/languages/Language.php
PHP | 2735 lines | 1740 code | 292 blank | 703 comment | 374 complexity | 55b91445e76d2958a8fff9a17f33dabc MD5 | raw file
Possible License(s): GPL-2.0, LGPL-3.0
Large files files are truncated, but you can click here to view the full file
- <?php
- /**
- * @defgroup Language Language
- *
- * @file
- * @ingroup Language
- */
- if( !defined( 'MEDIAWIKI' ) ) {
- echo "This file is part of MediaWiki, it is not a valid entry point.\n";
- exit( 1 );
- }
- # Read language names
- global $wgLanguageNames;
- require_once( dirname(__FILE__) . '/Names.php' ) ;
- global $wgInputEncoding, $wgOutputEncoding;
- /**
- * These are always UTF-8, they exist only for backwards compatibility
- */
- $wgInputEncoding = "UTF-8";
- $wgOutputEncoding = "UTF-8";
- if( function_exists( 'mb_strtoupper' ) ) {
- mb_internal_encoding('UTF-8');
- }
- /**
- * a fake language converter
- *
- * @ingroup Language
- */
- class FakeConverter {
- var $mLang;
- function FakeConverter($langobj) {$this->mLang = $langobj;}
- function convert($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, $ignoreOtherCond = false) {}
- function getExtraHashOptions() {return '';}
- function getParsedTitle() {return '';}
- function markNoConversion($text, $noParse=false) {return $text;}
- function convertCategoryKey( $key ) {return $key; }
- function convertLinkToAllVariants($text){ return array( $this->mLang->getCode() => $text); }
- function armourMath($text){ return $text; }
- }
- /**
- * Internationalisation code
- * @ingroup Language
- */
- class Language {
- var $mConverter, $mVariants, $mCode, $mLoaded = false;
- var $mMagicExtensions = array(), $mMagicHookDone = false;
- static public $mLocalisationKeys = array(
- 'fallback', 'namespaceNames', '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' );
- static public $mMergeableAliasListKeys = array( 'specialPageAliases' );
- static public $mLocalisationCache = array();
- static public $mLangObjCache = array();
- static public $mWeekdayMsgs = array(
- 'sunday', 'monday', 'tuesday', 'wednesday', 'thursday',
- 'friday', 'saturday'
- );
- static public $mWeekdayAbbrevMsgs = array(
- 'sun', 'mon', 'tue', 'wed', 'thu', 'fri', 'sat'
- );
- static public $mMonthMsgs = array(
- 'january', 'february', 'march', 'april', 'may_long', 'june',
- 'july', 'august', 'september', 'october', 'november',
- 'december'
- );
- static public $mMonthGenMsgs = array(
- 'january-gen', 'february-gen', 'march-gen', 'april-gen', 'may-gen', 'june-gen',
- 'july-gen', 'august-gen', 'september-gen', 'october-gen', 'november-gen',
- 'december-gen'
- );
- static public $mMonthAbbrevMsgs = array(
- 'jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug',
- 'sep', 'oct', 'nov', 'dec'
- );
- static public $mIranianCalendarMonthMsgs = array(
- 'iranian-calendar-m1', 'iranian-calendar-m2', 'iranian-calendar-m3',
- 'iranian-calendar-m4', 'iranian-calendar-m5', 'iranian-calendar-m6',
- 'iranian-calendar-m7', 'iranian-calendar-m8', 'iranian-calendar-m9',
- 'iranian-calendar-m10', 'iranian-calendar-m11', 'iranian-calendar-m12'
- );
- static public $mHebrewCalendarMonthMsgs = array(
- 'hebrew-calendar-m1', 'hebrew-calendar-m2', 'hebrew-calendar-m3',
- 'hebrew-calendar-m4', 'hebrew-calendar-m5', 'hebrew-calendar-m6',
- 'hebrew-calendar-m7', 'hebrew-calendar-m8', 'hebrew-calendar-m9',
- 'hebrew-calendar-m10', 'hebrew-calendar-m11', 'hebrew-calendar-m12',
- 'hebrew-calendar-m6a', 'hebrew-calendar-m6b'
- );
- static public $mHebrewCalendarMonthGenMsgs = array(
- 'hebrew-calendar-m1-gen', 'hebrew-calendar-m2-gen', 'hebrew-calendar-m3-gen',
- 'hebrew-calendar-m4-gen', 'hebrew-calendar-m5-gen', 'hebrew-calendar-m6-gen',
- 'hebrew-calendar-m7-gen', 'hebrew-calendar-m8-gen', 'hebrew-calendar-m9-gen',
- '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',
- 'hijri-calendar-m7', 'hijri-calendar-m8', 'hijri-calendar-m9',
- 'hijri-calendar-m10', 'hijri-calendar-m11', 'hijri-calendar-m12'
- );
- /**
- * Get a cached language object for a given language code
- */
- 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];
- }
- /**
- * Create a language object for a given language code
- */
- protected static function newFromCode( $code ) {
- global $IP;
- static $recursionLevel = 0;
- if ( $code == 'en' ) {
- $class = 'Language';
- } else {
- $class = 'Language' . str_replace( '-', '_', ucfirst( $code ) );
- // Preload base classes to work around APC/PHP5 bug
- if ( file_exists( "$IP/languages/classes/$class.deps.php" ) ) {
- include_once("$IP/languages/classes/$class.deps.php");
- }
- if ( file_exists( "$IP/languages/classes/$class.php" ) ) {
- include_once("$IP/languages/classes/$class.php");
- }
- }
- if ( $recursionLevel > 5 ) {
- throw new MWException( "Language fallback loop detected when creating class $class\n" );
- }
- if( ! class_exists( $class ) ) {
- $fallback = Language::getFallbackFor( $code );
- ++$recursionLevel;
- $lang = Language::newFromCode( $fallback );
- --$recursionLevel;
- $lang->setCode( $code );
- } else {
- $lang = new $class;
- }
- return $lang;
- }
- function __construct() {
- $this->mConverter = new FakeConverter($this);
- // Set the code to the name of the descendant
- if ( get_class( $this ) == 'Language' ) {
- $this->mCode = 'en';
- } else {
- $this->mCode = str_replace( '_', '-', strtolower( substr( get_class( $this ), 8 ) ) );
- }
- }
- /**
- * Reduce memory usage
- */
- function __destruct() {
- foreach ( $this as $name => $value ) {
- unset( $this->$name );
- }
- }
- /**
- * Hook which will be called if this is the content language.
- * Descendants can use this to register hook functions or modify globals
- */
- function initContLang() {}
- /**
- * @deprecated Use User::getDefaultOptions()
- * @return array
- */
- function getDefaultUserOptions() {
- wfDeprecated( __METHOD__ );
- return User::getDefaultOptions();
- }
- function getFallbackLanguageCode() {
- return self::getFallbackFor( $this->mCode );
- }
- /**
- * Exports $wgBookstoreListEn
- * @return array
- */
- function getBookstoreList() {
- $this->load();
- return $this->bookstoreList;
- }
- /**
- * @return array
- */
- function getNamespaces() {
- $this->load();
- return $this->namespaceNames;
- }
- /**
- * A convenience function that returns the same thing as
- * getNamespaces() except with the array values changed to ' '
- * where it found '_', useful for producing output to be displayed
- * e.g. in <select> forms.
- *
- * @return array
- */
- function getFormattedNamespaces() {
- $ns = $this->getNamespaces();
- foreach($ns as $k => $v) {
- $ns[$k] = strtr($v, '_', ' ');
- }
- return $ns;
- }
- /**
- * Get a namespace value by key
- * <code>
- * $mw_ns = $wgContLang->getNsText( NS_MEDIAWIKI );
- * echo $mw_ns; // prints 'MediaWiki'
- * </code>
- *
- * @param $index Int: the array key of the namespace to return
- * @return mixed, string if the namespace value exists, otherwise false
- */
- function getNsText( $index ) {
- $ns = $this->getNamespaces();
- return isset( $ns[$index] ) ? $ns[$index] : false;
- }
- /**
- * A convenience function that returns the same thing as
- * getNsText() except with '_' changed to ' ', useful for
- * producing output.
- *
- * @return array
- */
- function getFormattedNsText( $index ) {
- $ns = $this->getNsText( $index );
- return strtr($ns, '_', ' ');
- }
- /**
- * Get a namespace key by value, case insensitive.
- * Only matches namespace names for the current language, not the
- * canonical ones defined in Namespace.php.
- *
- * @param $text String
- * @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;
- }
- /**
- * Get a namespace key by value, case insensitive. Canonical namespace
- * names override custom ones defined for the current language.
- *
- * @param $text String
- * @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;
- }
- /**
- * short names for language variants used for language conversion links.
- *
- * @param $code String
- * @return string
- */
- function getVariantname( $code ) {
- return $this->getMessageFromDB( "variantname-$code" );
- }
- function specialPage( $name ) {
- $aliases = $this->getSpecialPageAliases();
- if ( isset( $aliases[$name][0] ) ) {
- $name = $aliases[$name][0];
- }
- return $this->getNsText( NS_SPECIAL ) . ':' . $name;
- }
- function getQuickbarSettings() {
- return array(
- $this->getMessage( 'qbsettings-none' ),
- $this->getMessage( 'qbsettings-fixedleft' ),
- $this->getMessage( 'qbsettings-fixedright' ),
- $this->getMessage( 'qbsettings-floatingleft' ),
- $this->getMessage( 'qbsettings-floatingright' )
- );
- }
- function getMathNames() {
- $this->load();
- return $this->mathNames;
- }
- function getDatePreferences() {
- $this->load();
- return $this->datePreferences;
- }
-
- function getDateFormats() {
- $this->load();
- return $this->dateFormats;
- }
- function getDefaultDateFormat() {
- $this->load();
- return $this->defaultDateFormat;
- }
- function getDatePreferenceMigrationMap() {
- $this->load();
- return $this->datePreferenceMigrationMap;
- }
- function getImageFile( $image ) {
- $this->load();
- return $this->imageFiles[$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();
- }
- }
- function getExtraUserToggles() {
- $this->load();
- return $this->extraUserToggles;
- }
- function getUserToggle( $tog ) {
- return $this->getMessageFromDB( "tog-$tog" );
- }
- /**
- * Get language names, indexed by code.
- * If $customisedOnly is true, only returns codes with a messages file
- */
- public static function getLanguageNames( $customisedOnly = false ) {
- global $wgLanguageNames, $wgExtraLanguageNames;
- $allNames = $wgExtraLanguageNames + $wgLanguageNames;
- if ( !$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];
- }
- }
- }
- closedir( $dir );
- return $names;
- }
- /**
- * Get a message from the MediaWiki namespace.
- *
- * @param $msg String: message name
- * @return string
- */
- function getMessageFromDB( $msg ) {
- return wfMsgExt( $msg, array( 'parsemag', 'language' => $this ) );
- }
- function getLanguageName( $code ) {
- $names = self::getLanguageNames();
- if ( !array_key_exists( $code, $names ) ) {
- return '';
- }
- return $names[$code];
- }
- function getMonthName( $key ) {
- return $this->getMessageFromDB( self::$mMonthMsgs[$key-1] );
- }
- function getMonthNameGen( $key ) {
- return $this->getMessageFromDB( self::$mMonthGenMsgs[$key-1] );
- }
- function getMonthAbbreviation( $key ) {
- return $this->getMessageFromDB( self::$mMonthAbbrevMsgs[$key-1] );
- }
- function getWeekdayName( $key ) {
- return $this->getMessageFromDB( self::$mWeekdayMsgs[$key-1] );
- }
- function getWeekdayAbbreviation( $key ) {
- return $this->getMessageFromDB( self::$mWeekdayAbbrevMsgs[$key-1] );
- }
- function getIranianCalendarMonthName( $key ) {
- return $this->getMessageFromDB( self::$mIranianCalendarMonthMsgs[$key-1] );
- }
- function getHebrewCalendarMonthName( $key ) {
- return $this->getMessageFromDB( self::$mHebrewCalendarMonthMsgs[$key-1] );
- }
- 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.
- *
- * @param $ts Int the time in date('YmdHis') format
- * @param $tz Mixed: adjust the time by this amount (default false, mean we
- * get user timecorrection setting)
- * @return int
- */
- function userAdjust( $ts, $tz = false ) {
- global $wgUser, $wgLocalTZoffset;
- if ( $tz === false ) {
- $tz = $wgUser->getOption( 'timecorrection' );
- }
- $data = explode( '|', $tz, 3 );
- 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;
- }
- # 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 {
- $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 == $minDiff ) return $ts;
- wfSuppressWarnings(); // E_STRICT system time bitching
- # 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) ), # 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
- * escaping format.
- *
- * 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
- * xr Use roman numerals for the next numeric format character
- * xh Use hebrew numerals for the next numeric format character
- * xx Literal x
- * xg Genitive month name
- *
- * xij j (day number) in Iranian calendar
- * xiF F (month name) in Iranian calendar
- * xin n (month number) in Iranian calendar
- * xiY Y (full year) in Iranian calendar
- *
- * xjj j (day number) in Hebrew calendar
- * xjF F (month name) in Hebrew calendar
- * xjt t (days in month) in Hebrew calendar
- * xjx xg (genitive month name) in Hebrew calendar
- * 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
- *
- * xkY Y (full year) in Thai solar calendar. 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
- * literal quotes. Example:
- *
- * "The month is" F => The month is January
- * i's" => 20'11"
- *
- * Backslash escaping is also supported.
- *
- * 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 = '';
- $raw = false;
- $roman = false;
- $hebrewNum = false;
- $unix = false;
- $rawToggle = false;
- $iranian = false;
- $hebrew = false;
- $hijri = false;
- $thai = false;
- for ( $p = 0; $p < strlen( $format ); $p++ ) {
- $num = false;
- $code = $format[$p];
- if ( $code == 'x' && $p < strlen( $format ) - 1 ) {
- $code .= $format[++$p];
- }
- if ( ( $code === 'xi' || $code == 'xj' || $code == 'xk' || $code == 'xm' ) && $p < strlen( $format ) - 1 ) {
- $code .= $format[++$p];
- }
- switch ( $code ) {
- case 'xx':
- $s .= 'x';
- break;
- case 'xn':
- $raw = true;
- break;
- case 'xN':
- $rawToggle = !$rawToggle;
- break;
- case 'xr':
- $roman = true;
- break;
- case 'xh':
- $hebrewNum = true;
- break;
- case 'xg':
- $s .= $this->getMonthNameGen( substr( $ts, 4, 2 ) );
- break;
- case 'xjx':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $s .= $this->getHebrewCalendarMonthNameGen( $hebrew[1] );
- break;
- case 'd':
- $num = substr( $ts, 6, 2 );
- break;
- case 'D':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $s .= $this->getWeekdayAbbreviation( gmdate( 'w', $unix ) + 1 );
- break;
- case 'j':
- $num = intval( substr( $ts, 6, 2 ) );
- break;
- case 'xij':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
- $num = $iranian[2];
- break;
- case 'xmj':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
- $num = $hijri[2];
- break;
- case 'xjj':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $num = $hebrew[2];
- break;
- case 'l':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $s .= $this->getWeekdayName( gmdate( 'w', $unix ) + 1 );
- break;
- case 'N':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $w = gmdate( 'w', $unix );
- $num = $w ? $w : 7;
- break;
- case 'w':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $num = gmdate( 'w', $unix );
- break;
- case 'z':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $num = gmdate( 'z', $unix );
- break;
- case 'W':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $num = gmdate( 'W', $unix );
- break;
- case 'F':
- $s .= $this->getMonthName( substr( $ts, 4, 2 ) );
- break;
- case 'xiF':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
- $s .= $this->getIranianCalendarMonthName( $iranian[1] );
- break;
- case 'xmF':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
- $s .= $this->getHijriCalendarMonthName( $hijri[1] );
- break;
- case 'xjF':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $s .= $this->getHebrewCalendarMonthName( $hebrew[1] );
- break;
- case 'm':
- $num = substr( $ts, 4, 2 );
- break;
- case 'M':
- $s .= $this->getMonthAbbreviation( substr( $ts, 4, 2 ) );
- break;
- case 'n':
- $num = intval( substr( $ts, 4, 2 ) );
- break;
- case 'xin':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
- $num = $iranian[1];
- break;
- case 'xmn':
- if ( !$hijri ) $hijri = self::tsToHijri ( $ts );
- $num = $hijri[1];
- break;
- case 'xjn':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $num = $hebrew[1];
- break;
- case 't':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $num = gmdate( 't', $unix );
- break;
- case 'xjt':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $num = $hebrew[3];
- break;
- case 'L':
- if ( !$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( $ts, 0, 4 );
- break;
- case 'xiY':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
- $num = $iranian[0];
- break;
- case 'xmY':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
- $num = $hijri[0];
- break;
- case 'xjY':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
- $num = $hebrew[0];
- break;
- case 'xkY':
- if ( !$thai ) $thai = self::tsToThai( $ts );
- $num = $thai[0];
- break;
- case 'y':
- $num = substr( $ts, 2, 2 );
- break;
- case 'a':
- $s .= intval( substr( $ts, 8, 2 ) ) < 12 ? 'am' : 'pm';
- break;
- case 'A':
- $s .= intval( substr( $ts, 8, 2 ) ) < 12 ? 'AM' : 'PM';
- break;
- case 'g':
- $h = substr( $ts, 8, 2 );
- $num = $h % 12 ? $h % 12 : 12;
- break;
- case 'G':
- $num = intval( substr( $ts, 8, 2 ) );
- break;
- case 'h':
- $h = substr( $ts, 8, 2 );
- $num = sprintf( '%02d', $h % 12 ? $h % 12 : 12 );
- break;
- case 'H':
- $num = substr( $ts, 8, 2 );
- break;
- case 'i':
- $num = substr( $ts, 10, 2 );
- break;
- case 's':
- $num = substr( $ts, 12, 2 );
- break;
- case 'c':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $s .= gmdate( 'c', $unix );
- break;
- case 'r':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $s .= gmdate( 'r', $unix );
- break;
- case 'U':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
- $num = $unix;
- break;
- case '\\':
- # Backslash escaping
- if ( $p < strlen( $format ) - 1 ) {
- $s .= $format[++$p];
- } else {
- $s .= '\\';
- }
- break;
- case '"':
- # Quoted literal
- if ( $p < strlen( $format ) - 1 ) {
- $endQuote = strpos( $format, '"', $p + 1 );
- if ( $endQuote === false ) {
- # No terminating quote, assume literal "
- $s .= '"';
- } else {
- $s .= substr( $format, $p + 1, $endQuote - $p - 1 );
- $p = $endQuote;
- }
- } else {
- # Quote at end of string, assume literal "
- $s .= '"';
- }
- break;
- default:
- $s .= $format[$p];
- }
- if ( $num !== false ) {
- if ( $rawToggle || $raw ) {
- $s .= $num;
- $raw = false;
- } elseif ( $roman ) {
- $s .= self::romanNumeral( $num );
- $roman = false;
- } elseif( $hebrewNum ) {
- $s .= self::hebrewNumeral( $num );
- $hebrewNum = false;
- } else {
- $s .= $this->formatNum( $num, true );
- }
- $num = false;
- }
- }
- return $s;
- }
- 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
- * 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 ) {
- $gy = substr( $ts, 0, 4 ) -1600;
- $gm = substr( $ts, 4, 2 ) -1;
- $gd = substr( $ts, 6, 2 ) -1;
- # Days passed from the beginning (including leap years)
- $gDayNo = 365*$gy
- + floor(($gy+3) / 4)
- - floor(($gy+99) / 100)
- + floor(($gy+399) / 400);
- // Add days of the past months of this year
- for( $i = 0; $i < $gm; $i++ ) {
- $gDayNo += self::$GREG_DAYS[$i];
- }
- // Leap years
- if ( $gm > 1 && (($gy%4===0 && $gy%100!==0 || ($gy%400==0)))) {
- $gDayNo++;
- }
- // Days passed in current month
- $gDayNo += $gd;
-
- $jDayNo = $gDayNo - 79;
- $jNp = floor($jDayNo / 12053);
- $jDayNo %= 12053;
- $jy = 979 + 33*$jNp + 4*floor($jDayNo/1461);
- $jDayNo %= 1461;
- if ( $jDayNo >= 366 ) {
- $jy += floor(($jDayNo-1)/365);
- $jDayNo = floor(($jDayNo-1)%365);
- }
- for ( $i = 0; $i < 11 && $jDayNo >= self::$IRANIAN_DAYS[$i]; $i++ ) {
- $jDayNo -= self::$IRANIAN_DAYS[$i];
- }
- $jm= $i+1;
- $jd= $jDayNo+1;
- return array($jy, $jm, $jd);
- }
- /**
- * Converting Gregorian dates to Hijri dates.
- *
- * Based on a PHP-Nuke block by Sharjeel which is released under GNU/GPL license
- *
- * @link http://phpnuke.org/modules.php?name=News&file=article&sid=8234&mode=thread&order=0&thold=0
- */
- private static function tsToHijri ( $ts ) {
- $year = substr( $ts, 0, 4 );
- $month = substr( $ts, 4, 2 );
- $day = substr( $ts, 6, 2 );
-
- $zyr = $year;
- $zd=$day;
- $zm=$month;
- $zy=$zyr;
- 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;
- $zj=((int)((10985-$zl)/5316))*((int)((50*$zl)/17719))+((int)($zl/5670))*((int)((43*$zl)/15238));
- $zl=$zl-((int)((30-$zj)/15))*((int)((17719*$zj)/50))-((int)($zj/16))*((int)((15238*$zj)/43))+29;
- $zm=(int)((24*$zl)/709);
- $zd=$zl-(int)((709*$zm)/24);
- $zy=30*$zn+$zj-30;
- return array ($zy, $zm, $zd);
- }
- /**
- * Converting Gregorian dates to Hebrew dates.
- *
- * Based on a JavaScript code by Abu Mami and Yisrael Hersch
- * (abu-mami@kaluach.net, http://www.kaluach.net), who permitted
- * to translate the relevant functions into PHP and release them under
- * GNU GPL.
- *
- * The months are counted from Tishrei = 1. In a leap year, Adar I is 13
- * and Adar II is 14. In a non-leap year, Adar is 6.
- */
- private static function tsToHebrew( $ts ) {
- # Parse date
- $year = substr( $ts, 0, 4 );
- $month = substr( $ts, 4, 2 );
- $day = substr( $ts, 6, 2 );
- # Calculate Hebrew year
- $hebrewYear = $year + 3760;
- # Month number when September = 1, August = 12
- $month += 4;
- if( $month > 12 ) {
- # Next year
- $month -= 12;
- $year++;
- $hebrewYear++;
- }
- # Calculate day of year from 1 September
- $dayOfYear = $day;
- for( $i = 1; $i < $month; $i++ ) {
- if( $i == 6 ) {
- # February
- $dayOfYear += 28;
- # Check if the year is leap
- if( $year % 400 == 0 || ( $year % 4 == 0 && $year % 100 > 0 ) ) {
- $dayOfYear++;
- }
- } elseif( $i == 8 || $i == 10 || $i == 1 || $i == 3 ) {
- $dayOfYear += 30;
- } else {
- $dayOfYear += 31;
- }
- }
- # Calculate the start of the Hebrew year
- $start = self::hebrewYearStart( $hebrewYear );
- # Calculate next year's start
- if( $dayOfYear <= $start ) {
- # Day is before the start of the year - it is the previous year
- # Next year's start
- $nextStart = $start;
- # Previous year
- $year--;
- $hebrewYear--;
- # Add days since previous year's 1 September
- $dayOfYear += 365;
- if( ( $year % 400 == 0 ) || ( $year % 100 != 0 && $year % 4 == 0 ) ) {
- # Leap year
- $dayOfYear++;
- }
- # Start of the new (previous) year
- $start = self::hebrewYearStart( $hebrewYear );
- } else {
- # Next year's start
- $nextStart = self::hebrewYearStart( $hebrewYear + 1 );
- }
- # Calculate Hebrew day of year
- $hebrewDayOfYear = $dayOfYear - $start;
- # Difference between year's days
- $diff = $nextStart - $start;
- # Add 12 (or 13 for leap years) days to ignore the difference between
- # Hebrew and Gregorian year (353 at least vs. 365/6) - now the
- # difference is only about the year type
- if( ( $year % 400 == 0 ) || ( $year % 100 != 0 && $year % 4 == 0 ) ) {
- $diff += 13;
- } else {
- $diff += 12;
- }
- # Check the year pattern, and is leap year
- # 0 means an incomplete year, 1 means a regular year, 2 means a complete year
- # This is mod 30, to work on both leap years (which add 30 days of Adar I)
- # and non-leap years
- $yearPattern = $diff % 30;
- # Check if leap year
- $isLeap = $diff >= 30;
- # Calculate day in the month from number of day in the Hebrew year
- # Don't check Adar - if the day is not in Adar, we will stop before;
- # if it is in Adar, we will use it to check if it is Adar I or Adar II
- $hebrewDay = $hebrewDayOfYear;
- $hebrewMonth = 1;
- $days = 0;
- while( $hebrewMonth <= 12 ) {
- # Calculate days in this month
- if( $isLeap && $hebrewMonth == 6 ) {
- # Adar in a leap year
- if( $isLeap ) {
- # Leap year - has Adar I, with 30 days, and Adar II, with 29 days
- $days = 30;
- if( $hebrewDay <= $days ) {
- # Day in Adar I
- $hebrewMonth = 13;
- } else {
- # Subtract the days of Adar I
- $hebrewDay -= $days;
- # Try Adar II
- $days = 29;
- if( $hebrewDay <= $days ) {
- # Day in Adar II
- $hebrewMonth = 14;
- }
- }
- }
- } elseif( $hebrewMonth == 2 && $yearPattern == 2 ) {
- # Cheshvan in a complete year (otherwise as the rule below)
- $days = 30;
- } elseif( $hebrewMonth == 3 && $yearPattern == 0 ) {
- # Kislev in an incomplete year (otherwise as the rule below)
- $days = 29;
- } else {
- # Odd months have 30 days, even have 29
- $days = 30 - ( $hebrewMonth - 1 ) % 2;
- }
- if( $hebrewDay <= $days ) {
- # In the current month
- break;
- } else {
- # Subtract the days of the current month
- $hebrewDay -= $days;
- # Try in the next month
- $hebrewMonth++;
- }
- }
- return array( $hebrewYear, $hebrewMonth, $hebrewDay, $days );
- }
- /**
- * This calculates the Hebrew year start, as days since 1 September.
- * Based on Carl Friedrich Gauss algorithm for finding Easter date.
- * Used for Hebrew date.
- */
- private static function hebrewYearStart( $year ) {
- $a = intval( ( 12 * ( $year - 1 ) + 17 ) % 19 );
- $b = intval( ( $year - 1 ) % 4 );
- $m = 32.044093161144 + 1.5542417966212 * $a + $b / 4.0 - 0.0031777940220923 * ( $year - 1 );
- if( $m < 0 ) {
- $m--;
- }
- $Mar = intval( $m );
- if( $m < 0 ) {
- $m++;
- }
- $m -= $Mar;
- $c = intval( ( $Mar + 3 * ( $year - 1 ) + 5 * $b + 5 ) % 7);
- if( $c == 0 && $a > 11 && $m >= 0.89772376543210 ) {
- $Mar++;
- } else if( $c == 1 && $a > 6 && $m >= 0.63287037037037 ) {
- $Mar += 2;
- } else if( $c == 2 || $c == 4 || $c == 6 ) {
- $Mar++;
- }
- $Mar += intval( ( $year - 3761 ) / 100 ) - intval( ( $year - 3761 ) / 400 ) - 24;
- return $Mar;
- }
- /**
- * Algorithm to convert Gregorian dates to Thai solar dates.
- *
- * Link: http://en.wikipedia.org/wiki/Thai_solar_calendar
- *
- * @param $ts String: 14-character timestamp
- * @return array converted year, month, day
- */
- private static function tsToThai( $ts ) {
- $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;
- return array( $gy_thai, $gm, $gd );
- }
- /**
- * Roman number formatting up to 3000
- */
- static function romanNumeral( $num ) {
- static $table = array(
- array( '', 'I', 'II', 'III', 'IV', 'V', 'VI', 'VII', 'VIII', 'IX', 'X' ),
- array( '', 'X', 'XX', 'XXX', 'XL', 'L', 'LX', 'LXX', 'LXXX', 'XC', 'C' ),
- 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;
- }
- $s = '';
- for ( $pow10 = 1000, $i = 3; $i >= 0; $pow10 /= 10, $i-- ) {
- if ( $num >= $pow10 ) {
- $s .= $table[$i][floor($num / $pow10)];
- }
- $num = $num % $pow10;
- }
- return $s;
- }
- /**
- * Hebrew Gematria number formatting up to 9999
- */
- static function hebrewNumeral( $num ) {
- static $table = array(
- array( '', 'א', 'ב', 'ג', 'ד', 'ה', 'ו', 'ז', 'ח', 'ט', 'י' ),
- array( '', 'י', 'כ', 'ל', 'מ', 'נ', 'ס', 'ע', 'פ', 'צ', 'ק' ),
- array( '', 'ק', 'ר', 'ש', 'ת', 'תק', 'תר', 'תש', 'תת', 'תתק', 'תתר' ),
- array( '', 'א', 'ב', 'ג', 'ד', 'ה', 'ו', 'ז', 'ח', 'ט', 'י' )
- );
- $num = intval( $num );
- if ( $num > 9999 || $num <= 0 ) {
- return $num;
- }
- $s = '';
- for ( $pow10 = 1000, $i = 3; $i >= 0; $pow10 /= 10, $i-- ) {
- if ( $num >= $pow10 ) {
- if ( $num == 15 || $num == 16 ) {
- $s .= $table[0][9] . $table[0][$num - 9];
- $num = 0;
- } else {
- $s .= $table[$i][intval( ( $num / $pow10 ) )];
- if( $pow10 == 1000 ) {
- $s .= "'";
- }
- }
- }
- $num = $num % $pow10;
- }
- if( strlen( $s ) == 2 ) {
- $str = $s . "'";
- } else {
- $str = substr( $s, 0, strlen( $s ) - 2 ) . '"';
- $str .= substr( $s, strlen( $s ) - 2, 2 );
- }
- $start = substr( $str, 0, strlen( $str ) - 2 );
- $end = substr( $str, strlen( $str ) - 2 );
- switch( $end ) {
- case 'כ':
- $str = $start . 'ך';
- break;
- case 'מ':
- $str = $start . 'ם';
- break;
- case 'נ':
- $str = $start . 'ן';
- break;
- case 'פ':
- $str = $start . 'ף';
- break;
- case 'צ':
- $str = $start . 'ץ';
- break;
- }
- return $str;
- }
- /**
- * This is meant to be used by time(), date(), and timeanddate() to get
- * the date preference they're supposed to use, it should be used in
- * all children.
- *
- *<code>
- * function timeanddate([...], $format = true) {
- * $datePreference = $this->dateFormat($format);
- * [...]
- * }
- *</code>
- *
- * @param $usePrefs Mixed: if true, the user's preference is used
- * if false, the site/language default is used
- * if int/string, assumed to be a format.
- * @return string
- */
- function dateFormat( $usePrefs = true ) {
- global $wgUser;
- if( is_bool( $usePrefs ) ) {
- if( $usePrefs ) {
- $datePreference = $wgUser->getDatePreference();
- } else {
- $options = User::getDefaultOptions();
- $datePreference = (string)$options['date'];
- }
- } else {
- $datePreference = (string)$usePrefs;
- }
- // return int
- if( $datePreference == '' ) {
- return 'default';
- }
-
- return $datePreference;
- }
- /**
- * @param $ts Mixed: the time format which needs to be turned into a
- * date('YmdHis') format with wfTimestamp(TS_MW,$ts)
- * @param $adj Bool: whether to adjust the time output according to the
- * user configured offset ($timecorrection)
- * @param $format Mixed: true to use user's date format preference
- * @param $timecorrection String: the time offset as returned by
- * validateTimeZone() in Special:Preferences
- * @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;
- }
- return $this->sprintfDate( $this->dateFormats["$pref date"], $ts );
- }
- /**
- * @param $ts Mixed: the time format which needs to be turned into a
- * date('YmdHis') format with wfTimestamp(TS_MW,$ts)
- * @param $adj Bool: whether to adjust the time output according to the
- * user configured offset ($timecorrection)
- * @param $format Mixed: true to use user's date format preference
- * @param $timecorrection String: the time offset as returned by
- * validateTimeZone() in Special:Preferences
- * @return string
- */
- function time( $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 time"] ) ) {
- $pref = $this->defaultDateFormat;
- }
- return $this->sprintfDate( $this->dateFormats["$pref time"], $ts );
- }
- /**
- * @param $ts Mixed: the time format which needs to be turned into a
- * date('YmdHis') format with wfTimestamp(TS_MW,$ts)
- * @param $adj Bool: whether to adjust the time output according to the
- * user configured offset ($timecorrection)
- * @param $format Mixed: what format to return, if it's false output the
- * default one (default true)
- * @param $timecorrection String: the time offset as returned by
- * validateTimeZone() in Special:Preferences
- * @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;
- }
- return $this->sprintfDate( $this->dateFormats["$pref both"], $ts );
- }
- function getMessage( $key ) {
- $this->load();
- return isset( $this->messages[$key] ) ? $this->messages[$key] : null;
- }
- function getAllMessages() {
- $this->load();
- return $this->messages;
- }
- function iconv( $in, $out, $string ) {
- # For most languages, this is a wrapper for iconv
- return iconv( $in, $out . '//IGNORE', $string );
- }
- // callback functions for uc(), lc(), ucwords(), ucwordbreaks()
- function ucwordbreaksCallbackAscii($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
- }
- function uc( $str, $first = false ) {
- if ( function_exists( 'mb_strtoupper' ) ) {
- if ( $first ) {
- if ( self::isMultibyte( $str ) ) {
- return mb_strtoupper( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 );
- } else {
- return ucfirst( $str );
- }
- } else {
- return self::isMultibyte( $str ) ? mb_strtoupper( $str ) : strtoupper( $str );
- }
- } else {
- if ( self::isMultibyte( $str ) ) {
- list( $wikiUpperChars ) = $this->getCaseMaps();
- $x = $first ? '^' : '';
- return preg_replace_callback(
- "/$x([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)/",
- array($this,"ucCallback"),
- $str
- );
- } else {
- return $first ? ucfirst( $str ) : strtoupper( $str );
- }
- }
- }
-
- 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]);
- return $str;
- }
- else return self::lc( $str, true );
- }
- function lc( $str, $first = false ) {
- if ( function_exists( 'mb_strtolower' ) )
- if ( $first )
- if ( self::isMultibyte( $str ) )
- return mb_strtolower( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 );
- else
- return strtolower( substr( $str, 0, 1 ) ) . substr( $str, 1 );
- else
- return self::isMultibyte( $str ) ? mb_strtolower( $str ) : strtolower( $str );
- else
- if ( self::isMultibyte( $str ) ) {
- list( , $wikiLowerChars ) = self::getCaseMaps();
- $x = $first ? '^' : '';
- return preg_replace_callback(
- "/$x([A-Z]|[\\xc0-\\xff][\\x80-\\xbf]*)/",
- array($this,"lcCallback"),
- $str
- );
- } else
- return $first ? strtolower( substr( $str, 0, 1 ) ) . substr( $str, 1 ) : strtolower( $str );
- }
- function isMultibyte( $str ) {
- return (bool)preg_match( '/[\x80-\xff]/', $str );
- }
- function ucwords($str) {
- if ( self::isMultibyte( $str ) ) {
- $str = self::lc($str);
- // regexp to find first letter in each word (i.e. after each space)
- $replaceRegexp = "/^([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)| ([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)/";
- // function to use to capitalize a single char
- if ( function_exists( 'mb_strtoupper' ) )
- return preg_replace_callback(
- $replaceRegexp,
- array($this,"ucwordsCallbackMB"),
- $str
- );
- else
- return preg_replace_callback(
- $replaceRegexp,
- array($this,"ucwordsCallbackWiki"),
- $str
- );
- }
- else
- return ucwords( strtolower( $str ) );
- }
- # capitalize words at word breaks
- function ucwordbreaks($str){
- if (self::isMultibyte( $str ) ) {
- $str = self::lc($str);
- // since \b doesn't work for UTF-8, we explicitely define word break chars
- $breaks= "[ \-\(\)\}\{\.,\?!]";
- // find first letter after word break
- $replaceRegexp = "/^([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)|$breaks([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)/";
- if ( function_exists( 'mb_strtoupper' ) )
- return preg_replace_callback(
- $replaceRegexp,
- array($this,"ucwordbreaksCallbackMB"),
- $str
- );
- else
- return preg_replace_callback(
- $replaceRegexp,
- array($this,"ucwordsCallbackWiki"),
- $str
- );
- }
- else
- return preg_replace_callback(
- '/\b([\w\x80-\xff]+)\b/',
- array($this,"ucwordbreaksCallbackAscii"),
- $str );
- }
- /**
- * Return a case-folded representation of $s
- *
- * This is a representation such that caseFold($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.
- *
- * Do *not* perform any other normalisation in this function. If a caller
- * uses this function when it should be using a more general normalisation
- * function, then fix the caller.
- */
- function caseFold( $s ) {
- return $this->uc( $s );
- }
- function checkTitleEncoding( $s ) {
- if( is_array( $s ) ) {
- wfDebugDieBacktrace( 'Given array to checkTitleEncoding.' );
- }
- # Check for non-UTF-8 URLs
- $ishigh = preg_match( '/[\x80-\xff]/', $s);
- if(!$ishigh) return $s;
- $isutf8 = preg_match( '/^([\x00-\x7f]|[\xc0-\xdf][\x80-\xbf]|' .
- '[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xf7][\x80-\xbf]{3})+$/', $s );
- if( $isutf8 ) return $s;
- return $this->iconv( $this->fallback8bitEncoding(), "utf-8", $s );
- }
- function fallback8bitEncoding() {
- $this->load();
- return $this->fallback8bitEncoding;
- }
-
- /**
- * 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.
- *
- * @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 );
- }
-
- // Periods within things like hostnames and IP addresses
- // are also important -- we want a search for "example.com"
- // or "192.168.1.1" to work sanely.
- //
- // MySQL's search seems to ignore them, so you'd match on
- // "example.wikipedia.com" and "192.168.83.1" as well.
- $out = preg_replace(
- "/(\w)\.(\w|\*)/u",
- "$1u82e$2",
- $out );
-
- wfProfileOut( __METHOD__ );
- return $out;
- }
-
- /**
- * 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.
- */
- protected function stripForSearchCallback( $matches ) {
- return 'u8' . bin2hex( $matches[1] );
- }
-
- /**
- * 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;
- }
- }
- return $this->minSearchLength;
- }
- function convertForSearchResult( $termsArray ) {
- # some languages, e.g. Chinese, need to do a conversion
- # in order for search results to be displayed correctly
- return $termsArray;
- }
- /**
- * Get the first character of a string.
- *
- * @param $s string
- * @return string
- */
- function firstChar( $s ) {
- $matches = array();
- preg_match( '/^([\x00-\x7f]|[\xc0-\xdf][\x80-\xbf]|' .
- '[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xf7][\x80-\xbf]{3})/', $s, $matches);
- if ( isset( $matches[1] ) ) {
- 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) {
- return $matches[1];
- } elseif ( $code < 0xb098 ) {
- return "\xe3\x84\xb1";
- } elseif ( $code < 0xb2e4 ) {
- return "\xe3\x84\xb4";
- } elseif ( $code < 0xb77c ) {
- return "\xe3\x84\xb7";
- } elseif ( $code < 0xb9c8 ) {
- return "\xe3\x84\xb9";
- } elseif ( $code < 0xbc14 ) {
- return "\xe3\x85\x81";
- } elseif ( $code < 0xc0ac ) {
- return "\xe3\x85\x82";
- } elseif ( $code < 0xc544 ) {
- return "\xe3\x85\x85";
- } elseif ( $code < 0xc790 ) {
- return "\xe3\x85\x87";
- } elseif ( $code < 0xcc28 ) {
- return "\xe3\x85\x88";
- } elseif ( $code < 0xce74 ) {
- return "\xe3\x85\x8a";
- } elseif ( $code < 0xd0c0 ) {
- return "\xe3\x85\x8b";
- } elseif ( $code < 0xd30c ) {
- return "\xe3\x85\x8c";
- } elseif ( $code < 0xd558 ) {
- return "\xe3\x85\x8d";
- } else {
- return "\xe3\x85\x8e";
- }
- } else {
- return "";
- }
- }
- function initEncoding() {
- # Some languages may have an alternate char encoding option
- # (Esperanto X-coding, Japanese furigana conversion, etc)
- # If this language is used as the primary content language,
- # an override to the defaults can be set here on startup.
- }
- function recodeForEdit( $s ) {
- # For some languages we'll want to explicitly specify
- # which characters make it into the edit box raw
- # or are converted in some way or another.
- # Note that if wgOutputEncoding is different from
- # wgInputEncoding, this text will be further converted
- # to wgOutputEncoding.
- global $wgEditEncoding;
- if( $wgEditEncoding == '' or
- $wgEditEncoding == 'UTF-8' ) {
- return $s;
- } else {
- return $this->iconv( 'UTF-8', $wgEditEncoding, $s );
- }
- }
- function recodeInput( $s ) {
- # Take the previous into account.
- global $wgEditEncoding;
- if($wgEditEncoding != "") {
- $enc = $wgEditEncoding;
- } else {
- $enc = 'UTF-8';
- }
- if( $enc == 'UTF-8' ) {
- return $s;
- } else {
- return $this->iconv( $enc, 'UTF-8', $s );
- }
- }
- /**
- * For right-to-left language support
- *
- * @return bool
- */
- function isRTL() {
- $this->load();
- return $this->rtl;
- }
- /**
- * A hidden direction mark (LRM or RLM), depending on the language direction
- *
- * @return string
- */
- function getDirMark() {
- return $this->isRTL() ? "\xE2\x80\x8F" : "\xE2\x80\x8E";
- }
- /**
- * An arrow, depending on the language direction
- *
- * @return string
- */
- function getArrow() {
- return $this->isRTL() ? '←' : '→';
- }
- /**
- * To allow "foo[[bar]]" to extend the link over the whole word "foobar"
- *
- * @return bool
- */
- function linkPrefixExtension() {
- $this->load();
- return $this->linkPrefixExtension;
- }
- function &getMagicWords() {
- $this->load();
- return $this->magicWords;
- }
- # Fill a MagicWord object with data from here
- function getMagic( &$mw ) {
- if ( !$this->mMagicHookDone ) {
- $this->mMagicHookDone = true;
- wfRunHooks( 'LanguageGetMagic', array( &$this->mMagicExtensions, $this->getCode() ) );
- }
- if ( isset( $this->mMagicExtensions[$mw->mId] ) ) {
- $rawEntry = $this->mMagicExtensions[$mw->mId];
- } else {
- $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("Ma…
Large files files are truncated, but you can click here to view the full file