Per the link above, Rusyn may need automatic transliteration from Cyrillic to Latin.
Version: unspecified
Severity: enhancement
URL: https://www.mediawiki.org/wiki/Thread:Project:Support_desk/Transliteration_of_Rusyn_Wikipedia_(Wikipedias_in_Multi-writing_System)
ruedev wrote:
Hello, community discussion is here
and here
The rules are described on pages 41-43 here:
http://www.unipo.sk/public/media/11523/Rusinsky_jazyk_v_zrkadle.pdf
The implementation could look like:
var $mToLatin = array(
'дє' => 'd\'e', 'дї' => 'd\'i', 'дё' => 'd\'o', 'дю' => 'd\'u', 'дя' => 'd\'a',
'зє' => 'z\'e', 'зї' => 'z\'i', 'зё' => 'z\'o', 'зю' => 'z\'u', 'зя' => 'z\'a',
'лє' => 'l\'e', 'лї' => 'l\'i', 'лё' => 'l\'o', 'лю' => 'l\'u', 'ля' => 'l\'a',
'нє' => 'n\'e', 'нї' => 'n\'i', 'нё' => 'n\'o', 'ню' => 'n\'u', 'ня' => 'n\'a',
'рє' => 'r\'e', 'рї' => 'r\'i', 'рё' => 'r\'o', 'рю' => 'r\'u', 'ря' => 'r\'a',
'сє' => 's\'e', 'сї' => 's\'i', 'сё' => 's\'o', 'сю' => 's\'u', 'ся' => 's\'a',
'тє' => 't\'e', 'тї' => 't\'i', 'тё' => 't\'o', 'тю' => 't\'u', 'тя' => 't\'a',
'цє' => 'c\'e', 'цї' => 'c\'i', 'цё' => 'c\'o', 'цю' => 'c\'u', 'ця' => 'c\'a',
'а' => 'a', 'б' => 'b', 'в' => 'v', 'ґ' => 'g', 'г' => 'h',
'д' => 'd', 'е' => 'e', 'є' => 'je', 'ё' => 'jo', 'ж' => 'ž',
'з' => 'z', 'і' => 'i', 'ї' => 'ji', 'и' => 'î', 'ы' => 'y',
'й' => 'j', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n',
'о' => 'o', 'р' => 'r', 'п' => 'p', 'о' => 'o', 'с' => 's',
'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'ch', 'ц' => 'c',
'ч' => 'č', 'ш' => 'š', 'щ' => 'šč', 'ю' => 'ju', 'я' => 'ja',
'ь' => '\'', 'ъ' => '',
'Дє' => 'D\'e', 'Дї' => 'D\'i', 'Дё' => 'D\'o', 'Дю' => 'D\'u', 'Дя' => 'D\'a',
'Зє' => 'Z\'e', 'Зї' => 'Z\'i', 'Зё' => 'Z\'o', 'Зю' => 'Z\'u', 'Зя' => 'Z\'a',
'Лє' => 'L\'e', 'Лї' => 'L\'i', 'Лё' => 'L\'o', 'Лю' => 'L\'u', 'Ля' => 'L\'a',
'Нє' => 'N\'e', 'Нї' => 'N\'i', 'Нё' => 'N\'o', 'Ню' => 'N\'u', 'Ня' => 'N\'a',
'Рє' => 'R\'e', 'Рї' => 'R\'i', 'Рё' => 'R\'o', 'Рю' => 'R\'u', 'Ря' => 'R\'a',
'Сє' => 'S\'e', 'Сї' => 'S\'i', 'Сё' => 'S\'o', 'Сю' => 'S\'u', 'Ся' => 'S\'a',
'Тє' => 'T\'e', 'Тї' => 'T\'i', 'Тё' => 'T\'o', 'Тю' => 'T\'u', 'Тя' => 'T\'a',
'Цє' => 'C\'e', 'Цї' => 'C\'i', 'Цё' => 'C\'o', 'Цю' => 'C\'u', 'Ця' => 'C\'a',
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Ґ' => 'G', 'Г' => 'H',
'Д' => 'D', 'Е' => 'E', 'Є' => 'Je', 'Ё' => 'Jo', 'Ж' => 'Ž',
'З' => 'Z', 'І' => 'I', 'Ї' => 'Ji', 'И' => 'Î', 'Ы' => 'Y',
'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N',
'О' => 'O', 'Р' => 'R', 'П' => 'P', 'О' => 'O', 'С' => 'S',
'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'Ch', 'Ц' => 'C',
'Ч' => 'Č', 'Ш' => 'Š', 'Щ' => 'Šč', 'Ю' => 'Ju', 'Я' => 'Ja',
'Ь' => '\'', 'Ъ' => '',
);
var $mToCyrillics = array(
'd\'e' => 'дє', 'd\'i' => 'дї', 'd\'o' => 'дё', 'd\'u' => 'дю', 'd\'a' => 'дя',
'z\'e' => 'зє', 'z\'i' => 'зї', 'z\'o' => 'зё', 'z\'u' => 'зю', 'z\'a' => 'зя',
'l\'e' => 'лє', 'l\'i' => 'лї', 'l\'o' => 'лё', 'l\'u' => 'лю', 'l\'a' => 'ля',
'n\'e' => 'нє', 'n\'i'=> 'нї', 'n\'o' => 'нё', 'n\'u' => 'ню', 'n\'a' => 'ня',
'r\'e' => 'рє', 'r\'i' => 'рї', 'r\'o' => 'рё', 'r\'u' => 'рю', 'r\'a' => 'ря',
's\'e' => 'сє', 's\'i' => 'сї', 's\'o' => 'сё', 's\'u' => 'сю', 's\'a' => 'ся',
't\'e' => 'тє', 't\'i' => 'тї', 't\'o' => 'тё', 't\'u' => 'тю', 't\'a' => 'тя',
'c\'e' => 'цє', 'c\'i' => 'цї', 'c\'o' => 'цё', 'c\'u' => 'цю', 'c\'a' => 'ця',
'dje' => 'дъє', 'dji' => 'дъї', 'djo' => 'дъё', 'dju' => 'дъю', 'dja' => 'дъя',
'zje' => 'зъє', 'zji' => 'зъї', 'zjo' => 'зъё', 'zju' => 'зъю', 'zja' => 'зъя',
'lje' => 'лъє', 'lji' => 'лъї', 'ljo' => 'лъё', 'lju' => 'лъю', 'lja' => 'лъя',
'nje' => 'нъє', 'nji' => 'нъї', 'njo' => 'нъё', 'nju' => 'нъю', 'nja' => 'нъя',
'rje' => 'ръє', 'rji' => 'ръї', 'rjo' => 'ръё', 'rju' => 'ръю', 'rja' => 'ръя',
'sje' => 'съє', 'sji' => 'съї', 'sjo' => 'съё', 'sju' => 'съю', 'sja' => 'съя',
'tje' => 'тъє', 'tji' => 'тъї', 'tjo' => 'тъё', 'tju' => 'тъю', 'tja' => 'тъя',
'cje' => 'цъє', 'cji' => 'цъї', 'cjo' => 'цъё', 'cju' => 'цъю', 'cja' => 'цъя',
'a' => 'а', 'b' => 'б', 'v' => 'в', 'g' => 'ґ', 'h' => 'г',
'd' => 'д', 'e' => 'е', 'je' => 'є', 'jo' => 'ё', 'ž' => 'ж',
'z' => 'з', 'i' => 'і', 'ji' => 'ї', 'î' => 'и', 'y' => 'ы',
'j' => 'й', 'k' => 'к', 'l' => 'л', 'm' => 'м', 'n' => 'н',
'o' => 'о', 'r' => 'р', 'p' => 'п', 'o' => 'о', 's' => 'с',
't' => 'т', 'u' => 'у', 'f' => 'ф', 'ch' => 'х', 'c' => 'ц',
'č' => 'ч', 'š' => 'ш', 'šč' => 'щ', 'ju' => 'ю', 'ja' => 'я',
'\'' => 'ь',
'D\'e' => 'Дє', 'D\'i' => 'Дї', 'D\'o' => 'Дё', 'D\'u' => 'Дю', 'D\'a' => 'Дя',
'Z\'e' => 'Зє', 'Z\'i' => 'Зї', 'Z\'o' => 'Зё', 'Z\'u' => 'Зю', 'Z\'a' => 'Зя',
'L\'e' => 'Лє', 'L\'i' => 'Лї', 'L\'o' => 'Лё', 'L\'u' => 'Лю', 'L\'a' => 'Ля',
'N\'e' => 'Нє', 'N\'i' => 'Нї', 'N\'o' => 'Нё', 'N\'u' => 'Ню', 'N\'a' => 'Ня',
'R\'e' => 'Рє', 'R\'i' => 'Рї', 'R\'o' => 'Рё', 'R\'u' => 'Рю', 'R\'a' => 'Ря',
'S\'e' => 'Сє', 'S\'i' => 'Сї', 'S\'o' => 'Сё', 'S\'u' => 'Сю', 'S\'a' => 'Ся',
'T\'e' => 'Тє', 'T\'i' => 'Тї', 'T\'o' => 'Тё', 'T\'u' => 'Тю', 'T\'a' => 'Тя',
'C\'e' => 'Цє', 'C\'i' => 'Цї', 'C\'o' => 'Цё', 'C\'u' => 'Цю', 'C\'a' => 'Ця',
'Dje' => 'Дъє', 'Dji' => 'Дъї', 'Djo' => 'Дъё', 'Dju' => 'Дъю', 'Dja' => 'Дъя',
'Zje' => 'Зъє', 'Zji' => 'Зъї', 'Zjo' => 'Зъё', 'Zju' => 'Зъю', 'Zja' => 'Зъя',
'Lje' => 'Лъє', 'Lji' => 'Лъї', 'Ljo' => 'Лъё', 'Lju' => 'Лъю', 'Lja' => 'Лъя',
'Nje' => 'Нъє', 'Nji' => 'Нъї', 'Njo' => 'Нъё', 'Nju' => 'Нъю', 'Nja' => 'Нъя',
'Rje' => 'Ръє', 'Rji' => 'Ръї', 'Rjo' => 'Ръё', 'Rju' => 'Ръю', 'Rja' => 'Ръя',
'Sje' => 'Съє', 'Sji' => 'Съї', 'Sjo' => 'Съё', 'Sju' => 'Съю', 'Sja' => 'Съя',
'Tje' => 'Тъє', 'Tji' => 'Тъї', 'Tjo' => 'Тъё', 'Tju' => 'Тъю', 'Tja' => 'Тъя',
'Cje' => 'Цъє', 'Cji' => 'Цъї', 'Cjo' => 'Цъё', 'Cju' => 'Цъю', 'Cja' => 'Цъя',
'A' => 'А', 'B' => 'Б', 'V' => 'В', 'G' => 'Ґ', 'H' => 'Г',
'D' => 'Д', 'E' => 'Е', 'Je' => 'Є', 'Jo' => 'Ё', 'Ž' => 'Ж',
'Z' => 'З', 'I' => 'І', 'Ji' => 'Ї', 'Î' => 'И', 'Y' => 'Ы',
'J' => 'Й', 'K' => 'К', 'L' => 'Л', 'M' => 'М', 'N' => 'Н',
'O' => 'О', 'R' => 'Р', 'P' => 'П', 'O' => 'О', 'S' => 'С',
'T' => 'Т', 'U' => 'У', 'F' => 'Ф', 'Ch' => 'Х', 'C' => 'Ц',
'Č' => 'Ч', 'Š' => 'Ш', 'Šč' => 'Щ', 'Ju' => 'Ю', 'Ja' => 'Я',
);But it was not tested yet.
Best Regards
Gazeb
ruedev wrote:
Hello, there was a little change for transliteration of ы and и. This came from Institute of Ruthenian Language and Culture and was published in Rusínsky jazyk pre začiatočníkov http://www.unipo.sk/public/media/16948/Rus%C3%ADnsky%20jazyk%20pre%20za%C4%8Diato%C4%8Dn%C3%ADkov.pdf on page 149.
So the new rules would be:
var $mToLatin = array(
'дє' => 'd´e', 'дї' => 'd´i', 'дё' => 'd´o', 'дю' => 'd´u',
'дя' => 'd´a',
'зє' => 'z´e', 'зї' => 'z´i', 'зё' => 'z´o', 'зю' => 'z´u',
'зя' => 'z´a',
'лє' => 'l´e', 'лї' => 'l´i', 'лё' => 'l´o', 'лю' => 'l´u',
'ля' => 'l´a',
'нє' => 'n´e', 'нї' => 'n´i', 'нё' => 'n´o', 'ню' => 'n´u',
'ня' => 'n´a',
'рє' => 'r´e', 'рї' => 'r´i', 'рё' => 'r´o', 'рю' => 'r´u',
'ря' => 'r´a',
'сє' => 's´e', 'сї' => 's´i', 'сё' => 's´o', 'сю' => 's´u',
'ся' => 's´a',
'тє' => 't´e', 'тї' => 't´i', 'тё' => 't´o', 'тю' => 't´u',
'тя' => 't´a',
'цє' => 'c´e', 'цї' => 'c´i', 'цё' => 'c´o', 'цю' => 'c´u',
'ця' => 'c´a',
'а' => 'a', 'б' => 'b', 'в' => 'v', 'ґ' => 'g', 'г' => 'h', 'д' => 'd', 'е' => 'e', 'є' => 'je', 'ё' => 'jo', 'ж' => 'ž', 'з' => 'z', 'і' => 'i', 'ї' => 'ji', 'и' => 'y', 'ы' => 'ŷ', 'й' => 'j', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n', 'о' => 'o', 'р' => 'r', 'п' => 'p', 'о' => 'o', 'с' => 's', 'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'ch', 'ц' => 'c', 'ч' => 'č', 'ш' => 'š', 'щ' => 'šč', 'ю' => 'ju', 'я' => 'ja', 'ь' => '´', 'ъ' => '', 'Дє' => 'D´e', 'Дї' => 'D´i', 'Дё' => 'D´o', 'Дю' => 'D´u',
'Дя' => 'D´a',
'Зє' => 'Z´e', 'Зї' => 'Z´i', 'Зё' => 'Z´o', 'Зю' => 'Z´u',
'Зя' => 'Z´a',
'Лє' => 'L´e', 'Лї' => 'L´i', 'Лё' => 'L´o', 'Лю' => 'L´u',
'Ля' => 'L´a',
'Нє' => 'N´e', 'Нї' => 'N´i', 'Нё' => 'N´o', 'Ню' => 'N´u',
'Ня' => 'N´a',
'Рє' => 'R´e', 'Рї' => 'R´i', 'Рё' => 'R´o', 'Рю' => 'R´u',
'Ря' => 'R´a',
'Сє' => 'S´e', 'Сї' => 'S´i', 'Сё' => 'S´o', 'Сю' => 'S´u',
'Ся' => 'S´a',
'Тє' => 'T´e', 'Тї' => 'T´i', 'Тё' => 'T´o', 'Тю' => 'T´u',
'Тя' => 'T´a',
'Цє' => 'C´e', 'Цї' => 'C´i', 'Цё' => 'C´o', 'Цю' => 'C´u',
'Ця' => 'C´a',
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Ґ' => 'G', 'Г' => 'H',
'Д' => 'D', 'Е' => 'E', 'Є' => 'Je', 'Ё' => 'Jo', 'Ж' => 'Ž',
'З' => 'Z', 'І' => 'I', 'Ї' => 'Ji', 'И' => 'Y', 'Ы' => 'Ŷ',
'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N',
'О' => 'O', 'Р' => 'R', 'П' => 'P', 'О' => 'O', 'С' => 'S',
'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'Ch', 'Ц' => 'C',
'Ч' => 'Č', 'Ш' => 'Š', 'Щ' => 'Šč', 'Ю' => 'Ju', 'Я' => 'Ja',
'Ь' => '´', 'Ъ' => '',
);
var $mToCyrillics = array(
'd´e' => 'дє', 'd´i' => 'дї', 'd´o' => 'дё', 'd´u' =>'дю', 'd´a' => 'дя',
'z´e' => 'зє', 'z´i' => 'зї', 'z´o' => 'зё', 'z´u' =>
'зю', 'z´a' => 'зя',
'l´e' => 'лє', 'l´i' => 'лї', 'l´o' => 'лё', 'l´u' =>
'лю', 'l´a' => 'ля',
'n´e' => 'нє', 'n´i'=> 'нї', 'n´o' => 'нё', 'n´u' => 'ню',
'n´a' => 'ня',
'r´e' => 'рє', 'r´i' => 'рї', 'r´o' => 'рё', 'r´u' =>
'рю', 'r´a' => 'ря',
's´e' => 'сє', 's´i' => 'сї', 's´o' => 'сё', 's´u' =>
'сю', 's´a' => 'ся',
't´e' => 'тє', 't´i' => 'тї', 't´o' => 'тё', 't´u' =>
'тю', 't´a' => 'тя',
'c´e' => 'цє', 'c´i' => 'цї', 'c´o' => 'цё', 'c´u' =>
'цю', 'c´a' => 'ця',
'dje' => 'дъє', 'dji' => 'дъї', 'djo' => 'дъё', 'dju' =>
'дъю', 'dja' => 'дъя',
'zje' => 'зъє', 'zji' => 'зъї', 'zjo' => 'зъё', 'zju' =>
'зъю', 'zja' => 'зъя',
'lje' => 'лъє', 'lji' => 'лъї', 'ljo' => 'лъё', 'lju' =>
'лъю', 'lja' => 'лъя',
'nje' => 'нъє', 'nji' => 'нъї', 'njo' => 'нъё', 'nju' =>
'нъю', 'nja' => 'нъя',
'rje' => 'ръє', 'rji' => 'ръї', 'rjo' => 'ръё', 'rju' =>
'ръю', 'rja' => 'ръя',
'sje' => 'съє', 'sji' => 'съї', 'sjo' => 'съё', 'sju' =>
'съю', 'sja' => 'съя',
'tje' => 'тъє', 'tji' => 'тъї', 'tjo' => 'тъё', 'tju' =>
'тъю', 'tja' => 'тъя',
'cje' => 'цъє', 'cji' => 'цъї', 'cjo' => 'цъё', 'cju' =>
'цъю', 'cja' => 'цъя',
'a' => 'а', 'b' => 'б', 'v' => 'в', 'g' => 'ґ', 'h' => 'г', 'd' => 'д', 'e' => 'е', 'je' => 'є', 'jo' => 'ё', 'ž' => 'ж', 'z' => 'з', 'i' => 'і', 'ji' => 'ї', 'y' => 'и', 'ŷ' => 'ы', 'j' => 'й', 'k' => 'к', 'l' => 'л', 'm' => 'м', 'n' => 'н', 'o' => 'о', 'r' => 'р', 'p' => 'п', 'o' => 'о', 's' => 'с', 't' => 'т', 'u' => 'у', 'f' => 'ф', 'ch' => 'х', 'c' => 'ц', 'č' => 'ч', 'š' => 'ш', 'šč' => 'щ', 'ju' => 'ю', 'ja' => 'я', '´' => 'ь', 'D´e' => 'Дє', 'D´i' => 'Дї', 'D´o' => 'Дё', 'D´u' => 'Дю',
'D´a' => 'Дя',
'Z´e' => 'Зє', 'Z´i' => 'Зї', 'Z´o' => 'Зё', 'Z´u' => 'Зю',
'Z´a' => 'Зя',
'L´e' => 'Лє', 'L´i' => 'Лї', 'L´o' => 'Лё', 'L´u' => 'Лю',
'L´a' => 'Ля',
'N´e' => 'Нє', 'N´i' => 'Нї', 'N´o' => 'Нё', 'N´u' => 'Ню',
'N´a' => 'Ня',
'R´e' => 'Рє', 'R´i' => 'Рї', 'R´o' => 'Рё', 'R´u' => 'Рю',
'R´a' => 'Ря',
'S´e' => 'Сє', 'S´i' => 'Сї', 'S´o' => 'Сё', 'S´u' => 'Сю',
'S´a' => 'Ся',
'T´e' => 'Тє', 'T´i' => 'Тї', 'T´o' => 'Тё', 'T´u' => 'Тю',
'T´a' => 'Тя',
'C´e' => 'Цє', 'C´i' => 'Цї', 'C´o' => 'Цё', 'C´u' => 'Цю',
'C´a' => 'Ця',
'Dje' => 'Дъє', 'Dji' => 'Дъї', 'Djo' => 'Дъё', 'Dju' => 'Дъю',
'Dja' => 'Дъя',
'Zje' => 'Зъє', 'Zji' => 'Зъї', 'Zjo' => 'Зъё', 'Zju' => 'Зъю',
'Zja' => 'Зъя',
'Lje' => 'Лъє', 'Lji' => 'Лъї', 'Ljo' => 'Лъё', 'Lju' => 'Лъю',
'Lja' => 'Лъя',
'Nje' => 'Нъє', 'Nji' => 'Нъї', 'Njo' => 'Нъё', 'Nju' => 'Нъю',
'Nja' => 'Нъя',
'Rje' => 'Ръє', 'Rji' => 'Ръї', 'Rjo' => 'Ръё', 'Rju' => 'Ръю',
'Rja' => 'Ръя',
'Sje' => 'Съє', 'Sji' => 'Съї', 'Sjo' => 'Съё', 'Sju' => 'Съю',
'Sja' => 'Съя',
'Tje' => 'Тъє', 'Tji' => 'Тъї', 'Tjo' => 'Тъё', 'Tju' => 'Тъю',
'Tja' => 'Тъя',
'Cje' => 'Цъє', 'Cji' => 'Цъї', 'Cjo' => 'Цъё', 'Cju' => 'Цъю',
'Cja' => 'Цъя',
'A' => 'А', 'B' => 'Б', 'V' => 'В', 'G' => 'Ґ', 'H' => 'Г',
'D' => 'Д', 'E' => 'Е', 'Je' => 'Є', 'Jo' => 'Ё', 'Ž' => 'Ж',
'Z' => 'З', 'I' => 'І', 'Ji' => 'Ї', 'Y' => 'И', 'Ŷ' => 'Ы',
'J' => 'Й', 'K' => 'К', 'L' => 'Л', 'M' => 'М', 'N' => 'Н',
'O' => 'О', 'R' => 'Р', 'P' => 'П', 'O' => 'О', 'S' => 'С',
'T' => 'Т', 'U' => 'У', 'F' => 'Ф', 'Ch' => 'Х', 'C' => 'Ц',
'Č' => 'Ч', 'Š' => 'Ш', 'Šč' => 'Щ', 'Ju' => 'Ю', 'Ja' => 'Я',
);I don't see a patch here that could be reviewed (hence removing the keyword), but a good implementation proposal.
If you're interested and you think the code you pasted would work, please send it to gerrit: https://www.mediawiki.org/wiki/Gerrit/Tutorial
There aren't many people working on language converter, so having one of them prepare the patch for you could actually reduce the chances to get it approved.