X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguage.php;h=74a7fe0dbba221f5419857ec8698750d75b74cb6;hb=f0d75be7d9f533e5099c7ee3d801faad7e05b20f;hp=0836cf60d89fcdb8d317d8a01709affe3a9652e5;hpb=6c3adddb6b789fb40a1fde1ea8198128785b36a9;p=lhc%2Fweb%2Fwiklou.git
diff --git a/languages/Language.php b/languages/Language.php
index 0836cf60d8..74a7fe0dbb 100644
--- a/languages/Language.php
+++ b/languages/Language.php
@@ -6,25 +6,25 @@
* @ingroup Language
*/
-if( !defined( 'MEDIAWIKI' ) ) {
+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' ) ;
+require_once( dirname( __FILE__ ) . '/Names.php' );
global $wgInputEncoding, $wgOutputEncoding;
/**
* These are always UTF-8, they exist only for backwards compatibility
*/
-$wgInputEncoding = "UTF-8";
-$wgOutputEncoding = "UTF-8";
+$wgInputEncoding = 'UTF-8';
+$wgOutputEncoding = 'UTF-8';
-if( function_exists( 'mb_strtoupper' ) ) {
- mb_internal_encoding('UTF-8');
+if ( function_exists( 'mb_strtoupper' ) ) {
+ mb_internal_encoding( 'UTF-8' );
}
/**
@@ -34,19 +34,20 @@ 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 FakeConverter( $langobj ) { $this->mLang = $langobj; }
+ function autoConvertToAllVariants( $text ) { return $text; }
+ function convert( $t ) { return $t; }
+ function convertTitle( $t ) { return $t->getPrefixedText(); }
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; }
+ 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; }
+ function convertCategoryKey( $key ) { return $key; }
+ function convertLinkToAllVariants( $text ) { return array( $this->mLang->getCode() => $text ); }
+ function armourMath( $text ) { return $text; }
}
/**
@@ -59,9 +60,13 @@ class Language {
var $mNamespaceIds, $namespaceNames, $namespaceAliases;
var $dateFormatStrings = array();
- var $minSearchLength;
var $mExtendedSpecialPageAliases;
+ /**
+ * ReplacementArray object caches
+ */
+ var $transformData = array();
+
static public $dataCache;
static public $mLangObjCache = array();
@@ -111,7 +116,7 @@ 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',
@@ -124,7 +129,7 @@ class Language {
*/
static function factory( $code ) {
if ( !isset( self::$mLangObjCache[$code] ) ) {
- if( count( self::$mLangObjCache ) > 10 ) {
+ if ( count( self::$mLangObjCache ) > 10 ) {
// Don't keep a billion objects around, that's stupid.
self::$mLangObjCache = array();
}
@@ -145,18 +150,18 @@ class Language {
$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/$class.deps.php");
+ include_once( "$IP/languages/classes/$class.deps.php" );
}
if ( file_exists( "$IP/languages/classes/$class.php" ) ) {
- include_once("$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 ) ) {
+ if ( !class_exists( $class ) ) {
$fallback = Language::getFallbackFor( $code );
++$recursionLevel;
$lang = Language::newFromCode( $fallback );
@@ -181,7 +186,7 @@ class Language {
}
function __construct() {
- $this->mConverter = new FakeConverter($this);
+ $this->mConverter = new FakeConverter( $this );
// Set the code to the name of the descendant
if ( get_class( $this ) == 'Language' ) {
$this->mCode = 'en';
@@ -204,7 +209,7 @@ class Language {
* Hook which will be called if this is the content language.
* Descendants can use this to register hook functions or modify globals
*/
- function initContLang() {}
+ function initContLang() { }
/**
* @deprecated Use User::getDefaultOptions()
@@ -237,7 +242,7 @@ class Language {
function getNamespaces() {
if ( is_null( $this->namespaceNames ) ) {
global $wgExtraNamespaces, $wgMetaNamespace, $wgMetaNamespaceTalk;
-
+
$this->namespaceNames = self::$dataCache->getItem( $this->mCode, 'namespaceNames' );
if ( $wgExtraNamespaces ) {
$this->namespaceNames = $wgExtraNamespaces + $this->namespaceNames;
@@ -251,7 +256,7 @@ class Language {
$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 );
@@ -269,8 +274,8 @@ class Language {
*/
function getFormattedNamespaces() {
$ns = $this->getNamespaces();
- foreach($ns as $k => $v) {
- $ns[$k] = strtr($v, '_', ' ');
+ foreach ( $ns as $k => $v ) {
+ $ns[$k] = strtr( $v, '_', ' ' );
}
return $ns;
}
@@ -299,7 +304,7 @@ class Language {
*/
function getFormattedNsText( $index ) {
$ns = $this->getNsText( $index );
- return strtr($ns, '_', ' ');
+ return strtr( $ns, '_', ' ' );
}
/**
@@ -311,7 +316,7 @@ class Language {
* @return mixed An integer if $text is a valid value otherwise false
*/
function getLocalNsIndex( $text ) {
- $lctext = $this->lc($text);
+ $lctext = $this->lc( $text );
$ids = $this->getNamespaceIds();
return isset( $ids[$lctext] ) ? $ids[$lctext] : false;
}
@@ -339,19 +344,19 @@ class Language {
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
+ # 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;
+ $this->mNamespaceIds[$this->lc( $name )] = $index;
}
foreach ( $this->getNamespaceAliases() as $name => $index ) {
- $this->mNamespaceIds[$this->lc($name)] = $index;
+ $this->mNamespaceIds[$this->lc( $name )] = $index;
}
if ( $wgNamespaceAliases ) {
foreach ( $wgNamespaceAliases as $name => $index ) {
- $this->mNamespaceIds[$this->lc($name)] = $index;
+ $this->mNamespaceIds[$this->lc( $name )] = $index;
}
}
}
@@ -367,7 +372,7 @@ class Language {
* @return mixed An integer if $text is a valid value otherwise false
*/
function getNsIndex( $text ) {
- $lctext = $this->lc($text);
+ $lctext = $this->lc( $text );
if ( ( $ns = MWNamespace::getCanonicalIndex( $lctext ) ) !== null ) {
return $ns;
}
@@ -410,7 +415,7 @@ class Language {
function getDatePreferences() {
return self::$dataCache->getItem( $this->mCode, 'datePreferences' );
}
-
+
function getDateFormats() {
return self::$dataCache->getItem( $this->mCode, 'dateFormats' );
}
@@ -455,17 +460,14 @@ class Language {
if ( !$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];
- }
+ while ( false !== ( $file = readdir( $dir ) ) ) {
+ $code = self::getCodeFromFileName( $file, 'Messages' );
+ if ( $code && isset( $allNames[$code] ) ) {
+ $names[$code] = $allNames[$code];
}
}
closedir( $dir );
@@ -491,41 +493,41 @@ class Language {
}
function getMonthName( $key ) {
- return $this->getMessageFromDB( self::$mMonthMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mMonthMsgs[$key - 1] );
}
function getMonthNameGen( $key ) {
- return $this->getMessageFromDB( self::$mMonthGenMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mMonthGenMsgs[$key - 1] );
}
function getMonthAbbreviation( $key ) {
- return $this->getMessageFromDB( self::$mMonthAbbrevMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mMonthAbbrevMsgs[$key - 1] );
}
function getWeekdayName( $key ) {
- return $this->getMessageFromDB( self::$mWeekdayMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mWeekdayMsgs[$key - 1] );
}
function getWeekdayAbbreviation( $key ) {
- return $this->getMessageFromDB( self::$mWeekdayAbbrevMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mWeekdayAbbrevMsgs[$key - 1] );
}
function getIranianCalendarMonthName( $key ) {
- return $this->getMessageFromDB( self::$mIranianCalendarMonthMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mIranianCalendarMonthMsgs[$key - 1] );
}
function getHebrewCalendarMonthName( $key ) {
- return $this->getMessageFromDB( self::$mHebrewCalendarMonthMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mHebrewCalendarMonthMsgs[$key - 1] );
}
function getHebrewCalendarMonthNameGen( $key ) {
- return $this->getMessageFromDB( self::$mHebrewCalendarMonthGenMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mHebrewCalendarMonthGenMsgs[$key - 1] );
}
-
+
function getHijriCalendarMonthName( $key ) {
- return $this->getMessageFromDB( self::$mHijriCalendarMonthMsgs[$key-1] );
+ return $this->getMessageFromDB( self::$mHijriCalendarMonthMsgs[$key - 1] );
}
-
+
/**
* Used by date() and time() to adjust the time output.
*
@@ -556,49 +558,55 @@ class Language {
$minDiff = 0;
if ( $data[0] == 'System' || $tz == '' ) {
- #Â Global offset in minutes.
- if( isset($wgLocalTZoffset) ) $minDiff = $wgLocalTZoffset;
+ # Â 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 ) {
+ 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;
+ if ( $data[0] < 0 ) {
+ $minDiff = -$minDiff;
+ }
} else {
$minDiff = intval( $data[0] ) * 60;
}
}
# No difference ? Return time unchanged
- if ( 0 == $minDiff ) return $ts;
+ 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
+ # 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, 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
-
+ (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 dDjlNwzWFmMntLoYyaAgGhHiscrU. See the
+ * 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":
@@ -646,7 +654,7 @@ 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
@@ -712,51 +720,73 @@ class Language {
$num = intval( substr( $ts, 6, 2 ) );
break;
case 'xij':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
+ if ( !$iranian ) {
+ $iranian = self::tsToIranian( $ts );
+ }
$num = $iranian[2];
break;
case 'xmj':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
+ if ( !$hijri ) {
+ $hijri = self::tsToHijri( $ts );
+ }
$num = $hijri[2];
break;
case 'xjj':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
+ if ( !$hebrew ) {
+ $hebrew = self::tsToHebrew( $ts );
+ }
$num = $hebrew[2];
break;
case 'l':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$s .= $this->getWeekdayName( gmdate( 'w', $unix ) + 1 );
break;
case 'N':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$w = gmdate( 'w', $unix );
$num = $w ? $w : 7;
break;
case 'w':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$num = gmdate( 'w', $unix );
break;
case 'z':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$num = gmdate( 'z', $unix );
break;
case 'W':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$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( $ts );
+ if ( !$iranian ) {
+ $iranian = self::tsToIranian( $ts );
+ }
$s .= $this->getIranianCalendarMonthName( $iranian[1] );
break;
case 'xmF':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
+ if ( !$hijri ) {
+ $hijri = self::tsToHijri( $ts );
+ }
$s .= $this->getHijriCalendarMonthName( $hijri[1] );
break;
case 'xjF':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
+ if ( !$hebrew ) {
+ $hebrew = self::tsToHebrew( $ts );
+ }
$s .= $this->getHebrewCalendarMonthName( $hebrew[1] );
break;
case 'm':
@@ -769,64 +799,91 @@ class Language {
$num = intval( substr( $ts, 4, 2 ) );
break;
case 'xin':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
+ if ( !$iranian ) {
+ $iranian = self::tsToIranian( $ts );
+ }
$num = $iranian[1];
break;
case 'xmn':
- if ( !$hijri ) $hijri = self::tsToHijri ( $ts );
+ if ( !$hijri ) {
+ $hijri = self::tsToHijri ( $ts );
+ }
$num = $hijri[1];
break;
case 'xjn':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
+ if ( !$hebrew ) {
+ $hebrew = self::tsToHebrew( $ts );
+ }
$num = $hebrew[1];
break;
case 't':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$num = gmdate( 't', $unix );
break;
case 'xjt':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
+ if ( !$hebrew ) {
+ $hebrew = self::tsToHebrew( $ts );
+ }
$num = $hebrew[3];
break;
case 'L':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$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, $ts );
- if ( version_compare(PHP_VERSION, '5.1.0') === 1 )
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
+ if ( version_compare( PHP_VERSION, '5.1.0' ) === 1 ) {
$num = date( 'o', $unix );
- else
+ } else {
$s .= 'o';
+ }
break;
case 'Y':
$num = substr( $ts, 0, 4 );
break;
case 'xiY':
- if ( !$iranian ) $iranian = self::tsToIranian( $ts );
+ if ( !$iranian ) {
+ $iranian = self::tsToIranian( $ts );
+ }
$num = $iranian[0];
break;
case 'xmY':
- if ( !$hijri ) $hijri = self::tsToHijri( $ts );
+ if ( !$hijri ) {
+ $hijri = self::tsToHijri( $ts );
+ }
$num = $hijri[0];
break;
case 'xjY':
- if ( !$hebrew ) $hebrew = self::tsToHebrew( $ts );
+ if ( !$hebrew ) {
+ $hebrew = self::tsToHebrew( $ts );
+ }
$num = $hebrew[0];
break;
case 'xkY':
- if ( !$thai ) $thai = self::tsToYear( $ts, 'thai' );
+ if ( !$thai ) {
+ $thai = self::tsToYear( $ts, 'thai' );
+ }
$num = $thai[0];
break;
case 'xoY':
- if ( !$minguo ) $minguo = self::tsToYear( $ts, 'minguo' );
+ if ( !$minguo ) {
+ $minguo = self::tsToYear( $ts, 'minguo' );
+ }
$num = $minguo[0];
break;
case 'xtY':
- if ( !$tenno ) $tenno = self::tsToYear( $ts, 'tenno' );
+ if ( !$tenno ) {
+ $tenno = self::tsToYear( $ts, 'tenno' );
+ }
$num = $tenno[0];
break;
case 'y':
@@ -848,7 +905,7 @@ 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;
@@ -859,15 +916,21 @@ class Language {
$num = substr( $ts, 12, 2 );
break;
case 'c':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$s .= gmdate( 'c', $unix );
break;
case 'r':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$s .= gmdate( 'r', $unix );
break;
case 'U':
- if ( !$unix ) $unix = wfTimestamp( TS_UNIX, $ts );
+ if ( !$unix ) {
+ $unix = wfTimestamp( TS_UNIX, $ts );
+ }
$num = $unix;
break;
case '\\':
@@ -904,7 +967,7 @@ class Language {
} elseif ( $roman ) {
$s .= self::romanNumeral( $num );
$roman = false;
- } elseif( $hebrewNum ) {
+ } elseif ( $hebrewNum ) {
$s .= self::hebrewNumeral( $num );
$hebrewNum = false;
} else {
@@ -919,11 +982,11 @@ 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 ) {
@@ -932,47 +995,48 @@ class Language {
$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);
+ $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++ ) {
+ 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)))) {
+ 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);
+ $jNp = floor( $jDayNo / 12053 );
$jDayNo %= 12053;
- $jy = 979 + 33*$jNp + 4*floor($jDayNo/1461);
+ $jy = 979 + 33 * $jNp + 4 * floor( $jDayNo / 1461 );
$jDayNo %= 1461;
if ( $jDayNo >= 366 ) {
- $jy += floor(($jDayNo-1)/365);
- $jDayNo = floor(($jDayNo-1)%365);
+ $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;
+ $jm = $i + 1;
+ $jd = $jDayNo + 1;
- return array($jy, $jm, $jd);
+ return array( $jy, $jm, $jd );
}
+
/**
* Converting Gregorian dates to Hijri dates.
*
@@ -980,39 +1044,40 @@ class Language {
*
* @link http://phpnuke.org/modules.php?name=News&file=article&sid=8234&mode=thread&order=0&thold=0
*/
- private static function tsToHijri ( $ts ) {
+ 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;
-
+ $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 ) + $zd + 1729777;
+ }
- if (($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;
+ $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);
+ return array( $zy, $zm, $zd );
}
/**
@@ -1037,7 +1102,7 @@ class Language {
# Month number when September = 1, August = 12
$month += 4;
- if( $month > 12 ) {
+ if ( $month > 12 ) {
# Next year
$month -= 12;
$year++;
@@ -1046,15 +1111,15 @@ class Language {
# Calculate day of year from 1 September
$dayOfYear = $day;
- for( $i = 1; $i < $month; $i++ ) {
- if( $i == 6 ) {
+ 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 ) ) {
+ if ( $year % 400 == 0 || ( $year % 4 == 0 && $year % 100 > 0 ) ) {
$dayOfYear++;
}
- } elseif( $i == 8 || $i == 10 || $i == 1 || $i == 3 ) {
+ } elseif ( $i == 8 || $i == 10 || $i == 1 || $i == 3 ) {
$dayOfYear += 30;
} else {
$dayOfYear += 31;
@@ -1065,7 +1130,7 @@ class Language {
$start = self::hebrewYearStart( $hebrewYear );
# Calculate next year's start
- if( $dayOfYear <= $start ) {
+ if ( $dayOfYear <= $start ) {
# Day is before the start of the year - it is the previous year
# Next year's start
$nextStart = $start;
@@ -1074,7 +1139,7 @@ class Language {
$hebrewYear--;
# Add days since previous year's 1 September
$dayOfYear += 365;
- if( ( $year % 400 == 0 ) || ( $year % 100 != 0 && $year % 4 == 0 ) ) {
+ if ( ( $year % 400 == 0 ) || ( $year % 100 != 0 && $year % 4 == 0 ) ) {
# Leap year
$dayOfYear++;
}
@@ -1093,7 +1158,7 @@ class Language {
# 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 ) ) {
+ if ( ( $year % 400 == 0 ) || ( $year % 100 != 0 && $year % 4 == 0 ) ) {
$diff += 13;
} else {
$diff += 12;
@@ -1113,14 +1178,14 @@ class Language {
$hebrewDay = $hebrewDayOfYear;
$hebrewMonth = 1;
$days = 0;
- while( $hebrewMonth <= 12 ) {
+ while ( $hebrewMonth <= 12 ) {
# Calculate days in this month
- if( $isLeap && $hebrewMonth == 6 ) {
+ if ( $isLeap && $hebrewMonth == 6 ) {
# Adar in a leap year
- if( $isLeap ) {
+ if ( $isLeap ) {
# Leap year - has Adar I, with 30 days, and Adar II, with 29 days
$days = 30;
- if( $hebrewDay <= $days ) {
+ if ( $hebrewDay <= $days ) {
# Day in Adar I
$hebrewMonth = 13;
} else {
@@ -1128,23 +1193,23 @@ class Language {
$hebrewDay -= $days;
# Try Adar II
$days = 29;
- if( $hebrewDay <= $days ) {
+ if ( $hebrewDay <= $days ) {
# Day in Adar II
$hebrewMonth = 14;
}
}
}
- } elseif( $hebrewMonth == 2 && $yearPattern == 2 ) {
+ } elseif ( $hebrewMonth == 2 && $yearPattern == 2 ) {
# Cheshvan in a complete year (otherwise as the rule below)
$days = 30;
- } elseif( $hebrewMonth == 3 && $yearPattern == 0 ) {
+ } 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 ) {
+ if ( $hebrewDay <= $days ) {
# In the current month
break;
} else {
@@ -1167,21 +1232,21 @@ class Language {
$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 ) {
+ if ( $m < 0 ) {
$m--;
}
$Mar = intval( $m );
- if( $m < 0 ) {
+ if ( $m < 0 ) {
$m++;
}
$m -= $Mar;
- $c = intval( ( $Mar + 3 * ( $year - 1 ) + 5 * $b + 5 ) % 7);
- if( $c == 0 && $a > 11 && $m >= 0.89772376543210 ) {
+ $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 ) {
+ } else if ( $c == 1 && $a > 6 && $m >= 0.63287037037037 ) {
$Mar += 2;
- } else if( $c == 2 || $c == 4 || $c == 6 ) {
+ } else if ( $c == 2 || $c == 4 || $c == 6 ) {
$Mar++;
}
@@ -1197,57 +1262,74 @@ class Language {
* http://en.wikipedia.org/wiki/Minguo_calendar
* http://en.wikipedia.org/wiki/Japanese_era_name
*
- * @param $ts String: 14-character timestamp, calender name
- * @return array converted year, month, day
+ * @param $ts String: 14-character timestamp
+ * @param $cName String: calender name
+ * @return Array: converted year, month, day
*/
private static function tsToYear( $ts, $cName ) {
$gy = substr( $ts, 0, 4 );
$gm = substr( $ts, 4, 2 );
$gd = substr( $ts, 6, 2 );
- if (!strcmp($cName,'thai')) {
+ 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')) {
+ } 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')) {
+ } else if ( !strcmp( $cName, 'tenno' ) ) {
# NengÅ dates up to Meiji period
# Deduct years from the Gregorian calendar
# depending on the nengo periods
# Months and days are identical
- if (($gy < 1912) || (($gy == 1912) && ($gm < 7)) || (($gy == 1912) && ($gm == 7) && ($gd < 31))) {
+ 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)
+ if ( $gy_gannen == 1 ) {
$gy_offset = 'å
';
- $gy_offset = 'ææ²»'.$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))) {
+ }
+ $gy_offset = 'ææ²»' . $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 ) )
+ )
+ {
# TaishÅ period
$gy_gannen = $gy - 1912 + 1;
$gy_offset = $gy_gannen;
- if ($gy_gannen == 1)
+ if ( $gy_gannen == 1 ) {
$gy_offset = 'å
';
- $gy_offset = '大æ£'.$gy_offset;
- } else if ((($gy == 1926) && ($gm == 12) && ($gd >= 26)) || (($gy > 1926) && ($gy < 1989)) || (($gy == 1989) && ($gm == 1) && ($gd < 8))) {
+ }
+ $gy_offset = '大æ£' . $gy_offset;
+ } else if (
+ ( ( $gy == 1926 ) && ( $gm == 12 ) && ( $gd >= 26 ) ) ||
+ ( ( $gy > 1926 ) && ( $gy < 1989 ) ) ||
+ ( ( $gy == 1989 ) && ( $gm == 1 ) && ( $gd < 8 ) )
+ )
+ {
# ShÅwa period
$gy_gannen = $gy - 1926 + 1;
$gy_offset = $gy_gannen;
- if ($gy_gannen == 1)
+ if ( $gy_gannen == 1 ) {
$gy_offset = 'å
';
- $gy_offset = 'æå'.$gy_offset;
+ }
+ $gy_offset = 'æå' . $gy_offset;
} else {
# Heisei period
$gy_gannen = $gy - 1989 + 1;
$gy_offset = $gy_gannen;
- if ($gy_gannen == 1)
+ if ( $gy_gannen == 1 ) {
$gy_offset = 'å
';
- $gy_offset = 'å¹³æ'.$gy_offset;
+ }
+ $gy_offset = 'å¹³æ' . $gy_offset;
}
} else {
$gy_offset = $gy;
@@ -1266,7 +1348,7 @@ 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;
@@ -1275,7 +1357,7 @@ class Language {
$s = '';
for ( $pow10 = 1000, $i = 3; $i >= 0; $pow10 /= 10, $i-- ) {
if ( $num >= $pow10 ) {
- $s .= $table[$i][floor($num / $pow10)];
+ $s .= $table[$i][floor( $num / $pow10 )];
}
$num = $num % $pow10;
}
@@ -1306,14 +1388,14 @@ class Language {
$num = 0;
} else {
$s .= $table[$i][intval( ( $num / $pow10 ) )];
- if( $pow10 == 1000 ) {
+ if ( $pow10 == 1000 ) {
$s .= "'";
}
}
}
$num = $num % $pow10;
}
- if( strlen( $s ) == 2 ) {
+ if ( strlen( $s ) == 2 ) {
$str = $s . "'";
} else {
$str = substr( $s, 0, strlen( $s ) - 2 ) . '"';
@@ -1361,22 +1443,21 @@ class Language {
function dateFormat( $usePrefs = true ) {
global $wgUser;
- if( is_bool( $usePrefs ) ) {
- if( $usePrefs ) {
+ if ( is_bool( $usePrefs ) ) {
+ if ( $usePrefs ) {
$datePreference = $wgUser->getDatePreference();
} else {
- $options = User::getDefaultOptions();
- $datePreference = (string)$options['date'];
+ $datePreference = (string)User::getDefaultOption( 'date' );
}
} else {
$datePreference = (string)$usePrefs;
}
// return int
- if( $datePreference == '' ) {
+ if ( $datePreference == '' ) {
return 'default';
}
-
+
return $datePreference;
}
@@ -1413,8 +1494,8 @@ class Language {
* @return string
*/
function date( $ts, $adj = false, $format = true, $timecorrection = false ) {
- if ( $adj ) {
- $ts = $this->userAdjust( $ts, $timecorrection );
+ if ( $adj ) {
+ $ts = $this->userAdjust( $ts, $timecorrection );
}
$df = $this->getDateFormatString( 'date', $this->dateFormat( $format ) );
return $this->sprintfDate( $df, $ts );
@@ -1431,8 +1512,8 @@ class Language {
* @return string
*/
function time( $ts, $adj = false, $format = true, $timecorrection = false ) {
- if ( $adj ) {
- $ts = $this->userAdjust( $ts, $timecorrection );
+ if ( $adj ) {
+ $ts = $this->userAdjust( $ts, $timecorrection );
}
$df = $this->getDateFormatString( 'time', $this->dateFormat( $format ) );
return $this->sprintfDate( $df, $ts );
@@ -1449,10 +1530,10 @@ class Language {
* validateTimeZone() in Special:Preferences
* @return string
*/
- function timeanddate( $ts, $adj = false, $format = true, $timecorrection = false) {
+ function timeanddate( $ts, $adj = false, $format = true, $timecorrection = false ) {
$ts = wfTimestamp( TS_MW, $ts );
- if ( $adj ) {
- $ts = $this->userAdjust( $ts, $timecorrection );
+ if ( $adj ) {
+ $ts = $this->userAdjust( $ts, $timecorrection );
}
$df = $this->getDateFormatString( 'both', $this->dateFormat( $format ) );
return $this->sprintfDate( $df, $ts );
@@ -1481,57 +1562,63 @@ class Language {
}
// callback functions for uc(), lc(), ucwords(), ucwordbreaks()
- function ucwordbreaksCallbackAscii($matches){
- return $this->ucfirst($matches[1]);
+ function ucwordbreaksCallbackAscii( $matches ) {
+ return $this->ucfirst( $matches[1] );
}
-
- function ucwordbreaksCallbackMB($matches){
- return mb_strtoupper($matches[0]);
+
+ function ucwordbreaksCallbackMB( $matches ) {
+ return mb_strtoupper( $matches[0] );
}
-
- function ucCallback($matches){
+
+ function ucCallback( $matches ) {
list( $wikiUpperChars ) = self::getCaseMaps();
return strtr( $matches[1], $wikiUpperChars );
}
-
- function lcCallback($matches){
+
+ function lcCallback( $matches ) {
list( , $wikiLowerChars ) = self::getCaseMaps();
return strtr( $matches[1], $wikiLowerChars );
}
-
- function ucwordsCallbackMB($matches){
- return mb_strtoupper($matches[0]);
+
+ function ucwordsCallbackMB( $matches ) {
+ return mb_strtoupper( $matches[0] );
}
-
- function ucwordsCallbackWiki($matches){
+
+ 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 $this->uc( $str, true );
+ }
}
function uc( $str, $first = false ) {
if ( function_exists( 'mb_strtoupper' ) ) {
if ( $first ) {
- if ( self::isMultibyte( $str ) ) {
+ if ( $this->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 );
+ return $this->isMultibyte( $str ) ? mb_strtoupper( $str ) : strtoupper( $str );
}
} else {
- if ( self::isMultibyte( $str ) ) {
+ if ( $this->isMultibyte( $str ) ) {
list( $wikiUpperChars ) = $this->getCaseMaps();
$x = $first ? '^' : '';
return preg_replace_callback(
"/$x([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)/",
- array($this,"ucCallback"),
+ array( $this, 'ucCallback' ),
$str
);
} else {
@@ -1539,103 +1626,114 @@ 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 $this->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 ) {
- if ( function_exists( 'mb_strtolower' ) )
- if ( $first )
- if ( self::isMultibyte( $str ) )
+ if ( function_exists( 'mb_strtolower' ) ) {
+ if ( $first ) {
+ if ( $this->isMultibyte( $str ) ) {
return mb_strtolower( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 );
- else
+ } 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 ) ) {
+ }
+ } else {
+ return $this->isMultibyte( $str ) ? mb_strtolower( $str ) : strtolower( $str );
+ }
+ } else {
+ if ( $this->isMultibyte( $str ) ) {
list( , $wikiLowerChars ) = self::getCaseMaps();
$x = $first ? '^' : '';
return preg_replace_callback(
"/$x([A-Z]|[\\xc0-\\xff][\\x80-\\xbf]*)/",
- array($this,"lcCallback"),
+ array( $this, 'lcCallback' ),
$str
);
- } else
+ } 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);
+ function ucwords( $str ) {
+ if ( $this->isMultibyte( $str ) ) {
+ $str = $this->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' ) )
+ if ( function_exists( 'mb_strtoupper' ) ) {
return preg_replace_callback(
$replaceRegexp,
- array($this,"ucwordsCallbackMB"),
+ array( $this, 'ucwordsCallbackMB' ),
$str
);
- else
+ } else {
return preg_replace_callback(
$replaceRegexp,
- array($this,"ucwordsCallbackWiki"),
+ array( $this, 'ucwordsCallbackWiki' ),
$str
);
- }
- else
+ }
+ } else {
return ucwords( strtolower( $str ) );
+ }
}
- # capitalize words at word breaks
- function ucwordbreaks($str){
- if (self::isMultibyte( $str ) ) {
- $str = self::lc($str);
+ # capitalize words at word breaks
+ function ucwordbreaks( $str ) {
+ if ( $this->isMultibyte( $str ) ) {
+ $str = $this->lc( $str );
// since \b doesn't work for UTF-8, we explicitely define word break chars
- $breaks= "[ \-\(\)\}\{\.,\?!]";
+ $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' ) )
+ if ( function_exists( 'mb_strtoupper' ) ) {
return preg_replace_callback(
$replaceRegexp,
- array($this,"ucwordbreaksCallbackMB"),
+ array( $this, 'ucwordbreaksCallbackMB' ),
$str
);
- else
+ } else {
return preg_replace_callback(
$replaceRegexp,
- array($this,"ucwordsCallbackWiki"),
+ array( $this, 'ucwordsCallbackWiki' ),
$str
);
- }
- else
+ }
+ } else {
return preg_replace_callback(
- '/\b([\w\x80-\xff]+)\b/',
- array($this,"ucwordbreaksCallbackAscii"),
- $str );
+ '/\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 $s1
+ * This is a representation such that caseFold($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.
*
@@ -1648,24 +1746,28 @@ class Language {
}
function checkTitleEncoding( $s ) {
- if( is_array( $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;
+ $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;
+ if ( $isutf8 ) {
+ return $s;
+ }
- return $this->iconv( $this->fallback8bitEncoding(), "utf-8", $s );
+ return $this->iconv( $this->fallback8bitEncoding(), 'utf-8', $s );
}
function fallback8bitEncoding() {
return self::$dataCache->getItem( $this->mCode, 'fallback8bitEncoding' );
}
-
+
/**
* Most writing systems use whitespace to break up words.
* Some languages such as Chinese don't conventionally do this,
@@ -1675,86 +1777,52 @@ class Language {
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 );
- }
-
- // 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;
+ 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...
+ * convert double-width roman characters to single-width.
+ * range: ff00-ff5f ~= 0020-007f
*/
- protected function minSearchLength() {
- if( is_null( $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;
- }
+ protected static function convertDoubleWidth( $string ) {
+ static $full = null;
+ static $half = null;
+
+ if ( $full === null ) {
+ $fullWidth = "ï¼ï¼ï¼ï¼ï¼ï¼ï¼ï¼ï¼ï¼ï¼¡ï¼¢ï¼£ï¼¤ï¼¥ï¼¦ï¼§ï¼¨ï¼©ï¼ªï¼«ï¼¬ï¼ï¼®ï¼¯ï¼°ï¼±ï¼²ï¼³ï¼´ï¼µï¼¶ï¼·ï¼¸ï¼¹ï¼ºï½ï½ï½ï½ï½
ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½ï½";
+ $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 ) {
@@ -1764,24 +1832,28 @@ class Language {
}
/**
- * Get the first character of a string.
+ * 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);
+ 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) {
+ if ( $code < 0xac00 || 0xd7a4 <= $code ) {
return $matches[1];
} elseif ( $code < 0xb098 ) {
return "\xe3\x84\xb1";
@@ -1813,7 +1885,7 @@ class Language {
return "\xe3\x85\x8e";
}
} else {
- return "";
+ return '';
}
}
@@ -1832,8 +1904,7 @@ class Language {
# wgInputEncoding, this text will be further converted
# to wgOutputEncoding.
global $wgEditEncoding;
- if( $wgEditEncoding == '' or
- $wgEditEncoding == 'UTF-8' ) {
+ if ( $wgEditEncoding == '' || $wgEditEncoding == 'UTF-8' ) {
return $s;
} else {
return $this->iconv( 'UTF-8', $wgEditEncoding, $s );
@@ -1843,27 +1914,96 @@ class Language {
function recodeInput( $s ) {
# Take the previous into account.
global $wgEditEncoding;
- if($wgEditEncoding != "") {
+ if ( $wgEditEncoding != '' ) {
$enc = $wgEditEncoding;
} else {
$enc = 'UTF-8';
}
- if( $enc == 'UTF-8' ) {
+ if ( $enc == 'UTF-8' ) {
return $s;
} else {
return $this->iconv( $enc, 'UTF-8', $s );
}
}
+ /**
+ * 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 ) {
+ global $wgAllUnicodeFixes;
+ $s = UtfNormal::cleanUp( $s );
+ if ( $wgAllUnicodeFixes ) {
+ $s = $this->transformUsingPairFile( 'normalize-ar.ser', $s );
+ $s = $this->transformUsingPairFile( 'normalize-ml.ser', $s );
+ }
+
+ return $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( $string );
+ }
+
/**
* For right-to-left language support
*
* @return bool
*/
- function isRTL() {
+ function isRTL() {
return self::$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';
+ }
+
/**
* A hidden direction mark (LRM or RLM), depending on the language direction
*
@@ -1903,7 +2043,9 @@ class Language {
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];
@@ -1916,7 +2058,7 @@ class Language {
}
}
- if( !is_array( $rawEntry ) ) {
+ if ( !is_array( $rawEntry ) ) {
error_log( "\"$rawEntry\" is not a valid magic thingie for \"$mw->mId\"" );
} else {
$mw->mCaseSensitive = $rawEntry[0];
@@ -1953,7 +2095,7 @@ class Language {
// Cache aliases because it may be slow to load them
if ( is_null( $this->mExtendedSpecialPageAliases ) ) {
// Initialise array
- $this->mExtendedSpecialPageAliases =
+ $this->mExtendedSpecialPageAliases =
self::$dataCache->getItem( $this->mCode, 'specialPageAliases' );
wfRunHooks( 'LanguageGetSpecialPageAliases',
array( &$this->mExtendedSpecialPageAliases, $this->getCode() ) );
@@ -1998,15 +2140,19 @@ class Language {
*/
function formatNum( $number, $nocommafy = false ) {
global $wgTranslateNumerals;
- if (!$nocommafy) {
- $number = $this->commafy($number);
+ if ( !$nocommafy ) {
+ $number = $this->commafy( $number );
$s = $this->separatorTransformTable();
- if ($s) { $number = strtr($number, $s); }
+ if ( $s ) {
+ $number = strtr( $number, $s );
+ }
}
- if ($wgTranslateNumerals) {
+ if ( $wgTranslateNumerals ) {
$s = $this->digitTransformTable();
- if ($s) { $number = strtr($number, $s); }
+ if ( $s ) {
+ $number = strtr( $number, $s );
+ }
}
return $number;
@@ -2014,12 +2160,16 @@ class Language {
function parseFormattedNumber( $number ) {
$s = $this->digitTransformTable();
- if ($s) { $number = strtr($number, array_flip($s)); }
+ if ( $s ) {
+ $number = strtr( $number, array_flip( $s ) );
+ }
$s = $this->separatorTransformTable();
- if ($s) { $number = strtr($number, array_flip($s)); }
+ if ( $s ) {
+ $number = strtr( $number, array_flip( $s ) );
+ }
- $number = strtr( $number, array (',' => '') );
+ $number = strtr( $number, array( ',' => '' ) );
return $number;
}
@@ -2029,8 +2179,8 @@ class Language {
* @param $_ mixed
* @return string
*/
- function commafy($_) {
- return strrev((string)preg_replace('/(\d{3})(?=\d)(?!\d*\.)/','$1,',strrev($_)));
+ function commafy( $_ ) {
+ return strrev( (string)preg_replace( '/(\d{3})(?=\d)(?!\d*\.)/', '$1,', strrev( $_ ) ) );
}
function digitTransformTable() {
@@ -2041,7 +2191,6 @@ class Language {
return self::$dataCache->getItem( $this->mCode, 'separatorTransformTable' );
}
-
/**
* Take a list of strings and build a locale-friendly comma-separated
* list, using the local comma-separator message.
@@ -2053,14 +2202,13 @@ class Language {
function listToText( $l ) {
$s = '';
$m = count( $l ) - 1;
- if( $m == 1 ) {
+ if ( $m == 1 ) {
return $l[0] . $this->getMessageFromDB( 'and' ) . $this->getMessageFromDB( 'word-separator' ) . $l[1];
- }
- else {
+ } else {
for ( $i = $m; $i >= 0; $i-- ) {
if ( $i == $m ) {
$s = $l[$i];
- } else if( $i == $m - 1 ) {
+ } 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;
@@ -2079,7 +2227,11 @@ class Language {
function commaList( $list ) {
return implode(
$list,
- wfMsgExt( 'comma-separator', array( 'parsemag', 'escapenoentities', 'language' => $this ) ) );
+ wfMsgExt(
+ 'comma-separator',
+ array( 'parsemag', 'escapenoentities', 'language' => $this )
+ )
+ );
}
/**
@@ -2091,7 +2243,11 @@ class Language {
function semicolonList( $list ) {
return implode(
$list,
- wfMsgExt( 'semicolon-separator', array( 'parsemag', 'escapenoentities', 'language' => $this ) ) );
+ wfMsgExt(
+ 'semicolon-separator',
+ array( 'parsemag', 'escapenoentities', 'language' => $this )
+ )
+ );
}
/**
@@ -2102,7 +2258,11 @@ class Language {
function pipeList( $list ) {
return implode(
$list,
- wfMsgExt( 'pipe-separator', array( 'escapenoentities', 'language' => $this ) ) );
+ wfMsgExt(
+ 'pipe-separator',
+ array( 'escapenoentities', 'language' => $this )
+ )
+ );
}
/**
@@ -2114,7 +2274,7 @@ 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
@@ -2122,38 +2282,205 @@ class Language {
*/
function truncate( $string, $length, $ellipsis = '...' ) {
# Use the localized ellipsis character
- if( $ellipsis == '...' ) {
+ if ( $ellipsis == '...' ) {
$ellipsis = wfMsgExt( 'ellipsis', array( 'escapenoentities', 'language' => $this ) );
}
-
- if( $length == 0 ) {
+ # 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 );
+ }
+ 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 ) );
}
- 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];
+ # 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 .= '' . array_pop( $openTags ) . '>'; // 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 = '';
}
}
@@ -2167,7 +2494,7 @@ class Language {
*/
function convertGrammar( $word, $case ) {
global $wgGrammarForms;
- if ( isset($wgGrammarForms[$this->getCode()][$case][$word]) ) {
+ if ( isset( $wgGrammarForms[$this->getCode()][$case][$word] ) ) {
return $wgGrammarForms[$this->getCode()][$case][$word];
}
return $word;
@@ -2182,11 +2509,17 @@ class Language {
* These details may be overriden per language.
*/
function gender( $gender, $forms ) {
- if ( !count($forms) ) { return ''; }
+ 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];
+ if ( $gender === 'male' ) {
+ return $forms[0];
+ }
+ if ( $gender === 'female' ) {
+ return $forms[1];
+ }
+ return isset( $forms[2] ) ? $forms[2] : $forms[0];
}
/**
@@ -2205,7 +2538,9 @@ class Language {
* @return string Correct form of plural for $count in this language
*/
function convertPlural( $count, $forms ) {
- if ( !count($forms) ) { return ''; }
+ if ( !count( $forms ) ) {
+ return '';
+ }
$forms = $this->preConvertPlural( $forms, 2 );
return ( $count == 1 ) ? $forms[0] : $forms[1];
@@ -2220,31 +2555,31 @@ class Language {
* @return array Padded array of forms or an exception if not an array
*/
protected function preConvertPlural( /* Array */ $forms, $count ) {
- while ( count($forms) < $count ) {
- $forms[] = $forms[count($forms)-1];
+ while ( count( $forms ) < $count ) {
+ $forms[] = $forms[count( $forms ) - 1];
}
return $forms;
}
/**
- * For translaing of expiry times
+ * For translating of expiry times
* @param $str String: the validated block time in English
* @return Somehow translated block time
* @see LanguageFi.php for example implementation
*/
function translateBlockExpiry( $str ) {
-
$scBlockExpiryOptions = $this->getMessageFromDB( 'ipboptions' );
- if ( $scBlockExpiryOptions == '-') {
+ if ( $scBlockExpiryOptions == '-' ) {
return $str;
}
- foreach (explode(',', $scBlockExpiryOptions) as $option) {
- if ( strpos($option, ":") === false )
+ foreach ( explode( ',', $scBlockExpiryOptions ) as $option ) {
+ if ( strpos( $option, ':' ) === false ) {
continue;
- list($show, $value) = explode(":", $option);
- if ( strcmp ( $str, $value) == 0 ) {
+ }
+ list( $show, $value ) = explode( ':', $option );
+ if ( strcmp( $str, $value ) == 0 ) {
return htmlspecialchars( trim( $show ) );
}
}
@@ -2274,31 +2609,30 @@ class Language {
}
# convert text to all supported variants
- function autoConvertToAllVariants($text) {
- return $this->mConverter->autoConvertToAllVariants($text);
+ 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);
+ function convert( $text ) {
+ return $this->mConverter->convert( $text );
}
- # Convert text from within Parser
- function parserConvert( $text, &$parser ) {
- return $this->mConverter->parserConvert( $text, $parser );
+ # Convert a Title object to a string in the preferred variant
+ function convertTitle( $title ) {
+ return $this->mConverter->convertTitle( $title );
}
# Check if this is a language with variants
- function hasVariants(){
- return sizeof($this->getVariants())>1;
+ function hasVariants() {
+ return sizeof( $this->getVariants() ) > 1;
}
# Put custom tags (e.g. -{ }-) around math to prevent conversion
- function armourMath($text){
- return $this->mConverter->armourMath($text);
+ function armourMath( $text ) {
+ return $this->mConverter->armourMath( $text );
}
-
/**
* Perform output conversion on a string, and encode for safe HTML output.
* @param $text String text to be converted
@@ -2315,7 +2649,7 @@ class Language {
}
/**
- * get the list of variants supported by this langauge
+ * Get the list of variants supported by this langauge
* see sample implementation in LanguageZh.php
*
* @return array an array of language codes
@@ -2324,20 +2658,19 @@ class Language {
return $this->mConverter->getVariants();
}
-
- function getPreferredVariant( $fromUser = true ) {
- return $this->mConverter->getPreferredVariant( $fromUser );
+ function getPreferredVariant( $fromUser = true, $fromHeader = false ) {
+ return $this->mConverter->getPreferredVariant( $fromUser, $fromHeader );
}
/**
- * if a language supports multiple variants, it is
+ * If a language supports multiple variants, it is
* possible that non-existing link in one variant
* actually exists in another variant. this function
* tries to find it. See e.g. LanguageZh.php
*
* @param $link String: the name of the link
* @param $nt Mixed: the title object of the link
- * @param boolean $ignoreOtherCond: to disable other conditions when
+ * @param $ignoreOtherCond Boolean: to disable other conditions when
* we need to transclude a template or update a category's link
* @return null the input parameters may be modified upon return
*/
@@ -2350,11 +2683,10 @@ class Language {
* into an array of all possible variants of the text:
* 'variant' => text in that variant
*/
- function convertLinkToAllVariants($text){
- return $this->mConverter->convertLinkToAllVariants($text);
+ function convertLinkToAllVariants( $text ) {
+ return $this->mConverter->convertLinkToAllVariants( $text );
}
-
/**
* returns language specific options used by User::getPageRenderHash()
* for example, the preferred language variant
@@ -2366,7 +2698,7 @@ class Language {
}
/**
- * for languages that support multiple variants, the title of an
+ * For languages that support multiple variants, the title of an
* article may be displayed differently in different variants. this
* function returns the apporiate title defined in the body of the article.
*
@@ -2384,7 +2716,7 @@ class Language {
* @param $noParse
* @return string the tagged text
*/
- function markNoConversion( $text, $noParse=false ) {
+ function markNoConversion( $text, $noParse = false ) {
return $this->mConverter->markNoConversion( $text, $noParse );
}
@@ -2413,10 +2745,34 @@ 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' );
@@ -2426,7 +2782,7 @@ class Language {
global $IP;
return self::getFileName( "$IP/languages/classes/Language", $code, '.php' );
}
-
+
/**
* Get the fallback for a given language
*/
@@ -2439,7 +2795,7 @@ class Language {
}
}
- /**
+ /**
* Get all messages for a given language
* WARNING: this may take a long time
*/
@@ -2447,7 +2803,7 @@ class Language {
return self::getLocalisationCache()->getItem( $code, 'messages' );
}
- /**
+ /**
* Get a message for a given language
*/
static function getMessageFor( $key, $code ) {
@@ -2455,16 +2811,18 @@ class Language {
}
function fixVariableInNamespace( $talk ) {
- if ( strpos( $talk, '$1' ) === false ) return $talk;
+ if ( strpos( $talk, '$1' ) === false ) {
+ return $talk;
+ }
global $wgMetaNamespace;
$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.
+ # 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',
+ $talk = preg_replace_callback( '/{{grammar:(.*?)\|(.*?)}}/i',
array( &$this, 'replaceGrammarInNamespace' ), $talk );
return str_replace( ' ', '_', $talk );
}
@@ -2482,7 +2840,7 @@ 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 );
@@ -2492,19 +2850,33 @@ class Language {
function formatTimePeriod( $seconds ) {
if ( $seconds < 10 ) {
- return $this->formatNum( sprintf( "%.1f", $seconds ) ) . wfMsg( 'seconds-abbrev' );
+ return $this->formatNum( sprintf( "%.1f", $seconds ) ) . $this->getMessageFromDB( 'seconds-abbrev' );
} elseif ( $seconds < 60 ) {
- return $this->formatNum( round( $seconds ) ) . wfMsg( 'seconds-abbrev' );
+ return $this->formatNum( round( $seconds ) ) . $this->getMessageFromDB( 'seconds-abbrev' );
} elseif ( $seconds < 3600 ) {
- return $this->formatNum( floor( $seconds / 60 ) ) . wfMsg( 'minutes-abbrev' ) .
- $this->formatNum( round( fmod( $seconds, 60 ) ) ) . wfMsg( 'seconds-abbrev' );
+ $minutes = floor( $seconds / 60 );
+ $secondsPart = round( fmod( $seconds, 60 ) );
+ if ( $secondsPart == 60 ) {
+ $secondsPart = 0;
+ $minutes++;
+ }
+ return $this->formatNum( $minutes ) . $this->getMessageFromDB( 'minutes-abbrev' ) . ' ' .
+ $this->formatNum( $secondsPart ) . $this->getMessageFromDB( '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' );
+ if ( $secondsPart == 60 ) {
+ $secondsPart = 0;
+ $minutes++;
+ }
+ if ( $minutes == 60 ) {
+ $minutes = 0;
+ $hours++;
+ }
+ return $this->formatNum( $hours ) . $this->getMessageFromDB( 'hours-abbrev' ) . ' ' .
+ $this->formatNum( $minutes ) . $this->getMessageFromDB( 'minutes-abbrev' ) . ' ' .
+ $this->formatNum( $secondsPart ) . $this->getMessageFromDB( 'seconds-abbrev' );
}
}
@@ -2533,13 +2905,13 @@ class Language {
function formatSize( $size ) {
// For small sizes no decimal places necessary
$round = 0;
- if( $size > 1024 ) {
+ if ( $size > 1024 ) {
$size = $size / 1024;
- if( $size > 1024 ) {
+ if ( $size > 1024 ) {
$size = $size / 1024;
// For MB and bigger two decimal places are smarter
$round = 2;
- if( $size > 1024 ) {
+ if ( $size > 1024 ) {
$size = $size / 1024;
$msg = 'size-gigabytes';
} else {
@@ -2555,4 +2927,70 @@ 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();
+ }
+
+ /**
+ * Given a string, convert it to a (hopefully short) key that can be used
+ * for efficient sorting. A binary sort according to the sortkeys
+ * corresponds to a logical sort of the corresponding strings. Current
+ * code expects that a null character should sort before all others, but
+ * has no other particular expectations (and that one can be changed if
+ * necessary).
+ *
+ * @param string $string UTF-8 string
+ * @return string Binary sortkey
+ */
+ public function convertToSortkey( $string ) {
+ # Fake function for now
+ return strtoupper( $string );
+ }
+
+ /**
+ * Does it make sense for lists to be split up into sections based on their
+ * first letter? Logogram-based scripts probably want to return false.
+ *
+ * TODO: Use this in CategoryPage.php.
+ *
+ * @return boolean
+ */
+ public function usesFirstLettersInLists() {
+ return true;
+ }
+
+ /**
+ * Given a string, return the logical "first letter" to be used for
+ * grouping on category pages and so on. This has to be coordinated
+ * carefully with convertToSortkey(), or else the sorted list might jump
+ * back and forth between the same "initial letters" or other pathological
+ * behavior. For instance, if you just return the first character, but "a"
+ * sorts the same as "A" based on convertToSortkey(), then you might get a
+ * list like
+ *
+ * == A ==
+ * * [[Aardvark]]
+ *
+ * == a ==
+ * * [[antelope]]
+ *
+ * == A ==
+ * * [[Ape]]
+ *
+ * etc., assuming for the sake of argument that $wgCapitalLinks is false.
+ * Obviously, this is ignored if usesFirstLettersInLists() is false.
+ *
+ * @param string $string UTF-8 string
+ * @return string UTF-8 string corresponding to the first letter of input
+ */
+ public function firstLetterForLists( $string ) {
+ if ( $string[0] == "\0" ) {
+ $string = substr( $string, 1 );
+ }
+ return strtoupper( $this->firstChar( $string ) );
+ }
}