diff options
Diffstat (limited to 'languages/classes')
35 files changed, 1627 insertions, 302 deletions
diff --git a/languages/classes/LanguageAr.php b/languages/classes/LanguageAr.php index 514ff028..1b9ae7bf 100644 --- a/languages/classes/LanguageAr.php +++ b/languages/classes/LanguageAr.php @@ -7,8 +7,10 @@ */ class LanguageAr extends Language { - function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { - $forms = array($w1, $w2, $w3, $w4, $w5); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 5 ); + if ( $count == 1 ) { $index = 0; } elseif( $count == 2 ) { diff --git a/languages/classes/LanguageBat_smg.php b/languages/classes/LanguageBat_smg.php new file mode 100644 index 00000000..fc830cf5 --- /dev/null +++ b/languages/classes/LanguageBat_smg.php @@ -0,0 +1,26 @@ +<?php +/** Samogitian (Žemaitėška) + * + * @addtogroup Language + * + * @author Niklas Laxström + */ +class LanguageBat_smg extends Language { + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 4 ); + + $count = abs( $count ); + if ( $count === 0 || ($count%100 === 0 || ($count%100 >= 10 && $count%100 < 20)) ) { + return $forms[2]; + } elseif ( $count%10 === 1 ) { + return $forms[0]; + } elseif ( $count%10 === 2 ) { + return $forms[1]; + } else { + return $forms[3]; + } + } + +}
\ No newline at end of file diff --git a/languages/classes/LanguageBe.php b/languages/classes/LanguageBe.php index e0665e68..cc3e4e37 100644 --- a/languages/classes/LanguageBe.php +++ b/languages/classes/LanguageBe.php @@ -14,17 +14,20 @@ */ class LanguageBe extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageBe_tarask.php b/languages/classes/LanguageBe_tarask.php index 5e168b7e..d2dd4825 100644 --- a/languages/classes/LanguageBe_tarask.php +++ b/languages/classes/LanguageBe_tarask.php @@ -1,5 +1,5 @@ <?php -/** Belarusian in Taraskievica orthography (Беларуская тарашкевіца) +/** Belarusian in Taraškievica orthography (Беларуская тарашкевіца) * * @addtogroup Language * @@ -11,17 +11,32 @@ */ class LanguageBe_tarask extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + /** + * Plural form transformations + * + * $wordform1 - singular form (for 1, 21, 31, 41...) + * $wordform2 - plural form (for 2, 3, 4, 22, 23, 24, 32, 33, 34...) + * $wordform3 - plural form (for 0, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 25, 26...) + * $wordform4 - plural form for messages without number + */ + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + + $count = abs( $count ); + if ( isset($forms[3]) && $count != 1 ) + return $forms[3]; + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageBs.php b/languages/classes/LanguageBs.php index 119280e6..410c3d62 100644 --- a/languages/classes/LanguageBs.php +++ b/languages/classes/LanguageBs.php @@ -6,17 +6,19 @@ class LanguageBs extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageCs.php b/languages/classes/LanguageCs.php index ac80f296..4a52368e 100644 --- a/languages/classes/LanguageCs.php +++ b/languages/classes/LanguageCs.php @@ -19,6 +19,20 @@ class LanguageCs extends Language { # allowed values for $case: # 1sg, 2sg, ..., 7sg -- nominative, genitive, ... (in singular) switch ( $word ) { + case 'Wikibooks': + case 'Wikiknihy': + switch ( $case ) { + case '2sg': + return 'Wikiknih'; + case '3sg': + return 'Wikiknihám'; + case '6sg'; + return 'Wikiknihách'; + case '7sg': + return 'Wikiknihami'; + default: + return 'Wikiknihy'; + } case 'Wikipedia': case 'Wikipedie': switch ( $case ) { @@ -34,17 +48,17 @@ class LanguageCs extends Language { case 'Wiktionary': case 'Wikcionář': + case 'Wikislovník': switch ( $case ) { case '2sg': - return 'Wikcionáře'; case '3sg': case '5sg'; case '6sg'; - return 'Wikcionáři'; + return 'Wikislovníku'; case '7sg': - return 'Wikcionářem'; + return 'Wikislovníkem'; default: - return 'Wikcionář'; + return 'Wikislovník'; } case 'Wikiquote': @@ -64,23 +78,17 @@ class LanguageCs extends Language { return $word; } - # Plural form transformations, needed for some languages. - # Invoked by {{plural:count|wordform1|wordform2|wordform3}} - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace( '\xc2\xa0', '', $count ); - switch ( $count ) { - case 1: - return $wordform1; + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); - case 2: - case 3: - case 4: - return $wordform2; + switch ( $count ) { + case 1: return $forms[0]; + case 2: + case 3: + case 4: return $forms[1]; + default: return $forms[2]; + } + } - default: - return $wordform3; - }; - } } - - diff --git a/languages/classes/LanguageCu.php b/languages/classes/LanguageCu.php index 61128f24..fba895ec 100644 --- a/languages/classes/LanguageCu.php +++ b/languages/classes/LanguageCu.php @@ -35,13 +35,16 @@ class LanguageCu extends Language { return $word; } - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $wordform4, $w5) { + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 4 ); + switch ($count % 10) { - case 1: return $wordform1; - case 2: return $wordform2; - case 3: return $wordform3; - case 4: return $wordform3; - default: return $wordform4; + case 1: return $forms[0]; + case 2: return $forms[1]; + case 3: + case 4: return $forms[2]; + default: return $forms[3]; } } diff --git a/languages/classes/LanguageCy.php b/languages/classes/LanguageCy.php new file mode 100644 index 00000000..aea24019 --- /dev/null +++ b/languages/classes/LanguageCy.php @@ -0,0 +1,21 @@ +<?php +/** Welsh (Cymraeg) + * + * @addtogroup Language + * + * @author Niklas Laxström + */ +class LanguageCy extends Language { + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 6 ); + $count = abs( $count ); + if ( $count >= 0 && $count <= 3 ) { + return $forms[$count]; + } elseif ( $count == 6 ) { + return $forms[4]; + } else { + return $forms[5]; + } + } +} diff --git a/languages/classes/LanguageDsb.php b/languages/classes/LanguageDsb.php new file mode 100644 index 00000000..7408217e --- /dev/null +++ b/languages/classes/LanguageDsb.php @@ -0,0 +1,115 @@ +<?php +/** Lower Sorbian (Dolnoserbski) + * + * @addtogroup Language + */ + +class LanguageDsb extends Language { + + # Convert from the nominative form of a noun to some other case + # Invoked with {{GRAMMAR:case|word}} + + function convertGrammar( $word, $case ) { + global $wgGrammarForms; + if ( isset( $wgGrammarForms['hsb'][$case][$word] ) ) { + return $wgGrammarForms['hsb'][$case][$word]; + } + + switch ( $case ) { + case 'genitiw': # genitive + if ( $word == 'Wikipedija' ) { + $word = 'Wikipedije'; + } elseif ( $word == 'Wikiknihi' ) { + $word = 'Wikiknih'; + } elseif ( $word == 'Wikinowiny' ) { + $word = 'Wikinowin'; + } elseif ( $word == 'Wikižórło' ) { + $word = 'Wikižórła'; + } elseif ( $word == 'Wikicitaty' ) { + $word = 'Wikicitatow'; + } elseif ( $word == 'Wikisłownik' ) { + $word = 'Wikisłownika'; + } + break; + case 'datiw': # dativ + if ( $word == 'Wikipedija' ) { + $word = 'Wikipediji'; + } elseif ( $word == 'Wikiknihi' ) { + $word = 'Wikikniham'; + } elseif ( $word == 'Wikinowiny' ) { + $word = 'Wikinowinam'; + } elseif ( $word == 'Wikižórło' ) { + $word = 'Wikižórłu'; + } elseif ( $word == 'Wikicitaty' ) { + $word = 'Wikicitatam'; + } elseif ( $word == 'Wikisłownik' ) { + $word = 'Wikisłownikej'; + } + break; + case 'akuzativ': # akuzativ + if ( $word == 'Wikipedija' ) { + $word = 'Wikipediju'; + } elseif ( $word == 'Wikiknihi' ) { + $word = 'Wikiknknihi'; + } elseif ( $word == 'Wikinowiny' ) { + $word = 'Wikinowiny'; + } elseif ( $word == 'Wikižórło' ) { + $word = 'Wikižórło'; + } elseif ( $word == 'Wikicitaty' ) { + $word = 'Wikicitaty'; + } elseif ( $word == 'Wikisłownik' ) { + $word = 'Wikisłownik'; + } + break; + case 'instrumental': # instrumental + if ( $word == 'Wikipedija' ) { + $word = 'Wikipediju'; + } elseif ( $word == 'Wikiknihi' ) { + $word = 'Wikiknihami'; + } elseif ( $word == 'Wikinowiny' ) { + $word = 'Wikinowinami'; + } elseif ( $word == 'Wikižórło' ) { + $word = 'Wikižórłom'; + } elseif ( $word == 'Wikicitaty' ) { + $word = 'Wikicitatami'; + } elseif ( $word == 'Wikisłownik' ) { + $word = 'Wikisłownikom'; + } else { + $word = 'z ' . $word; + } + break; + case 'lokatiw': # lokatiw + if ( $word == 'Wikipedija' ) { + $word = 'Wikipediji'; + } elseif ( $word == 'Wikiknihi' ) { + $word = 'Wikiknihach'; + } elseif ( $word == 'Wikinowiny' ) { + $word = 'Wikinowinach'; + } elseif ( $word == 'Wikižórło' ) { + $word = 'Wikižórłu'; + } elseif ( $word == 'Wikicitaty' ) { + $word = 'Wikicitatach'; + } elseif ( $word == 'Wikisłownik' ) { + $word = 'Wikisłowniku'; + } else { + $word = 'wo ' . $word; + } + break; + } + + return $word; # this will return the original value for 'nominatiw' (nominativ) and all undefined case values + } + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 4 ); + + switch ( abs( $count ) % 100 ) { + case 1: return $forms[0]; // singular + case 2: return $forms[1]; // dual + case 3: + case 4: return $forms[2]; // plural + default: return $forms[3]; // pluralgen + } + } +} diff --git a/languages/classes/LanguageFi.php b/languages/classes/LanguageFi.php index 0d02dfe7..7c1778cc 100644 --- a/languages/classes/LanguageFi.php +++ b/languages/classes/LanguageFi.php @@ -139,11 +139,7 @@ class LanguageFi extends Language { $final .= ' ' . $item; } - if ( $forContent ) { - return htmlspecialchars( trim( $final ) ); - } else { - return '<span class="blockexpiry" title="' . htmlspecialchars($str). '">”' . trim( $final ) . '”</span>'; - } + return htmlspecialchars( trim( $final ) ); } } diff --git a/languages/classes/LanguageFr.php b/languages/classes/LanguageFr.php index 87d28b22..dfd8af4b 100644 --- a/languages/classes/LanguageFr.php +++ b/languages/classes/LanguageFr.php @@ -9,8 +9,12 @@ class LanguageFr extends Language { /** * Use singular form for zero (see bug 7309) */ - function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { - return $count <= '1' ? $w1 : $w2; - } + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 2 ); + + return ($count <= 1) ? $forms[0] : $forms[1]; + } + } diff --git a/languages/classes/LanguageHe.php b/languages/classes/LanguageHe.php index ca760c1a..59b76333 100644 --- a/languages/classes/LanguageHe.php +++ b/languages/classes/LanguageHe.php @@ -57,13 +57,16 @@ class LanguageHe extends Language { * * @return string of the suited form of word */ - public function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ( $count == '1' ) { - return $w1; - } elseif ( $count == '2' && $w3 ) { - return $w3; + return $forms[0]; + } elseif ( $count == '2' && isset($forms[2]) ) { + return $forms[2]; } else { - return $w2; + return $forms[1]; } } } diff --git a/languages/classes/LanguageHr.php b/languages/classes/LanguageHr.php index 5a875a71..4a64f879 100644 --- a/languages/classes/LanguageHr.php +++ b/languages/classes/LanguageHr.php @@ -5,17 +5,20 @@ */ class LanguageHr extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageHsb.php b/languages/classes/LanguageHsb.php index 7cbc17de..68df96be 100644 --- a/languages/classes/LanguageHsb.php +++ b/languages/classes/LanguageHsb.php @@ -100,17 +100,16 @@ class LanguageHsb extends Language { return $word; # this will return the original value for 'nominatiw' (nominativ) and all undefined case values } - function convertPlural( $count, $singular, $dual, $plural, $pluralgen, $w5 ) { + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 4 ); + switch ( abs( $count ) % 100 ) { - case 1: - return $singular; - case 2: - return $dual; + case 1: return $forms[0]; // singular + case 2: return $forms[1]; // dual case 3: - case 4: - return $plural; - default: - return $pluralgen; + case 4: return $forms[2]; // plural + default: return $forms[3]; // pluralgen } } } diff --git a/languages/classes/LanguageHy.php b/languages/classes/LanguageHy.php index 34fb6c74..cc3492be 100644 --- a/languages/classes/LanguageHy.php +++ b/languages/classes/LanguageHy.php @@ -49,13 +49,11 @@ class LanguageHy extends Language { return $word; } - function convertPlural( $count, $wordform1, $wordform2) { - $count = str_replace (' ', '', $count); - if (abs($count) <= 1) { - return $wordform1; - } else { - return $wordform2; - } + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 2 ); + + return (abs($count) <= 1) ? $forms[0] : $forms[1]; } /* diff --git a/languages/classes/LanguageKaa.php b/languages/classes/LanguageKaa.php new file mode 100644 index 00000000..4a451dcc --- /dev/null +++ b/languages/classes/LanguageKaa.php @@ -0,0 +1,43 @@ +<?php +/** Karakalpak (Qaraqalpaqsha) + * + * + * @addtogroup Language + */ + +class LanguageKaa extends Language { + + # Convert from the nominative form of a noun to some other case + # Invoked with {{GRAMMAR:case|word}} + /** + * Cases: genitive, dative, accusative, locative, ablative, comitative + possessive forms + */ + function convertGrammar( $word, $case ) { + global $wgGrammarForms; + if ( isset( $wgGrammarForms['kaa'][$case][$word] ) ) { + return $wgGrammarForms['kaa'][$case][$word]; + } + /* Full code of function convertGrammar() is in development. Updates coming soon. */ + return $word; + } + + function ucfirst ( $string ) { + if ( $string[0] == 'i' ) { + return 'İ' . substr( $string, 1 ); + } else { + return parent::ucfirst( $string ); + } + } + + /** + * Avoid grouping whole numbers between 0 to 9999 + */ + function commafy( $_ ) { + if ( !preg_match( '/^\d{1,4}$/', $_ ) ) { + return strrev( (string)preg_replace( '/(\d{3})(?=\d)(?!\d*\.)/', '$1,', strrev($_) ) ); + } else { + return $_; + } + } + +}
\ No newline at end of file diff --git a/languages/classes/LanguageKk.deps.php b/languages/classes/LanguageKk.deps.php index 336692a2..2b96de96 100644 --- a/languages/classes/LanguageKk.deps.php +++ b/languages/classes/LanguageKk.deps.php @@ -7,6 +7,5 @@ require_once( dirname(__FILE__).'/../LanguageConverter.php' ); -require_once( dirname(__FILE__).'/LanguageKk_kz.php' ); - +require_once( dirname(__FILE__).'/LanguageKk_cyrl.php' ); diff --git a/languages/classes/LanguageKk.php b/languages/classes/LanguageKk.php index 68775b3a..cf90e96e 100644 --- a/languages/classes/LanguageKk.php +++ b/languages/classes/LanguageKk.php @@ -6,105 +6,196 @@ */ require_once( dirname(__FILE__).'/../LanguageConverter.php' ); -require_once( dirname(__FILE__).'/LanguageKk_kz.php' ); +require_once( dirname(__FILE__).'/LanguageKk_cyrl.php' ); + +define( 'KK_C_UC', 'АӘБВГҒДЕЁЖЗИЙКҚЛМНҢОӨПРСТУҰҮФХҺЦЧШЩЪЫІЬЭЮЯ' ); # Kazakh Cyrillic uppercase +define( 'KK_C_LC', 'аәбвгғдеёжзийкқлмнңоөпрстуұүфхһцчшщъыіьэюя' ); # Kazakh Cyrillic lowercase +define( 'KK_L_UC', 'AÄBCÇDEÉFGĞHIİÏJKLMNÑOÖPQRSŞTUÜVWXYÝZ' ); # Kazakh Latin uppercase +define( 'KK_L_LC', 'aäbcçdeéfgğhıiïjklmnñoöpqrsştuüvwxyýz' ); # Kazakh Latin lowercase +//define( 'KK_A', 'ٴابپتجحدرزسشعفقكلمنڭەوۇۋۆىيچھ' ); # Kazakh Arabic +define( 'H_HAMZA', 'ٴ' ); # U+0674 ARABIC LETTER HIGH HAMZA +//define( 'ZWNJ', '' ); # U+200C ZERO WIDTH NON-JOINER class KkConverter extends LanguageConverter { - var $mLatinToCyrillic = array( - 'YA' => 'Я', 'Ya' => 'Я', 'ya' => 'я', 'YE' => 'Е', 'Ye' => 'У', 'ye' => 'е', - 'YO' => 'Ё', 'Yo' => 'Ё', 'yo' => 'ё', 'YU' => 'Ю', 'Yu' => 'Ю', 'yu' => 'ю', - 'YW' => 'Ю', 'Yw' => 'Ю', 'yw' => 'ю', - - 'bʺ' => 'бъ', 'dʺ' => 'дъ', 'fʺ' => 'фъ', 'gʺ' => 'гъ', 'kʺ' => 'къ', 'lʺ' => 'лъ', - 'mʺ' => 'мъ', 'nʺ' => 'нъ', 'pʺ' => 'пъ', 'rʺ' => 'ръ', 'sʺ' => 'съ', 'tʺ' => 'тъ', - 'vʺ' => 'въ', 'zʺ' => 'зъ', - /* 'jʺ' => 'жъ', 'cʺ' => 'цъ', 'çʺ' => 'чъ', 'şʺ' => 'шъ', */ - - 'ŞÇʹ'=> 'ЩЬ', 'Şçʹ'=> 'Щь', 'Bʺ' => 'БЪ', 'Dʺ' => 'ДЪ', 'Fʺ' => 'ФЪ', 'Gʺ' => 'ГЪ', 'Kʺ' => 'КЪ', 'Lʺ' => 'ЛЪ', - 'Mʺ' => 'МЪ', 'Nʺ' => 'НЪ', 'Pʺ' => 'ПЪ', 'Rʺ' => 'РЪ', 'Sʺ' => 'СЪ', 'Tʺ' => 'ТЪ', - 'Vʺ' => 'ВЪ', 'Zʺ' => 'ЗЪ', - /* 'Jʺ' => 'ЖЪ', 'Cʺ' => 'ЦЪ', 'Çʺ' => 'ЧЪ', 'Şʺ' => 'ШЪ', */ - - 'şçʹ'=> 'щь', 'bʹ' => 'бь', 'dʹ' => 'дь', 'fʹ' => 'фь', 'gʹ' => 'гь', 'kʹ' => 'кь', 'lʹ' => 'ль', - 'mʹ' => 'мь', 'nʹ' => 'нь', 'pʹ' => 'пь', 'rʹ' => 'рь', 'sʹ' => 'сь', 'tʹ' => 'ть', - 'vʹ' => 'вь', 'zʹ' => 'зь', 'jʹ' => 'жь', 'cʹ' => 'ць', 'çʹ' => 'чь', 'şʹ' => 'шь', - - 'Bʹ' => 'БЬ', 'Dʹ' => 'ДЬ', 'Fʹ' => 'ФЬ', 'Gʹ' => 'ГЬ', 'Kʹ' => 'КЬ', 'Lʹ' => 'ЛЬ', - 'Mʹ' => 'МЬ', 'Nʹ' => 'НЬ', 'Pʹ' => 'ПЬ', 'Rʹ' => 'РЬ', 'Sʹ' => 'СЬ', 'Tʹ' => 'ТЬ', - 'Vʹ' => 'ВЬ', 'Zʹ' => 'ЗЬ', 'Jʹ' => 'ЖЬ', 'Cʹ' => 'ЦЬ', 'Çʹ' => 'ЧЬ', 'Şʹ' => 'ШЬ', - - 'ŞÇ' => 'Щ', 'Şç' => 'Щ', 'şç' => 'щ', - - 'a' => 'а', 'ä' => 'ә', 'b' => 'б', 'c' => 'ц', 'ç' => 'ч', 'd' => 'д', 'e' => 'е', - 'é' => 'э', 'f' => 'ф', 'g' => 'г', 'ğ' => 'ғ', 'h' => 'һ', 'i' => 'і', 'ı' => 'ы', - 'ï' => 'и', 'j' => 'ж', 'k' => 'к', 'l' => 'л', 'm' => 'м', 'n' => 'н', 'ñ' => 'ң', - 'o' => 'о', 'ö' => 'ө', 'p' => 'п', 'q' => 'қ', 'r' => 'р', 's' => 'с', 'ş' => 'ш', - 't' => 'т', 'u' => 'ұ', 'ü' => 'ү', 'v' => 'в', 'w' => 'у', 'x' => 'х', 'ý' => 'й', - 'z' => 'з', - - 'A' => 'А', 'Ä' => 'Ә', 'B' => 'Б', 'C' => 'Ц', 'Ç' => 'Ч', 'D' => 'Д', 'E' => 'Е', - 'É' => 'Э', 'F' => 'Ф', 'G' => 'Г', 'Ğ' => 'Ғ', 'H' => 'Һ', 'İ' => 'І', 'I' => 'Ы', - 'Ï' => 'И', 'J' => 'Ж', 'K' => 'К', 'L' => 'Л', 'M' => 'М', 'N' => 'Н', 'Ñ' => 'Ң', - 'O' => 'О', 'Ö' => 'Ө', 'P' => 'П', 'Q' => 'Қ', 'R' => 'Р', 'S' => 'С', 'Ş' => 'Ш', - 'T' => 'Т', 'U' => 'Ұ', 'Ü' => 'Ү', 'V' => 'В', 'W' => 'У', 'Ý' => 'Й', 'X' => 'Х', - 'Z' => 'З' - ); - - var $mCyrillicToLatin = array( - 'а' => 'a', 'ә' => 'ä', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'ғ' => 'ğ', - 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'j', 'з' => 'z', 'и' => 'ï', - 'й' => 'ý', 'к' => 'k', 'қ' => 'q', 'л' => 'l', 'м' => 'm', 'н' => 'n', - 'ң' => 'ñ', 'о' => 'o', 'ө' => 'ö', 'п' => 'p', 'р' => 'r', 'с' => 's', - 'т' => 't', 'у' => 'w', 'ұ' => 'u', 'ү' => 'ü', 'ф' => 'f', 'х' => 'x', - 'һ' => 'h', 'ц' => 'c', 'ч' => 'ç', 'ш' => 'ş', 'щ' => 'şç', 'ъ' => 'ʺ', - 'ы' => 'ı', 'ь' => 'ʹ', 'і' => 'i', 'э' => 'é', 'ю' => 'yw', 'я' => 'ya', - - 'А' => 'A', 'Ә' => 'Ä', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Ғ' => 'Ğ', - 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'J', 'З' => 'Z', 'И' => 'Ï', - 'Й' => 'Ý', 'К' => 'K', 'Қ' => 'Q', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', - 'Ң' => 'Ñ', 'О' => 'O', 'Ө' => 'Ö', 'П' => 'P', 'Р' => 'R', 'С' => 'S', - 'Т' => 'T', 'У' => 'W', 'Ұ' => 'U', 'Ү' => 'Ü', 'Ф' => 'F', 'Х' => 'X', - 'Һ' => 'H', 'Ц' => 'C', 'Ч' => 'Ç', 'Ш' => 'Ş', 'Щ' => 'Şç', 'Ъ' => 'ʺ', - 'Ы' => 'I', 'Ь' => 'ʹ', 'І' => 'İ', 'Э' => 'É', 'Ю' => 'Yw', 'Я' => 'Ya' - ); - - var $mCyrillicToArabic = array( - 'ла' => 'لا', 'лА' => 'لا', 'ЛА' => 'لا', 'Ла' => 'لا', - - 'а' => 'ا', 'ә' => 'ٵ', 'б' => 'ب', 'в' => 'ۆ', 'г' => 'گ', 'ғ' => 'ع', - 'д' => 'د', 'е' => 'ە', 'ё' => 'يو', 'ж' => 'ج', 'з' => 'ز', 'и' => 'ي', - 'й' => 'ي', 'к' => 'ك', 'қ' => 'ق', 'л' => 'ل', 'м' => 'م', 'н' => 'ن', - 'ң' => 'ڭ', 'о' => 'و', 'ө' => 'ٶ', 'п' => 'پ', 'р' => 'ر', 'с' => 'س', - 'т' => 'ت', 'у' => 'ۋ', 'ұ' => 'ۇ', 'ү' => 'ٷ', 'ф' => 'ف', 'х' => 'ح', - 'һ' => 'ھ', 'ц' => 'تس', 'ч' => 'چ', 'ш' => 'ش', 'щ' => 'شش', 'ъ' => 'ي', - 'ы' => 'ى', 'ь' => 'ي', 'і' => 'ٸ', 'э' => 'ە', 'ю' => 'يۋ', 'я' => 'يا', - - 'А' => 'ا', 'Ә' => 'ٵ', 'Б' => 'ب', 'В' => 'ۆ', 'Г' => 'گ', 'Ғ' => 'ع', - 'Д' => 'د', 'Е' => 'ە', 'Ё' => 'يو', 'Ж' => 'ج', 'З' => 'ز', 'И' => 'ي', - 'Й' => 'ي', 'К' => 'ك', 'Қ' => 'ق', 'Л' => 'ل', 'М' => 'م', 'Н' => 'ن', - 'Ң' => 'ڭ', 'О' => 'و', 'Ө' => 'ٶ', 'П' => 'پ', 'Р' => 'ر', 'С' => 'س', - 'Т' => 'ت', 'У' => 'ۋ', 'Ұ' => 'ۇ', 'Ү' => 'ٷ', 'Ф' => 'ف', 'Х' => 'ح', - 'Һ' => 'ھ', 'Ц' => 'تس', 'Ч' => 'چ', 'Ш' => 'ش', 'Щ' => 'شش', 'Ъ' => 'ي', - 'Ы' => 'ى', 'Ь' => 'ي', 'І' => 'ٸ', 'Э' => 'ە', 'Ю' => 'يۋ', 'Я' => 'يا', - - '?' => '؟', - '%' => '٪', - ',' => '،', - ';' => '؛' - ); + + function __construct($langobj, $maincode, + $variants=array(), + $variantfallbacks=array(), + $markup=array(), + $flags = array()) { + parent::__construct( $langobj, $maincode, + $variants, $variantfallbacks, $markup, $flags ); + + // No point delaying this since they're in code. + // Waiting until loadDefaultTables() means they never get loaded + // when the tables themselves are loaded from cache. + $this->loadRegs(); + } function loadDefaultTables() { + // require( dirname(__FILE__)."/../../includes/KkConversion.php" ); + // Placeholder for future implementing. Remove variables declarations + // after generating KkConversion.php + $kk2Cyrl = array(); + $kk2Latn = array(); + $kk2Arab = array(); + $kk2KZ = array(); + $kk2TR = array(); + $kk2CN = array(); + $this->mTables = array( - 'kk-kz' => new ReplacementArray( $this->mLatinToCyrillic ), - 'kk-tr' => new ReplacementArray( $this->mCyrillicToLatin ), - 'kk-cn' => new ReplacementArray( $this->mCyrillicToArabic ), - 'kk' => new ReplacementArray() + 'kk-cyrl' => new ReplacementArray( $kk2Cyrl ), + 'kk-latn' => new ReplacementArray( $kk2Latn ), + 'kk-arab' => new ReplacementArray( $kk2Arab ), + 'kk-kz' => new ReplacementArray( array_merge($kk2Cyrl, $kk2KZ) ), + 'kk-tr' => new ReplacementArray( array_merge($kk2Latn, $kk2TR) ), + 'kk-cn' => new ReplacementArray( array_merge($kk2Arab, $kk2CN) ), + 'kk' => new ReplacementArray() ); } + function postLoadTables() { + $this->mTables['kk-kz']->merge( $this->mTables['kk-cyrl'] ); + $this->mTables['kk-tr']->merge( $this->mTables['kk-latn'] ); + $this->mTables['kk-cn']->merge( $this->mTables['kk-arab'] ); + } + + function loadRegs() { + + $this->mCyrl2Latn = array( + ## Punctuation + '/№/u' => 'No.', + ## Е after vowels + '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])Е/u' => '$1YE', + '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])е/ui' => '$1ye', + ## leading ЁЮЯЩ + '/^Ё(['.KK_C_UC.']|$)/u' => 'YO$1', '/^Ё(['.KK_C_LC.']|$)/u' => 'Yo$1', + '/^Ю(['.KK_C_UC.']|$)/u' => 'YU$1', '/^Ю(['.KK_C_LC.']|$)/u' => 'Yu$1', + '/^Я(['.KK_C_UC.']|$)/u' => 'YA$1', '/^Я(['.KK_C_LC.']|$)/u' => 'Ya$1', + '/^Щ(['.KK_C_UC.']|$)/u' => 'ŞÇ$1', '/^Щ(['.KK_C_LC.']|$)/u' => 'Şç$1', + ## other ЁЮЯ + '/Ё/u' => 'YO', '/ё/u' => 'yo', + '/Ю/u' => 'YU', '/ю/u' => 'yu', + '/Я/u' => 'YA', '/я/u' => 'ya', + '/Щ/u' => 'ŞÇ', '/щ/u' => 'şç', + ## soft and hard signs + '/[ъЪ]/u' => 'ʺ', '/[ьЬ]/u' => 'ʹ', + ## other characters + '/А/u' => 'A', '/а/u' => 'a', '/Ә/u' => 'Ä', '/ә/u' => 'ä', + '/Б/u' => 'B', '/б/u' => 'b', '/В/u' => 'V', '/в/u' => 'v', + '/Г/u' => 'G', '/г/u' => 'g', '/Ғ/u' => 'Ğ', '/ғ/u' => 'ğ', + '/Д/u' => 'D', '/д/u' => 'd', '/Е/u' => 'E', '/е/u' => 'e', + '/Ж/u' => 'J', '/ж/u' => 'j', '/З/u' => 'Z', '/з/u' => 'z', + '/И/u' => 'Ï', '/и/u' => 'ï', '/Й/u' => 'Ý', '/й/u' => 'ý', + '/К/u' => 'K', '/к/u' => 'k', '/Қ/u' => 'Q', '/қ/u' => 'q', + '/Л/u' => 'L', '/л/u' => 'l', '/М/u' => 'M', '/м/u' => 'm', + '/Н/u' => 'N', '/н/u' => 'n', '/Ң/u' => 'Ñ', '/ң/u' => 'ñ', + '/О/u' => 'O', '/о/u' => 'o', '/Ө/u' => 'Ö', '/ө/u' => 'ö', + '/П/u' => 'P', '/п/u' => 'p', '/Р/u' => 'R', '/р/u' => 'r', + '/С/u' => 'S', '/с/u' => 's', '/Т/u' => 'T', '/т/u' => 't', + '/У/u' => 'W', '/у/u' => 'w', '/Ұ/u' => 'U', '/ұ/u' => 'u', + '/Ү/u' => 'Ü', '/ү/u' => 'ü', '/Ф/u' => 'F', '/ф/u' => 'f', + '/Х/u' => 'X', '/х/u' => 'x', '/Һ/u' => 'H', '/һ/u' => 'h', + '/Ц/u' => 'C', '/ц/u' => 'c', '/Ч/u' => 'Ç', '/ч/u' => 'ç', + '/Ш/u' => 'Ş', '/ш/u' => 'ş', '/Ы/u' => 'I', '/ы/u' => 'ı', + '/І/u' => 'İ', '/і/u' => 'i', '/Э/u' => 'É', '/э/u' => 'é', + ); + + $this->mLatn2Cyrl = array( + ## Punctuation + '/#|No\./' => '№', + ## Şç + '/ŞÇʹ/u'=> 'ЩЬ', '/Şçʹ/u'=> 'Щь', '/Şçʹ/u'=> 'Щь', + '/Ş[Çç]/u' => 'Щ', '/şç/u' => 'щ', + ## soft and hard signs + '/(['.KK_L_UC.'])ʺ(['.KK_L_UC.'])/u' => '$1Ъ$2', + '/ʺ(['.KK_L_LC.'])/u' => 'ъ$1', + '/(['.KK_L_UC.'])ʹ(['.KK_L_UC.'])/u' => '$1Ь$2', + '/ʹ(['.KK_L_LC.'])/u' => 'ь$1', + '/ʺ/u' => 'ъ', + '/ʹ/u' => 'ь', + ## Ye Yo Yu Ya. + '/Y[Ee]/u' => 'Е', '/ye/u' => 'е', + '/Y[Oo]/u' => 'Ё', '/yo/u' => 'ё', + '/Y[UWuw]/u' => 'Ю', '/y[uw]/u' => 'ю', + '/Y[Aa]/u' => 'Я', '/ya/u' => 'я', + ## other characters + '/A/u' => 'А', '/a/u' => 'а', '/Ä/u' => 'Ә', '/ä/u' => 'ә', + '/B/u' => 'Б', '/b/u' => 'б', '/C/u' => 'Ц', '/c/u' => 'ц', + '/Ç/u' => 'Ч', '/ç/u' => 'ч', '/D/u' => 'Д', '/d/u' => 'д', + '/E/u' => 'Е', '/e/u' => 'е', '/É/u' => 'Э', '/é/u' => 'э', + '/F/u' => 'Ф', '/f/u' => 'ф', '/G/u' => 'Г', '/g/u' => 'г', + '/Ğ/u' => 'Ғ', '/ğ/u' => 'ғ', '/H/u' => 'Һ', '/h/u' => 'һ', + '/I/u' => 'Ы', '/ı/u' => 'ы', '/İ/u' => 'І', '/i/u' => 'і', + '/Ï/u' => 'И', '/ï/u' => 'и', '/J/u' => 'Ж', '/j/u' => 'ж', + '/K/u' => 'К', '/k/u' => 'к', '/L/u' => 'Л', '/l/u' => 'л', + '/M/u' => 'М', '/m/u' => 'м', '/N/u' => 'Н', '/n/u' => 'н', + '/Ñ/u' => 'Ң', '/ñ/u' => 'ң', '/O/u' => 'О', '/o/u' => 'о', + '/Ö/u' => 'Ө', '/ö/u' => 'ө', '/P/u' => 'П', '/p/u' => 'п', + '/Q/u' => 'Қ', '/q/u' => 'қ', '/R/u' => 'Р', '/r/u' => 'р', + '/S/u' => 'С', '/s/u' => 'с', '/Ş/u' => 'Ш', '/ş/u' => 'ш', + '/T/u' => 'Т', '/t/u' => 'т', '/U/u' => 'Ұ', '/u/u' => 'ұ', + '/Ü/u' => 'Ү', '/ü/u' => 'ү', '/V/u' => 'В', '/v/u' => 'в', + '/W/u' => 'У', '/w/u' => 'у', '/Ý/u' => 'Й', '/ý/u' => 'й', + '/X/u' => 'Х', '/x/u' => 'х', '/Z/u' => 'З', '/z/u' => 'з', + ); + + $this->mCyLa2Arab = array( + ## Punctuation -> Arabic + '/#|№|No\./u' => '', # ؀ + '/\,/' => '،', # ، + '/;/' => '؛', # ؛ + '/\?/' => '؟', # ؟ + '/%/' => '٪', # ٪ + '/\*/' => '٭', # ٭ + ## Digits -> Arabic + '/0/' => '۰', # ۰ + '/1/' => '۱', # ۱ + '/2/' => '۲', # ۲ + '/3/' => '۳', # ۳ + '/4/' => '۴', # ۴ + '/5/' => '۵', # ۵ + '/6/' => '۶', # ۶ + '/7/' => '۷', # ۷ + '/8/' => '۸', # ۸ + '/9/' => '۹', # ۹ + ## Cyrillic -> Arabic + '/Аллаһ/ui' => 'ﷲ', + '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])е/ui' => '$1يە', + '/[еэ]/ui' => 'ە', '/[ъь]/ui' => '', + '/[аә]/ui' => 'ا', '/[оө]/ui' => 'و', '/[ұү]/ui' => 'ۇ', '/[ыі]/ui' => 'ى', + '/[и]/ui' => 'ىي', '/ё/ui' => 'يو', '/ю/ui' => 'يۋ', '/я/ui' => 'يا', '/[й]/ui' => 'ي', + '/ц/ui' => 'تس', '/щ/ui' => 'شش', + '/һ/ui' => 'ح', '/ч/ui' => 'تش', + #'/һ/ui' => 'ھ', '/ч/ui' => 'چ', + '/б/ui' => 'ب', '/в/ui' => 'ۆ', '/г/ui' => 'گ', '/ғ/ui' => 'ع', + '/д/ui' => 'د', '/ж/ui' => 'ج', '/з/ui' => 'ز', '/к/ui' => 'ك', + '/қ/ui' => 'ق', '/л/ui' => 'ل', '/м/ui' => 'م', '/н/ui' => 'ن', + '/ң/ui' => 'ڭ', '/п/ui' => 'پ', '/р/ui' => 'ر', '/с/ui' => 'س', + '/т/ui' => 'ت', '/у/ui' => 'ۋ', '/ф/ui' => 'ف', '/х/ui' => 'ح', + '/ш/ui' => 'ش', + ## Latin -> Arabic // commented for now... + /*'/Allah/ui' => 'ﷲ', + '/[eé]/ui' => 'ە', '/[yý]/ui' => 'ي', '/[ʺʹ]/ui' => '', + '/[aä]/ui' => 'ا', '/[oö]/ui' => 'و', '/[uü]/ui' => 'ۇ', + '/[ï]/ui' => 'ىي', '/[ıIiİ]/u' => 'ى', + '/c/ui' => 'تس', + '/ç/ui' => 'تش', '/h/ui' => 'ح', + #'/ç/ui' => 'چ', '/h/ui' => 'ھ', + '/b/ui' => 'ب','/d/ui' => 'د', + '/f/ui' => 'ف', '/g/ui' => 'گ', '/ğ/ui' => 'ع', + '/j/ui' => 'ج', '/k/ui' => 'ك', '/l/ui' => 'ل', '/m/ui' => 'م', + '/n/ui' => 'ن', '/ñ/ui' => 'ڭ', '/p/ui' => 'پ', '/q/ui' => 'ق', + '/r/ui' => 'ر', '/s/ui' => 'س', '/ş/ui' => 'ش', '/t/ui' => 'ت', + '/v/ui' => 'ۆ', '/w/ui' => 'ۋ', '/x/ui' => 'ح', '/z/ui' => 'ز',*/ + ); + + } + /* rules should be defined as -{ekavian | iyekavian-} -or- -{code:text | code:text | ...}- update: delete all rule parsing because it's not used - currently, and just produces a couple of bugs + currently, and just produces a couple of bugs */ function parseManualRule($rule, $flags=array()) { if(in_array('T',$flags)){ @@ -131,9 +222,9 @@ class KkConverter extends LanguageConverter { /* * A function wrapper: - * - if there is no selected variant, leave the link - * names as they were - * - do not try to find variants for usernames + * - if there is no selected variant, leave the link + * names as they were + * - do not try to find variants for usernames */ function findVariantLink( &$link, &$nt ) { // check for user namespace @@ -150,16 +241,6 @@ class KkConverter extends LanguageConverter { } /* - * We want our external link captions to be converted in variants, - * so we return the original text instead -{$text}-, except for URLs - */ - function markNoConversion($text, $noParse=false) { - if($noParse || preg_match("/^https?:\/\/|ftp:\/\/|irc:\/\//",$text)) - return parent::markNoConversion($text); - return $text; - } - - /* * An ugly function wrapper for parsing Image titles * (to prevent image name conversion) */ @@ -173,71 +254,204 @@ class KkConverter extends LanguageConverter { } /** - * It translates text into variant, specials: - * - ommiting roman numbers + * It translates text into variant */ - function translate($text, $toVariant){ - $breaks = '[^\w\x80-\xff]'; - - // regexp for roman numbers - $roman = 'M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})'; - - $reg = '/^'.$roman.'$|^'.$roman.$breaks.'|'.$breaks.$roman.'$|'.$breaks.$roman.$breaks.'/'; - - $matches = preg_split($reg, $text, -1, PREG_SPLIT_OFFSET_CAPTURE); - - $m = array_shift($matches); - if( !isset( $this->mTables[$toVariant] ) ) { - throw new MWException( "Broken variant table: " . implode( ',', array_keys( $this->mTables ) ) ); + function translate( $text, $toVariant ){ + global $wgContLanguageCode; + $text = parent::translate( $text, $toVariant ); + + $letters = ''; + switch( $toVariant ) { + case 'kk-cyrl': + case 'kk-kz': + $letters = KK_L_UC . KK_L_LC . 'ʺʹ#0123456789'; + $wgContLanguageCode = 'kk'; + break; + case 'kk-latn': + case 'kk-tr': + $letters = KK_C_UC . KK_C_LC . '№0123456789'; + $wgContLanguageCode = 'kk-Latn'; + break; + case 'kk-arab': + case 'kk-cn': + $letters = KK_C_UC.KK_C_LC./*KK_L_UC.KK_L_LC.'ʺʹ'.*/',;\?%\*№0123456789'; + $wgContLanguageCode = 'kk-Arab'; + break; + default: + $wgContLanguageCode = 'kk'; + return $text; } - $ret = $this->mTables[$toVariant]->replace( $m[0] ); - $mstart = $m[1]+strlen($m[0]); - foreach($matches as $m) { - $ret .= substr($text, $mstart, $m[1]-$mstart); - $ret .= parent::translate($m[0], $toVariant); + // disable conversion variables like $1, $2... + $varsfix = '\$[0-9]'; + + $matches = preg_split( '/' . $varsfix . '[^' . $letters . ']+/u', $text, -1, PREG_SPLIT_OFFSET_CAPTURE); + $mstart = 0; + $ret = ''; + foreach( $matches as $m ) { + $ret .= substr( $text, $mstart, $m[1]-$mstart ); + $ret .= $this->regsConverter( $m[0], $toVariant ); $mstart = $m[1] + strlen($m[0]); } - return $ret; } + function regsConverter( $text, $toVariant ) { + if ($text == '') return $text; + + $pat = array(); + $rep = array(); + switch( $toVariant ) { + case 'kk-arab': + case 'kk-cn': + $letters = KK_C_LC.KK_C_UC/*.KK_L_LC.KK_L_UC*/; + $front = 'әөүіӘӨҮІ'/*.'äöüiÄÖÜİ'*/; + $excludes = 'еэгғкқЕЭГҒКҚ'/*.'eégğkqEÉGĞKQ'*/; + // split text to words + $matches = preg_split( '/[\b\s\-\.:]+/', $text, -1, PREG_SPLIT_OFFSET_CAPTURE); + $mstart = 0; + $ret = ''; + foreach( $matches as $m ) { + $ret .= substr( $text, $mstart, $m[1] - $mstart ); + // is matched the word to front vowels? + // exclude a words matched to е, э, г, к, к, қ, + // them should be without hamza + if ( preg_match('/['.$front.']/u', $m[0]) && !preg_match('/['.$excludes.']/u', $m[0]) ) { + $ret .= preg_replace('/['.$letters.']+/u', H_HAMZA.'$0', $m[0]); + } else { + $ret .= $m[0]; + } + $mstart = $m[1] + strlen($m[0]); + } + $text =& $ret; + foreach( $this->mCyLa2Arab as $pat => $rep ) { + $text = preg_replace( $pat, $rep, $text ); + } + return $text; + break; + case 'kk-latn': + case 'kk-tr': + foreach( $this->mCyrl2Latn as $pat => $rep ) { + $text = preg_replace( $pat, $rep, $text ); + } + return $text; + break; + case 'kk-cyrl': + case 'kk-kz': + foreach( $this->mLatn2Cyrl as $pat => $rep ) { + $text = preg_replace( $pat, $rep, $text ); + } + return $text; + break; + default: + return $text; + } + } + + /* + * We want our external link captions to be converted in variants, + * so we return the original text instead -{$text}-, except for URLs + */ + function markNoConversion( $text, $noParse=false ) { + if( $noParse || preg_match( "/^https?:\/\/|ftp:\/\/|irc:\/\//", $text ) ) + return parent::markNoConversion( $text ); + return $text; + } + + function convertCategoryKey( $key ) { + return $this->autoConvert( $key, 'kk' ); + } + } -class LanguageKk extends LanguageKk_kz { +/* class that handles Cyrillic, Latin and Arabic scripts for Kazakh + right now it only distinguish kk_cyrl, kk_latn, kk_arab and kk_kz, kk_tr, kk_cn. +*/ +class LanguageKk extends LanguageKk_cyrl { function __construct() { global $wgHooks; parent::__construct(); - $variants = array( 'kk', 'kk-kz', 'kk-tr', 'kk-cn' ); + $variants = array( 'kk', 'kk-cyrl', 'kk-latn', 'kk-arab', 'kk-kz', 'kk-tr', 'kk-cn' ); $variantfallbacks = array( - 'kk' => 'kk-kz', - 'kk-kz' => 'kk', - 'kk-tr' => 'kk', - 'kk-cn' => 'kk' + 'kk' => 'kk-kz', + 'kk-cyrl' => 'kk', + 'kk-latn' => 'kk', + 'kk-arab' => 'kk', + 'kk-kz' => 'kk-cyrl', + 'kk-tr' => 'kk-latn', + 'kk-cn' => 'kk-arab' ); $this->mConverter = new KkConverter( $this, 'kk', $variants, $variantfallbacks ); + $wgHooks['ArticleSaveComplete'][] = $this->mConverter; } + /** + * Work around for right-to-left direction support in kk-arab and kk-cn + * + * @return bool + */ + function isRTL() { + $variant = $this->getPreferredVariant(); + if ( $variant == 'kk-arab' || $variant == 'kk-cn' ) { + return true; + } else { + return parent::isRTL(); + } + } + + /* + * It fixes issue with ucfirst for transforming 'i' to 'İ' + * + */ + function ucfirst ( $string ) { + $variant = $this->getPreferredVariant(); + if ( ($variant == 'kk-latn' || $variant == 'kk-tr') && $string[0] == 'i' ) { + $string = 'İ' . substr( $string, 1 ); + } else { + $string = parent::ucfirst( $string ); + } + return $string; + } + + /* + * It fixes issue with lcfirst for transforming 'I' to 'ı' + * + */ + function lcfirst ( $string ) { + $variant = $this->getPreferredVariant(); + if ( ($variant == 'kk-latn' || $variant == 'kk-tr') && $string[0] == 'I' ) { + $string = 'ı' . substr( $string, 1 ); + } else { + $string = parent::lcfirst( $string ); + } + return $string; + } + function convertGrammar( $word, $case ) { - $fname="LanguageKk::convertGrammar"; - wfProfileIn( $fname ); - - //always convert to kk-kz before convertGrammar - $w1 = $word; - $word = $this->mConverter->autoConvert( $word, 'kk-kz' ); - $w2 = $word; - $word = parent::convertGrammar( $word, $case ); - //restore encoding - if( $w1 != $w2 ) { - $word = $this->mConverter->translate( $word, 'kk-tr' ); + wfProfileIn( __METHOD__ ); + + $variant = $this->getPreferredVariant(); + switch ( $variant ) { + case 'kk-arab': + case 'kk-cn': + $word = parent::convertGrammarKk_arab( $word, $case ); + break; + case 'kk-latn': + case 'kk-tr': + $word = parent::convertGrammarKk_latn( $word, $case ); + break; + case 'kk-cyrl': + case 'kk-kz': + case 'kk': + default: + $word = parent::convertGrammarKk_cyrl( $word, $case ); } - wfProfileOut( $fname ); + + wfProfileOut( __METHOD__ ); return $word; } } - - diff --git a/languages/classes/LanguageKk_cyrl.php b/languages/classes/LanguageKk_cyrl.php new file mode 100644 index 00000000..a7f07573 --- /dev/null +++ b/languages/classes/LanguageKk_cyrl.php @@ -0,0 +1,722 @@ +<?php +/** Kazakh (Қазақша) + * + * + * @addtogroup Language + */ + + +class LanguageKk_cyrl extends Language { + + # Convert from the nominative form of a noun to some other case + # Invoked with {{GRAMMAR:case|word}} + /** + * Cases: genitive, dative, accusative, locative, ablative, comitative + possessive forms + */ + + function convertGrammarKk_cyrl( $word, $case ) { + global $wgGrammarForms; + if ( isset( $wgGrammarForms['kk-kz'][$case][$word] ) ) { + return $wgGrammarForms['kk-kz'][$case][$word]; + } + if ( isset( $wgGrammarForms['kk-cyrl'][$case][$word] ) ) { + return $wgGrammarForms['kk-cyrl'][$case][$word]; + } + // Set up some constants... + // Vowels in last syllable + $frontVowels = array( "е", "ө", "ү", "і", "ә", "э", "я", "ё", "и" ); + $backVowels = array( "а", "о", "ұ", "ы" ); + $allVowels = array( "е", "ө", "ү", "і", "ә", "э", "а", "о", "ұ", "ы", "я", "ё", "и" ); + // Preceding letters + $Nasals = array( "м", "н", "ң" ); + $Sonants = array( "и", "й", "л", "р", "у", "ю"); + $Consonants = array( "п", "ф", "к", "қ", "т", "ш", "с", "х", "ц", "ч", "щ", "б", "в", "г", "д" ); + $Sibilants = array( "ж", "з" ); + $Sonorants = array( "и", "й", "л", "р", "у", "ю", "м", "н", "ң", "ж", "з"); + + // Possessives + $firstPerson = array( "м", "ң" ); // 1st singular, 2nd unformal + $secondPerson = array( "з" ); // 1st plural, 2nd formal + $thirdPerson = array( "ы", "і" ); // 3rd + + $lastLetter = self::lastLetter( $word, $allVowels ); + $wordEnding =& $lastLetter[0]; + $wordLastVowel =& $lastLetter[1]; + + // Now convert the word + switch ( $case ) { + case "dc1": + case "genitive": #ilik + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "тің"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "тың"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "нің"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ның"; + } + } elseif ( in_array( $wordEnding, $Sonants ) || in_array( $wordEnding, $Sibilants )) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "дің"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "дың"; + } + } + break; + case "dc2": + case "dative": #barıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ке"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "қа"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ге"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ға"; + } + } + break; + case "dc21": + case "possessive dative": #täweldık + barıs + if ( in_array( $wordEnding, $firstPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "е"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "а"; + } + } elseif ( in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ге"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ға"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "не"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "на"; + } + } + break; + case "dc3": + case "accusative": #tabıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ті"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ты"; + } + } elseif ( in_array( $wordEnding, $allVowels ) ) { + if ( in_array($wordLastVowel, $frontVowels ) ) { + $word = $word . "ні"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ны"; + } + } elseif ( in_array( $wordEnding, $Sonorants) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "ді"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ды"; + } + } + break; + case "dc31": + case "possessive accusative": #täweldık + tabıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ді"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ды"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + $word = $word . "н"; + } + break; + case "dc4": + case "locative": #jatıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "те"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "та"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "де"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "да"; + } + } + break; + case "dc41": + case "possessive locative": #täweldık + jatıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "де"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "да"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "нде"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "нда"; + } + } + break; + case "dc5": + case "ablative": #şığıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "тен"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "тан"; + } + } elseif ( in_array($wordEnding, $allVowels ) || in_array($wordEnding, $Sonants ) || in_array($wordEnding, $Sibilants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ден"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "дан"; + } + } elseif ( in_array($wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "нен"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "нан"; + } + } + break; + case "dc51": + case "possessive ablative": #täweldık + şığıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "нен"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "нан"; + } + } elseif ( in_array($wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ден"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "дан"; + } + } + break; + case "dc6": + case "comitative": #kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "пен"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "мен"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "бен"; + } + break; + case "dc61": + case "possessive comitative": #täweldık + kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "пенен"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "менен"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "бенен"; + } + break; + default: #dc0 #nominative #ataw + } + return $word; + } + + function convertGrammarKk_latn( $word, $case ) { + global $wgGrammarForms; + if ( isset( $wgGrammarForms['kk-tr'][$case][$word] ) ) { + return $wgGrammarForms['kk-tr'][$case][$word]; + } + if ( isset( $wgGrammarForms['kk-latn'][$case][$word] ) ) { + return $wgGrammarForms['kk-latn'][$case][$word]; + } + // Set up some constants... + // Vowels in last syllable + $frontVowels = array( "e", "ö", "ü", "i", "ä", "é" ); + $backVowels = array( "a", "o", "u", "ı" ); + $allVowels = array( "e", "ö", "ü", "i", "ä", "é", "a", "o", "u", "ı" ); + // Preceding letters + $Nasals = array( "m", "n", "ñ" ); + $Sonants = array( "ï", "y", "ý", "l", "r", "w"); + $Consonants = array( "p", "f", "k", "q", "t", "ş", "s", "x", "c", "ç", "b", "v", "g", "d" ); + $Sibilants = array( "j", "z" ); + $Sonorants = array( "ï", "y", "ý", "l", "r", "w", "m", "n", "ñ", "j", "z"); + + // Possessives + $firstPerson = array( "m", "ñ" ); // 1st singular, 2nd unformal + $secondPerson = array( "z" ); // 1st plural, 2nd formal + $thirdPerson = array( "ı", "i" ); // 3rd + + $lastLetter = self::lastLetter( $word, $allVowels ); + $wordEnding =& $lastLetter[0]; + $wordLastVowel =& $lastLetter[1]; + + // Now convert the word + switch ( $case ) { + case "dc1": + case "genitive": #ilik + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "tiñ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "tıñ"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "niñ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "nıñ"; + } + } elseif ( in_array( $wordEnding, $Sonants ) || in_array( $wordEnding, $Sibilants )) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "diñ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "dıñ"; + } + } + break; + case "dc2": + case "dative": #barıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ke"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "qa"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ge"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ğa"; + } + } + break; + case "dc21": + case "possessive dative": #täweldık + barıs + if ( in_array( $wordEnding, $firstPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "e"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "a"; + } + } elseif ( in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ge"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ğa"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ne"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "na"; + } + } + break; + case "dc3": + case "accusative": #tabıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ti"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "tı"; + } + } elseif ( in_array( $wordEnding, $allVowels ) ) { + if ( in_array($wordLastVowel, $frontVowels ) ) { + $word = $word . "ni"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "nı"; + } + } elseif ( in_array( $wordEnding, $Sonorants) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "di"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "dı"; + } + } + break; + case "dc31": + case "possessive accusative": #täweldık + tabıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "di"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "dı"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + $word = $word . "n"; + } + break; + case "dc4": + case "locative": #jatıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "te"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ta"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "de"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "da"; + } + } + break; + case "dc41": + case "possessive locative": #täweldık + jatıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "de"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "da"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "nde"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "nda"; + } + } + break; + case "dc5": + case "ablative": #şığıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ten"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "tan"; + } + } elseif ( in_array($wordEnding, $allVowels ) || in_array($wordEnding, $Sonants ) || in_array($wordEnding, $Sibilants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "den"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "dan"; + } + } elseif ( in_array($wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "nen"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "nan"; + } + } + break; + case "dc51": + case "possessive ablative": #täweldık + şığıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "nen"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "nan"; + } + } elseif ( in_array($wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "den"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "dan"; + } + } + break; + case "dc6": + case "comitative": #kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "pen"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "men"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "ben"; + } + break; + case "dc61": + case "possessive comitative": #täweldık + kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "penen"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "menen"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "benen"; + } + break; + default: #dc0 #nominative #ataw + } + return $word; + } + + function convertGrammarKk_arab( $word, $case ) { + global $wgGrammarForms; + if ( isset( $wgGrammarForms['kk-cn'][$case][$word] ) ) { + return $wgGrammarForms['kk-cn'][$case][$word]; + } + if ( isset( $wgGrammarForms['kk-arab'][$case][$word] ) ) { + return $wgGrammarForms['kk-arab'][$case][$word]; + } + // Set up some constants... + // Vowels in last syllable + $frontVowels = array( "ە", "ٶ", "ٷ", "ٸ", "ٵ", "ە" ); + $backVowels = array( "ا", "و", "ۇ", "ى" ); + $allVowels = array( "ە", "ٶ", "ٷ", "ٸ", "ٵ", "ە", "ا", "و", "ۇ", "ى" ); + // Preceding letters + $Nasals = array( "م", "ن", "ڭ" ); + $Sonants = array( "ي", "ي", "ل", "ر", "ۋ"); + $Consonants = array( "پ", "ف", "ك", "ق", "ت", "ش", "س", "ح", "تس", "چ", "ب", "ۆ", "گ", "د" ); + $Sibilants = array( "ج", "ز" ); + $Sonorants = array( "ي", "ي", "ل", "ر", "ۋ", "م", "ن", "ڭ", "ج", "ز"); + + // Possessives + $firstPerson = array( "م", "ڭ" ); // 1st singular, 2nd unformal + $secondPerson = array( "ز" ); // 1st plural, 2nd formal + $thirdPerson = array( "ى", "ٸ" ); // 3rd + + $lastLetter = self::lastLetter( $word, $allVowels ); + $wordEnding =& $lastLetter[0]; + $wordLastVowel =& $lastLetter[1]; + + // Now convert the word + switch ( $case ) { + case "dc1": + case "genitive": #ilik + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "تٸڭ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "تىڭ"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "نٸڭ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "نىڭ"; + } + } elseif ( in_array( $wordEnding, $Sonants ) || in_array( $wordEnding, $Sibilants )) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "دٸڭ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دىڭ"; + } + } + break; + case "dc2": + case "dative": #barıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "كە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "قا"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "گە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "عا"; + } + } + break; + case "dc21": + case "possessive dative": #täweldık + barıs + if ( in_array( $wordEnding, $firstPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "ە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ا"; + } + } elseif ( in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "گە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "عا"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "نە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "نا"; + } + } + break; + case "dc3": + case "accusative": #tabıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "تٸ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "تى"; + } + } elseif ( in_array( $wordEnding, $allVowels ) ) { + if ( in_array($wordLastVowel, $frontVowels ) ) { + $word = $word . "نٸ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "نى"; + } + } elseif ( in_array( $wordEnding, $Sonorants) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "دٸ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دى"; + } + } + break; + case "dc31": + case "possessive accusative": #täweldık + tabıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "دٸ"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دى"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + $word = $word . "ن"; + } + break; + case "dc4": + case "locative": #jatıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "تە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "تا"; + } + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "دە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دا"; + } + } + break; + case "dc41": + case "possessive locative": #täweldık + jatıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "دە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دا"; + } + } elseif ( in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels) ) { + $word = $word . "ندە"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "ندا"; + } + } + break; + case "dc5": + case "ablative": #şığıs + if ( in_array( $wordEnding, $Consonants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "تەن"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "تان"; + } + } elseif ( in_array($wordEnding, $allVowels ) || in_array($wordEnding, $Sonants ) || in_array($wordEnding, $Sibilants ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "دەن"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دان"; + } + } elseif ( in_array($wordEnding, $Nasals ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "نەن"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "نان"; + } + } + break; + case "dc51": + case "possessive ablative": #täweldık + şığıs + if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $thirdPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "نەن"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "نان"; + } + } elseif ( in_array($wordEnding, $secondPerson ) ) { + if ( in_array( $wordLastVowel, $frontVowels ) ) { + $word = $word . "دەن"; + } elseif ( in_array( $wordLastVowel, $backVowels ) ) { + $word = $word . "دان"; + } + } + break; + case "dc6": + case "comitative": #kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "پەن"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "مەن"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "بەن"; + } + break; + case "dc61": + case "possessive comitative": #täweldık + kömektes + if ( in_array( $wordEnding, $Consonants ) ) { + $word = $word . "پەنەن"; + } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) || in_array( $wordEnding, $Sonants ) ) { + $word = $word . "مەنەن"; + } elseif ( in_array( $wordEnding, $Sibilants ) ) { + $word = $word . "بەنەن"; + } + break; + default: #dc0 #nominative #ataw + } + return $word; + } + + function lastLetter( $word, $allVowels ) { + $lastLetter = array(); + $ar = array(); + + // Put the word in a form we can play with since we're using UTF-8 + $ar = preg_split('//u', parent::lc($word), -1, PREG_SPLIT_NO_EMPTY); + + // Here's an array with the order of the letters in the word reversed + // so we can find a match quicker *shrug* + $wordReversed = array_reverse( $ar ); + + // Here's the last letter in the word + $lastLetter[0] = $ar[count( $ar ) - 1]; + + // Find the last vowel in the word + $lastLetter[1] = NULL; + foreach ( $wordReversed as $xvalue ) { + foreach ( $allVowels as $yvalue ) { + if ( strcmp( $xvalue, $yvalue ) == 0 ) { + $lastLetter[1] = $xvalue; + break; + } else { + continue; + } + } + if ( $lastLetter[1] !== NULL ) { + break; + } else { + continue; + } + } + + return $lastLetter; + } + + /** + * Avoid grouping whole numbers between 0 to 9999 + */ + function commafy( $_ ) { + if ( !preg_match( '/^\d{1,4}$/', $_ ) ) { + return strrev( (string)preg_replace( '/(\d{3})(?=\d)(?!\d*\.)/', '$1,', strrev($_) ) ); + } else { + return $_; + } + } +} diff --git a/languages/classes/LanguageKsh.php b/languages/classes/LanguageKsh.php index c53667cf..f72046e7 100644 --- a/languages/classes/LanguageKsh.php +++ b/languages/classes/LanguageKsh.php @@ -21,14 +21,16 @@ class LanguageKsh extends Language { /** * Handle cases of (1, other, 0) or (1, other) */ - public function convertPlural( $count, $w1, $w2, $w3, $w4, $w5 ) { - $count = str_replace (' ', '', $count); - if ( $count == '1' ) { - return $w1; - } elseif ( $count == '0' && $w3 ) { - return $w3; + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + + if ( $count == 1 ) { + return $forms[0]; + } elseif ( $count == 0 ) { + return $forms[2]; } else { - return $w2; + return $forms[1]; } } } diff --git a/languages/classes/LanguageKu.php b/languages/classes/LanguageKu.php index a08d3d73..d37d4287 100644 --- a/languages/classes/LanguageKu.php +++ b/languages/classes/LanguageKu.php @@ -15,6 +15,9 @@ class KuConverter extends LanguageConverter { 'م' => 'm', 'ن' => 'n', 'پ' => 'p', 'ق' => 'q', 'ر' => 'r', 'س' => 's', 'ش' => 'ş', 'ت' => 't', 'ڤ' => 'v', 'خ' => 'x', 'غ' => 'x', 'ز' => 'z', +// ک و => ku -- ist richtig +// و ك=> ku -- ist auch richtig + /* Doppel- und Halbvokale */ 'ڵ' => 'll', #ll 'ڕ' => 'rr', #rr @@ -34,6 +37,18 @@ class KuConverter extends LanguageConverter { '،' => ',', 'ع' => '\'', # ayn '؟' => '?', + + # digits + '٠' => '0', # ٠ + '١' => '1', # ١ + '٢' => '2', # ٢ + '٣' => '3', # ٣ + '٤' => '4', # ٤ + '٥' => '5', # ٥ + '٦' => '6', # ٦ + '٧' => '7', # ٧ + '٨' => '8', # ٨ + '٩' => '9', # ٩ ); var $mLatinToArabic = array( @@ -95,7 +110,20 @@ class KuConverter extends LanguageConverter { # eyn erstmal deaktivieren, einfache Anführungsstriche sind einfach zu häufig, um sie als eyn zu interpretieren # '\'' => 'ع', - ); +/* # deactivated for now, breaks links i.e. in header of Special:Recentchanges :-( + # digits + '0' => '٠', # ٠ + '1' => '١', # ١ + '2' => '٢', # ٢ + '3' => '٣', # ٣ + '4' => '٤', # ٤ + '5' => '٥', # ٥ + '6' => '٦', # ٦ + '7' => '٧', # ٧ + '8' => '٨', # ٨ + '9' => '٩', # ٩ +*/ + ); function loadDefaultTables() { $this->mTables = array( @@ -236,5 +264,3 @@ class LanguageKu extends LanguageKu_ku { } */ } - - diff --git a/languages/classes/LanguageLt.php b/languages/classes/LanguageLt.php index f2b29cad..0e14cbf8 100644 --- a/languages/classes/LanguageLt.php +++ b/languages/classes/LanguageLt.php @@ -11,11 +11,17 @@ class LanguageLt extends Language { 2 - trys (3) lapai 3 - penkiolika (15) lapų */ - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - if ($count%10==1 && $count%100!=11) return $wordform1; - if ($count%10>=2 && ($count%100<10 || $count%100>=20)) return $wordform2; - //if third form not specified, then use second form - return empty($wordform3)?$wordform2:$wordform3; + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + + //if no number with word, then use $form[0] for singular and $form[1] for plural or zero + if( count($forms) === 2 ) return $count == 1 ? $forms[0] : $forms[1]; + + $forms = $this->preConvertPlural( $forms, 3 ); + + if ($count%10==1 && $count%100!=11) return $forms[0]; + if ($count%10>=2 && ($count%100<10 || $count%100>=20)) return $forms[1]; + return $forms[2]; } } diff --git a/languages/classes/LanguageLv.php b/languages/classes/LanguageLv.php index 8a46bb9d..a3f076e8 100644 --- a/languages/classes/LanguageLv.php +++ b/languages/classes/LanguageLv.php @@ -21,8 +21,11 @@ class LanguageLv extends Language { * @param string $wordform3 (not used) * @return string */ - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5 ) { - return ( ( $count % 10 == 1 ) && ( $count % 100 != 11 ) ) ? $wordform1 : $wordform2; + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 2 ); + + return ( ( $count % 10 == 1 ) && ( $count % 100 != 11 ) ) ? $forms[0] : $forms[1]; } # Convert from the nominative form of a noun to some other case diff --git a/languages/classes/LanguagePl.php b/languages/classes/LanguagePl.php new file mode 100644 index 00000000..35b2a9c0 --- /dev/null +++ b/languages/classes/LanguagePl.php @@ -0,0 +1,24 @@ +<?php +/** Polish (polski) + * + * @addtogroup Language + */ + +class LanguagePl extends Language { + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + $count = abs( $count ); + if ( $count == 1 ) + return $forms[0]; // singular + switch ( $count % 10 ) { + case 2: + case 3: + case 4: + if ( $count / 10 % 10 != 1 ) + return $forms[1]; // plural + default: + return $forms[2]; // plural genitive + } + } +}
\ No newline at end of file diff --git a/languages/classes/LanguagePt_br.php b/languages/classes/LanguagePt_br.php index 31574ed8..78965ae3 100644 --- a/languages/classes/LanguagePt_br.php +++ b/languages/classes/LanguagePt_br.php @@ -9,8 +9,11 @@ class LanguagePt_br extends Language { /** * Use singular form for zero (see bug 7309) */ - function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { - return $count <= '1' ? $w1 : $w2; - } + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 2 ); + + return ($count <= 1) ? $forms[0] : $forms[1]; + } } diff --git a/languages/classes/LanguageRu.php b/languages/classes/LanguageRu.php index 7d088053..f6311b33 100644 --- a/languages/classes/LanguageRu.php +++ b/languages/classes/LanguageRu.php @@ -56,17 +56,38 @@ class LanguageRu extends Language { return $word; } - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace (' ', '', $count); + /** + * Plural form transformations + * + * $forms[0] - singular form (for 1, 21, 31, 41...) + * $forms[1] - paucal form (for 2, 3, 4, 22, 23, 24, 32, 33, 34...) + * $forms[2] - plural form (for 0, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 25, 26...) + * + * Examples: + * message with number + * "Сделано $1 {{PLURAL:$1|изменение|изменения|изменений}}" + * message without number + * "Действие не может быть выполнено по {{PLURAL:$1|следующей причине|следующим причинам}}:" + * + */ + + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + + //if no number with word, then use $form[0] for singular and $form[1] for plural or zero + if( count($forms) === 2 ) return $count == 1 ? $forms[0] : $forms[1]; + + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } @@ -84,3 +105,4 @@ class LanguageRu extends Language { } } + diff --git a/languages/classes/LanguageSk.php b/languages/classes/LanguageSk.php index 1b9832cc..edbe011c 100644 --- a/languages/classes/LanguageSk.php +++ b/languages/classes/LanguageSk.php @@ -76,9 +76,10 @@ class LanguageSk extends Language { return $word; } - function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { - $count = str_replace ('.', '', $count); - $forms = array( $w1, $w2, $w3); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ( $count == 1 ) { $index = 0; } elseif ( $count == 2 || $count == 3 || $count == 4 ) { diff --git a/languages/classes/LanguageSl.php b/languages/classes/LanguageSl.php index 2513d6bd..9b1e5c2b 100644 --- a/languages/classes/LanguageSl.php +++ b/languages/classes/LanguageSl.php @@ -71,9 +71,10 @@ class LanguageSl extends Language { return $word; # this will return the original value for 'imenovalnik' (nominativ) and all undefined case values } - function convertPlural( $count, $w1, $w2, $w3, $w4, $w5) { - $count = str_replace ('.', '', $count); - $forms = array( $w1, $w2, $w3, $w4, $w5 ); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 5 ); + if ( $count % 100 == 1 ) { $index = 0; } elseif ( $count % 100 == 2 ) { diff --git a/languages/classes/LanguageSr_ec.php b/languages/classes/LanguageSr_ec.php index 42647ae6..1f9bb716 100644 --- a/languages/classes/LanguageSr_ec.php +++ b/languages/classes/LanguageSr_ec.php @@ -8,17 +8,19 @@ #-------------------------------------------------------------------------- class LanguageSr_ec extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageSr_el.php b/languages/classes/LanguageSr_el.php index 66118cc9..a444e3b7 100644 --- a/languages/classes/LanguageSr_el.php +++ b/languages/classes/LanguageSr_el.php @@ -8,17 +8,19 @@ #-------------------------------------------------------------------------- class LanguageSr_el extends Language { - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace ('.', '', $count); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageUk.php b/languages/classes/LanguageUk.php index d87b7f58..7d2f58bf 100644 --- a/languages/classes/LanguageUk.php +++ b/languages/classes/LanguageUk.php @@ -58,17 +58,19 @@ class LanguageUk extends Language { return $word; } - function convertPlural( $count, $wordform1, $wordform2, $wordform3, $w4, $w5) { - $count = str_replace (' ', '', $count); + function convertPlural( $count, $forms ) { + if ( !count($forms) ) { return ''; } + $forms = $this->preConvertPlural( $forms, 3 ); + if ($count > 10 && floor(($count % 100) / 10) == 1) { - return $wordform3; + return $forms[2]; } else { switch ($count % 10) { - case 1: return $wordform1; + case 1: return $forms[0]; case 2: case 3: - case 4: return $wordform2; - default: return $wordform3; + case 4: return $forms[1]; + default: return $forms[2]; } } } diff --git a/languages/classes/LanguageYue.php b/languages/classes/LanguageYue.php new file mode 100644 index 00000000..26e45984 --- /dev/null +++ b/languages/classes/LanguageYue.php @@ -0,0 +1,23 @@ +<?php +/** + * @addtogroup Language + */ +class LanguageYue extends Language { + function stripForSearch( $string ) { + # MySQL fulltext index doesn't grok utf-8, so we + # need to fold cases and convert to hex + # we also separate characters as "words" + if( function_exists( 'mb_strtolower' ) ) { + return preg_replace( + "/([\\xc0-\\xff][\\x80-\\xbf]*)/e", + "' U8' . bin2hex( \"$1\" )", + mb_strtolower( $string ) ); + } else { + list( , $wikiLowerChars ) = Language::getCaseMaps(); + return preg_replace( + "/([\\xc0-\\xff][\\x80-\\xbf]*)/e", + "' U8' . bin2hex( strtr( \"\$1\", \$wikiLowerChars ) )", + $string ); + } + } +} diff --git a/languages/classes/LanguageZh.deps.php b/languages/classes/LanguageZh.deps.php index 9a9dacb1..05e51799 100644 --- a/languages/classes/LanguageZh.deps.php +++ b/languages/classes/LanguageZh.deps.php @@ -5,6 +5,5 @@ // changed on a subsequent page view. // see http://mail.wikipedia.org/pipermail/wikitech-l/2006-January/033660.html -require_once( dirname(__FILE__).'/LanguageZh_cn.php' ); +require_once( dirname(__FILE__).'/LanguageZh_hans.php' ); require_once( dirname(__FILE__).'/../LanguageConverter.php' ); - diff --git a/languages/classes/LanguageZh.php b/languages/classes/LanguageZh.php index bcdf7dd8..337783a6 100644 --- a/languages/classes/LanguageZh.php +++ b/languages/classes/LanguageZh.php @@ -3,24 +3,28 @@ * @addtogroup Language */ require_once( dirname(__FILE__).'/../LanguageConverter.php' ); -require_once( dirname(__FILE__).'/LanguageZh_cn.php' ); +require_once( dirname(__FILE__).'/LanguageZh_hans.php' ); class ZhConverter extends LanguageConverter { function loadDefaultTables() { require( dirname(__FILE__)."/../../includes/ZhConversion.php" ); $this->mTables = array( - 'zh-cn' => new ReplacementArray( $zh2CN ), - 'zh-tw' => new ReplacementArray( $zh2TW ), - 'zh-sg' => new ReplacementArray( array_merge($zh2CN, $zh2SG) ), - 'zh-hk' => new ReplacementArray( array_merge($zh2TW, $zh2HK) ), - 'zh' => new ReplacementArray + 'zh-hans' => new ReplacementArray( $zh2Hans ), + 'zh-hant' => new ReplacementArray( $zh2Hant ), + 'zh-cn' => new ReplacementArray( array_merge($zh2Hans, $zh2CN) ), + 'zh-tw' => new ReplacementArray( array_merge($zh2Hant, $zh2TW) ), + 'zh-sg' => new ReplacementArray( array_merge($zh2Hans, $zh2SG) ), + 'zh-hk' => new ReplacementArray( array_merge($zh2Hant, $zh2HK) ), + 'zh' => new ReplacementArray ); } function postLoadTables() { - $this->mTables['zh-sg']->merge( $this->mTables['zh-cn'] ); - $this->mTables['zh-hk']->merge( $this->mTables['zh-tw'] ); - } + $this->mTables['zh-cn']->merge( $this->mTables['zh-hans'] ); + $this->mTables['zh-tw']->merge( $this->mTables['zh-hant'] ); + $this->mTables['zh-sg']->merge( $this->mTables['zh-hans'] ); + $this->mTables['zh-hk']->merge( $this->mTables['zh-hant'] ); + } /* there shouldn't be any latin text in Chinese conversion, so no need to mark anything. @@ -31,26 +35,33 @@ class ZhConverter extends LanguageConverter { } function convertCategoryKey( $key ) { - return $this->autoConvert( $key, 'zh-cn' ); + return $this->autoConvert( $key, 'zh' ); } } /* class that handles both Traditional and Simplified Chinese - right now it only distinguish zh_cn, zh_tw, zh_sg and zh_hk. + right now it only distinguish zh_hans, zh_hant, zh_cn, zh_tw, zh_sg and zh_hk. */ -class LanguageZh extends LanguageZh_cn { +class LanguageZh extends LanguageZh_hans { function __construct() { global $wgHooks; parent::__construct(); - $this->mConverter = new ZhConverter($this, 'zh', - array('zh', 'zh-cn', 'zh-tw', 'zh-sg', 'zh-hk'), - array('zh'=>'zh-cn', - 'zh-cn'=>'zh-sg', - 'zh-sg'=>'zh-cn', - 'zh-tw'=>'zh-hk', - 'zh-hk'=>'zh-tw')); + + $variants = array('zh', 'zh-hans', 'zh-hant', 'zh-cn', 'zh-tw', 'zh-sg', 'zh-hk'); + $variantfallbacks = array( + 'zh' => 'zh-hans', + 'zh-hans' => 'zh', + 'zh-hant' => 'zh', + 'zh-cn' => 'zh-hans', + 'zh-sg' => 'zh-hans', + 'zh-tw' => 'zh-hant', + 'zh-hk' => 'zh-hant', + ); + + $this->mConverter = new ZhConverter( $this, 'zh', $variants, $variantfallbacks ); + $wgHooks['ArticleSaveComplete'][] = $this->mConverter; } @@ -79,12 +90,12 @@ class LanguageZh extends LanguageZh_cn { "/([\\xc0-\\xff][\\x80-\\xbf]*)/e", "' ' .\"$1\"", $string); - //always convert to zh-cn before indexing. it should be - //better to use zh-cn for search, since conversion from + //always convert to zh-hans before indexing. it should be + //better to use zh-hans for search, since conversion from //Traditional to Simplified is less ambiguous than the //other way around - $t = $this->mConverter->autoConvert($t, 'zh-cn'); + $t = $this->mConverter->autoConvert($t, 'zh-hans'); $t = parent::stripForSearch( $t ); wfProfileOut( $fname ); return $t; @@ -99,4 +110,3 @@ class LanguageZh extends LanguageZh_cn { } } - diff --git a/languages/classes/LanguageZh_hans.php b/languages/classes/LanguageZh_hans.php new file mode 100644 index 00000000..ed7da2b9 --- /dev/null +++ b/languages/classes/LanguageZh_hans.php @@ -0,0 +1,23 @@ +<?php +/** + * @addtogroup Language + */ +class LanguageZh_hans extends Language { + function stripForSearch( $string ) { + # MySQL fulltext index doesn't grok utf-8, so we + # need to fold cases and convert to hex + # we also separate characters as "words" + if( function_exists( 'mb_strtolower' ) ) { + return preg_replace( + "/([\\xc0-\\xff][\\x80-\\xbf]*)/e", + "' U8' . bin2hex( \"$1\" )", + mb_strtolower( $string ) ); + } else { + list( , $wikiLowerChars ) = Language::getCaseMaps(); + return preg_replace( + "/([\\xc0-\\xff][\\x80-\\xbf]*)/e", + "' U8' . bin2hex( strtr( \"\$1\", \$wikiLowerChars ) )", + $string ); + } + } +} |