#!/usr/local/bin/perl -p # http://czyborra.com/translit/iso9 1998-07-13 roman@czyborra.com # This little script is a partial implementation of the 1995 edition # international standard ISO 9 Transliteration of Cyrillic characters # into Latin characters. It takes a UTF-8 string as input and # replaces all applicable Cyrillic Unicode characters with their ISO 9 # Latin transliteration. # Some Latin transliterations like CAPITAL LETTER J WITH CARON do not # exist as precomposed characters in Unicode 2.0 and are expressed # with combining characters like CAPITAL LETTER J + COMBINING CARON. # For some historic letters like CYRILLIC LETTER OMEGA there seems to # be no transliteration in ISO 9, they are left untouched. For some # non-Slavic Cyrillic letters with an ISO 9 transliteration like # CYRILLIC LETTER YU WITH CARON there is no precomposed Unicode 2.0 # character but this script does not bother to look ahead for # combining characters and thus does not handle them all correctly. s;Ё;Ë;g; s;Ђ;Ð;g; s;Ѓ;Ǵ;g; s;Є;Ě;g; s;Ѕ;Ẑ;g; s;І;Ì;g; s;Ї;Ï;g; s;Ј;J̌;g; s;Љ;Ľ;g; s;Њ;Ň;g; s;Ћ;Ć;g; s;Ќ;Ḱ;g; s;Ў;Ǔ;g; s;Џ;D̂;g; s;А;A;g; s;Б;B;g; s;В;V;g; s;Г;G;g; s;Д;D;g; s;Е;E;g; s;Ж;Ž;g; s;З;Z;g; s;И;I;g; s;Й;J;g; s;К;K;g; s;Л;L;g; s;М;M;g; s;Н;N;g; s;О;O;g; s;П;P;g; s;Р;R;g; s;С;S;g; s;Т;T;g; s;У;U;g; s;Ф;F;g; s;Х;H;g; s;Ц;C;g; s;Ч;Č;g; s;Ш;Š;g; s;Щ;Ŝ;g; s;Ъ;";g; s;Ы;Y;g; s;Ь;';g; s;Э;È;g; s;Ю;Û;g; s;Я;Â;g; s;а;a;g; s;б;b;g; s;в;v;g; s;г;g;g; s;д;d;g; s;е;e;g; s;ж;ž;g; s;з;z;g; s;и;i;g; s;й;j;g; s;к;k;g; s;л;l;g; s;м;m;g; s;н;n;g; s;о;o;g; s;п;p;g; s;р;r;g; s;с;s;g; s;т;t;g; s;у;u;g; s;ф;f;g; s;х;h;g; s;ц;c;g; s;ч;č;g; s;ш;š;g; s;щ;ŝ;g; s;ъ;";g; s;ы;y;g; s;ь;';g; s;э;è;g; s;ю;û;g; s;я;â;g; s;ё;ë;g; s;ђ;đ;g; s;ѓ;ǵ;g; s;є;ê;g; s;ѕ;ẑ;g; s;і;ì;g; s;ї;ï;g; s;ј;ǰ;g; s;љ;l̂;g; s;њ;n̂;g; s;ћ;ć;g; s;ќ;ḱ;g; s;ў;ǔ;g; s;џ;d̂;g; s;Ѣ;Ě;g; s;ѣ;ě;g; s;Ѫ;Ǎ;g; s;ѫ;ǎ;g; s;Ѳ;F̀;g; s;ѳ;f̀;g; s;Ѵ;Ỳ;g; s;ѵ;ỳ;g; s;Ґ;G̀;g; s;ґ;g̀;g; s;Ғ;Ġ;g; s;ғ;ġ;g; s;Ҕ;Ğ;g; s;ҕ;ğ;g; s;Җ;Ž̦;g; s;җ;ž̦;g; s;Ҙ;Z̦;g; s;ҙ;z̦;g; s;Қ;K̦;g; s;қ;k̦;g; s;Ҝ;K̂;g; s;ҝ;k̂;g; s;Ҟ;K̄;g; s;ҟ;k̄;g; s;Ҡ;Ǩ;g; s;ҡ;ǩ;g; s;Ң;N̦;g; s;ң;n̦;g; s;Ҥ;Ṅ;g; s;ҥ;ṅ;g; s;Ҧ;Ṕ;g; s;ҧ;ṕ;g; s;Ҩ;Ò;g; s;ҩ;ò;g; s;Ҫ;Ș;g; s;ҫ;ș;g; s;Ҭ;Ț;g; s;ҭ;ț;g; s;Ү;Ù;g; s;ү;ù;g; s;Ұ;U̇;g; s;ұ;u̇;g; s;Ҳ;H̦;g; s;ҳ;h̦;g; s;Ҵ;C̄;g; s;ҵ;c̄;g; s;Ҷ;C̦;g; s;ҷ;c̥;g; s;Ҹ;Ĉ;g; s;ҹ;ĉ;g; s;Һ;Ḥ;g; s;һ;ḥ;g; s;Ҽ;C̅;g; s;ҽ;c̅;g; s;Ҿ;Ç̅;g; s;ҿ;ç̅;g; s;Ӏ;‡;g; s;Ӂ;Z̅;g; s;ӂ;z̅;g; s;Ӄ;Ḳ;g; s;ӄ;ḳ;g; s;Ӈ;Ṇ;g; s;ӈ;ṇ;g; s;Ӌ;C̣;g; s;ӌ;c̣;g; s;Ӑ;Ă;g; s;ӑ;ă;g; s;Ӓ;Ä;g; s;ӓ;ä;g; s;Ӕ;Æ;g; s;ӕ;æ;g; s;Ӗ;Ĕ;g; s;ӗ;ĕ;g; s;Ә;A̋;g; s;ә;a̋;g; s;Ӛ;À;g; s;ӛ;à;g; s;Ӝ;Z̄;g; s;ӝ;z̄;g; s;Ӟ;Z̈;g; s;ӟ;z̈;g; s;Ӡ;Ź;g; s;ӡ;ź;g; s;Ӣ;Ī;g; s;ӣ;ī;g; s;Ӥ;Î;g; s;ӥ;î;g; s;Ӧ;Ö;g; s;ӧ;ö;g; s;Ө;Ô;g; s;ө;ô;g; s;Ӫ;Ő;g; s;ӫ;ő;g; s;Ӯ;Ū;g; s;ӯ;ū;g; s;Ӱ;Ü;g; s;ӱ;ü;g; s;Ӳ;Ű;g; s;ӳ;ű;g; s;Ӵ;C̈;g; s;ӵ;c̈;g; s;Ӹ;Ÿ;g; s;ӹ;ÿ;g;