X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguage.php;h=aa1a65c34abe2cf75d6c24636ddb70a0add5b1cf;hb=0372e9b3f679aa761e3741f1bc4e9270e821e55b;hp=8e4c5760bd16095d5e257bee4b87e4f96f414429;hpb=7ebf0e431b0689b220d42b258e5ced37323bd564;p=lhc%2Fweb%2Fwiklou.git diff --git a/languages/Language.php b/languages/Language.php index 8e4c5760bd..aa1a65c34a 100644 --- a/languages/Language.php +++ b/languages/Language.php @@ -35,11 +35,12 @@ if( function_exists( 'mb_strtoupper' ) ) { class FakeConverter { var $mLang; function FakeConverter($langobj) {$this->mLang = $langobj;} + function autoConvertToAllVariants($text) {return $text;} function convert($t, $i) {return $t;} - function parserConvert($t, $p) {return $t;} function getVariants() { return array( $this->mLang->getCode() ); } - function getPreferredVariant() {return $this->mLang->getCode(); } - function findVariantLink(&$l, &$n, $forTemplate = false) {} + function getPreferredVariant() { return $this->mLang->getCode(); } + function getConvRuleTitle() { return false; } + function findVariantLink(&$l, &$n, $ignoreOtherCond = false) {} function getExtraHashOptions() {return '';} function getParsedTitle() {return '';} function markNoConversion($text, $noParse=false) {return $text;} @@ -56,24 +57,16 @@ class Language { var $mConverter, $mVariants, $mCode, $mLoaded = false; var $mMagicExtensions = array(), $mMagicHookDone = false; - static public $mLocalisationKeys = array( 'fallback', 'namespaceNames', - 'skinNames', 'mathNames', - 'bookstoreList', 'magicWords', 'messages', 'rtl', 'digitTransformTable', - 'separatorTransformTable', 'fallback8bitEncoding', 'linkPrefixExtension', - 'defaultUserOptionOverrides', 'linkTrail', 'namespaceAliases', - 'dateFormats', 'datePreferences', 'datePreferenceMigrationMap', - 'defaultDateFormat', 'extraUserToggles', 'specialPageAliases', - 'imageFiles' - ); - - static public $mMergeableMapKeys = array( 'messages', 'namespaceNames', 'mathNames', - 'dateFormats', 'defaultUserOptionOverrides', 'magicWords', 'imageFiles' ); - - static public $mMergeableListKeys = array( 'extraUserToggles' ); + var $mNamespaceIds, $namespaceNames, $namespaceAliases; + var $dateFormatStrings = array(); + var $mExtendedSpecialPageAliases; - static public $mMergeableAliasListKeys = array( 'specialPageAliases' ); + /** + * ReplacementArray object caches + */ + var $transformData = array(); - static public $mLocalisationCache = array(); + static public $dataCache; static public $mLangObjCache = array(); static public $mWeekdayMsgs = array( @@ -122,7 +115,7 @@ class Language { 'hebrew-calendar-m10-gen', 'hebrew-calendar-m11-gen', 'hebrew-calendar-m12-gen', 'hebrew-calendar-m6a-gen', 'hebrew-calendar-m6b-gen' ); - + static public $mHijriCalendarMonthMsgs = array( 'hijri-calendar-m1', 'hijri-calendar-m2', 'hijri-calendar-m3', 'hijri-calendar-m4', 'hijri-calendar-m5', 'hijri-calendar-m6', @@ -135,6 +128,10 @@ class Language { */ static function factory( $code ) { if ( !isset( self::$mLangObjCache[$code] ) ) { + if( count( self::$mLangObjCache ) > 10 ) { + // Don't keep a billion objects around, that's stupid. + self::$mLangObjCache = array(); + } self::$mLangObjCache[$code] = self::newFromCode( $code ); } return self::$mLangObjCache[$code]; @@ -161,7 +158,7 @@ class Language { if ( $recursionLevel > 5 ) { throw new MWException( "Language fallback loop detected when creating class $class\n" ); - } + } if( ! class_exists( $class ) ) { $fallback = Language::getFallbackFor( $code ); @@ -175,6 +172,18 @@ class Language { return $lang; } + /** + * Get the LocalisationCache instance + */ + public static function getLocalisationCache() { + if ( is_null( self::$dataCache ) ) { + global $wgLocalisationCacheConf; + $class = $wgLocalisationCacheConf['class']; + self::$dataCache = new $class( $wgLocalisationCacheConf ); + } + return self::$dataCache; + } + function __construct() { $this->mConverter = new FakeConverter($this); // Set the code to the name of the descendant @@ -183,6 +192,7 @@ class Language { } else { $this->mCode = str_replace( '_', '-', strtolower( substr( get_class( $this ), 8 ) ) ); } + self::getLocalisationCache(); } /** @@ -210,7 +220,11 @@ class Language { } function getFallbackLanguageCode() { - return self::getFallbackFor( $this->mCode ); + if ( $this->mCode === 'en' ) { + return false; + } else { + return self::$dataCache->getItem( $this->mCode, 'fallback' ); + } } /** @@ -218,15 +232,34 @@ class Language { * @return array */ function getBookstoreList() { - $this->load(); - return $this->bookstoreList; + return self::$dataCache->getItem( $this->mCode, 'bookstoreList' ); } /** * @return array */ function getNamespaces() { - $this->load(); + if ( is_null( $this->namespaceNames ) ) { + global $wgExtraNamespaces, $wgMetaNamespace, $wgMetaNamespaceTalk; + + $this->namespaceNames = self::$dataCache->getItem( $this->mCode, 'namespaceNames' ); + if ( $wgExtraNamespaces ) { + $this->namespaceNames = $wgExtraNamespaces + $this->namespaceNames; + } + + $this->namespaceNames[NS_PROJECT] = $wgMetaNamespace; + if ( $wgMetaNamespaceTalk ) { + $this->namespaceNames[NS_PROJECT_TALK] = $wgMetaNamespaceTalk; + } else { + $talk = $this->namespaceNames[NS_PROJECT_TALK]; + $this->namespaceNames[NS_PROJECT_TALK] = + $this->fixVariableInNamespace( $talk ); + } + + # The above mixing may leave namespaces out of canonical order. + # Re-order by namespace ID number... + ksort( $this->namespaceNames ); + } return $this->namespaceNames; } @@ -282,11 +315,54 @@ class Language { * @return mixed An integer if $text is a valid value otherwise false */ function getLocalNsIndex( $text ) { - $this->load(); $lctext = $this->lc($text); - return isset( $this->mNamespaceIds[$lctext] ) ? $this->mNamespaceIds[$lctext] : false; + $ids = $this->getNamespaceIds(); + return isset( $ids[$lctext] ) ? $ids[$lctext] : false; + } + + function getNamespaceAliases() { + if ( is_null( $this->namespaceAliases ) ) { + $aliases = self::$dataCache->getItem( $this->mCode, 'namespaceAliases' ); + if ( !$aliases ) { + $aliases = array(); + } else { + foreach ( $aliases as $name => $index ) { + if ( $index === NS_PROJECT_TALK ) { + unset( $aliases[$name] ); + $name = $this->fixVariableInNamespace( $name ); + $aliases[$name] = $index; + } + } + } + $this->namespaceAliases = $aliases; + } + return $this->namespaceAliases; + } + + function getNamespaceIds() { + if ( is_null( $this->mNamespaceIds ) ) { + global $wgNamespaceAliases; + # Put namespace names and aliases into a hashtable. + # If this is too slow, then we should arrange it so that it is done + # before caching. The catch is that at pre-cache time, the above + # class-specific fixup hasn't been done. + $this->mNamespaceIds = array(); + foreach ( $this->getNamespaces() as $index => $name ) { + $this->mNamespaceIds[$this->lc($name)] = $index; + } + foreach ( $this->getNamespaceAliases() as $name => $index ) { + $this->mNamespaceIds[$this->lc($name)] = $index; + } + if ( $wgNamespaceAliases ) { + foreach ( $wgNamespaceAliases as $name => $index ) { + $this->mNamespaceIds[$this->lc($name)] = $index; + } + } + } + return $this->mNamespaceIds; } + /** * Get a namespace key by value, case insensitive. Canonical namespace * names override custom ones defined for the current language. @@ -295,10 +371,12 @@ class Language { * @return mixed An integer if $text is a valid value otherwise false */ function getNsIndex( $text ) { - $this->load(); $lctext = $this->lc($text); - if( ( $ns = MWNamespace::getCanonicalIndex( $lctext ) ) !== null ) return $ns; - return isset( $this->mNamespaceIds[$lctext] ) ? $this->mNamespaceIds[$lctext] : false; + if ( ( $ns = MWNamespace::getCanonicalIndex( $lctext ) ) !== null ) { + return $ns; + } + $ids = $this->getNamespaceIds(); + return isset( $ids[$lctext] ) ? $ids[$lctext] : false; } /** @@ -316,7 +394,7 @@ class Language { if ( isset( $aliases[$name][0] ) ) { $name = $aliases[$name][0]; } - return $this->getNsText(NS_SPECIAL) . ':' . $name; + return $this->getNsText( NS_SPECIAL ) . ':' . $name; } function getQuickbarSettings() { @@ -329,54 +407,42 @@ class Language { ); } - function getSkinNames() { - $this->load(); - return $this->skinNames; - } - function getMathNames() { - $this->load(); - return $this->mathNames; + return self::$dataCache->getItem( $this->mCode, 'mathNames' ); } function getDatePreferences() { - $this->load(); - return $this->datePreferences; + return self::$dataCache->getItem( $this->mCode, 'datePreferences' ); } - + function getDateFormats() { - $this->load(); - return $this->dateFormats; + return self::$dataCache->getItem( $this->mCode, 'dateFormats' ); } function getDefaultDateFormat() { - $this->load(); - return $this->defaultDateFormat; + $df = self::$dataCache->getItem( $this->mCode, 'defaultDateFormat' ); + if ( $df === 'dmy or mdy' ) { + global $wgAmericanDates; + return $wgAmericanDates ? 'mdy' : 'dmy'; + } else { + return $df; + } } function getDatePreferenceMigrationMap() { - $this->load(); - return $this->datePreferenceMigrationMap; + return self::$dataCache->getItem( $this->mCode, 'datePreferenceMigrationMap' ); } function getImageFile( $image ) { - $this->load(); - return $this->imageFiles[$image]; + return self::$dataCache->getSubitem( $this->mCode, 'imageFiles', $image ); } function getDefaultUserOptionOverrides() { - $this->load(); - # XXX - apparently some languageas get empty arrays, didn't get to it yet -- midom - if (is_array($this->defaultUserOptionOverrides)) { - return $this->defaultUserOptionOverrides; - } else { - return array(); - } + return self::$dataCache->getItem( $this->mCode, 'defaultUserOptionOverrides' ); } function getExtraUserToggles() { - $this->load(); - return $this->extraUserToggles; + return self::$dataCache->getItem( $this->mCode, 'extraUserToggles' ); } function getUserToggle( $tog ) { @@ -393,17 +459,14 @@ class Language { if ( !$customisedOnly ) { return $allNames; } - + global $IP; $names = array(); $dir = opendir( "$IP/languages/messages" ); while( false !== ( $file = readdir( $dir ) ) ) { - $m = array(); - if( preg_match( '/Messages([A-Z][a-z_]+)\.php$/', $file, $m ) ) { - $code = str_replace( '_', '-', strtolower( $m[1] ) ); - if ( isset( $allNames[$code] ) ) { - $names[$code] = $allNames[$code]; - } + $code = self::getCodeFromFileName( $file, 'Messages' ); + if ( $code && isset( $allNames[$code] ) ) { + $names[$code] = $allNames[$code]; } } closedir( $dir ); @@ -459,11 +522,11 @@ class Language { function getHebrewCalendarMonthNameGen( $key ) { return $this->getMessageFromDB( self::$mHebrewCalendarMonthGenMsgs[$key-1] ); } - + function getHijriCalendarMonthName( $key ) { return $this->getMessageFromDB( self::$mHijriCalendarMonthMsgs[$key-1] ); } - + /** * Used by date() and time() to adjust the time output. * @@ -475,59 +538,71 @@ class Language { function userAdjust( $ts, $tz = false ) { global $wgUser, $wgLocalTZoffset; - if (!$tz) { + if ( $tz === false ) { $tz = $wgUser->getOption( 'timecorrection' ); } - # minutes and hours differences: - $minDiff = 0; - $hrDiff = 0; + $data = explode( '|', $tz, 3 ); - if ( $tz === '' ) { - # Global offset in minutes. - if( isset($wgLocalTZoffset) ) { - if( $wgLocalTZoffset >= 0 ) { - $hrDiff = floor($wgLocalTZoffset / 60); - } else { - $hrDiff = ceil($wgLocalTZoffset / 60); - } - $minDiff = $wgLocalTZoffset % 60; + if ( $data[0] == 'ZoneInfo' ) { + if ( function_exists( 'timezone_open' ) && @timezone_open( $data[2] ) !== false ) { + $date = date_create( $ts, timezone_open( 'UTC' ) ); + date_timezone_set( $date, timezone_open( $data[2] ) ); + $date = date_format( $date, 'YmdHis' ); + return $date; } - } elseif ( strpos( $tz, ':' ) !== false ) { - $tzArray = explode( ':', $tz ); - $hrDiff = intval($tzArray[0]); - $minDiff = intval($hrDiff < 0 ? -$tzArray[1] : $tzArray[1]); + # Unrecognized timezone, default to 'Offset' with the stored offset. + $data[0] = 'Offset'; + } + + $minDiff = 0; + if ( $data[0] == 'System' || $tz == '' ) { + # Global offset in minutes. + if( isset($wgLocalTZoffset) ) $minDiff = $wgLocalTZoffset; + } else if ( $data[0] == 'Offset' ) { + $minDiff = intval( $data[1] ); } else { - $hrDiff = intval( $tz ); + $data = explode( ':', $tz ); + if( count( $data ) == 2 ) { + $data[0] = intval( $data[0] ); + $data[1] = intval( $data[1] ); + $minDiff = abs( $data[0] ) * 60 + $data[1]; + if ( $data[0] < 0 ) $minDiff = -$minDiff; + } else { + $minDiff = intval( $data[0] ) * 60; + } } # No difference ? Return time unchanged - if ( 0 == $hrDiff && 0 == $minDiff ) { return $ts; } + if ( 0 == $minDiff ) return $ts; wfSuppressWarnings(); // E_STRICT system time bitching - # Generate an adjusted date + # Generate an adjusted date; take advantage of the fact that mktime + # will normalize out-of-range values so we don't have to split $minDiff + # into hours and minutes. $t = mktime( ( - (int)substr( $ts, 8, 2) ) + $hrDiff, # Hours + (int)substr( $ts, 8, 2) ), # Hours (int)substr( $ts, 10, 2 ) + $minDiff, # Minutes (int)substr( $ts, 12, 2 ), # Seconds (int)substr( $ts, 4, 2 ), # Month (int)substr( $ts, 6, 2 ), # Day (int)substr( $ts, 0, 4 ) ); #Year - + $date = date( 'YmdHis', $t ); wfRestoreWarnings(); - + return $date; } /** * This is a workalike of PHP's date() function, but with better - * internationalisation, a reduced set of format characters, and a better + * internationalisation, a reduced set of format characters, and a better * escaping format. * - * Supported format characters are dDjlNwzWFmMntLYyaAgGhHiscrU. See the - * PHP manual for definitions. There are a number of extensions, which - * start with "x": + * Supported format characters are dDjlNwzWFmMntLoYyaAgGhHiscrU. See the + * PHP manual for definitions. "o" format character is supported since + * PHP 5.1.0, previous versions return literal o. + * There are a number of extensions, which start with "x": * * xn Do not translate digits of the next numeric format character * xN Toggle raw digit (xn) flag, stays set until explicitly unset @@ -548,13 +623,18 @@ class Language { * xjn n (month number) in Hebrew calendar * xjY Y (full year) in Hebrew calendar * - * xmj j (day number) in Hijri calendar - * xmF F (month name) in Hijri calendar - * xmn n (month number) in Hijri calendar - * xmY Y (full year) in Hijri calendar + * xmj j (day number) in Hijri calendar + * xmF F (month name) in Hijri calendar + * xmn n (month number) in Hijri calendar + * xmY Y (full year) in Hijri calendar * * xkY Y (full year) in Thai solar calendar. Months and days are * identical to the Gregorian calendar + * xoY Y (full year) in Minguo calendar or Juche year. + * Months and days are identical to the + * Gregorian calendar + * xtY Y (full year) in Japanese nengo. Months and days are + * identical to the Gregorian calendar * * Characters enclosed in double quotes will be considered literal (with * the quotes themselves removed). Unmatched quotes will be considered @@ -567,11 +647,13 @@ class Language { * * Input timestamp is assumed to be pre-normalized to the desired local * time zone, if any. - * + * * @param $format String * @param $ts String: 14-character timestamp * YYYYMMDDHHMMSS * 01234567890123 + * @todo emulation of "o" format character for PHP pre 5.1.0 + * @todo handling of "o" format character for Iranian, Hebrew, Hijri & Thai? */ function sprintfDate( $format, $ts ) { $s = ''; @@ -584,6 +666,8 @@ class Language { $hebrew = false; $hijri = false; $thai = false; + $minguo = false; + $tenno = false; for ( $p = 0; $p < strlen( $format ); $p++ ) { $num = false; $code = $format[$p]; @@ -591,7 +675,7 @@ class Language { $code .= $format[++$p]; } - if ( ( $code === 'xi' || $code == 'xj' || $code == 'xk' || $code == 'xm' ) && $p < strlen( $format ) - 1 ) { + if ( ( $code === 'xi' || $code == 'xj' || $code == 'xk' || $code == 'xm' || $code == 'xo' || $code == 'xt' ) && $p < strlen( $format ) - 1 ) { $code .= $format[++$p]; } @@ -709,6 +793,16 @@ class Language { if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts ); $num = gmdate( 'L', $unix ); break; + # 'o' is supported since PHP 5.1.0 + # return literal if not supported + # TODO: emulation for pre 5.1.0 versions + case 'o': + if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts ); + if ( version_compare(PHP_VERSION, '5.1.0') === 1 ) + $num = date( 'o', $unix ); + else + $s .= 'o'; + break; case 'Y': $num = substr( $ts, 0, 4 ); break; @@ -725,9 +819,17 @@ class Language { $num = $hebrew[0]; break; case 'xkY': - if ( !$thai ) $thai = self::tsToThai( $ts ); + if ( !$thai ) $thai = self::tsToYear( $ts, 'thai' ); $num = $thai[0]; break; + case 'xoY': + if ( !$minguo ) $minguo = self::tsToYear( $ts, 'minguo' ); + $num = $minguo[0]; + break; + case 'xtY': + if ( !$tenno ) $tenno = self::tsToYear( $ts, 'tenno' ); + $num = $tenno[0]; + break; case 'y': $num = substr( $ts, 2, 2 ); break; @@ -747,7 +849,7 @@ class Language { case 'h': $h = substr( $ts, 8, 2 ); $num = sprintf( '%02d', $h % 12 ? $h % 12 : 12 ); - break; + break; case 'H': $num = substr( $ts, 8, 2 ); break; @@ -818,11 +920,11 @@ class Language { private static $GREG_DAYS = array( 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 ); private static $IRANIAN_DAYS = array( 31, 31, 31, 31, 31, 31, 30, 30, 30, 30, 30, 29 ); /** - * Algorithm by Roozbeh Pournader and Mohammad Toossi to convert + * Algorithm by Roozbeh Pournader and Mohammad Toossi to convert * Gregorian dates to Iranian dates. Originally written in C, it * is released under the terms of GNU Lesser General Public * License. Conversion to PHP was performed by Niklas Laxström. - * + * * Link: http://www.farsiweb.info/jalali/jalali.c */ private static function tsToIranian( $ts ) { @@ -849,7 +951,7 @@ class Language { // Days passed in current month $gDayNo += $gd; - + $jDayNo = $gDayNo - 79; $jNp = floor($jDayNo / 12053); @@ -883,7 +985,7 @@ class Language { $year = substr( $ts, 0, 4 ); $month = substr( $ts, 4, 2 ); $day = substr( $ts, 6, 2 ); - + $zyr = $year; $zd=$day; $zm=$month; @@ -893,15 +995,15 @@ class Language { if (($zy>1582)||(($zy==1582)&&($zm>10))||(($zy==1582)&&($zm==10)&&($zd>14))) { - - + + $zjd=(int)((1461*($zy + 4800 + (int)( ($zm-14) /12) ))/4) + (int)((367*($zm-2-12*((int)(($zm-14)/12))))/12)-(int)((3*(int)(( ($zy+4900+(int)(($zm-14)/12))/100)))/4)+$zd-32075; } else { $zjd = 367*$zy-(int)((7*($zy+5001+(int)(($zm-9)/7)))/4)+(int)((275*$zm)/9)+$zd+1729777; } - + $zl=$zjd-1948440+10632; $zn=(int)(($zl-1)/10631); $zl=$zl-10631*$zn+354; @@ -1089,26 +1191,73 @@ class Language { } /** - * Algorithm to convert Gregorian dates to Thai solar dates. + * Algorithm to convert Gregorian dates to Thai solar dates, + * Minguo dates or Minguo dates. * * Link: http://en.wikipedia.org/wiki/Thai_solar_calendar + * http://en.wikipedia.org/wiki/Minguo_calendar + * http://en.wikipedia.org/wiki/Japanese_era_name * * @param $ts String: 14-character timestamp - * @return array converted year, month, day + * @param $cName String: calender name + * @return Array: converted year, month, day */ - private static function tsToThai( $ts ) { + private static function tsToYear( $ts, $cName ) { $gy = substr( $ts, 0, 4 ); $gm = substr( $ts, 4, 2 ); $gd = substr( $ts, 6, 2 ); - # Add 543 years to the Gregorian calendar - # Months and days are identical - $gy_thai = $gy + 543; + if (!strcmp($cName,'thai')) { + # Thai solar dates + # Add 543 years to the Gregorian calendar + # Months and days are identical + $gy_offset = $gy + 543; + } else if ((!strcmp($cName,'minguo')) || !strcmp($cName,'juche')) { + # Minguo dates + # Deduct 1911 years from the Gregorian calendar + # Months and days are identical + $gy_offset = $gy - 1911; + } else if (!strcmp($cName,'tenno')) { + # Nengō dates up to Meiji period + # Deduct years from the Gregorian calendar + # depending on the nengo periods + # Months and days are identical + if (($gy < 1912) || (($gy == 1912) && ($gm < 7)) || (($gy == 1912) && ($gm == 7) && ($gd < 31))) { + # Meiji period + $gy_gannen = $gy - 1868 + 1; + $gy_offset = $gy_gannen; + if ($gy_gannen == 1) + $gy_offset = '元'; + $gy_offset = '明治'.$gy_offset; + } else if ((($gy == 1912) && ($gm == 7) && ($gd == 31)) || (($gy == 1912) && ($gm >= 8)) || (($gy > 1912) && ($gy < 1926)) || (($gy == 1926) && ($gm < 12)) || (($gy == 1926) && ($gm == 12) && ($gd < 26))) { + # Taishō period + $gy_gannen = $gy - 1912 + 1; + $gy_offset = $gy_gannen; + if ($gy_gannen == 1) + $gy_offset = '元'; + $gy_offset = '大正'.$gy_offset; + } else if ((($gy == 1926) && ($gm == 12) && ($gd >= 26)) || (($gy > 1926) && ($gy < 1989)) || (($gy == 1989) && ($gm == 1) && ($gd < 8))) { + # Shōwa period + $gy_gannen = $gy - 1926 + 1; + $gy_offset = $gy_gannen; + if ($gy_gannen == 1) + $gy_offset = '元'; + $gy_offset = '昭和'.$gy_offset; + } else { + # Heisei period + $gy_gannen = $gy - 1989 + 1; + $gy_offset = $gy_gannen; + if ($gy_gannen == 1) + $gy_offset = '元'; + $gy_offset = '平成'.$gy_offset; + } + } else { + $gy_offset = $gy; + } - return array( $gy_thai, $gm, $gd ); + return array( $gy_offset, $gm, $gd ); } - /** * Roman number formatting up to 3000 */ @@ -1119,7 +1268,7 @@ class Language { array( '', 'C', 'CC', 'CCC', 'CD', 'D', 'DC', 'DCC', 'DCCC', 'CM', 'M' ), array( '', 'M', 'MM', 'MMM' ) ); - + $num = intval( $num ); if ( $num > 3000 || $num <= 0 ) { return $num; @@ -1218,8 +1367,7 @@ class Language { if( $usePrefs ) { $datePreference = $wgUser->getDatePreference(); } else { - $options = User::getDefaultOptions(); - $datePreference = (string)$options['date']; + $datePreference = (string)User::getDefaultOption( 'date' ); } } else { $datePreference = (string)$usePrefs; @@ -1229,10 +1377,32 @@ class Language { if( $datePreference == '' ) { return 'default'; } - + return $datePreference; } + /** + * Get a format string for a given type and preference + * @param $type May be date, time or both + * @param $pref The format name as it appears in Messages*.php + */ + function getDateFormatString( $type, $pref ) { + if ( !isset( $this->dateFormatStrings[$type][$pref] ) ) { + if ( $pref == 'default' ) { + $pref = $this->getDefaultDateFormat(); + $df = self::$dataCache->getSubitem( $this->mCode, 'dateFormats', "$pref $type" ); + } else { + $df = self::$dataCache->getSubitem( $this->mCode, 'dateFormats', "$pref $type" ); + if ( is_null( $df ) ) { + $pref = $this->getDefaultDateFormat(); + $df = self::$dataCache->getSubitem( $this->mCode, 'dateFormats', "$pref $type" ); + } + } + $this->dateFormatStrings[$type][$pref] = $df; + } + return $this->dateFormatStrings[$type][$pref]; + } + /** * @param $ts Mixed: the time format which needs to be turned into a * date('YmdHis') format with wfTimestamp(TS_MW,$ts) @@ -1244,16 +1414,11 @@ class Language { * @return string */ function date( $ts, $adj = false, $format = true, $timecorrection = false ) { - $this->load(); - if ( $adj ) { - $ts = $this->userAdjust( $ts, $timecorrection ); - } - - $pref = $this->dateFormat( $format ); - if( $pref == 'default' || !isset( $this->dateFormats["$pref date"] ) ) { - $pref = $this->defaultDateFormat; + if ( $adj ) { + $ts = $this->userAdjust( $ts, $timecorrection ); } - return $this->sprintfDate( $this->dateFormats["$pref date"], $ts ); + $df = $this->getDateFormatString( 'date', $this->dateFormat( $format ) ); + return $this->sprintfDate( $df, $ts ); } /** @@ -1267,16 +1432,11 @@ class Language { * @return string */ function time( $ts, $adj = false, $format = true, $timecorrection = false ) { - $this->load(); - if ( $adj ) { - $ts = $this->userAdjust( $ts, $timecorrection ); + if ( $adj ) { + $ts = $this->userAdjust( $ts, $timecorrection ); } - - $pref = $this->dateFormat( $format ); - if( $pref == 'default' || !isset( $this->dateFormats["$pref time"] ) ) { - $pref = $this->defaultDateFormat; - } - return $this->sprintfDate( $this->dateFormats["$pref time"], $ts ); + $df = $this->getDateFormatString( 'time', $this->dateFormat( $format ) ); + return $this->sprintfDate( $df, $ts ); } /** @@ -1291,69 +1451,74 @@ class Language { * @return string */ function timeanddate( $ts, $adj = false, $format = true, $timecorrection = false) { - $this->load(); - $ts = wfTimestamp( TS_MW, $ts ); - - if ( $adj ) { - $ts = $this->userAdjust( $ts, $timecorrection ); - } - - $pref = $this->dateFormat( $format ); - if( $pref == 'default' || !isset( $this->dateFormats["$pref both"] ) ) { - $pref = $this->defaultDateFormat; + if ( $adj ) { + $ts = $this->userAdjust( $ts, $timecorrection ); } - - return $this->sprintfDate( $this->dateFormats["$pref both"], $ts ); + $df = $this->getDateFormatString( 'both', $this->dateFormat( $format ) ); + return $this->sprintfDate( $df, $ts ); } function getMessage( $key ) { - $this->load(); - return isset( $this->messages[$key] ) ? $this->messages[$key] : null; + return self::$dataCache->getSubitem( $this->mCode, 'messages', $key ); } function getAllMessages() { - $this->load(); - return $this->messages; + return self::$dataCache->getItem( $this->mCode, 'messages' ); } function iconv( $in, $out, $string ) { - # For most languages, this is a wrapper for iconv - return iconv( $in, $out . '//IGNORE', $string ); + # This is a wrapper for iconv in all languages except esperanto, + # which does some nasty x-conversions beforehand + + # Even with //IGNORE iconv can whine about illegal characters in + # *input* string. We just ignore those too. + # REF: http://bugs.php.net/bug.php?id=37166 + # REF: https://bugzilla.wikimedia.org/show_bug.cgi?id=16885 + wfSuppressWarnings(); + $text = iconv( $in, $out . '//IGNORE', $string ); + wfRestoreWarnings(); + return $text; } // callback functions for uc(), lc(), ucwords(), ucwordbreaks() function ucwordbreaksCallbackAscii($matches){ return $this->ucfirst($matches[1]); } - + function ucwordbreaksCallbackMB($matches){ return mb_strtoupper($matches[0]); } - + function ucCallback($matches){ list( $wikiUpperChars ) = self::getCaseMaps(); return strtr( $matches[1], $wikiUpperChars ); } - + function lcCallback($matches){ list( , $wikiLowerChars ) = self::getCaseMaps(); return strtr( $matches[1], $wikiLowerChars ); } - + function ucwordsCallbackMB($matches){ return mb_strtoupper($matches[0]); } - + function ucwordsCallbackWiki($matches){ list( $wikiUpperChars ) = self::getCaseMaps(); return strtr( $matches[0], $wikiUpperChars ); } function ucfirst( $str ) { - if ( empty($str) ) return $str; - if ( ord($str[0]) < 128 ) return ucfirst($str); - else return self::uc($str,true); // fall back to more complex logic in case of multibyte strings + $o = ord( $str ); + if ( $o < 96 ) { + return $str; + } elseif ( $o < 128 ) { + return ucfirst($str); + } else { + // fall back to more complex logic in case of multibyte strings + return self::uc($str,true); + } } function uc( $str, $first = false ) { @@ -1381,15 +1546,19 @@ class Language { } } } - + function lcfirst( $str ) { - if ( empty($str) ) return $str; - if ( is_string( $str ) && ord($str[0]) < 128 ) { - // editing string in place = cool - $str[0]=strtolower($str[0]); + $o = ord( $str ); + if ( !$o ) { + return strval( $str ); + } elseif ( $o >= 128 ) { + return self::lc( $str, true ); + } elseif ( $o > 96 ) { + return $str; + } else { + $str[0] = strtolower( $str[0] ); return $str; } - else return self::lc( $str, true ); } function lc( $str, $first = false ) { @@ -1432,7 +1601,7 @@ class Language { array($this,"ucwordsCallbackMB"), $str ); - else + else return preg_replace_callback( $replaceRegexp, array($this,"ucwordsCallbackWiki"), @@ -1460,7 +1629,7 @@ class Language { array($this,"ucwordbreaksCallbackMB"), $str ); - else + else return preg_replace_callback( $replaceRegexp, array($this,"ucwordsCallbackWiki"), @@ -1477,7 +1646,7 @@ class Language { /** * Return a case-folded representation of $s * - * This is a representation such that caseFold($s1)==caseFold($s2) if $s1 + * This is a representation such that caseFold($s1)==caseFold($s2) if $s1 * and $s2 are the same except for the case of their characters. It is not * necessary for the value returned to make sense when displayed. * @@ -1505,78 +1674,64 @@ class Language { } function fallback8bitEncoding() { - $this->load(); - return $this->fallback8bitEncoding; + return self::$dataCache->getItem( $this->mCode, 'fallback8bitEncoding' ); + } + + /** + * Most writing systems use whitespace to break up words. + * Some languages such as Chinese don't conventionally do this, + * which requires special handling when breaking up words for + * searching etc. + */ + function hasWordBreaks() { + return true; } /** - * Some languages have special punctuation to strip out - * or characters which need to be converted for MySQL's - * indexing to grok it correctly. Make such changes here. - * + * Some languages such as Chinese require word segmentation, + * Specify such segmentation when overridden in derived class. + * * @param $string String * @return String */ - function stripForSearch( $string ) { - global $wgDBtype; - if ( $wgDBtype != 'mysql' ) { - return $string; - } - - - wfProfileIn( __METHOD__ ); - - // MySQL fulltext index doesn't grok utf-8, so we - // need to fold cases and convert to hex - $out = preg_replace_callback( - "/([\\xc0-\\xff][\\x80-\\xbf]*)/", - array( $this, 'stripForSearchCallback' ), - $this->lc( $string ) ); - - // And to add insult to injury, the default indexing - // ignores short words... Pad them so we can pass them - // through without reconfiguring the server... - $minLength = $this->minSearchLength(); - if( $minLength > 1 ) { - $n = $minLength-1; - $out = preg_replace( - "/\b(\w{1,$n})\b/", - "$1U800", - $out ); - } - - wfProfileOut( __METHOD__ ); - return $out; + function segmentByWord( $string ) { + return $string; } - + /** - * Armor a case-folded UTF-8 string to get through MySQL's - * fulltext search without being mucked up by funny charset - * settings or anything else of the sort. + * Some languages have special punctuation need to be normalized. + * Make such changes here. + * + * @param $string String + * @return String */ - protected function stripForSearchCallback( $matches ) { - return 'U8' . bin2hex( $matches[1] ); + function normalizeForSearch( $string ) { + return self::convertDoubleWidth($string); } - + /** - * Check MySQL server's ft_min_word_len setting so we know - * if we need to pad short words... - */ - protected function minSearchLength() { - if( !isset( $this->minSearchLength ) ) { - $sql = "show global variables like 'ft\\_min\\_word\\_len'"; - $dbr = wfGetDB( DB_SLAVE ); - $result = $dbr->query( $sql ); - $row = $result->fetchObject(); - $result->free(); - - if( $row && $row->Variable_name == 'ft_min_word_len' ) { - $this->minSearchLength = intval( $row->Value ); - } else { - $this->minSearchLength = 0; - } + * convert double-width roman characters to single-width. + * range: ff00-ff5f ~= 0020-007f + */ + protected static function convertDoubleWidth( $string ) { + static $full = null; + static $half = null; + + if( $full === null ) { + $fullWidth = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"; + $halfWidth = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"; + $full = str_split( $fullWidth, 3 ); + $half = str_split( $halfWidth ); } - return $this->minSearchLength; + + $string = str_replace( $full, $half, $string ); + return $string; + } + + protected static function insertSpace( $string, $pattern ) { + $string = preg_replace( $pattern, " $1 ", $string ); + $string = preg_replace( '/ +/', ' ', $string ); + return $string; } function convertForSearchResult( $termsArray ) { @@ -1586,7 +1741,7 @@ class Language { } /** - * Get the first character of a string. + * Get the first character of a string. * * @param $s string * @return string @@ -1600,7 +1755,7 @@ class Language { if ( strlen( $matches[1] ) != 3 ) { return $matches[1]; } - + // Break down Hangul syllables to grab the first jamo $code = utf8ToCodepoint( $matches[1] ); if ( $code < 0xac00 || 0xd7a4 <= $code) { @@ -1677,14 +1832,75 @@ class Language { } } + /** + * Convert a UTF-8 string to normal form C. In Malayalam and Arabic, this + * also cleans up certain backwards-compatible sequences, converting them + * to the modern Unicode equivalent. + * + * This is language-specific for performance reasons only. + */ + function normalize( $s ) { + return UtfNormal::cleanUp( $s ); + } + + /** + * Transform a string using serialized data stored in the given file (which + * must be in the serialized subdirectory of $IP). The file contains pairs + * mapping source characters to destination characters. + * + * The data is cached in process memory. This will go faster if you have the + * FastStringSearch extension. + */ + function transformUsingPairFile( $file, $string ) { + if ( !isset( $this->transformData[$file] ) ) { + $data = wfGetPrecompiledData( $file ); + if ( $data === false ) { + throw new MWException( __METHOD__.": The transformation file $file is missing" ); + } + $this->transformData[$file] = new ReplacementArray( $data ); + } + return $this->transformData[$file]->replace( $string ); + } + /** * For right-to-left language support * * @return bool */ - function isRTL() { - $this->load(); - return $this->rtl; + function isRTL() { + return self::$dataCache->getItem( $this->mCode, 'rtl' ); + } + + /** + * Return the correct HTML 'dir' attribute value for this language. + * @return String + */ + function getDir() { + return $this->isRTL() ? 'rtl' : 'ltr'; + } + + /** + * Return 'left' or 'right' as appropriate alignment for line-start + * for this language's text direction. + * + * Should be equivalent to CSS3 'start' text-align value.... + * + * @return String + */ + function alignStart() { + return $this->isRTL() ? 'right' : 'left'; + } + + /** + * Return 'right' or 'left' as appropriate alignment for line-end + * for this language's text direction. + * + * Should be equivalent to CSS3 'end' text-align value.... + * + * @return String + */ + function alignEnd() { + return $this->isRTL() ? 'left' : 'right'; } /** @@ -1696,6 +1912,10 @@ class Language { return $this->isRTL() ? "\xE2\x80\x8F" : "\xE2\x80\x8E"; } + function capitalizeAllNouns() { + return self::$dataCache->getItem( $this->mCode, 'capitalizeAllNouns' ); + } + /** * An arrow, depending on the language direction * @@ -1711,34 +1931,29 @@ class Language { * @return bool */ function linkPrefixExtension() { - $this->load(); - return $this->linkPrefixExtension; + return self::$dataCache->getItem( $this->mCode, 'linkPrefixExtension' ); } - function &getMagicWords() { - $this->load(); - return $this->magicWords; + function getMagicWords() { + return self::$dataCache->getItem( $this->mCode, 'magicWords' ); } # Fill a MagicWord object with data from here - function getMagic( &$mw ) { + function getMagic( $mw ) { if ( !$this->mMagicHookDone ) { $this->mMagicHookDone = true; + wfProfileIn( 'LanguageGetMagic' ); wfRunHooks( 'LanguageGetMagic', array( &$this->mMagicExtensions, $this->getCode() ) ); + wfProfileOut( 'LanguageGetMagic' ); } if ( isset( $this->mMagicExtensions[$mw->mId] ) ) { $rawEntry = $this->mMagicExtensions[$mw->mId]; } else { - $magicWords =& $this->getMagicWords(); + $magicWords = $this->getMagicWords(); if ( isset( $magicWords[$mw->mId] ) ) { $rawEntry = $magicWords[$mw->mId]; } else { - # Fall back to English if local list is incomplete - $magicWords =& Language::getMagicWords(); - if ( !isset($magicWords[$mw->mId]) ) { - throw new MWException("Magic word '{$mw->mId}' not found" ); - } - $rawEntry = $magicWords[$mw->mId]; + $rawEntry = false; } } @@ -1776,43 +1991,11 @@ class Language { * case folded alias => real name */ function getSpecialPageAliases() { - $this->load(); - // Cache aliases because it may be slow to load them - if ( !isset( $this->mExtendedSpecialPageAliases ) ) { - + if ( is_null( $this->mExtendedSpecialPageAliases ) ) { // Initialise array - $this->mExtendedSpecialPageAliases = $this->specialPageAliases; - - global $wgExtensionAliasesFiles; - foreach ( $wgExtensionAliasesFiles as $file ) { - - // Fail fast - if ( !file_exists($file) ) - throw new MWException( "Aliases file does not exist: $file" ); - - $aliases = array(); - require($file); - - // Check the availability of aliases - if ( !isset($aliases['en']) ) - throw new MWException( "Malformed aliases file: $file" ); - - // Merge all aliases in fallback chain - $code = $this->getCode(); - do { - if ( !isset($aliases[$code]) ) continue; - - $aliases[$code] = $this->fixSpecialPageAliases( $aliases[$code] ); - /* Merge the aliases, THIS will break if there is special page name - * which looks like a numerical key, thanks to PHP... - * See the array_merge_recursive manual entry */ - $this->mExtendedSpecialPageAliases = array_merge_recursive( - $this->mExtendedSpecialPageAliases, $aliases[$code] ); - - } while ( $code = self::getFallbackFor( $code ) ); - } - + $this->mExtendedSpecialPageAliases = + self::$dataCache->getItem( $this->mCode, 'specialPageAliases' ); wfRunHooks( 'LanguageGetSpecialPageAliases', array( &$this->mExtendedSpecialPageAliases, $this->getCode() ) ); } @@ -1820,20 +2003,6 @@ class Language { return $this->mExtendedSpecialPageAliases; } - /** - * Function to fix special page aliases. Will convert the first letter to - * upper case and spaces to underscores. Can be given a full aliases array, - * in which case it will recursively fix all aliases. - */ - public function fixSpecialPageAliases( $mixed ) { - // Work recursively until in string level - if ( is_array($mixed) ) { - $callback = array( $this, 'fixSpecialPageAliases' ); - return array_map( $callback, $mixed ); - } - return str_replace( ' ', '_', $this->ucfirst( $mixed ) ); - } - /** * Italic is unsuitable for some languages * @@ -1873,12 +2042,12 @@ class Language { if (!$nocommafy) { $number = $this->commafy($number); $s = $this->separatorTransformTable(); - if (!is_null($s)) { $number = strtr($number, $s); } + if ($s) { $number = strtr($number, $s); } } if ($wgTranslateNumerals) { $s = $this->digitTransformTable(); - if (!is_null($s)) { $number = strtr($number, $s); } + if ($s) { $number = strtr($number, $s); } } return $number; @@ -1886,10 +2055,10 @@ class Language { function parseFormattedNumber( $number ) { $s = $this->digitTransformTable(); - if (!is_null($s)) { $number = strtr($number, array_flip($s)); } + if ($s) { $number = strtr($number, array_flip($s)); } $s = $this->separatorTransformTable(); - if (!is_null($s)) { $number = strtr($number, array_flip($s)); } + if ($s) { $number = strtr($number, array_flip($s)); } $number = strtr( $number, array (',' => '') ); return $number; @@ -1906,49 +2075,66 @@ class Language { } function digitTransformTable() { - $this->load(); - return $this->digitTransformTable; + return self::$dataCache->getItem( $this->mCode, 'digitTransformTable' ); } function separatorTransformTable() { - $this->load(); - return $this->separatorTransformTable; + return self::$dataCache->getItem( $this->mCode, 'separatorTransformTable' ); } /** - * For the credit list in includes/Credits.php (action=credits) + * Take a list of strings and build a locale-friendly comma-separated + * list, using the local comma-separator message. + * The last two strings are chained with an "and". * * @param $l Array * @return string */ function listToText( $l ) { $s = ''; - $m = count($l) - 1; - for ($i = $m; $i >= 0; $i--) { - if ($i == $m) { - $s = $l[$i]; - } else if ($i == $m - 1) { - $s = $l[$i] . $this->getMessageFromDB( 'and' ) . $this->getMessageFromDB( 'word-separator' ) . $s; - } else { - $s = $l[$i] . $this->getMessageFromDB( 'comma-separator' ) . $s; + $m = count( $l ) - 1; + if( $m == 1 ) { + return $l[0] . $this->getMessageFromDB( 'and' ) . $this->getMessageFromDB( 'word-separator' ) . $l[1]; + } + else { + for ( $i = $m; $i >= 0; $i-- ) { + if ( $i == $m ) { + $s = $l[$i]; + } else if( $i == $m - 1 ) { + $s = $l[$i] . $this->getMessageFromDB( 'and' ) . $this->getMessageFromDB( 'word-separator' ) . $s; + } else { + $s = $l[$i] . $this->getMessageFromDB( 'comma-separator' ) . $s; + } } + return $s; } - return $s; } - + /** * Take a list of strings and build a locale-friendly comma-separated * list, using the local comma-separator message. * @param $list array of strings to put in a comma list * @return string */ - function commaList( $list, $forContent = false ) { + function commaList( $list ) { return implode( $list, - wfMsgExt( 'comma-separator', array( 'escapenoentities', 'language' => $this ) ) ); + wfMsgExt( 'comma-separator', array( 'parsemag', 'escapenoentities', 'language' => $this ) ) ); } - + + /** + * Take a list of strings and build a locale-friendly semicolon-separated + * list, using the local semicolon-separator message. + * @param $list array of strings to put in a semicolon list + * @return string + */ + function semicolonList( $list ) { + return implode( + $list, + wfMsgExt( 'semicolon-separator', array( 'parsemag', 'escapenoentities', 'language' => $this ) ) ); + } + /** * Same as commaList, but separate it with the pipe instead. * @param $list array of strings to put in a pipe list @@ -1969,41 +2155,213 @@ class Language { * are included, otherwise broken characters can be passed to the user * * If $length is negative, the string will be truncated from the beginning - * + * * @param $string String to truncate * @param $length Int: maximum length (excluding ellipses) * @param $ellipsis String to append to the truncated text * @return string */ - function truncate( $string, $length, $ellipsis = "" ) { - if( $length == 0 ) { + function truncate( $string, $length, $ellipsis = '...' ) { + # Use the localized ellipsis character + if ( $ellipsis == '...' ) { + $ellipsis = wfMsgExt( 'ellipsis', array( 'escapenoentities', 'language' => $this ) ); + } + # Check if there is no need to truncate + if ( $length == 0 ) { return $ellipsis; + } elseif ( strlen( $string ) <= abs( $length ) ) { + return $string; + } + $stringOriginal = $string; + if ( $length > 0 ) { + $string = substr( $string, 0, $length ); // xyz... + $string = $this->removeBadCharLast( $string ); + $string = $string . $ellipsis; + } else { + $string = substr( $string, $length ); // ...xyz + $string = $this->removeBadCharFirst( $string ); + $string = $ellipsis . $string; } - if ( strlen( $string ) <= abs( $length ) ) { + # Do not truncate if the ellipsis makes the string longer/equal (bug 22181) + if ( strlen( $string ) < strlen( $stringOriginal ) ) { return $string; + } else { + return $stringOriginal; + } + } + + /** + * Remove bytes that represent an incomplete Unicode character + * at the end of string (e.g. bytes of the char are missing) + * + * @param $string String + * @return string + */ + protected function removeBadCharLast( $string ) { + $char = ord( $string[strlen( $string ) - 1] ); + $m = array(); + if ( $char >= 0xc0 ) { + # We got the first byte only of a multibyte char; remove it. + $string = substr( $string, 0, -1 ); + } elseif ( $char >= 0x80 && + preg_match( '/^(.*)(?:[\xe0-\xef][\x80-\xbf]|' . + '[\xf0-\xf7][\x80-\xbf]{1,2})$/', $string, $m ) ) + { + # We chopped in the middle of a character; remove it + $string = $m[1]; + } + return $string; + } + + /** + * Remove bytes that represent an incomplete Unicode character + * at the start of string (e.g. bytes of the char are missing) + * + * @param $string String + * @return string + */ + protected function removeBadCharFirst( $string ) { + $char = ord( $string[0] ); + if ( $char >= 0x80 && $char < 0xc0 ) { + # We chopped in the middle of a character; remove the whole thing + $string = preg_replace( '/^[\x80-\xbf]+/', '', $string ); } - if( $length > 0 ) { - $string = substr( $string, 0, $length ); - $char = ord( $string[strlen( $string ) - 1] ); - $m = array(); - if ($char >= 0xc0) { - # We got the first byte only of a multibyte char; remove it. - $string = substr( $string, 0, -1 ); - } elseif( $char >= 0x80 && - preg_match( '/^(.*)(?:[\xe0-\xef][\x80-\xbf]|' . - '[\xf0-\xf7][\x80-\xbf]{1,2})$/', $string, $m ) ) { - # We chopped in the middle of a character; remove it - $string = $m[1]; + return $string; + } + + /* + * Truncate a string of valid HTML to a specified length in bytes, + * appending an optional string (e.g. for ellipses), and return valid HTML + * + * This is only intended for styled/linked text, such as HTML with + * tags like and , were the tags are self-contained (valid HTML) + * + * Note: tries to fix broken HTML with MWTidy + * + * @param string $text String to truncate + * @param int $length (zero/positive) Maximum length (excluding ellipses) + * @param string $ellipsis String to append to the truncated text + * @returns string + */ + function truncateHtml( $text, $length, $ellipsis = '...' ) { + # Use the localized ellipsis character + if ( $ellipsis == '...' ) { + $ellipsis = wfMsgExt( 'ellipsis', array( 'escapenoentities', 'language' => $this ) ); + } + # Check if there is no need to truncate + if ( $length <= 0 ) { + return $ellipsis; // no text shown, nothing to format + } elseif ( strlen($text) <= $length ) { + return $text; // string short enough even *with* HTML + } + $text = MWTidy::tidy( $text ); // fix tags + $displayLen = 0; // innerHTML legth so far + $testingEllipsis = false; // checking if ellipses will make string longer/equal? + $tagType = 0; // 0-open, 1-close + $bracketState = 0; // 1-tag start, 2-tag name, 0-neither + $entityState = 0; // 0-not entity, 1-entity + $tag = $ret = $ch = ''; + $openTags = array(); + $textLen = strlen($text); + for( $pos = 0; $pos < $textLen; ++$pos ) { + $ch = $text[$pos]; + $lastCh = $pos ? $text[$pos-1] : ''; + $ret .= $ch; // add to result string + if ( $ch == '<' ) { + $this->truncate_endBracket( $tag, $tagType, $lastCh, $openTags ); // for bad HTML + $entityState = 0; // for bad HTML + $bracketState = 1; // tag started (checking for backslash) + } elseif ( $ch == '>' ) { + $this->truncate_endBracket( $tag, $tagType, $lastCh, $openTags ); + $entityState = 0; // for bad HTML + $bracketState = 0; // out of brackets + } elseif ( $bracketState == 1 ) { + if ( $ch == '/' ) { + $tagType = 1; // close tag (e.g. "") + } else { + $tagType = 0; // open tag (e.g. "") + $tag .= $ch; + } + $bracketState = 2; // building tag name + } elseif ( $bracketState == 2 ) { + if ( $ch != ' ' ) { + $tag .= $ch; + } else { + // Name found (e.g. "truncate_skip( $ret, $text, "<>", $pos + 1 ); + } + } elseif ( $bracketState == 0 ) { + if ( $entityState ) { + if ( $ch == ';' ) { + $entityState = 0; + $displayLen++; // entity is one displayed char + } + } else { + if ( $ch == '&' ) { + $entityState = 1; // entity found, (e.g. " ") + } else { + $displayLen++; // this char is displayed + // Add on the other display text after this... + $skipped = $this->truncate_skip( + $ret, $text, "<>&", $pos + 1, $length - $displayLen ); + $displayLen += $skipped; + $pos += $skipped; + } + } } - return $string . $ellipsis; - } else { - $string = substr( $string, $length ); - $char = ord( $string[0] ); - if( $char >= 0x80 && $char < 0xc0 ) { - # We chopped in the middle of a character; remove the whole thing - $string = preg_replace( '/^[\x80-\xbf]+/', '', $string ); + # Consider truncation once the display length has reached the maximim. + # Double-check that we're not in the middle of a bracket/entity... + if ( $displayLen >= $length && $bracketState == 0 && $entityState == 0 ) { + if ( !$testingEllipsis ) { + $testingEllipsis = true; + # Save where we are; we will truncate here unless + # the ellipsis actually makes the string longer. + $pOpenTags = $openTags; // save state + $pRet = $ret; // save state + } elseif ( $displayLen > ($length + strlen($ellipsis)) ) { + # Ellipsis won't make string longer/equal, the truncation point was OK. + $openTags = $pOpenTags; // reload state + $ret = $this->removeBadCharLast( $pRet ); // reload state, multi-byte char fix + $ret .= $ellipsis; // add ellipsis + break; + } + } + } + if ( $displayLen == 0 ) { + return ''; // no text shown, nothing to format + } + $this->truncate_endBracket( $tag, $text[$textLen-1], $tagType, $openTags ); // for bad HTML + while ( count( $openTags ) > 0 ) { + $ret .= ''; // close open tags + } + return $ret; + } + + // truncateHtml() helper function + // like strcspn() but adds the skipped chars to $ret + private function truncate_skip( &$ret, $text, $search, $start, $len = -1 ) { + $skipCount = 0; + if( $start < strlen($text) ) { + $skipCount = strcspn( $text, $search, $start, $len ); + $ret .= substr( $text, $start, $skipCount ); + } + return $skipCount; + } + + // truncateHtml() helper function + // (a) push or pop $tag from $openTags as needed + // (b) clear $tag value + private function truncate_endBracket( &$tag, $tagType, $lastCh, &$openTags ) { + $tag = ltrim( $tag ); + if( $tag != '' ) { + if( $tagType == 0 && $lastCh != '/' ) { + $openTags[] = $tag; // tag opened (didn't close itself) + } else if( $tagType == 1 ) { + if( $openTags && $tag == $openTags[count($openTags)-1] ) { + array_pop( $openTags ); // tag closed + } } - return $ellipsis . $string; + $tag = ''; } } @@ -2023,6 +2381,22 @@ class Language { return $word; } + /** + * Provides an alternative text depending on specified gender. + * Usage {{gender:username|masculine|feminine|neutral}}. + * username is optional, in which case the gender of current user is used, + * but only in (some) interface messages; otherwise default gender is used. + * If second or third parameter are not specified, masculine is used. + * These details may be overriden per language. + */ + function gender( $gender, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 2 ); + if ( $gender === 'male' ) return $forms[0]; + if ( $gender === 'female' ) return $forms[1]; + return isset($forms[2]) ? $forms[2] : $forms[0]; + } + /** * Plural form transformations, needed for some languages. * For example, there are 3 form of plural in Russian and Polish, @@ -2107,31 +2481,31 @@ class Language { return $text; } + # convert text to all supported variants + function autoConvertToAllVariants($text) { + return $this->mConverter->autoConvertToAllVariants($text); + } + # convert text to different variants of a language. function convert( $text, $isTitle = false) { return $this->mConverter->convert($text, $isTitle); } - # Convert text from within Parser - function parserConvert( $text, &$parser ) { - return $this->mConverter->parserConvert( $text, $parser ); - } - # Check if this is a language with variants function hasVariants(){ return sizeof($this->getVariants())>1; } # Put custom tags (e.g. -{ }-) around math to prevent conversion - function armourMath($text){ + function armourMath($text){ return $this->mConverter->armourMath($text); } /** * Perform output conversion on a string, and encode for safe HTML output. - * @param $text String - * @param $isTitle Bool -- wtf? + * @param $text String text to be converted + * @param $isTitle Bool whether this conversion is for the article title * @return string * @todo this should get integrated somewhere sane */ @@ -2154,8 +2528,8 @@ class Language { } - function getPreferredVariant( $fromUser = true ) { - return $this->mConverter->getPreferredVariant( $fromUser ); + function getPreferredVariant( $fromUser = true, $fromHeader = false ) { + return $this->mConverter->getPreferredVariant( $fromUser, $fromHeader ); } /** @@ -2166,10 +2540,12 @@ class Language { * * @param $link String: the name of the link * @param $nt Mixed: the title object of the link + * @param $ignoreOtherCond Boolean: to disable other conditions when + * we need to transclude a template or update a category's link * @return null the input parameters may be modified upon return */ - function findVariantLink( &$link, &$nt, $forTemplate = false ) { - $this->mConverter->findVariantLink($link, $nt, $forTemplate ); + function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) { + $this->mConverter->findVariantLink( $link, $nt, $ignoreOtherCond ); } /** @@ -2177,7 +2553,6 @@ class Language { * into an array of all possible variants of the text: * 'variant' => text in that variant */ - function convertLinkToAllVariants($text){ return $this->mConverter->convertLinkToAllVariants($text); } @@ -2223,8 +2598,7 @@ class Language { * @return string */ function linkTrail() { - $this->load(); - return $this->linkTrail; + return self::$dataCache->getItem( $this->mCode, 'linkTrail' ); } function getLangObj() { @@ -2242,10 +2616,34 @@ class Language { $this->mCode = $code; } + /** + * Get the name of a file for a certain language code + * @param $prefix string Prepend this to the filename + * @param $code string Language code + * @param $suffix string Append this to the filename + * @return string $prefix . $mangledCode . $suffix + */ static function getFileName( $prefix = 'Language', $code, $suffix = '.php' ) { return $prefix . str_replace( '-', '_', ucfirst( $code ) ) . $suffix; } + /** + * Get the language code from a file name. Inverse of getFileName() + * @param $filename string $prefix . $languageCode . $suffix + * @param $prefix string Prefix before the language code + * @param $suffix string Suffix after the language code + * @return Language code, or false if $prefix or $suffix isn't found + */ + static function getCodeFromFileName( $filename, $prefix = 'Language', $suffix = '.php' ) { + $m = null; + preg_match( '/' . preg_quote( $prefix, '/' ) . '([A-Z][a-z_]+)' . + preg_quote( $suffix, '/' ) . '/', $filename, $m ); + if ( !count( $m ) ) { + return false; + } + return str_replace( '_', '-', strtolower( $m[1] ) ); + } + static function getMessagesFileName( $code ) { global $IP; return self::getFileName( "$IP/languages/messages/Messages", $code, '.php' ); @@ -2255,296 +2653,47 @@ class Language { global $IP; return self::getFileName( "$IP/languages/classes/Language", $code, '.php' ); } - - static function getLocalisationArray( $code, $disableCache = false ) { - self::loadLocalisation( $code, $disableCache ); - return self::$mLocalisationCache[$code]; - } - /** - * Load localisation data for a given code into the static cache - * - * @return array Dependencies, map of filenames to mtimes - */ - static function loadLocalisation( $code, $disableCache = false ) { - static $recursionGuard = array(); - global $wgMemc, $wgCheckSerialized; - - if ( !$code ) { - throw new MWException( "Invalid language code requested" ); - } - - if ( !$disableCache ) { - # Try the per-process cache - if ( isset( self::$mLocalisationCache[$code] ) ) { - return self::$mLocalisationCache[$code]['deps']; - } - - wfProfileIn( __METHOD__ ); - - # Try the serialized directory - $cache = wfGetPrecompiledData( self::getFileName( "Messages", $code, '.ser' ) ); - if ( $cache ) { - if ( $wgCheckSerialized && self::isLocalisationOutOfDate( $cache ) ) { - $cache = false; - wfDebug( "Language::loadLocalisation(): precompiled data file for $code is out of date\n" ); - } else { - self::$mLocalisationCache[$code] = $cache; - wfDebug( "Language::loadLocalisation(): got localisation for $code from precompiled data file\n" ); - wfProfileOut( __METHOD__ ); - return self::$mLocalisationCache[$code]['deps']; - } - } - - # Try the global cache - $memcKey = wfMemcKey('localisation', $code ); - $fbMemcKey = wfMemcKey('fallback', $cache['fallback'] ); - $cache = $wgMemc->get( $memcKey ); - if ( $cache ) { - if ( self::isLocalisationOutOfDate( $cache ) ) { - $wgMemc->delete( $memcKey ); - $wgMemc->delete( $fbMemcKey ); - $cache = false; - wfDebug( "Language::loadLocalisation(): localisation cache for $code had expired\n" ); - } else { - self::$mLocalisationCache[$code] = $cache; - wfDebug( "Language::loadLocalisation(): got localisation for $code from cache\n" ); - wfProfileOut( __METHOD__ ); - return $cache['deps']; - } - } - } else { - wfProfileIn( __METHOD__ ); - } - - # Default fallback, may be overridden when the messages file is included - if ( $code != 'en' ) { - $fallback = 'en'; - } else { - $fallback = false; - } - - # Load the primary localisation from the source file - $filename = self::getMessagesFileName( $code ); - if ( !file_exists( $filename ) ) { - wfDebug( "Language::loadLocalisation(): no localisation file for $code, using implicit fallback to en\n" ); - $cache = compact( self::$mLocalisationKeys ); // Set correct fallback - $deps = array(); - } else { - $deps = array( $filename => filemtime( $filename ) ); - require( $filename ); - $cache = compact( self::$mLocalisationKeys ); - wfDebug( "Language::loadLocalisation(): got localisation for $code from source\n" ); - } - - if ( !empty( $fallback ) ) { - # Load the fallback localisation, with a circular reference guard - if ( isset( $recursionGuard[$code] ) ) { - throw new MWException( "Error: Circular fallback reference in language code $code" ); - } - $recursionGuard[$code] = true; - $newDeps = self::loadLocalisation( $fallback, $disableCache ); - unset( $recursionGuard[$code] ); - - $secondary = self::$mLocalisationCache[$fallback]; - $deps = array_merge( $deps, $newDeps ); - - # Merge the fallback localisation with the current localisation - foreach ( self::$mLocalisationKeys as $key ) { - if ( isset( $cache[$key] ) ) { - if ( isset( $secondary[$key] ) ) { - if ( in_array( $key, self::$mMergeableMapKeys ) ) { - $cache[$key] = $cache[$key] + $secondary[$key]; - } elseif ( in_array( $key, self::$mMergeableListKeys ) ) { - $cache[$key] = array_merge( $secondary[$key], $cache[$key] ); - } elseif ( in_array( $key, self::$mMergeableAliasListKeys ) ) { - $cache[$key] = array_merge_recursive( $cache[$key], $secondary[$key] ); - } - } - } else { - $cache[$key] = $secondary[$key]; - } - } - - # Merge bookstore lists if requested - if ( !empty( $cache['bookstoreList']['inherit'] ) ) { - $cache['bookstoreList'] = array_merge( $cache['bookstoreList'], $secondary['bookstoreList'] ); - } - if ( isset( $cache['bookstoreList']['inherit'] ) ) { - unset( $cache['bookstoreList']['inherit'] ); - } - } - - # Add dependencies to the cache entry - $cache['deps'] = $deps; - - # Replace spaces with underscores in namespace names - $cache['namespaceNames'] = str_replace( ' ', '_', $cache['namespaceNames'] ); - - # And do the same for specialpage aliases. $page is an array. - foreach ( $cache['specialPageAliases'] as &$page ) { - $page = str_replace( ' ', '_', $page ); - } - # Decouple the reference to prevent accidental damage - unset($page); - - # Save to both caches - self::$mLocalisationCache[$code] = $cache; - if ( !$disableCache ) { - $wgMemc->set( $memcKey, $cache ); - $wgMemc->set( $fbMemcKey, (string) $cache['fallback'] ); - } - - wfProfileOut( __METHOD__ ); - return $deps; - } - - /** - * Test if a given localisation cache is out of date with respect to the - * source Messages files. This is done automatically for the global cache - * in $wgMemc, but is only done on certain occasions for the serialized - * data file. - * - * @param $cache mixed Either a language code or a cache array - */ - static function isLocalisationOutOfDate( $cache ) { - if ( !is_array( $cache ) ) { - self::loadLocalisation( $cache ); - $cache = self::$mLocalisationCache[$cache]; - } - $expired = false; - foreach ( $cache['deps'] as $file => $mtime ) { - if ( !file_exists( $file ) || filemtime( $file ) > $mtime ) { - $expired = true; - break; - } - } - return $expired; - } - /** * Get the fallback for a given language */ static function getFallbackFor( $code ) { - // Shortcut - if ( $code === 'en' ) return false; - - // Local cache - static $cache = array(); - // Quick return - if ( isset($cache[$code]) ) return $cache[$code]; - - // Try memcache - global $wgMemc; - $memcKey = wfMemcKey( 'fallback', $code ); - $fbcode = $wgMemc->get( $memcKey ); - - if ( is_string($fbcode) ) { - // False is stored as a string to detect failures in memcache properly - if ( $fbcode === '' ) $fbcode = false; - - // Update local cache and return - $cache[$code] = $fbcode; - return $fbcode; + if ( $code === 'en' ) { + // Shortcut + return false; + } else { + return self::getLocalisationCache()->getItem( $code, 'fallback' ); } - - // Nothing in caches, load and and update both caches - self::loadLocalisation( $code ); - $fbcode = self::$mLocalisationCache[$code]['fallback']; - - $cache[$code] = $fbcode; - $wgMemc->set( $memcKey, (string) $fbcode ); - - return $fbcode; } - /** + /** * Get all messages for a given language + * WARNING: this may take a long time */ static function getMessagesFor( $code ) { - self::loadLocalisation( $code ); - return self::$mLocalisationCache[$code]['messages']; + return self::getLocalisationCache()->getItem( $code, 'messages' ); } - /** + /** * Get a message for a given language */ static function getMessageFor( $key, $code ) { - self::loadLocalisation( $code ); - return isset( self::$mLocalisationCache[$code]['messages'][$key] ) ? self::$mLocalisationCache[$code]['messages'][$key] : null; + return self::getLocalisationCache()->getSubitem( $code, 'messages', $key ); } - /** - * Load localisation data for this object - */ - function load() { - if ( !$this->mLoaded ) { - self::loadLocalisation( $this->getCode() ); - $cache =& self::$mLocalisationCache[$this->getCode()]; - foreach ( self::$mLocalisationKeys as $key ) { - $this->$key = $cache[$key]; - } - $this->mLoaded = true; - - $this->fixUpSettings(); - } - } + function fixVariableInNamespace( $talk ) { + if ( strpos( $talk, '$1' ) === false ) return $talk; - /** - * Do any necessary post-cache-load settings adjustment - */ - function fixUpSettings() { - global $wgExtraNamespaces, $wgMetaNamespace, $wgMetaNamespaceTalk, - $wgNamespaceAliases, $wgAmericanDates; - wfProfileIn( __METHOD__ ); - if ( $wgExtraNamespaces ) { - $this->namespaceNames = $wgExtraNamespaces + $this->namespaceNames; - } + global $wgMetaNamespace; + $talk = str_replace( '$1', $wgMetaNamespace, $talk ); - $this->namespaceNames[NS_PROJECT] = $wgMetaNamespace; - if ( $wgMetaNamespaceTalk ) { - $this->namespaceNames[NS_PROJECT_TALK] = $wgMetaNamespaceTalk; - } else { - $talk = $this->namespaceNames[NS_PROJECT_TALK]; - $talk = str_replace( '$1', $wgMetaNamespace, $talk ); - - # Allow grammar transformations - # Allowing full message-style parsing would make simple requests - # such as action=raw much more expensive than they need to be. - # This will hopefully cover most cases. - $talk = preg_replace_callback( '/{{grammar:(.*?)\|(.*?)}}/i', - array( &$this, 'replaceGrammarInNamespace' ), $talk ); - $talk = str_replace( ' ', '_', $talk ); - $this->namespaceNames[NS_PROJECT_TALK] = $talk; - } - - # The above mixing may leave namespaces out of canonical order. - # Re-order by namespace ID number... - ksort( $this->namespaceNames ); - - # Put namespace names and aliases into a hashtable. - # If this is too slow, then we should arrange it so that it is done - # before caching. The catch is that at pre-cache time, the above - # class-specific fixup hasn't been done. - $this->mNamespaceIds = array(); - foreach ( $this->namespaceNames as $index => $name ) { - $this->mNamespaceIds[$this->lc($name)] = $index; - } - if ( $this->namespaceAliases ) { - foreach ( $this->namespaceAliases as $name => $index ) { - $this->mNamespaceIds[$this->lc($name)] = $index; - } - } - if ( $wgNamespaceAliases ) { - foreach ( $wgNamespaceAliases as $name => $index ) { - $this->mNamespaceIds[$this->lc($name)] = $index; - } - } - - if ( $this->defaultDateFormat == 'dmy or mdy' ) { - $this->defaultDateFormat = $wgAmericanDates ? 'mdy' : 'dmy'; - } - wfProfileOut( __METHOD__ ); + # Allow grammar transformations + # Allowing full message-style parsing would make simple requests + # such as action=raw much more expensive than they need to be. + # This will hopefully cover most cases. + $talk = preg_replace_callback( '/{{grammar:(.*?)\|(.*?)}}/i', + array( &$this, 'replaceGrammarInNamespace' ), $talk ); + return str_replace( ' ', '_', $talk ); } function replaceGrammarInNamespace( $m ) { @@ -2560,7 +2709,7 @@ class Language { wfProfileIn( __METHOD__ ); $arr = wfGetPrecompiledData( 'Utf8Case.ser' ); if ( $arr === false ) { - throw new MWException( + throw new MWException( "Utf8Case.ser is missing, please run \"make\" in the serialized directory\n" ); } extract( $arr ); @@ -2570,19 +2719,19 @@ class Language { function formatTimePeriod( $seconds ) { if ( $seconds < 10 ) { - return $this->formatNum( sprintf( "%.1f", $seconds ) ) . wfMsg( 'seconds-abbrev' ); + return $this->formatNum( sprintf( "%.1f", $seconds ) ) . ' ' . wfMsg( 'seconds-abbrev' ); } elseif ( $seconds < 60 ) { - return $this->formatNum( round( $seconds ) ) . wfMsg( 'seconds-abbrev' ); + return $this->formatNum( round( $seconds ) ) . ' ' . wfMsg( 'seconds-abbrev' ); } elseif ( $seconds < 3600 ) { - return $this->formatNum( floor( $seconds / 60 ) ) . wfMsg( 'minutes-abbrev' ) . - $this->formatNum( round( fmod( $seconds, 60 ) ) ) . wfMsg( 'seconds-abbrev' ); + return $this->formatNum( floor( $seconds / 60 ) ) . ' ' . wfMsg( 'minutes-abbrev' ) . ' ' . + $this->formatNum( round( fmod( $seconds, 60 ) ) ) . ' ' . wfMsg( 'seconds-abbrev' ); } else { $hours = floor( $seconds / 3600 ); $minutes = floor( ( $seconds - $hours * 3600 ) / 60 ); $secondsPart = round( $seconds - $hours * 3600 - $minutes * 60 ); - return $this->formatNum( $hours ) . wfMsg( 'hours-abbrev' ) . - $this->formatNum( $minutes ) . wfMsg( 'minutes-abbrev' ) . - $this->formatNum( $secondsPart ) . wfMsg( 'seconds-abbrev' ); + return $this->formatNum( $hours ) . ' ' . wfMsg( 'hours-abbrev' ) . ' ' . + $this->formatNum( $minutes ) . ' ' . wfMsg( 'minutes-abbrev' ) . ' ' . + $this->formatNum( $secondsPart ) . ' ' . wfMsg( 'seconds-abbrev' ); } } @@ -2633,4 +2782,11 @@ class Language { $text = $this->getMessageFromDB( $msg ); return str_replace( '$1', $this->formatNum( $size ), $text ); } + + /** + * Get the conversion rule title, if any. + */ + function getConvRuleTitle() { + return $this->mConverter->getConvRuleTitle(); + } }