalizeAllNouns', 'digitTransformTable', - 'separatorTransformTable', 'fallback8bitEncoding', 'linkPrefixExtension', - 'linkTrail', 'linkPrefixCharset', 'namespaceAliases', - 'dateFormats', 'datePreferences', 'datePreferenceMigrationMap', - 'defaultDateFormat', 'extraUserToggles', 'specialPageAliases', - 'imageFiles', 'preloadedMessages', 'namespaceGenderAliases', - 'digitGroupingPattern', 'pluralRules', 'pluralRuleTypes', 'compiledPluralRules', - ]; - - /** - * Keys for items which consist of associative arrays, which may be merged - * by a fallback sequence. - */ - static public $mergeableMapKeys = [ 'messages', 'namespaceNames', - 'namespaceAliases', 'dateFormats', 'imageFiles', 'preloadedMessages' - ]; - - /** - * Keys for items which are a numbered array. - */ - static public $mergeableListKeys = [ 'extraUserToggles' ]; - - /** - * Keys for items which contain an array of arrays of equivalent aliases - * for each subitem. The aliases may be merged by a fallback sequence. - */ - static public $mergeableAliasListKeys = [ 'specialPageAliases' ]; - - /** - * Keys for items which contain an associative array, and may be merged if - * the primary value contains the special array key "inherit". That array - * key is removed after the first merge. - */ - static public $optionalMergeKeys = [ 'bookstoreList' ]; - - /** - * Keys for items that are formatted like $magicWords - */ - static public $magicWordKeys = [ 'magicWords' ]; - - /** - * Keys for items where the subitems are stored in the backend separately. - */ - static public $splitKeys = [ 'messages' ]; - - /** - * Keys which are loaded automatically by initLanguage() - */ - static public $preloadedKeys = [ 'dateFormats', 'namespaceNames' ]; - - /** - * Associative array of cached plural rules. The key is the language code, - * the value is an array of plural rules for that language. - */ - private $pluralRules = null; - - /** - * Associative array of cached plural rule types. The key is the language - * code, the value is an array of plural rule types for that language. For - * example, $pluralRuleTypes['ar'] = ['zero', 'one', 'two', 'few', 'many']. - * The index for each rule type matches the index for the rule in - * $pluralRules, thus allowing correlation between the two. The reason we - * don't just use the type names as the keys in $pluralRules is because - * Language::convertPlural applies the rules based on numeric order (or - * explicit numeric parameter), not based on the name of the rule type. For - * example, {{plural:count|wordform1|wordform2|wordform3}}, rather than - * {{plural:count|one=wordform1|two=wordform2|many=wordform3}}. - */ - private $pluralRuleTypes = null; - - private $mergeableKeys = null; - - /** - * Constructor. - * For constructor parameters, see the documentation in DefaultSettings.php - * for $wgLocalisationCacheConf. - * - * @param array $conf - * @throws MWException - */ - function __construct( $conf ) { - global $wgCacheDirectory; - - $this->conf = $conf; - $storeConf = []; - if ( !empty( $conf['storeClass'] ) ) { - $storeClass = $conf['storeClass']; - } else { - switch ( $conf['store'] ) { - case 'files': - case 'file': - $storeClass = 'LCStoreCDB'; - break; - case 'db': - $storeClass = 'LCStoreDB'; - break; - case 'array': - $storeClass = 'LCStoreStaticArray'; - break; - case 'detect': - if ( !empty( $conf['storeDirectory'] ) ) { - $storeClass = 'LCStoreCDB'; - } else { - $cacheDir = $wgCacheDirectory ?: wfTempDir(); - if ( $cacheDir ) { - $storeConf['directory'] = $cacheDir; - $storeClass = 'LCStoreCDB'; - } else { - $storeClass = 'LCStoreDB'; - } - } - break; - default: - throw new MWException( - 'Please set $wgLocalisationCacheConf[\'store\'] to something sensible.' ); - } - } - - wfDebugLog( 'caches', get_class( $this ) . ": using store $storeClass" ); - if ( !empty( $conf['storeDirectory'] ) ) { - $storeConf['directory'] = $conf['storeDirectory']; - } - - $this->store = new $storeClass( $storeConf ); - foreach ( [ 'manualRecache', 'forceRecache' ] as $var ) { - if ( isset( $conf[$var] ) ) { - $this->$var = $conf[$var]; - } - } - } - - /** - * Returns true if the given key is mergeable, that is, if it is an associative - * array which can be merged through a fallback sequence. - * @param string $key - * @return bool - */ - public function isMergeableKey( $key ) { - if ( $this->mergeableKeys === null ) { - $this->mergeableKeys = array_flip( array_merge( - self::$mergeableMapKeys, - self::$mergeableListKeys, - self::$mergeableAliasListKeys, - self::$optionalMergeKeys, - self::$magicWordKeys - ) ); - } - - return isset( $this->mergeableKeys[$key] ); - } - - /** - * Get a cache item. - * - * Warning: this may be slow for split items (messages), since it will - * need to fetch all of the subitems from the cache individually. - * @param string $code - * @param string $key - * @return mixed - */ - public function getItem( $code, $key ) { - if ( !isset( $this->loadedItems[$code][$key] ) ) { - $this->loadItem( $code, $key ); - } - - if ( $key === 'fallback' && isset( $this->shallowFallbacks[$code] ) ) { - return $this->shallowFallbacks[$code]; - } - - return $this->data[$code][$key]; - } - - /** - * Get a subitem, for instance a single message for a given language. - * @param string $code - * @param string $key - * @param string $subkey - * @return mixed|null - */ - public function getSubitem( $code, $key, $subkey ) { - if ( !isset( $this->loadedSubitems[$code][$key][$subkey] ) && - !isset( $this->loadedItems[$code][$key] ) - ) { - $this->loadSubitem( $code, $key, $subkey ); - } - - if ( isset( $this->data[$code][$key][$subkey] ) ) { - return $this->data[$code][$key][$subkey]; - } else { - return null; - } - } - - /** - * Get the list of subitem keys for a given item. - * - * This is faster than array_keys($lc->getItem(...)) for the items listed in - * self::$splitKeys. - * - * Will return null if the item is not found, or false if the item is not an - * array. - * @param string $code - * @param string $key - * @return bool|null|string - */ - public function getSubitemList( $code, $key ) { - if ( in_array( $key, self::$splitKeys ) ) { - return $this->getSubitem( $code, 'list', $key ); - } else { - $item = $this->getItem( $code, $key ); - if ( is_array( $item ) ) { - return array_keys( $item ); - } else { - return false; - } - } - } - - /** - * Load an item into the cache. - * @param string $code - * @param string $key - */ - protected function loadItem( $code, $key ) { - if ( !isset( $this->initialisedLangs[$code] ) ) { - $this->initLanguage( $code ); - } - - // Check to see if initLanguage() loaded it for us - if ( isset( $this->loadedItems[$code][$key] ) ) { - return; - } - - if ( isset( $this->shallowFallbacks[$code] ) ) { - $this->loadItem( $this->shallowFallbacks[$code], $key ); - - return; - } - - if ( in_array( $key, self::$splitKeys ) ) { - $subkeyList = $this->getSubitem( $code, 'list', $key ); - foreach ( $subkeyList as $subkey ) { - if ( isset( $this->data[$code][$key][$subkey] ) ) { - continue; - } - $this->data[$code][$key][$subkey] = $this->getSubitem( $code, $key, $subkey ); - } - } else { - $this->data[$code][$key] = $this->store->get( $code, $key ); - } - - $this->loadedItems[$code][$key] = true; - } - - /** - * Load a subitem into the cache - * @param string $code - * @param string $key - * @param string $subkey - */ - protected function loadSubitem( $code, $key, $subkey ) { - if ( !in_array( $key, self::$splitKeys ) ) { - $this->loadItem( $code, $key ); - - return; - } - - if ( !isset( $this->initialisedLangs[$code] ) ) { - $this->initLanguage( $code ); - } - - // Check to see if initLanguage() loaded it for us - if ( isset( $this->loadedItems[$code][$key] ) || - isset( $this->loadedSubitems[$code][$key][$subkey] ) - ) { - return; - } - - if ( isset( $this->shallowFallbacks[$code] ) ) { - $this->loadSubitem( $this->shallowFallbacks[$code], $key, $subkey ); - - return; - } - - $value = $this->store->get( $code, "$key:$subkey" ); - $this->data[$code][$key][$subkey] = $value; - $this->loadedSubitems[$code][$key][$subkey] = true; - } - - /** - * Returns true if the cache identified by $code is missing or expired. - * - * @param string $code - * - * @return bool - */ - public function isExpired( $code ) { - if ( $this->forceRecache && !isset( $this->recachedLangs[$code] ) ) { - wfDebug( __METHOD__ . "($code): forced reload\n" ); - - return true; - } - - $deps = $this->store->get( $code, 'deps' ); - $keys = $this->store->get( $code, 'list' ); - $preload = $this->store->get( $code, 'preload' ); - // Different keys may expire separately for some stores - if ( $deps === null || $keys === null || $preload === null ) { - wfDebug( __METHOD__ . "($code): cache missing, need to make one\n" ); - - return true; - } - - foreach ( $deps as $dep ) { - // Because we're unserializing stuff from cache, we - // could receive objects of classes that don't exist - // anymore (e.g. uninstalled extensions) - // When this happens, always expire the cache - if ( !$dep instanceof CacheDependency || $dep->isExpired() ) { - wfDebug( __METHOD__ . "($code): cache for $code expired due to " . - get_class( $dep ) . "\n" ); - - return true; - } - } - - return false; - } - - /** - * Initialise a language in this object. Rebuild the cache if necessary. - * @param string $code - * @throws MWException - */ - protected function initLanguage( $code ) { - if ( isset( $this->initialisedLangs[$code] ) ) { - return; - } - - $this->initialisedLangs[$code] = true; - - # If the code is of the wrong form for a Messages*.php file, do a shallow fallback - if ( !Language::isValidBuiltInCode( $code ) ) { - $this->initShallowFallback( $code, 'en' ); - - return; - } - - # Recache the data if necessary - if ( !$this->manualRecache && $this->isExpired( $code ) ) { - if ( Language::isSupportedLanguage( $code ) ) { - $this->recache( $code ); - } elseif ( $code === 'en' ) { - throw new MWException( 'MessagesEn.php is missing.' ); - } else { - $this->initShallowFallback( $code, 'en' ); - } - - return; - } - - # Preload some stuff - $preload = $this->getItem( $code, 'preload' ); - if ( $preload === null ) { - if ( $this->manualRecache ) { - // No Messages*.php file. Do shallow fallback to en. - if ( $code === 'en' ) { - throw new MWException( 'No localisation cache found for English. ' . - 'Please run maintenance/rebuildLocalisationCache.php.' ); - } - $this->initShallowFallback( $code, 'en' ); - - return; - } else { - throw new MWException( 'Invalid or missing localisation cache.' ); - } - } - $this->data[$code] = $preload; - foreach ( $preload as $key => $item ) { - if ( in_array( $key, self::$splitKeys ) ) { - foreach ( $item as $subkey => $subitem ) { - $this->loadedSubitems[$code][$key][$subkey] = true; - } - } else { - $this->loadedItems[$code][$key] = true; - } - } - } - - /** - * Create a fallback from one language to another, without creating a - * complete persistent cache. - * @param string $primaryCode - * @param string $fallbackCode - */ - public function initShallowFallback( $primaryCode, $fallbackCode ) { - $this->data[$primaryCode] =& $this->data[$fallbackCode]; - $this->loadedItems[$primaryCode] =& $this->loadedItems[$fallbackCode]; - $this->loadedSubitems[$primaryCode] =& $this->loadedSubitems[$fallbackCode]; - $this->shallowFallbacks[$primaryCode] = $fallbackCode; - } - - /** - * Read a PHP file containing localisation data. - * @param string $_fileName - * @param string $_fileType - * @throws MWException - * @return array - */ - protected function readPHPFile( $_fileName, $_fileType ) { - // Disable APC caching - MediaWiki\suppressWarnings(); - $_apcEnabled = ini_set( 'apc.cache_by_default', '0' ); - MediaWiki\restoreWarnings(); - - include $_fileName; - - MediaWiki\suppressWarnings(); - ini_set( 'apc.cache_by_default', $_apcEnabled ); - MediaWiki\restoreWarnings(); - - if ( $_fileType == 'core' || $_fileType == 'extension' ) { - $data = compact( self::$allKeys ); - } elseif ( $_fileType == 'aliases' ) { - $data = compact( 'aliases' ); - } else { - throw new MWException( __METHOD__ . ": Invalid file type: $_fileType" ); - } - - return $data; - } - - /** - * Read a JSON file containing localisation messages. - * @param string $fileName Name of file to read - * @throws MWException If there is a syntax error in the JSON file - * @return array Array with a 'messages' key, or empty array if the file doesn't exist - */ - public function readJSONFile( $fileName ) { - - if ( !is_readable( $fileName ) ) { - return []; - } - - $json = file_get_contents( $fileName ); - if ( $json === false ) { - return []; - } - - $data = FormatJson::decode( $json, true ); - if ( $data === null ) { - - throw new MWException( __METHOD__ . ": Invalid JSON file: $fileName" ); - } - - // Remove keys starting with '@', they're reserved for metadata and non-message data - foreach ( $data as $key => $unused ) { - if ( $key === '' || $key[0] === '@' ) { - unset( $data[$key] ); - } - } - - // The JSON format only supports messages, none of the other variables, so wrap the data - return [ 'messages' => $data ]; - } - - /** - * Get the compiled plural rules for a given language from the XML files. - * @since 1.20 - * @param string $code - * @return array|null - */ - public function getCompiledPluralRules( $code ) { - $rules = $this->getPluralRules( $code ); - if ( $rules === null ) { - return null; - } - try { - $compiledRules = Evaluator::compile( $rules ); - } catch ( CLDRPluralRuleError $e ) { - wfDebugLog( 'l10n', $e->getMessage() ); - - return []; - } - - return $compiledRules; - } - - /** - * Get the plural rules for a given language from the XML files. - * Cached. - * @since 1.20 - * @param string $code - * @return array|null - */ - public function getPluralRules( $code ) { - if ( $this->pluralRules === null ) { - $this->loadPluralFiles(); - } - if ( !isset( $this->pluralRules[$code] ) ) { - return null; - } else { - return $this->pluralRules[$code]; - } - } - - /** - * Get the plural rule types for a given language from the XML files. - * Cached. - * @since 1.22 - * @param string $code - * @return array|null - */ - public function getPluralRuleTypes( $code ) { - if ( $this->pluralRuleTypes === null ) { - $this->loadPluralFiles(); - } - if ( !isset( $this->pluralRuleTypes[$code] ) ) { - return null; - } else { - return $this->pluralRuleTypes[$code]; - } - } - - /** - * Load the plural XML files. - */ - protected function loadPluralFiles() { - global $IP; - $cldrPlural = "$IP/languages/data/plurals.xml"; - $mwPlural = "$IP/languages/data/plurals-mediawiki.xml"; - // Load CLDR plural rules - $this->loadPluralFile( $cldrPlural ); - if ( file_exists( $mwPlural ) ) { - // Override or extend - $this->loadPluralFile( $mwPlural ); - } - } - - /** - * Load a plural XML file with the given filename, compile the relevant - * rules, and save the compiled rules in a process-local cache. - * - * @param string $fileName - * @throws MWException - */ - protected function loadPluralFile( $fileName ) { - // Use file_get_contents instead of DOMDocument::load (T58439) - $xml = file_get_contents( $fileName ); - if ( !$xml ) { - throw new MWException( "Unable to read plurals file $fileName" ); - } - $doc = new DOMDocument; - $doc->loadXML( $xml ); - $rulesets = $doc->getElementsByTagName( "pluralRules" ); - foreach ( $rulesets as $ruleset ) { - $codes = $ruleset->getAttribute( 'locales' ); - $rules = []; - $ruleTypes = []; - $ruleElements = $ruleset->getElementsByTagName( "pluralRule" ); - foreach ( $ruleElements as $elt ) { - $ruleType = $elt->getAttribute( 'count' ); - if ( $ruleType === 'other' ) { - // Don't record "other" rules, which have an empty condition - continue; - } - $rules[] = $elt->nodeValue; - $ruleTypes[] = $ruleType; - } - foreach ( explode( ' ', $codes ) as $code ) { - $this->pluralRules[$code] = $rules; - $this->pluralRuleTypes[$code] = $ruleTypes; - } - } - } - - /** - * Read the data from the source files for a given language, and register - * the relevant dependencies in the $deps array. If the localisation - * exists, the data array is returned, otherwise false is returned. - * - * @param string $code - * @param array $deps - * @return array - */ - protected function readSourceFilesAndRegisterDeps( $code, &$deps ) { - global $IP; - - // This reads in the PHP i18n file with non-messages l10n data - $fileName = Language::getMessagesFileName( $code ); - if ( !file_exists( $fileName ) ) { - $data = []; - } else { - $deps[] = new FileDependency( $fileName ); - $data = $this->readPHPFile( $fileName, 'core' ); - } - - # Load CLDR plural rules for JavaScript - $data['pluralRules'] = $this->getPluralRules( $code ); - # And for PHP - $data['compiledPluralRules'] = $this->getCompiledPluralRules( $code ); - # Load plural rule types - $data['pluralRuleTypes'] = $this->getPluralRuleTypes( $code ); - - $deps['plurals'] = new FileDependency( "$IP/languages/data/plurals.xml" ); - $deps['plurals-mw'] = new FileDependency( "$IP/languages/data/plurals-mediawiki.xml" ); - - return $data; - } - - /** - * Merge two localisation values, a primary and a fallback, overwriting the - * primary value in place. - * @param string $key - * @param mixed $value - * @param mixed $fallbackValue - */ - protected function mergeItem( $key, &$value, $fallbackValue ) { - if ( !is_null( $value ) ) { - if ( !is_null( $fallbackValue ) ) { - if ( in_array( $key, self::$mergeableMapKeys ) ) { - $value = $value + $fallbackValue; - } elseif ( in_array( $key, self::$mergeableListKeys ) ) { - $value = array_unique( array_merge( $fallbackValue, $value ) ); - } elseif ( in_array( $key, self::$mergeableAliasListKeys ) ) { - $value = array_merge_recursive( $value, $fallbackValue ); - } elseif ( in_array( $key, self::$optionalMergeKeys ) ) { - if ( !empty( $value['inherit'] ) ) { - $value = array_merge( $fallbackValue, $value ); - } - - if ( isset( $value['inherit'] ) ) { - unset( $value['inherit'] ); - } - } elseif ( in_array( $key, self::$magicWordKeys ) ) { - $this->mergeMagicWords( $value, $fallbackValue ); - } - } - } else { - $value = $fallbackValue; - } - } - - /** - * @param mixed $value - * @param mixed $fallbackValue - */ - protected function mergeMagicWords( &$value, $fallbackValue ) { - foreach ( $fallbackValue as $magicName => $fallbackInfo ) { - if ( !isset( $value[$magicName] ) ) { - $value[$magicName] = $fallbackInfo; - } else { - $oldSynonyms = array_slice( $fallbackInfo, 1 ); - $newSynonyms = array_slice( $value[$magicName], 1 ); - $synonyms = array_values( array_unique( array_merge( - $newSynonyms, $oldSynonyms ) ) ); - $value[$magicName] = array_merge( [ $fallbackInfo[0] ], $synonyms ); - } - } - } - - /** - * Given an array mapping language code to localisation value, such as is - * found in extension *.i18n.php files, iterate through a fallback sequence - * to merge the given data with an existing primary value. - * - * Returns true if any data from the extension array was used, false - * otherwise. - * @param array $codeSequence - * @param string $key - * @param mixed $value - * @param mixed $fallbackValue - * @return bool - */ - protected function mergeExtensionItem( $codeSequence, $key, &$value, $fallbackValue ) { - $used = false; - foreach ( $codeSequence as $code ) { - if ( isset( $fallbackValue[$code] ) ) { - $this->mergeItem( $key, $value, $fallbackValue[$code] ); - $used = true; - } - } - - return $used; - } - - /** - * Gets the combined list of messages dirs from - * core and extensions - * - * @since 1.25 - * @return array - */ - public function getMessagesDirs() { - global $wgMessagesDirs, $IP; - return [ - 'core' => "$IP/languages/i18n", - 'api' => "$IP/includes/api/i18n", - 'oojs-ui' => "$IP/resources/lib/oojs-ui/i18n", - ] + $wgMessagesDirs; - } - - /** - * Load localisation data for a given language for both core and extensions - * and save it to the persistent cache store and the process cache - * @param string $code - * @throws MWException - */ - public function recache( $code ) { - global $wgExtensionMessagesFiles; - - if ( !$code ) { - throw new MWException( "Invalid language code requested" ); - } - $this->recachedLangs[$code] = true; - - # Initial values - $initialData = array_fill_keys( self::$allKeys, null ); - $coreData = $initialData; - $deps = []; - - # Load the primary localisation from the source file - $data = $this->readSourceFilesAndRegisterDeps( $code, $deps ); - if ( $data === false ) { - wfDebug( __METHOD__ . ": no localisation file for $code, using fallback to en\n" ); - $coreData['fallback'] = 'en'; - } else { - wfDebug( __METHOD__ . ": got localisation for $code from source\n" ); - - # Merge primary localisation - foreach ( $data as $key => $value ) { - $this->mergeItem( $key, $coreData[$key], $value ); - } - } - - # Fill in the fallback if it's not there already - if ( is_null( $coreData['fallback'] ) ) { - $coreData['fallback'] = $code === 'en' ? false : 'en'; - } - if ( $coreData['fallback'] === false ) { - $coreData['fallbackSequence'] = []; - } else { - $coreData['fallbackSequence'] = array_map( 'trim', explode( ',', $coreData['fallback'] ) ); - $len = count( $coreData['fallbackSequence'] ); - - # Ensure that the sequence ends at en - if ( $coreData['fallbackSequence'][$len - 1] !== 'en' ) { - $coreData['fallbackSequence'][] = 'en'; - } - } - - $codeSequence = array_merge( [ $code ], $coreData['fallbackSequence'] ); - $messageDirs = $this->getMessagesDirs(); - - # Load non-JSON localisation data for extensions - $extensionData = array_fill_keys( $codeSequence, $initialData ); - foreach ( $wgExtensionMessagesFiles as $extension => $fileName ) { - if ( isset( $messageDirs[$extension] ) ) { - # This extension has JSON message data; skip the PHP shim - continue; - } - - $data = $this->readPHPFile( $fileName, 'extension' ); - $used = false; - - foreach ( $data as $key => $item ) { - foreach ( $codeSequence as $csCode ) { - if ( isset( $item[$csCode] ) ) { - $this->mergeItem( $key, $extensionData[$csCode][$key], $item[$csCode] ); - $used = true; - } - } - } - - if ( $used ) { - $deps[] = new FileDependency( $fileName ); - } - } - - # Load the localisation data for each fallback, then merge it into the full array - $allData = $initialData; - foreach ( $codeSequence as $csCode ) { - $csData = $initialData; - - # Load core messages and the extension localisations. - foreach ( $messageDirs as $dirs ) { - foreach ( (array)$dirs as $dir ) { - $fileName = "$dir/$csCode.json"; - $data = $this->readJSONFile( $fileName ); - - foreach ( $data as $key => $item ) { - $this->mergeItem( $key, $csData[$key], $item ); - } - - $deps[] = new FileDependency( $fileName ); - } - } - - # Merge non-JSON extension data - if ( isset( $extensionData[$csCode] ) ) { - foreach ( $extensionData[$csCode] as $key => $item ) { - $this->mergeItem( $key, $csData[$key], $item ); - } - } - - if ( $csCode === $code ) { - # Merge core data into extension data - foreach ( $coreData as $key => $item ) { - $this->mergeItem( $key, $csData[$key], $item ); - } - } else { - # Load the secondary localisation from the source file to - # avoid infinite cycles on cyclic fallbacks - $fbData = $this->readSourceFilesAndRegisterDeps( $csCode, $deps ); - if ( $fbData !== false ) { - # Only merge the keys that make sense to merge - foreach ( self::$allKeys as $key ) { - if ( !isset( $fbData[$key] ) ) { - continue; - } - - if ( is_null( $coreData[$key] ) || $this->isMergeableKey( $key ) ) { - $this->mergeItem( $key, $csData[$key], $fbData[$key] ); - } - } - } - } - - # Allow extensions an opportunity to adjust the data for this - # fallback - Hooks::run( 'LocalisationCacheRecacheFallback', [ $this, $csCode, &$csData ] ); - - # Merge the data for this fallback into the final array - if ( $csCode === $code ) { - $allData = $csData; - } else { - foreach ( self::$allKeys as $key ) { - if ( !isset( $csData[$key] ) ) { - continue; - } - - if ( is_null( $allData[$key] ) || $this->isMergeableKey( $key ) ) { - $this->mergeItem( $key, $allData[$key], $csData[$key] ); - } - } - } - } - - # Add cache dependencies for any referenced globals - $deps['wgExtensionMessagesFiles'] = new GlobalDependency( 'wgExtensionMessagesFiles' ); - // $wgMessagesDirs is used in LocalisationCache::getMessagesDirs() - $deps['wgMessagesDirs'] = new GlobalDependency( 'wgMessagesDirs' ); - $deps['version'] = new ConstantDependency( 'LocalisationCache::VERSION' ); - - # Add dependencies to the cache entry - $allData['deps'] = $deps; - - # Replace spaces with underscores in namespace names - $allData['namespaceNames'] = str_replace( ' ', '_', $allData['namespaceNames'] ); - - # And do the same for special page aliases. $page is an array. - foreach ( $allData['specialPageAliases'] as &$page ) { - $page = str_replace( ' ', '_', $page ); - } - # Decouple the reference to prevent accidental damage - unset( $page ); - - # If there were no plural rules, return an empty array - if ( $allData['pluralRules'] === null ) { - $allData['pluralRules'] = []; - } - if ( $allData['compiledPluralRules'] === null ) { - $allData['compiledPluralRules'] = []; - } - # If there were no plural rule types, return an empty array - if ( $allData['pluralRuleTypes'] === null ) { - $allData['pluralRuleTypes'] = []; - } - - # Set the list keys - $allData['list'] = []; - foreach ( self::$splitKeys as $key ) { - $allData['list'][$key] = array_keys( $allData[$key] ); - } - # Run hooks - $purgeBlobs = true; - Hooks::run( 'LocalisationCacheRecache', [ $this, $code, &$allData, &$purgeBlobs ] ); - - if ( is_null( $allData['namespaceNames'] ) ) { - throw new MWException( __METHOD__ . ': Localisation data failed sanity check! ' . - 'Check that your languages/messages/MessagesEn.php file is intact.' ); - } - - # Set the preload key - $allData['preload'] = $this->buildPreload( $allData ); - - # Save to the process cache and register the items loaded - $this->data[$code] = $allData; - foreach ( $allData as $key => $item ) { - $this->loadedItems[$code][$key] = true; - } - - # Save to the persistent cache - $this->store->startWrite( $code ); - foreach ( $allData as $key => $value ) { - if ( in_array( $key, self::$splitKeys ) ) { - foreach ( $value as $subkey => $subvalue ) { - $this->store->set( "$key:$subkey", $subvalue ); - } - } else { - $this->store->set( $key, $value ); - } - } - $this->store->finishWrite(); - - # Clear out the MessageBlobStore - # HACK: If using a null (i.e. disabled) storage backend, we - # can't write to the MessageBlobStore either - if ( $purgeBlobs && !$this->store instanceof LCStoreNull ) { - $blobStore = new MessageBlobStore(); - $blobStore->clear(); - } - - } - - /** - * Build the preload item from the given pre-cache data. - * - * The preload item will be loaded automatically, improving performance - * for the commonly-requested items it contains. - * @param array $data - * @return array - */ - protected function buildPreload( $data ) { - $preload = [ 'messages' => [] ]; - foreach ( self::$preloadedKeys as $key ) { - $preload[$key] = $data[$key]; - } - - foreach ( $data['preloadedMessages'] as $subkey ) { - if ( isset( $data['messages'][$subkey] ) ) { - $subitem = $data['messages'][$subkey]; - } else { - $subitem = null; - } - $preload['messages'][$subkey] = $subitem; - } - - return $preload; - } - - /** - * Unload the data for a given language from the object cache. - * Reduces memory usage. - * @param string $code - */ - public function unload( $code ) { - unset( $this->data[$code] ); - unset( $this->loadedItems[$code] ); - unset( $this->loadedSubitems[$code] ); - unset( $this->initialisedLangs[$code] ); - unset( $this->shallowFallbacks[$code] ); - - foreach ( $this->shallowFallbacks as $shallowCode => $fbCode ) { - if ( $fbCode === $code ) { - $this->unload( $shallowCode ); - } - } - } - - /** - * Unload all data - */ - public function unloadAll() { - foreach ( $this->initialisedLangs as $lang => $unused ) { - $this->unload( $lang ); - } - } - - /** - * Disable the storage backend - */ - public function disableBackend() { - $this->store = new LCStoreNull; - $this->manualRecache = false; - } -} - -/** - * Interface for the persistence layer of LocalisationCache. - * - * The persistence layer is two-level hierarchical cache. The first level - * is the language, the second level is the item or subitem. - * - * Since the data for a whole language is rebuilt in one operation, it needs - * to have a fast and atomic method for deleting or replacing all of the - * current data for a given language. The interface reflects this bulk update - * operation. Callers writing to the cache must first call startWrite(), then - * will call set() a couple of thousand times, then will call finishWrite() - * to commit the operation. When finishWrite() is called, the cache is - * expected to delete all data previously stored for that language. - * - * The values stored are PHP variables suitable for serialize(). Implementations - * of LCStore are responsible for serializing and unserializing. - */ -interface LCStore { - /** - * Get a value. - * @param string $code Language code - * @param string $key Cache key - */ - function get( $code, $key ); - - /** - * Start a write transaction. - * @param string $code Language code - */ - function startWrite( $code ); - - /** - * Finish a write transaction. - */ - function finishWrite(); - - /** - * Set a key to a given value. startWrite() must be called before this - * is called, and finishWrite() must be called afterwards. - * @param string $key - * @param mixed $value - */ - function set( $key, $value ); -} - -/** - * LCStore implementation which uses the standard DB functions to store data. - * This will work on any MediaWiki installation. - */ -class LCStoreDB implements LCStore { - /** @var string */ - private $currentLang; - /** @var bool */ - private $writesDone = false; - /** @var IDatabase */ - private $dbw; - /** @var array */ - private $batch = []; - /** @var bool */ - private $readOnly = false; - - public function get( $code, $key ) { - if ( $this->writesDone && $this->dbw ) { - $db = $this->dbw; // see the changes in finishWrite() - } else { - $db = wfGetDB( DB_SLAVE ); - } - - $value = $db->selectField( - 'l10n_cache', - 'lc_value', - [ 'lc_lang' => $code, 'lc_key' => $key ], - __METHOD__ - ); - - return ( $value !== false ) ? unserialize( $db->decodeBlob( $value ) ) : null; - } - - public function startWrite( $code ) { - if ( $this->readOnly ) { - return; - } elseif ( !$code ) { - throw new MWException( __METHOD__ . ": Invalid language \"$code\"" ); - } - - $this->dbw = wfGetDB( DB_MASTER ); - $this->readOnly = $this->dbw->isReadOnly(); - - $this->currentLang = $code; - $this->batch = []; - } - - public function finishWrite() { - if ( $this->readOnly ) { - return; - } elseif ( is_null( $this->currentLang ) ) { - throw new MWException( __CLASS__ . ': must call startWrite() before finishWrite()' ); - } - - $this->dbw->startAtomic( __METHOD__ ); - try { - $this->dbw->delete( - 'l10n_cache', - [ 'lc_lang' => $this->currentLang ], - __METHOD__ - ); - foreach ( array_chunk( $this->batch, 500 ) as $rows ) { - $this->dbw->insert( 'l10n_cache', $rows, __METHOD__ ); - } - $this->writesDone = true; - } catch ( DBQueryError $e ) { - if ( $this->dbw->wasReadOnlyError() ) { - $this->readOnly = true; // just avoid site down time - } else { - throw $e; - } - } - $this->dbw->endAtomic( __METHOD__ ); - - $this->currentLang = null; - $this->batch = []; - } - - public function set( $key, $value ) { - if ( $this->readOnly ) { - return; - } elseif ( is_null( $this->currentLang ) ) { - throw new MWException( __CLASS__ . ': must call startWrite() before set()' ); - } - - $this->batch[] = [ - 'lc_lang' => $this->currentLang, - 'lc_key' => $key, - 'lc_value' => $this->dbw->encodeBlob( serialize( $value ) ) - ]; - } -} - -/** - * LCStore implementation which stores data as a collection of CDB files in the - * directory given by $wgCacheDirectory. If $wgCacheDirectory is not set, this - * will throw an exception. - * - * Profiling indicates that on Linux, this implementation outperforms MySQL if - * the directory is on a local filesystem and there is ample kernel cache - * space. The performance advantage is greater when the DBA extension is - * available than it is with the PHP port. - * - * See Cdb.php and http://cr.yp.to/cdb.html - */ -class LCStoreCDB implements LCStore { - /** @var CdbReader[] */ - private $readers; - - /** @var CdbWriter */ - private $writer; - - /** @var string Current language code */ - private $currentLang; - - /** @var bool|string Cache directory. False if not set */ - private $directory; - - function __construct( $conf = [] ) { - global $wgCacheDirectory; - - if ( isset( $conf['directory'] ) ) { - $this->directory = $conf['directory']; - } else { - $this->directory = $wgCacheDirectory; - } - } - - public function get( $code, $key ) { - if ( !isset( $this->readers[$code] ) ) { - $fileName = $this->getFileName( $code ); - - $this->readers[$code] = false; - if ( file_exists( $fileName ) ) { - try { - $this->readers[$code] = CdbReader::open( $fileName ); - } catch ( CdbException $e ) { - wfDebug( __METHOD__ . ": unable to open cdb file for reading\n" ); - } - } - } - - if ( !$this->readers[$code] ) { - return null; - } else { - $value = false; - try { - $value = $this->readers[$code]->get( $key ); - } catch ( CdbException $e ) { - wfDebug( __METHOD__ . ": CdbException caught, error message was " - . $e->getMessage() . "\n" ); - } - if ( $value === false ) { - return null; - } - - return unserialize( $value ); - } - } - - public function startWrite( $code ) { - if ( !file_exists( $this->directory ) ) { - if ( !wfMkdirParents( $this->directory, null, __METHOD__ ) ) { - throw new MWException( "Unable to create the localisation store " . - "directory \"{$this->directory}\"" ); - } - } - - // Close reader to stop permission errors on write - if ( !empty( $this->readers[$code] ) ) { - $this->readers[$code]->close(); - } - - try { - $this->writer = CdbWriter::open( $this->getFileName( $code ) ); - } catch ( CdbException $e ) { - throw new MWException( $e->getMessage() ); - } - $this->currentLang = $code; - } - - public function finishWrite() { - // Close the writer - try { - $this->writer->close(); - } catch ( CdbException $e ) { - throw new MWException( $e->getMessage() ); - } - $this->writer = null; - unset( $this->readers[$this->currentLang] ); - $this->currentLang = null; - } - - public function set( $key, $value ) { - if ( is_null( $this->writer ) ) { - throw new MWException( __CLASS__ . ': must call startWrite() before calling set()' ); - } - try { - $this->writer->set( $key, serialize( $value ) ); - } catch ( CdbException $e ) { - throw new MWException( $e->getMessage() ); - } - } - - protected function getFileName( $code ) { - if ( strval( $code ) === '' || strpos( $code, '/' ) !== false ) { - throw new MWException( __METHOD__ . ": Invalid language \"$code\"" ); - } - - return "{$this->directory}/l10n_cache-$code.cdb"; - } -} - -/** - * Null store backend, used to avoid DB errors during install - */ -class LCStoreNull implements LCStore { - public function get( $code, $key ) { - return null; - } - - public function startWrite( $code ) { - } - - public function finishWrite() { - } - - public function set( $key, $value ) { - } -} - -/** - * A localisation cache optimised for loading large amounts of data for many - * languages. Used by rebuildLocalisationCache.php. - */ -class LocalisationCacheBulkLoad extends LocalisationCache { - /** - * A cache of the contents of data files. - * Core files are serialized to avoid using ~1GB of RAM during a recache. - */ - private $fileCache = []; - - /** - * Most recently used languages. Uses the linked-list aspect of PHP hashtables - * to keep the most recently used language codes at the end of the array, and - * the language codes that are ready to be deleted at the beginning. - */ - private $mruLangs = []; - - /** - * Maximum number of languages that may be loaded into $this->data - */ - private $maxLoadedLangs = 10; - - /** - * @param string $fileName - * @param string $fileType - * @return array|mixed - */ - protected function readPHPFile( $fileName, $fileType ) { - $serialize = $fileType === 'core'; - if ( !isset( $this->fileCache[$fileName][$fileType] ) ) { - $data = parent::readPHPFile( $fileName, $fileType ); - - if ( $serialize ) { - $encData = serialize( $data ); - } else { - $encData = $data; - } - - $this->fileCache[$fileName][$fileType] = $encData; - - return $data; - } elseif ( $serialize ) { - return unserialize( $this->fileCache[$fileName][$fileType] ); - } else { - return $this->fileCache[$fileName][$fileType]; - } - } - - /** - * @param string $code - * @param string $key - * @return mixed - */ - public function getItem( $code, $key ) { - unset( $this->mruLangs[$code] ); - $this->mruLangs[$code] = true; - - return parent::getItem( $code, $key ); - } - - /** - * @param string $code - * @param string $key - * @param string $subkey - * @return mixed - */ - public function getSubitem( $code, $key, $subkey ) { - unset( $this->mruLangs[$code] ); - $this->mruLangs[$code] = true; - - return parent::getSubitem( $code, $key, $subkey ); - } - - /** - * @param string $code - */ - public function recache( $code ) { - parent::recache( $code ); - unset( $this->mruLangs[$code] ); - $this->mruLangs[$code] = true; - $this->trimCache(); - } - - /** - * @param string $code - */ - public function unload( $code ) { - unset( $this->mruLangs[$code] ); - parent::unload( $code ); - } - - /** - * Unload cached languages until there are less than $this->maxLoadedLangs - */ - protected function trimCache() { - while ( count( $this->data ) > $this->maxLoadedLangs && count( $this->mruLangs ) ) { - reset( $this->mruLangs ); - $code = key( $this->mruLangs ); - wfDebug( __METHOD__ . ": unloading $code\n" ); - $this->unload( $code ); - } - } -} diff --git a/includes/cache/localisation/LCStore.php b/includes/cache/localisation/LCStore.php new file mode 100644 index 0000000000..cb1e261256 --- /dev/null +++ b/includes/cache/localisation/LCStore.php @@ -0,0 +1,66 @@ +directory = $conf['directory']; + } else { + $this->directory = $wgCacheDirectory; + } + } + + public function get( $code, $key ) { + if ( !isset( $this->readers[$code] ) ) { + $fileName = $this->getFileName( $code ); + + $this->readers[$code] = false; + if ( file_exists( $fileName ) ) { + try { + $this->readers[$code] = CdbReader::open( $fileName ); + } catch ( CdbException $e ) { + wfDebug( __METHOD__ . ": unable to open cdb file for reading\n" ); + } + } + } + + if ( !$this->readers[$code] ) { + return null; + } else { + $value = false; + try { + $value = $this->readers[$code]->get( $key ); + } catch ( CdbException $e ) { + wfDebug( __METHOD__ . ": CdbException caught, error message was " + . $e->getMessage() . "\n" ); + } + if ( $value === false ) { + return null; + } + + return unserialize( $value ); + } + } + + public function startWrite( $code ) { + if ( !file_exists( $this->directory ) ) { + if ( !wfMkdirParents( $this->directory, null, __METHOD__ ) ) { + throw new MWException( "Unable to create the localisation store " . + "directory \"{$this->directory}\"" ); + } + } + + // Close reader to stop permission errors on write + if ( !empty( $this->readers[$code] ) ) { + $this->readers[$code]->close(); + } + + try { + $this->writer = CdbWriter::open( $this->getFileName( $code ) ); + } catch ( CdbException $e ) { + throw new MWException( $e->getMessage() ); + } + $this->currentLang = $code; + } + + public function finishWrite() { + // Close the writer + try { + $this->writer->close(); + } catch ( CdbException $e ) { + throw new MWException( $e->getMessage() ); + } + $this->writer = null; + unset( $this->readers[$this->currentLang] ); + $this->currentLang = null; + } + + public function set( $key, $value ) { + if ( is_null( $this->writer ) ) { + throw new MWException( __CLASS__ . ': must call startWrite() before calling set()' ); + } + try { + $this->writer->set( $key, serialize( $value ) ); + } catch ( CdbException $e ) { + throw new MWException( $e->getMessage() ); + } + } + + protected function getFileName( $code ) { + if ( strval( $code ) === '' || strpos( $code, '/' ) !== false ) { + throw new MWException( __METHOD__ . ": Invalid language \"$code\"" ); + } + + return "{$this->directory}/l10n_cache-$code.cdb"; + } + +} diff --git a/includes/cache/localisation/LCStoreDB.php b/includes/cache/localisation/LCStoreDB.php new file mode 100644 index 0000000000..c3501782b4 --- /dev/null +++ b/includes/cache/localisation/LCStoreDB.php @@ -0,0 +1,114 @@ +writesDone && $this->dbw ) { + $db = $this->dbw; // see the changes in finishWrite() + } else { + $db = wfGetDB( DB_SLAVE ); + } + + $value = $db->selectField( + 'l10n_cache', + 'lc_value', + [ 'lc_lang' => $code, 'lc_key' => $key ], + __METHOD__ + ); + + return ( $value !== false ) ? unserialize( $db->decodeBlob( $value ) ) : null; + } + + public function startWrite( $code ) { + if ( $this->readOnly ) { + return; + } elseif ( !$code ) { + throw new MWException( __METHOD__ . ": Invalid language \"$code\"" ); + } + + $this->dbw = wfGetDB( DB_MASTER ); + $this->readOnly = $this->dbw->isReadOnly(); + + $this->currentLang = $code; + $this->batch = []; + } + + public function finishWrite() { + if ( $this->readOnly ) { + return; + } elseif ( is_null( $this->currentLang ) ) { + throw new MWException( __CLASS__ . ': must call startWrite() before finishWrite()' ); + } + + $this->dbw->startAtomic( __METHOD__ ); + try { + $this->dbw->delete( + 'l10n_cache', + [ 'lc_lang' => $this->currentLang ], + __METHOD__ + ); + foreach ( array_chunk( $this->batch, 500 ) as $rows ) { + $this->dbw->insert( 'l10n_cache', $rows, __METHOD__ ); + } + $this->writesDone = true; + } catch ( DBQueryError $e ) { + if ( $this->dbw->wasReadOnlyError() ) { + $this->readOnly = true; // just avoid site down time + } else { + throw $e; + } + } + $this->dbw->endAtomic( __METHOD__ ); + + $this->currentLang = null; + $this->batch = []; + } + + public function set( $key, $value ) { + if ( $this->readOnly ) { + return; + } elseif ( is_null( $this->currentLang ) ) { + throw new MWException( __CLASS__ . ': must call startWrite() before set()' ); + } + + $this->batch[] = [ + 'lc_lang' => $this->currentLang, + 'lc_key' => $key, + 'lc_value' => $this->dbw->encodeBlob( serialize( $value ) ) + ]; + } + +} diff --git a/includes/cache/localisation/LCStoreNull.php b/includes/cache/localisation/LCStoreNull.php new file mode 100644 index 0000000000..62f88ebf2d --- /dev/null +++ b/includes/cache/localisation/LCStoreNull.php @@ -0,0 +1,39 @@ +directory = $conf['directory']; + } else { + $this->directory = $wgCacheDirectory; + } + } + + public function startWrite( $code ) { + $this->currentLang = $code; + $this->fname = $this->directory . '/' . $code . '.l10n.php'; + $this->data[$code] = []; + if ( file_exists( $this->fname ) ) { + $this->data[$code] = require $this->fname; + } + } + + public function set( $key, $value ) { + $this->data[$this->currentLang][$key] = self::encode( $value ); + } + + /** + * Encodes a value into an array format + * + * @param mixed $value + * @return array + * @throws RuntimeException + */ + public static function encode( $value ) { + if ( is_scalar( $value ) || $value === null ) { + // [V]alue + return [ 'v', $value ]; + } + if ( is_object( $value ) ) { + // [S]erialized + return [ 's', serialize( $value ) ]; + } + if ( is_array( $value ) ) { + // [A]rray + return [ 'a', array_map( function ( $v ) { + return LCStoreStaticArray::encode( $v ); + }, $value ) ]; + } + + throw new RuntimeException( 'Cannot encode ' . var_export( $value, true ) ); + } + + /** + * Decode something that was encoded with encode + * + * @param array $encoded + * @return array|mixed + * @throws RuntimeException + */ + public static function decode( array $encoded ) { + $type = $encoded[0]; + $data = $encoded[1]; + + switch ( $type ) { + case 'v': + return $data; + case 's': + return unserialize( $data ); + case 'a': + return array_map( function ( $v ) { + return LCStoreStaticArray::decode( $v ); + }, $data ); + default: + throw new RuntimeException( + 'Unable to decode ' . var_export( $encoded, true ) ); + } + } + + public function finishWrite() { + file_put_contents( + $this->fname, + "data[$this->currentLang], true ) . ';' + ); + $this->currentLang = null; + $this->fname = null; + } + + public function get( $code, $key ) { + if ( !array_key_exists( $code, $this->data ) ) { + $fname = $this->directory . '/' . $code . '.l10n.php'; + if ( !file_exists( $fname ) ) { + return null; + } + $this->data[$code] = require $fname; + } + $data = $this->data[$code]; + if ( array_key_exists( $key, $data ) ) { + return self::decode( $data[$key] ); + } + return null; + } +} diff --git a/includes/cache/localisation/LocalisationCache.php b/includes/cache/localisation/LocalisationCache.php new file mode 100644 index 0000000000..dd7d81a33c --- /dev/null +++ b/includes/cache/localisation/LocalisationCache.php @@ -0,0 +1,1098 @@ + + * zh-hans -> en ). Some common errors are corrected, for example namespace + * names with spaces instead of underscores, but heavyweight processing, such + * as grammatical transformation, is done by the caller. + */ +class LocalisationCache { + const VERSION = 4; + + /** Configuration associative array */ + private $conf; + + /** + * True if recaching should only be done on an explicit call to recache(). + * Setting this reduces the overhead of cache freshness checking, which + * requires doing a stat() for every extension i18n file. + */ + private $manualRecache = false; + + /** + * True to treat all files as expired until they are regenerated by this object. + */ + private $forceRecache = false; + + /** + * The cache data. 3-d array, where the first key is the language code, + * the second key is the item key e.g. 'messages', and the third key is + * an item specific subkey index. Some items are not arrays and so for those + * items, there are no subkeys. + */ + protected $data = []; + + /** + * The persistent store object. An instance of LCStore. + * + * @var LCStore + */ + private $store; + + /** + * A 2-d associative array, code/key, where presence indicates that the item + * is loaded. Value arbitrary. + * + * For split items, if set, this indicates that all of the subitems have been + * loaded. + */ + private $loadedItems = []; + + /** + * A 3-d associative array, code/key/subkey, where presence indicates that + * the subitem is loaded. Only used for the split items, i.e. messages. + */ + private $loadedSubitems = []; + + /** + * An array where presence of a key indicates that that language has been + * initialised. Initialisation includes checking for cache expiry and doing + * any necessary updates. + */ + private $initialisedLangs = []; + + /** + * An array mapping non-existent pseudo-languages to fallback languages. This + * is filled by initShallowFallback() when data is requested from a language + * that lacks a Messages*.php file. + */ + private $shallowFallbacks = []; + + /** + * An array where the keys are codes that have been recached by this instance. + */ + private $recachedLangs = []; + + /** + * All item keys + */ + static public $allKeys = [ + 'fallback', 'namespaceNames', 'bookstoreList', + 'magicWords', 'messages', 'rtl', 'capitalizeAllNouns', 'digitTransformTable', + 'separatorTransformTable', 'fallback8bitEncoding', 'linkPrefixExtension', + 'linkTrail', 'linkPrefixCharset', 'namespaceAliases', + 'dateFormats', 'datePreferences', 'datePreferenceMigrationMap', + 'defaultDateFormat', 'extraUserToggles', 'specialPageAliases', + 'imageFiles', 'preloadedMessages', 'namespaceGenderAliases', + 'digitGroupingPattern', 'pluralRules', 'pluralRuleTypes', 'compiledPluralRules', + ]; + + /** + * Keys for items which consist of associative arrays, which may be merged + * by a fallback sequence. + */ + static public $mergeableMapKeys = [ 'messages', 'namespaceNames', + 'namespaceAliases', 'dateFormats', 'imageFiles', 'preloadedMessages' + ]; + + /** + * Keys for items which are a numbered array. + */ + static public $mergeableListKeys = [ 'extraUserToggles' ]; + + /** + * Keys for items which contain an array of arrays of equivalent aliases + * for each subitem. The aliases may be merged by a fallback sequence. + */ + static public $mergeableAliasListKeys = [ 'specialPageAliases' ]; + + /** + * Keys for items which contain an associative array, and may be merged if + * the primary value contains the special array key "inherit". That array + * key is removed after the first merge. + */ + static public $optionalMergeKeys = [ 'bookstoreList' ]; + + /** + * Keys for items that are formatted like $magicWords + */ + static public $magicWordKeys = [ 'magicWords' ]; + + /** + * Keys for items where the subitems are stored in the backend separately. + */ + static public $splitKeys = [ 'messages' ]; + + /** + * Keys which are loaded automatically by initLanguage() + */ + static public $preloadedKeys = [ 'dateFormats', 'namespaceNames' ]; + + /** + * Associative array of cached plural rules. The key is the language code, + * the value is an array of plural rules for that language. + */ + private $pluralRules = null; + + /** + * Associative array of cached plural rule types. The key is the language + * code, the value is an array of plural rule types for that language. For + * example, $pluralRuleTypes['ar'] = ['zero', 'one', 'two', 'few', 'many']. + * The index for each rule type matches the index for the rule in + * $pluralRules, thus allowing correlation between the two. The reason we + * don't just use the type names as the keys in $pluralRules is because + * Language::convertPlural applies the rules based on numeric order (or + * explicit numeric parameter), not based on the name of the rule type. For + * example, {{plural:count|wordform1|wordform2|wordform3}}, rather than + * {{plural:count|one=wordform1|two=wordform2|many=wordform3}}. + */ + private $pluralRuleTypes = null; + + private $mergeableKeys = null; + + /** + * Constructor. + * For constructor parameters, see the documentation in DefaultSettings.php + * for $wgLocalisationCacheConf. + * + * @param array $conf + * @throws MWException + */ + function __construct( $conf ) { + global $wgCacheDirectory; + + $this->conf = $conf; + $storeConf = []; + if ( !empty( $conf['storeClass'] ) ) { + $storeClass = $conf['storeClass']; + } else { + switch ( $conf['store'] ) { + case 'files': + case 'file': + $storeClass = 'LCStoreCDB'; + break; + case 'db': + $storeClass = 'LCStoreDB'; + break; + case 'array': + $storeClass = 'LCStoreStaticArray'; + break; + case 'detect': + if ( !empty( $conf['storeDirectory'] ) ) { + $storeClass = 'LCStoreCDB'; + } else { + $cacheDir = $wgCacheDirectory ?: wfTempDir(); + if ( $cacheDir ) { + $storeConf['directory'] = $cacheDir; + $storeClass = 'LCStoreCDB'; + } else { + $storeClass = 'LCStoreDB'; + } + } + break; + default: + throw new MWException( + 'Please set $wgLocalisationCacheConf[\'store\'] to something sensible.' ); + } + } + + wfDebugLog( 'caches', get_class( $this ) . ": using store $storeClass" ); + if ( !empty( $conf['storeDirectory'] ) ) { + $storeConf['directory'] = $conf['storeDirectory']; + } + + $this->store = new $storeClass( $storeConf ); + foreach ( [ 'manualRecache', 'forceRecache' ] as $var ) { + if ( isset( $conf[$var] ) ) { + $this->$var = $conf[$var]; + } + } + } + + /** + * Returns true if the given key is mergeable, that is, if it is an associative + * array which can be merged through a fallback sequence. + * @param string $key + * @return bool + */ + public function isMergeableKey( $key ) { + if ( $this->mergeableKeys === null ) { + $this->mergeableKeys = array_flip( array_merge( + self::$mergeableMapKeys, + self::$mergeableListKeys, + self::$mergeableAliasListKeys, + self::$optionalMergeKeys, + self::$magicWordKeys + ) ); + } + + return isset( $this->mergeableKeys[$key] ); + } + + /** + * Get a cache item. + * + * Warning: this may be slow for split items (messages), since it will + * need to fetch all of the subitems from the cache individually. + * @param string $code + * @param string $key + * @return mixed + */ + public function getItem( $code, $key ) { + if ( !isset( $this->loadedItems[$code][$key] ) ) { + $this->loadItem( $code, $key ); + } + + if ( $key === 'fallback' && isset( $this->shallowFallbacks[$code] ) ) { + return $this->shallowFallbacks[$code]; + } + + return $this->data[$code][$key]; + } + + /** + * Get a subitem, for instance a single message for a given language. + * @param string $code + * @param string $key + * @param string $subkey + * @return mixed|null + */ + public function getSubitem( $code, $key, $subkey ) { + if ( !isset( $this->loadedSubitems[$code][$key][$subkey] ) && + !isset( $this->loadedItems[$code][$key] ) + ) { + $this->loadSubitem( $code, $key, $subkey ); + } + + if ( isset( $this->data[$code][$key][$subkey] ) ) { + return $this->data[$code][$key][$subkey]; + } else { + return null; + } + } + + /** + * Get the list of subitem keys for a given item. + * + * This is faster than array_keys($lc->getItem(...)) for the items listed in + * self::$splitKeys. + * + * Will return null if the item is not found, or false if the item is not an + * array. + * @param string $code + * @param string $key + * @return bool|null|string + */ + public function getSubitemList( $code, $key ) { + if ( in_array( $key, self::$splitKeys ) ) { + return $this->getSubitem( $code, 'list', $key ); + } else { + $item = $this->getItem( $code, $key ); + if ( is_array( $item ) ) { + return array_keys( $item ); + } else { + return false; + } + } + } + + /** + * Load an item into the cache. + * @param string $code + * @param string $key + */ + protected function loadItem( $code, $key ) { + if ( !isset( $this->initialisedLangs[$code] ) ) { + $this->initLanguage( $code ); + } + + // Check to see if initLanguage() loaded it for us + if ( isset( $this->loadedItems[$code][$key] ) ) { + return; + } + + if ( isset( $this->shallowFallbacks[$code] ) ) { + $this->loadItem( $this->shallowFallbacks[$code], $key ); + + return; + } + + if ( in_array( $key, self::$splitKeys ) ) { + $subkeyList = $this->getSubitem( $code, 'list', $key ); + foreach ( $subkeyList as $subkey ) { + if ( isset( $this->data[$code][$key][$subkey] ) ) { + continue; + } + $this->data[$code][$key][$subkey] = $this->getSubitem( $code, $key, $subkey ); + } + } else { + $this->data[$code][$key] = $this->store->get( $code, $key ); + } + + $this->loadedItems[$code][$key] = true; + } + + /** + * Load a subitem into the cache + * @param string $code + * @param string $key + * @param string $subkey + */ + protected function loadSubitem( $code, $key, $subkey ) { + if ( !in_array( $key, self::$splitKeys ) ) { + $this->loadItem( $code, $key ); + + return; + } + + if ( !isset( $this->initialisedLangs[$code] ) ) { + $this->initLanguage( $code ); + } + + // Check to see if initLanguage() loaded it for us + if ( isset( $this->loadedItems[$code][$key] ) || + isset( $this->loadedSubitems[$code][$key][$subkey] ) + ) { + return; + } + + if ( isset( $this->shallowFallbacks[$code] ) ) { + $this->loadSubitem( $this->shallowFallbacks[$code], $key, $subkey ); + + return; + } + + $value = $this->store->get( $code, "$key:$subkey" ); + $this->data[$code][$key][$subkey] = $value; + $this->loadedSubitems[$code][$key][$subkey] = true; + } + + /** + * Returns true if the cache identified by $code is missing or expired. + * + * @param string $code + * + * @return bool + */ + public function isExpired( $code ) { + if ( $this->forceRecache && !isset( $this->recachedLangs[$code] ) ) { + wfDebug( __METHOD__ . "($code): forced reload\n" ); + + return true; + } + + $deps = $this->store->get( $code, 'deps' ); + $keys = $this->store->get( $code, 'list' ); + $preload = $this->store->get( $code, 'preload' ); + // Different keys may expire separately for some stores + if ( $deps === null || $keys === null || $preload === null ) { + wfDebug( __METHOD__ . "($code): cache missing, need to make one\n" ); + + return true; + } + + foreach ( $deps as $dep ) { + // Because we're unserializing stuff from cache, we + // could receive objects of classes that don't exist + // anymore (e.g. uninstalled extensions) + // When this happens, always expire the cache + if ( !$dep instanceof CacheDependency || $dep->isExpired() ) { + wfDebug( __METHOD__ . "($code): cache for $code expired due to " . + get_class( $dep ) . "\n" ); + + return true; + } + } + + return false; + } + + /** + * Initialise a language in this object. Rebuild the cache if necessary. + * @param string $code + * @throws MWException + */ + protected function initLanguage( $code ) { + if ( isset( $this->initialisedLangs[$code] ) ) { + return; + } + + $this->initialisedLangs[$code] = true; + + # If the code is of the wrong form for a Messages*.php file, do a shallow fallback + if ( !Language::isValidBuiltInCode( $code ) ) { + $this->initShallowFallback( $code, 'en' ); + + return; + } + + # Recache the data if necessary + if ( !$this->manualRecache && $this->isExpired( $code ) ) { + if ( Language::isSupportedLanguage( $code ) ) { + $this->recache( $code ); + } elseif ( $code === 'en' ) { + throw new MWException( 'MessagesEn.php is missing.' ); + } else { + $this->initShallowFallback( $code, 'en' ); + } + + return; + } + + # Preload some stuff + $preload = $this->getItem( $code, 'preload' ); + if ( $preload === null ) { + if ( $this->manualRecache ) { + // No Messages*.php file. Do shallow fallback to en. + if ( $code === 'en' ) { + throw new MWException( 'No localisation cache found for English. ' . + 'Please run maintenance/rebuildLocalisationCache.php.' ); + } + $this->initShallowFallback( $code, 'en' ); + + return; + } else { + throw new MWException( 'Invalid or missing localisation cache.' ); + } + } + $this->data[$code] = $preload; + foreach ( $preload as $key => $item ) { + if ( in_array( $key, self::$splitKeys ) ) { + foreach ( $item as $subkey => $subitem ) { + $this->loadedSubitems[$code][$key][$subkey] = true; + } + } else { + $this->loadedItems[$code][$key] = true; + } + } + } + + /** + * Create a fallback from one language to another, without creating a + * complete persistent cache. + * @param string $primaryCode + * @param string $fallbackCode + */ + public function initShallowFallback( $primaryCode, $fallbackCode ) { + $this->data[$primaryCode] =& $this->data[$fallbackCode]; + $this->loadedItems[$primaryCode] =& $this->loadedItems[$fallbackCode]; + $this->loadedSubitems[$primaryCode] =& $this->loadedSubitems[$fallbackCode]; + $this->shallowFallbacks[$primaryCode] = $fallbackCode; + } + + /** + * Read a PHP file containing localisation data. + * @param string $_fileName + * @param string $_fileType + * @throws MWException + * @return array + */ + protected function readPHPFile( $_fileName, $_fileType ) { + // Disable APC caching + MediaWiki\suppressWarnings(); + $_apcEnabled = ini_set( 'apc.cache_by_default', '0' ); + MediaWiki\restoreWarnings(); + + include $_fileName; + + MediaWiki\suppressWarnings(); + ini_set( 'apc.cache_by_default', $_apcEnabled ); + MediaWiki\restoreWarnings(); + + if ( $_fileType == 'core' || $_fileType == 'extension' ) { + $data = compact( self::$allKeys ); + } elseif ( $_fileType == 'aliases' ) { + $data = compact( 'aliases' ); + } else { + throw new MWException( __METHOD__ . ": Invalid file type: $_fileType" ); + } + + return $data; + } + + /** + * Read a JSON file containing localisation messages. + * @param string $fileName Name of file to read + * @throws MWException If there is a syntax error in the JSON file + * @return array Array with a 'messages' key, or empty array if the file doesn't exist + */ + public function readJSONFile( $fileName ) { + + if ( !is_readable( $fileName ) ) { + return []; + } + + $json = file_get_contents( $fileName ); + if ( $json === false ) { + return []; + } + + $data = FormatJson::decode( $json, true ); + if ( $data === null ) { + + throw new MWException( __METHOD__ . ": Invalid JSON file: $fileName" ); + } + + // Remove keys starting with '@', they're reserved for metadata and non-message data + foreach ( $data as $key => $unused ) { + if ( $key === '' || $key[0] === '@' ) { + unset( $data[$key] ); + } + } + + // The JSON format only supports messages, none of the other variables, so wrap the data + return [ 'messages' => $data ]; + } + + /** + * Get the compiled plural rules for a given language from the XML files. + * @since 1.20 + * @param string $code + * @return array|null + */ + public function getCompiledPluralRules( $code ) { + $rules = $this->getPluralRules( $code ); + if ( $rules === null ) { + return null; + } + try { + $compiledRules = Evaluator::compile( $rules ); + } catch ( CLDRPluralRuleError $e ) { + wfDebugLog( 'l10n', $e->getMessage() ); + + return []; + } + + return $compiledRules; + } + + /** + * Get the plural rules for a given language from the XML files. + * Cached. + * @since 1.20 + * @param string $code + * @return array|null + */ + public function getPluralRules( $code ) { + if ( $this->pluralRules === null ) { + $this->loadPluralFiles(); + } + if ( !isset( $this->pluralRules[$code] ) ) { + return null; + } else { + return $this->pluralRules[$code]; + } + } + + /** + * Get the plural rule types for a given language from the XML files. + * Cached. + * @since 1.22 + * @param string $code + * @return array|null + */ + public function getPluralRuleTypes( $code ) { + if ( $this->pluralRuleTypes === null ) { + $this->loadPluralFiles(); + } + if ( !isset( $this->pluralRuleTypes[$code] ) ) { + return null; + } else { + return $this->pluralRuleTypes[$code]; + } + } + + /** + * Load the plural XML files. + */ + protected function loadPluralFiles() { + global $IP; + $cldrPlural = "$IP/languages/data/plurals.xml"; + $mwPlural = "$IP/languages/data/plurals-mediawiki.xml"; + // Load CLDR plural rules + $this->loadPluralFile( $cldrPlural ); + if ( file_exists( $mwPlural ) ) { + // Override or extend + $this->loadPluralFile( $mwPlural ); + } + } + + /** + * Load a plural XML file with the given filename, compile the relevant + * rules, and save the compiled rules in a process-local cache. + * + * @param string $fileName + * @throws MWException + */ + protected function loadPluralFile( $fileName ) { + // Use file_get_contents instead of DOMDocument::load (T58439) + $xml = file_get_contents( $fileName ); + if ( !$xml ) { + throw new MWException( "Unable to read plurals file $fileName" ); + } + $doc = new DOMDocument; + $doc->loadXML( $xml ); + $rulesets = $doc->getElementsByTagName( "pluralRules" ); + foreach ( $rulesets as $ruleset ) { + $codes = $ruleset->getAttribute( 'locales' ); + $rules = []; + $ruleTypes = []; + $ruleElements = $ruleset->getElementsByTagName( "pluralRule" ); + foreach ( $ruleElements as $elt ) { + $ruleType = $elt->getAttribute( 'count' ); + if ( $ruleType === 'other' ) { + // Don't record "other" rules, which have an empty condition + continue; + } + $rules[] = $elt->nodeValue; + $ruleTypes[] = $ruleType; + } + foreach ( explode( ' ', $codes ) as $code ) { + $this->pluralRules[$code] = $rules; + $this->pluralRuleTypes[$code] = $ruleTypes; + } + } + } + + /** + * Read the data from the source files for a given language, and register + * the relevant dependencies in the $deps array. If the localisation + * exists, the data array is returned, otherwise false is returned. + * + * @param string $code + * @param array $deps + * @return array + */ + protected function readSourceFilesAndRegisterDeps( $code, &$deps ) { + global $IP; + + // This reads in the PHP i18n file with non-messages l10n data + $fileName = Language::getMessagesFileName( $code ); + if ( !file_exists( $fileName ) ) { + $data = []; + } else { + $deps[] = new FileDependency( $fileName ); + $data = $this->readPHPFile( $fileName, 'core' ); + } + + # Load CLDR plural rules for JavaScript + $data['pluralRules'] = $this->getPluralRules( $code ); + # And for PHP + $data['compiledPluralRules'] = $this->getCompiledPluralRules( $code ); + # Load plural rule types + $data['pluralRuleTypes'] = $this->getPluralRuleTypes( $code ); + + $deps['plurals'] = new FileDependency( "$IP/languages/data/plurals.xml" ); + $deps['plurals-mw'] = new FileDependency( "$IP/languages/data/plurals-mediawiki.xml" ); + + return $data; + } + + /** + * Merge two localisation values, a primary and a fallback, overwriting the + * primary value in place. + * @param string $key + * @param mixed $value + * @param mixed $fallbackValue + */ + protected function mergeItem( $key, &$value, $fallbackValue ) { + if ( !is_null( $value ) ) { + if ( !is_null( $fallbackValue ) ) { + if ( in_array( $key, self::$mergeableMapKeys ) ) { + $value = $value + $fallbackValue; + } elseif ( in_array( $key, self::$mergeableListKeys ) ) { + $value = array_unique( array_merge( $fallbackValue, $value ) ); + } elseif ( in_array( $key, self::$mergeableAliasListKeys ) ) { + $value = array_merge_recursive( $value, $fallbackValue ); + } elseif ( in_array( $key, self::$optionalMergeKeys ) ) { + if ( !empty( $value['inherit'] ) ) { + $value = array_merge( $fallbackValue, $value ); + } + + if ( isset( $value['inherit'] ) ) { + unset( $value['inherit'] ); + } + } elseif ( in_array( $key, self::$magicWordKeys ) ) { + $this->mergeMagicWords( $value, $fallbackValue ); + } + } + } else { + $value = $fallbackValue; + } + } + + /** + * @param mixed $value + * @param mixed $fallbackValue + */ + protected function mergeMagicWords( &$value, $fallbackValue ) { + foreach ( $fallbackValue as $magicName => $fallbackInfo ) { + if ( !isset( $value[$magicName] ) ) { + $value[$magicName] = $fallbackInfo; + } else { + $oldSynonyms = array_slice( $fallbackInfo, 1 ); + $newSynonyms = array_slice( $value[$magicName], 1 ); + $synonyms = array_values( array_unique( array_merge( + $newSynonyms, $oldSynonyms ) ) ); + $value[$magicName] = array_merge( [ $fallbackInfo[0] ], $synonyms ); + } + } + } + + /** + * Given an array mapping language code to localisation value, such as is + * found in extension *.i18n.php files, iterate through a fallback sequence + * to merge the given data with an existing primary value. + * + * Returns true if any data from the extension array was used, false + * otherwise. + * @param array $codeSequence + * @param string $key + * @param mixed $value + * @param mixed $fallbackValue + * @return bool + */ + protected function mergeExtensionItem( $codeSequence, $key, &$value, $fallbackValue ) { + $used = false; + foreach ( $codeSequence as $code ) { + if ( isset( $fallbackValue[$code] ) ) { + $this->mergeItem( $key, $value, $fallbackValue[$code] ); + $used = true; + } + } + + return $used; + } + + /** + * Gets the combined list of messages dirs from + * core and extensions + * + * @since 1.25 + * @return array + */ + public function getMessagesDirs() { + global $wgMessagesDirs, $IP; + return [ + 'core' => "$IP/languages/i18n", + 'api' => "$IP/includes/api/i18n", + 'oojs-ui' => "$IP/resources/lib/oojs-ui/i18n", + ] + $wgMessagesDirs; + } + + /** + * Load localisation data for a given language for both core and extensions + * and save it to the persistent cache store and the process cache + * @param string $code + * @throws MWException + */ + public function recache( $code ) { + global $wgExtensionMessagesFiles; + + if ( !$code ) { + throw new MWException( "Invalid language code requested" ); + } + $this->recachedLangs[$code] = true; + + # Initial values + $initialData = array_fill_keys( self::$allKeys, null ); + $coreData = $initialData; + $deps = []; + + # Load the primary localisation from the source file + $data = $this->readSourceFilesAndRegisterDeps( $code, $deps ); + if ( $data === false ) { + wfDebug( __METHOD__ . ": no localisation file for $code, using fallback to en\n" ); + $coreData['fallback'] = 'en'; + } else { + wfDebug( __METHOD__ . ": got localisation for $code from source\n" ); + + # Merge primary localisation + foreach ( $data as $key => $value ) { + $this->mergeItem( $key, $coreData[$key], $value ); + } + } + + # Fill in the fallback if it's not there already + if ( is_null( $coreData['fallback'] ) ) { + $coreData['fallback'] = $code === 'en' ? false : 'en'; + } + if ( $coreData['fallback'] === false ) { + $coreData['fallbackSequence'] = []; + } else { + $coreData['fallbackSequence'] = array_map( 'trim', explode( ',', $coreData['fallback'] ) ); + $len = count( $coreData['fallbackSequence'] ); + + # Ensure that the sequence ends at en + if ( $coreData['fallbackSequence'][$len - 1] !== 'en' ) { + $coreData['fallbackSequence'][] = 'en'; + } + } + + $codeSequence = array_merge( [ $code ], $coreData['fallbackSequence'] ); + $messageDirs = $this->getMessagesDirs(); + + # Load non-JSON localisation data for extensions + $extensionData = array_fill_keys( $codeSequence, $initialData ); + foreach ( $wgExtensionMessagesFiles as $extension => $fileName ) { + if ( isset( $messageDirs[$extension] ) ) { + # This extension has JSON message data; skip the PHP shim + continue; + } + + $data = $this->readPHPFile( $fileName, 'extension' ); + $used = false; + + foreach ( $data as $key => $item ) { + foreach ( $codeSequence as $csCode ) { + if ( isset( $item[$csCode] ) ) { + $this->mergeItem( $key, $extensionData[$csCode][$key], $item[$csCode] ); + $used = true; + } + } + } + + if ( $used ) { + $deps[] = new FileDependency( $fileName ); + } + } + + # Load the localisation data for each fallback, then merge it into the full array + $allData = $initialData; + foreach ( $codeSequence as $csCode ) { + $csData = $initialData; + + # Load core messages and the extension localisations. + foreach ( $messageDirs as $dirs ) { + foreach ( (array)$dirs as $dir ) { + $fileName = "$dir/$csCode.json"; + $data = $this->readJSONFile( $fileName ); + + foreach ( $data as $key => $item ) { + $this->mergeItem( $key, $csData[$key], $item ); + } + + $deps[] = new FileDependency( $fileName ); + } + } + + # Merge non-JSON extension data + if ( isset( $extensionData[$csCode] ) ) { + foreach ( $extensionData[$csCode] as $key => $item ) { + $this->mergeItem( $key, $csData[$key], $item ); + } + } + + if ( $csCode === $code ) { + # Merge core data into extension data + foreach ( $coreData as $key => $item ) { + $this->mergeItem( $key, $csData[$key], $item ); + } + } else { + # Load the secondary localisation from the source file to + # avoid infinite cycles on cyclic fallbacks + $fbData = $this->readSourceFilesAndRegisterDeps( $csCode, $deps ); + if ( $fbData !== false ) { + # Only merge the keys that make sense to merge + foreach ( self::$allKeys as $key ) { + if ( !isset( $fbData[$key] ) ) { + continue; + } + + if ( is_null( $coreData[$key] ) || $this->isMergeableKey( $key ) ) { + $this->mergeItem( $key, $csData[$key], $fbData[$key] ); + } + } + } + } + + # Allow extensions an opportunity to adjust the data for this + # fallback + Hooks::run( 'LocalisationCacheRecacheFallback', [ $this, $csCode, &$csData ] ); + + # Merge the data for this fallback into the final array + if ( $csCode === $code ) { + $allData = $csData; + } else { + foreach ( self::$allKeys as $key ) { + if ( !isset( $csData[$key] ) ) { + continue; + } + + if ( is_null( $allData[$key] ) || $this->isMergeableKey( $key ) ) { + $this->mergeItem( $key, $allData[$key], $csData[$key] ); + } + } + } + } + + # Add cache dependencies for any referenced globals + $deps['wgExtensionMessagesFiles'] = new GlobalDependency( 'wgExtensionMessagesFiles' ); + // $wgMessagesDirs is used in LocalisationCache::getMessagesDirs() + $deps['wgMessagesDirs'] = new GlobalDependency( 'wgMessagesDirs' ); + $deps['version'] = new ConstantDependency( 'LocalisationCache::VERSION' ); + + # Add dependencies to the cache entry + $allData['deps'] = $deps; + + # Replace spaces with underscores in namespace names + $allData['namespaceNames'] = str_replace( ' ', '_', $allData['namespaceNames'] ); + + # And do the same for special page aliases. $page is an array. + foreach ( $allData['specialPageAliases'] as &$page ) { + $page = str_replace( ' ', '_', $page ); + } + # Decouple the reference to prevent accidental damage + unset( $page ); + + # If there were no plural rules, return an empty array + if ( $allData['pluralRules'] === null ) { + $allData['pluralRules'] = []; + } + if ( $allData['compiledPluralRules'] === null ) { + $allData['compiledPluralRules'] = []; + } + # If there were no plural rule types, return an empty array + if ( $allData['pluralRuleTypes'] === null ) { + $allData['pluralRuleTypes'] = []; + } + + # Set the list keys + $allData['list'] = []; + foreach ( self::$splitKeys as $key ) { + $allData['list'][$key] = array_keys( $allData[$key] ); + } + # Run hooks + $purgeBlobs = true; + Hooks::run( 'LocalisationCacheRecache', [ $this, $code, &$allData, &$purgeBlobs ] ); + + if ( is_null( $allData['namespaceNames'] ) ) { + throw new MWException( __METHOD__ . ': Localisation data failed sanity check! ' . + 'Check that your languages/messages/MessagesEn.php file is intact.' ); + } + + # Set the preload key + $allData['preload'] = $this->buildPreload( $allData ); + + # Save to the process cache and register the items loaded + $this->data[$code] = $allData; + foreach ( $allData as $key => $item ) { + $this->loadedItems[$code][$key] = true; + } + + # Save to the persistent cache + $this->store->startWrite( $code ); + foreach ( $allData as $key => $value ) { + if ( in_array( $key, self::$splitKeys ) ) { + foreach ( $value as $subkey => $subvalue ) { + $this->store->set( "$key:$subkey", $subvalue ); + } + } else { + $this->store->set( $key, $value ); + } + } + $this->store->finishWrite(); + + # Clear out the MessageBlobStore + # HACK: If using a null (i.e. disabled) storage backend, we + # can't write to the MessageBlobStore either + if ( $purgeBlobs && !$this->store instanceof LCStoreNull ) { + $blobStore = new MessageBlobStore(); + $blobStore->clear(); + } + + } + + /** + * Build the preload item from the given pre-cache data. + * + * The preload item will be loaded automatically, improving performance + * for the commonly-requested items it contains. + * @param array $data + * @return array + */ + protected function buildPreload( $data ) { + $preload = [ 'messages' => [] ]; + foreach ( self::$preloadedKeys as $key ) { + $preload[$key] = $data[$key]; + } + + foreach ( $data['preloadedMessages'] as $subkey ) { + if ( isset( $data['messages'][$subkey] ) ) { + $subitem = $data['messages'][$subkey]; + } else { + $subitem = null; + } + $preload['messages'][$subkey] = $subitem; + } + + return $preload; + } + + /** + * Unload the data for a given language from the object cache. + * Reduces memory usage. + * @param string $code + */ + public function unload( $code ) { + unset( $this->data[$code] ); + unset( $this->loadedItems[$code] ); + unset( $this->loadedSubitems[$code] ); + unset( $this->initialisedLangs[$code] ); + unset( $this->shallowFallbacks[$code] ); + + foreach ( $this->shallowFallbacks as $shallowCode => $fbCode ) { + if ( $fbCode === $code ) { + $this->unload( $shallowCode ); + } + } + } + + /** + * Unload all data + */ + public function unloadAll() { + foreach ( $this->initialisedLangs as $lang => $unused ) { + $this->unload( $lang ); + } + } + + /** + * Disable the storage backend + */ + public function disableBackend() { + $this->store = new LCStoreNull; + $this->manualRecache = false; + } + +} diff --git a/includes/cache/localisation/LocalisationCacheBulkLoad.php b/includes/cache/localisation/LocalisationCacheBulkLoad.php new file mode 100644 index 0000000000..30c7d37516 --- /dev/null +++ b/includes/cache/localisation/LocalisationCacheBulkLoad.php @@ -0,0 +1,126 @@ +data + */ + private $maxLoadedLangs = 10; + + /** + * @param string $fileName + * @param string $fileType + * @return array|mixed + */ + protected function readPHPFile( $fileName, $fileType ) { + $serialize = $fileType === 'core'; + if ( !isset( $this->fileCache[$fileName][$fileType] ) ) { + $data = parent::readPHPFile( $fileName, $fileType ); + + if ( $serialize ) { + $encData = serialize( $data ); + } else { + $encData = $data; + } + + $this->fileCache[$fileName][$fileType] = $encData; + + return $data; + } elseif ( $serialize ) { + return unserialize( $this->fileCache[$fileName][$fileType] ); + } else { + return $this->fileCache[$fileName][$fileType]; + } + } + + /** + * @param string $code + * @param string $key + * @return mixed + */ + public function getItem( $code, $key ) { + unset( $this->mruLangs[$code] ); + $this->mruLangs[$code] = true; + + return parent::getItem( $code, $key ); + } + + /** + * @param string $code + * @param string $key + * @param string $subkey + * @return mixed + */ + public function getSubitem( $code, $key, $subkey ) { + unset( $this->mruLangs[$code] ); + $this->mruLangs[$code] = true; + + return parent::getSubitem( $code, $key, $subkey ); + } + + /** + * @param string $code + */ + public function recache( $code ) { + parent::recache( $code ); + unset( $this->mruLangs[$code] ); + $this->mruLangs[$code] = true; + $this->trimCache(); + } + + /** + * @param string $code + */ + public function unload( $code ) { + unset( $this->mruLangs[$code] ); + parent::unload( $code ); + } + + /** + * Unload cached languages until there are less than $this->maxLoadedLangs + */ + protected function trimCache() { + while ( count( $this->data ) > $this->maxLoadedLangs && count( $this->mruLangs ) ) { + reset( $this->mruLangs ); + $code = key( $this->mruLangs ); + wfDebug( __METHOD__ . ": unloading $code\n" ); + $this->unload( $code ); + } + } + +}