From 05d705aa7111ad181149d8715529242d186a821a Mon Sep 17 00:00:00 2001 From: =?utf8?q?=C3=86var=20Arnfj=C3=B6r=C3=B0=20Bjarmason?= Date: Sun, 27 Mar 2005 02:25:25 +0000 Subject: [PATCH] Converted entities to their respective literals with the following Perlscript #!/usr/bin/evn perl use utf8; use HTML::Entities; binmode STDOUT, ":utf8"; @file = <>; $file = join /\n/, @file; for $i (0..length $file) { if ( (substr($file, $i, 1) eq '&') and (substr($file, ($i+1), 1) eq '#') ) { $eat = 1; # Yummie entities undef $food; next; } elsif ($eat && substr($file, $i, 1) eq '#') { next; } elsif ($eat && substr($file, $i, 1) =~ /\d/) { $food .= substr($file, $i, 1); next; } elsif ($eat && substr($file, $i, 1) =~ /;/) { undef $eat; $out .= chr($food); undef $food; next; } $out .= substr($file, $i, 1); } $out = decode_entities($out); print $out; --- languages/Names.php | 226 ++++++++++++++++++++++---------------------- 1 file changed, 113 insertions(+), 113 deletions(-) diff --git a/languages/Names.php b/languages/Names.php index 02223c876a..7c9e59f14a 100644 --- a/languages/Names.php +++ b/languages/Names.php @@ -1,183 +1,183 @@ 'Afar', # Afar - 'ab' => 'Аҧсуа', # Abkhaz, should possibly add ' бысжѡа' + 'ab' => 'Аҧсуа', # Abkhaz, should possibly add ' бысжѡа' 'af' => 'Afrikaans', # Afrikaans 'ak' => 'Akana', # Akan 'als' => 'Alemannisch', # Alemannic - 'am' => 'አማርኛ', # Amharic - 'an' => 'Aragonés', # Aragonese + 'am' => 'አማርኛ', # Amharic + 'an' => 'Aragonés', # Aragonese 'ang' => 'Anglo Saxon', # Old English - 'ar' => 'العربية', # Arabic - 'arc' => 'ܕܥܒܪܸܝܛ', # Aramaic - 'as' => 'অসমীয়া', # Assamese + 'ar' => 'العربية', # Arabic + 'arc' => 'ܕܥܒܪܸܝܛ', # Aramaic + 'as' => 'অসমীয়া', # Assamese 'ast' => 'Asturianu', # Asturian - 'av' => 'Авар', # Avar - 'ay' => 'Aymar', # Aymara, should possibly be Aymará - 'az' => 'Azərbaycan', # Azerbaijani - 'ba' => 'Башҡорт', # Bashkir - 'be' => 'Беларуская', # Belarusian ''or'' Byelarussian - 'bg' => 'Български', # Bulgarian - 'bh' => 'भोजपुरी', # Bihara + 'av' => 'Авар', # Avar + 'ay' => 'Aymar', # Aymara, should possibly be Aymará + 'az' => 'Azərbaycan', # Azerbaijani + 'ba' => 'Башҡорт', # Bashkir + 'be' => 'Беларуская', # Belarusian ''or'' Byelarussian + 'bg' => 'Български', # Bulgarian + 'bh' => 'भोजपुरी', # Bihara 'bi' => 'Bislama', # Bislama 'bm' => 'Bamanankan', # Bambara - 'bn' => 'বাংলা', # Bengali - 'bo' => 'བོད་ཡིག', # Tibetan + 'bn' => 'বাংলা', # Bengali + 'bo' => 'བོད་ཡིག', # Tibetan 'br' => 'Brezhoneg', # Breton 'bs' => 'Bosanski', # Bosnian - 'ca' => 'Català', # Catalan - 'ce' => 'Нохчийн', # Chechen + 'ca' => 'Català', # Catalan + 'ce' => 'Нохчийн', # Chechen 'ch' => 'Chamoru', # Chamorro 'cho' => 'Choctaw', # Choctaw - 'chr' => 'ᏣᎳᎩ', # Cherokee - 'chy' => 'Tsetsêhestâhese', # Cheyenne + 'chr' => 'ᏣᎳᎩ', # Cherokee + 'chy' => 'Tsetsêhestâhese', # Cheyenne 'co' => 'Corsu', # Corsican 'cr' => 'Nehiyaw', # Cree - 'cs' => 'Česky', # Czech - 'csb' => 'Kaszëbscziej', # Cassubian, should possibly be Kaszëbsczi - 'cv' => 'Чӑваш - (Ĉăvaŝ)', # Chuvash + 'cs' => 'Česky', # Czech + 'csb' => 'Kaszëbscziej', # Cassubian, should possibly be Kaszëbsczi + 'cv' => 'Чӑваш - (Ĉăvaŝ)', # Chuvash 'cy' => 'Cymraeg', # Welsh 'da' => 'Dansk', # Danish 'de' => 'Deutsch', # German 'dk' => 'Dansk', # Unused code currently redirecting to Danish, 'da' is correct for the language - 'dv' => 'ހިބަސް', # Dhivehi - 'dz' => 'ཇོང་ཁ', # Bhutani - 'ee' => 'Ɛʋɛ', # Ewe - 'el' => 'Ελληνικά', # Greek + 'dv' => 'ހިބަސް', # Dhivehi + 'dz' => 'ཇོང་ཁ', # Bhutani + 'ee' => 'Ɛʋɛ', # Ewe + 'el' => 'Ελληνικά', # Greek 'en' => 'English', # English 'eo' => 'Esperanto', # Esperanto - 'es' => 'Español', # Spanish + 'es' => 'Español', # Spanish 'et' => 'Eesti', # Estonian 'eu' => 'Euskara', # Basque - 'fa' => 'فارسی', # Persian + 'fa' => 'فارسی', # Persian 'ff' => 'Fulfulde', # Fulah 'fi' => 'Suomi', # Finnish 'fj' => 'Na Vosa Vakaviti', # Fijian - 'fo' => 'Føroyskt', # Faroese - 'fr' => 'Français', # French + 'fo' => 'Føroyskt', # Faroese + 'fr' => 'Français', # French 'fur' => 'Furlan', # Friulian 'fy' => 'Frysk', # Frisian 'ga' => 'Gaeilge', # Irish - 'gd' => 'Gàidhlig', # Scots Gaelic + 'gd' => 'Gàidhlig', # Scots Gaelic 'gl' => 'Galego', # Gallegan - 'gn' => 'Avañe\'ẽ', # Guarani - 'got' => '𐌲𐌿𐍄𐌹𐍃𐌺', # Gothic - 'gu' => 'ગુજરાતી', # Gujarati + 'gn' => 'Avañe\'ẽ', # Guarani + 'got' => 'x⡜xFЉx⡨xâ¡£x⡧xAЉ', # Gothic + 'gu' => 'ગુજરાતી', # Gujarati 'gv' => 'Gaelg', # Manx - 'ha' => 'هَوُسَ', # Hausa + 'ha' => 'هَوُسَ', # Hausa 'haw' => 'Hawai`i', # Hawaiian - 'he' => 'עברית', # Hebrew - 'hi' => 'हिन्दी', # Hindi + 'he' => 'עברית', # Hebrew + 'hi' => 'हिन्दी', # Hindi 'ho' => 'Hiri Motu', # Hiri Motu 'hr' => 'Hrvatski', # Croatian - 'ht' => 'Krèyol ayisyen', # Haitian, common/popular form is Kreyòl + 'ht' => 'Krèyol ayisyen', # Haitian, common/popular form is Kreyòl 'hu' => 'Magyar', # Hungarian - 'hy' => 'Հայերեն', # Armenian + 'hy' => 'Հայերեն', # Armenian 'hz' => 'Otsiherero', # Herero 'ia' => 'Interlingua', # Interlingua (IALA) 'id' => 'Bahasa Indonesia', # Indonesian 'ie' => 'Interlingue', # Interlingue (Occidental) 'ig' => 'Igbo', # Igbo - 'ii' => 'ꆇꉙ', # Sichuan Yi - 'ik' => 'Iñupiak', # Inupiak + 'ii' => 'ꆇꉙ', # Sichuan Yi + 'ik' => 'Iñupiak', # Inupiak 'io' => 'Ido', # Ido - 'is' => 'Íslenska', # Icelandic + 'is' => 'Íslenska', # Icelandic 'it' => 'Italiano', # Italian - 'iu' => 'ᐃᓄᒃᑎᑐᑦ', # Inuktitut - 'ja' => '日本語', # Japanese + 'iu' => 'ᐃᓄᒃᑎᑐᑦ', # Inuktitut + 'ja' => '日本語', # Japanese 'jbo' => 'Lojban', # Lojban 'jv' => 'Bahasa Jawa', # Javanese - 'ka' => 'ქართული', # Georgian + 'ka' => 'ქართული', # Georgian 'kg' => 'Kongo', # Kongo, (FIXME!) should probaly be KiKongo or KiKoongo - 'ki' => 'Gĩkũyũ', # Kikuyu, correctness not guaranteed + 'ki' => 'GÄ©kÅ©yÅ©', # Kikuyu, correctness not guaranteed 'kj' => 'Kuanyama', # Kuanyama (FIXME!) - 'kk' => 'қазақша', # Kazakh + 'kk' => 'қазақша', # Kazakh 'kl' => 'Kalaallisut', # Greenlandic - 'km' => 'ភាសាខ្មែរ', # Cambodian - 'kn' => 'ಕನ್ನಡ', # Kannada - 'ko' => '한국어', # Korean + 'km' => 'ភាសាខ្មែរ', # Cambodian + 'kn' => 'ಕನ್ನಡ', # Kannada + 'ko' => '한국어', # Korean 'kr' => 'Kanuri', # Kanuri (FIXME!) - 'ks' => 'कश्मीरी - (كشميري)', # Kashmiri - 'ku' => 'Kurdî', # Kurdish - 'kv' => 'Коми', # Komi, cyrillic is common script but also written in latin script + 'ks' => 'कश्मीरी - (كشميري)', # Kashmiri + 'ku' => 'Kurdî', # Kurdish + 'kv' => 'Коми', # Komi, cyrillic is common script but also written in latin script 'kw' => 'Kernewek', # Cornish - 'ky' => 'Kırgızca', # Kirghiz + 'ky' => 'Kırgızca', # Kirghiz 'la' => 'Latina', # Latin - 'lb' => 'Lëtzebuergesch', # Luxemburguish + 'lb' => 'Lëtzebuergesch', # Luxemburguish 'lg' => 'Luganda', # Ganda - 'li' => 'Lèmburgs', # Limburgian + 'li' => 'Lèmburgs', # Limburgian 'ln' => 'Lingala', # Lingala - 'lo' => 'ລາວ',# Laotian - 'lt' => 'Lietuvių', # Lithuanian - 'lv' => 'Latviešu', # Latvian + 'lo' => 'ລາວ',# Laotian + 'lt' => 'Lietuvių', # Lithuanian + 'lv' => 'LatvieÅ¡u', # Latvian 'mg' => 'Malagasy', # Malagasy 'mh' => 'Ebon', # Marshallese - 'mi' => 'Māori', # Maori - 'minnan' => 'Bân-lâm-gú', # Min-nan (also zh-min-nan) - 'mk' => 'Македонски', # Macedonian - 'ml' => 'മലയാളം', # Malayalam - 'mn' => 'Монгол', # Mongoloian + 'mi' => 'Māori', # Maori + 'minnan' => 'Bân-lâm-gú', # Min-nan (also zh-min-nan) + 'mk' => 'Македонски', # Macedonian + 'ml' => 'മലയാളം', # Malayalam + 'mn' => 'Монгол', # Mongoloian 'mo' => 'Moldoveana', # Moldovan - 'mr' => 'मराठी', # Marathi + 'mr' => 'मराठी', # Marathi 'ms' => 'Bahasa Melayu', # Malay 'mt' => 'bil-Malti', # Maltese 'mus' => 'Muscogee', # Creek, should possibly be Muskogee 'my' => 'Myanmasa', # Burmese - 'na' => 'Ekakairũ Naoero', # Nauruan - 'nah' => 'Nahuatl', # Nahuatl, en:Wikipedia writes Nahuatlahtolli, while another form is Náhuatl - 'nb' => 'Norsk (bokmål)', # Norwegian (Bokmal) - 'nds' => 'Plattdüütsch', # Low German ''or'' Low Saxon - 'ne' => 'नेपाली', # Nepali + 'na' => 'EkakairÅ© Naoero', # Nauruan + 'nah' => 'Nahuatl', # Nahuatl, en:Wikipedia writes Nahuatlahtolli, while another form is Náhuatl + 'nb' => 'Norsk (bokmål)', # Norwegian (Bokmal) + 'nds' => 'Plattdüütsch', # Low German ''or'' Low Saxon + 'ne' => 'नेपाली', # Nepali 'ng' => 'Oshiwambo', # Ndonga 'nl' => 'Nederlands', # Dutch 'nn' => 'Norsk (nynorsk)' , # Norwegian (Nynorsk) 'no' => 'Norsk', # Norwegian - 'non' => 'Norrǿna', # Old Norse - 'nv' => 'Diné bizaad', # Navajo + 'non' => 'NorrÇ¿na', # Old Norse + 'nv' => 'Diné bizaad', # Navajo 'ny' => 'Chi-Chewa', # Chichewa 'oc' => 'Occitan', # Occitan 'om' => 'Oromoo', # Oromo - 'or' => 'ଓଡ଼ିଆ', # Oriya - 'os' => 'Иронау', # Ossetic - 'pa' => 'ਪੰਜਾਬੀ', # Punjabi - 'pi' => 'पािऴ', # Pali + 'or' => 'ଓଡ଼ିଆ', # Oriya + 'os' => 'Иронау', # Ossetic + 'pa' => 'ਪੰਜਾਬੀ', # Punjabi + 'pi' => 'पािऴ', # Pali 'pl' => 'Polski', # Polish - 'ps' => 'پښتو', # Pashto - 'pt' => 'Português', # Portuguese + 'ps' => 'پښتو', # Pashto + 'pt' => 'Português', # Portuguese 'qu' => 'Runa Simi', # Quechua 'rm' => 'Rumantsch', # Raeto-Romance 'rn' => 'Kirundi', # Kirundi - 'ro' => 'Română', # Romanian - 'roa-rup' => 'Armâneashti', # Aromanian - 'ru' => 'Русский', # Russian + 'ro' => 'Română', # Romanian + 'roa-rup' => 'Armâneashti', # Aromanian + 'ru' => 'Русский', # Russian 'rw' => 'Kinyarwanda', # Kinyarwanda, should possibly be Kinyarwandi - 'sa' => 'संस्कृत', # Sanskrit + 'sa' => 'संस्कृत', # Sanskrit 'sc' => 'Sardu', # Sardinian 'scn' => 'Sicilianu', # Sicilian - 'sd' => 'सिनधि', # Sindhi - 'se' => 'Sámegiella', # Northern Sami - 'sg' => 'Sängö', # Sango, possible alternative is Sangho -# 'sh' => 'Српскохрватски (Srbskohrvatski)', ## Serbocroatian -- Obsolete - 'si' => 'සිංහල', # Sinhalese + 'sd' => 'सिनधि', # Sindhi + 'se' => 'Sámegiella', # Northern Sami + 'sg' => 'Sängö', # Sango, possible alternative is Sangho +# 'sh' => 'Српскохрватски (Srbskohrvatski)', ## Serbocroatian -- Obsolete + 'si' => 'සිංහල', # Sinhalese 'simple' => 'Simple English', # Simple English - 'sk' => 'Slovenčina', # Slovak - 'sl' => 'Slovenščina', # Slovenian + 'sk' => 'Slovenčina', # Slovak + 'sl' => 'Slovenščina', # Slovenian 'sm' => 'Gagana Samoa', # Samoan 'sn' => 'chiShona', # Shona 'so' => 'Soomaaliga', # Somali 'sq' => 'Shqip', # Albanian - 'sr' => 'Српски / Srpski', # Serbian + 'sr' => 'Српски / Srpski', # Serbian 'ss' => 'SiSwati', # Swati 'st' => 'seSotho', # Southern Sotho 'su' => 'Bahasa Sunda', # Sundanese 'sv' => 'Svenska', # Swedish 'sw' => 'Kiswahili', # Swahili - 'ta' => 'தமிழ்', # Tamil - 'te' => 'తెలుగు', # Telugu - 'tg' => 'Тоҷикӣ', # Tajik - 'th' => 'ไทย', # Thai - 'ti' => 'ትግርኛ', # Tigrinya - 'tk' => 'تركمن / Туркмен', # Turkmen + 'ta' => 'தமிழ்', # Tamil + 'te' => 'తెలుగు', # Telugu + 'tg' => 'Тоҷикӣ', # Tajik + 'th' => 'ไทย', # Thai + 'ti' => 'ትግርኛ', # Tigrinya + 'tk' => 'تركمن / Туркмен', # Turkmen 'tl' => 'Tagalog', # Tagalog (Filipino) #'tlh' => 'tlhIngan-Hol', # Klingon - no interlanguage links allowed 'tn' => 'Setswana', # Setswana @@ -185,32 +185,32 @@ 'tokipona' => 'Toki Pona', # Toki Pona 'tp' => 'Toki Pona', # Toki Pona - non-standard language code 'tpi' => 'Tok Pisin', # Tok Pisin - 'tr' => 'Türkçe', # Turkish + 'tr' => 'Türkçe', # Turkish 'ts' => 'Xitsonga', # Tsonga - 'tt' => 'Tatarça', # Tatar + 'tt' => 'Tatarça', # Tatar 'tum' => 'chiTumbuka', # Tumbuka 'tw' => 'Twi', # Twi, (FIXME!) - 'ty' => 'Reo Mā`ohi', # Tahitian + 'ty' => 'Reo Mā`ohi', # Tahitian 'ug' => 'Oyghurque', # Uyghur - 'uk' => 'Українська', # Ukrainian - 'ur' => 'اردو', # Urdu - 'uz' => 'Ўзбек', # Uzbek + 'uk' => 'Українська', # Ukrainian + 'ur' => 'اردو', # Urdu + 'uz' => 'Ўзбек', # Uzbek 've' => 'Tshivenda', # Venda - 'vi' => 'Tiếng Việt', # Vietnamese - 'vo' => 'Volapük', # Volapük + 'vi' => 'Tiếng Việt', # Vietnamese + 'vo' => 'Volapük', # Volapük 'wa' => 'Walon', # Walloon 'wo' => 'Wollof', # Wolof 'xh' => 'isiXhosa', # Xhosan - 'yi' => 'ייִדיש', # Yiddish - 'yo' => 'Yorùbá', # Yoruba + 'yi' => 'ייִדיש', # Yiddish + 'yo' => 'Yorùbá', # Yoruba 'za' => '(Cuengh)', # Zhuang - 'zh' => '中文', # (Zhōng Wén) - Chinese - 'zh-cfr' => '閩南語', # Min-nan alias (site is at minnan) - 'zh-cn' => '中文(简体)', # Simplified - 'zh-hk' => '中文(繁體)', # Traditional (Hong Kong) - 'zh-min-nan' => 'Bân-lâm-gú', # Min-nan - 'zh-sg' => '中文(简体)', # Simplified (Singapore) - 'zh-tw' => '中文(繁體)', # Traditional + 'zh' => '中文', # (Zhōng Wén) - Chinese + 'zh-cfr' => '閩南語', # Min-nan alias (site is at minnan) + 'zh-cn' => '中文(简体)', # Simplified + 'zh-hk' => '中文(繁體)', # Traditional (Hong Kong) + 'zh-min-nan' => 'Bân-lâm-gú', # Min-nan + 'zh-sg' => '中文(简体)', # Simplified (Singapore) + 'zh-tw' => '中文(繁體)', # Traditional 'zu' => 'isiZulu' # Zulu ); ?> -- 2.20.1