hepburn
Version:
Convert Japanese Hiragana and Katakana script to, and from, Romaji using Hepburn romanisation
400 lines (337 loc) • 15.2 kB
JavaScript
/*jslint node: true */
;
var bulkReplace = require("bulk-replace");
var hiraganaMonographs = {
"あ": "A", "い": "I", "う": "U", "え": "E", "お": "O",
"か": "KA", "き": "KI", "く": "KU", "け": "KE", "こ": "KO",
"さ": "SA", "し": "SHI", "す": "SU", "せ": "SE", "そ": "SO",
"た": "TA", "ち": "CHI", "つ": "TSU", "て": "TE", "と": "TO",
"な": "NA", "に": "NI", "ぬ": "NU", "ね": "NE", "の": "NO",
"は": "HA", "ひ": "HI", "ふ": "FU", "へ": "HE", "ほ": "HO",
"ま": "MA", "み": "MI", "む": "MU", "め": "ME", "も": "MO",
"や": "YA", "ゆ": "YU", "よ": "YO",
"ら": "RA", "り": "RI", "る": "RU", "れ": "RE", "ろ": "RO",
"わ": "WA", "ゐ": "WI", "ゑ": "WE", "を": "WO", "ん": "N'",
"が": "GA", "ぎ": "GI", "ぐ": "GU", "げ": "GE", "ご": "GO",
"ざ": "ZA", "じ": "JI", "ず": "ZU", "ぜ": "ZE", "ぞ": "ZO",
"だ": "DA", "ぢ": "DJI", "づ": "DZU", "で": "DE", "ど": "DO",
"ば": "BA", "び": "BI", "ぶ": "BU", "べ": "BE", "ぼ": "BO",
"ぱ": "PA", "ぴ": "PI", "ぷ": "PU", "ぺ": "PE", "ぽ": "PO"
};
var hiraganaDigraphs = {
"きゃ": "KYA", "きゅ": "KYU", "きょ": "KYO",
"しゃ": "SHA", "しゅ": "SHU", "しょ": "SHO",
"ちゃ": "CHA", "ちゅ": "CHU", "ちょ": "CHO",
"にゃ": "NYA", "にゅ": "NYU", "にょ": "NYO",
"ひゃ": "HYA", "ひゅ": "HYU", "ひょ": "HYO",
"みゃ": "MYA", "みゅ": "MYU", "みょ": "MYO",
"りゃ": "RYA", "りゅ": "RYU", "りょ": "RYO",
"ぎゃ": "GYA", "ぎゅ": "GYU", "ぎょ": "GYO",
"じゃ": "JA", "じゅ": "JU", "じょ": "JO",
"びゃ": "BYA", "びゅ": "BYU", "びょ": "BYO",
"ぴゃ": "PYA", "ぴゅ": "PYU", "ぴょ": "PYO"
};
var katakanaMonographs = {
"ア": "A", "イ": "I", "ウ": "U", "エ": "E", "オ": "O",
"カ": "KA", "キ": "KI", "ク": "KU", "ケ": "KE", "コ": "KO",
"サ": "SA", "シ": "SHI", "ス": "SU", "セ": "SE", "ソ": "SO",
"タ": "TA", "チ": "CHI", "ツ": "TSU", "テ": "TE", "ト": "TO",
"ナ": "NA", "ニ": "NI", "ヌ": "NU", "ネ": "NE", "ノ": "NO",
"ハ": "HA", "ヒ": "HI", "フ": "FU", "ヘ": "HE", "ホ": "HO",
"マ": "MA", "ミ": "MI", "ム": "MU", "メ": "ME", "モ": "MO",
"ヤ": "YA", "ユ": "YU", "ヨ": "YO",
"ラ": "RA", "リ": "RI", "ル": "RU", "レ": "RE", "ロ": "RO",
"ワ": "WA", "ヰ": "WI", "ヱ": "WE", "ヲ": "WO", "ン": "N",
"ガ": "GA", "ギ": "GI", "グ": "GU", "ゲ": "GE", "ゴ": "GO",
"ザ": "ZA", "ジ": "JI", "ズ": "ZU", "ゼ": "ZE", "ゾ": "ZO",
"ダ": "DA", "ヂ": "DJI", "ヅ": "DZU", "デ": "DE", "ド": "DO",
"バ": "BA", "ビ": "BI", "ブ": "BU", "ベ": "BE", "ボ": "BO",
"パ": "PA", "ピ": "PI", "プ": "PU", "ペ": "PE", "ポ": "PO"
};
var katakanaDigraphs = {
"アー": "Ā", "イー": "Ī", "ウー": "Ū", "エー": "Ē", "オー": "Ō",
"カー": "KĀ", "キー": "KĪ", "クー": "KŪ", "ケー": "KĒ", "コー": "KŌ",
"サー": "SĀ", "シー": "SHĪ", "スー": "SŪ", "セー": "SĒ", "ソー": "SŌ",
"ター": "TĀ", "チー": "CHĪ", "ツー": "TSŪ", "テー": "TĒ", "トー": "TŌ",
"ナー": "NĀ", "ニー": "NĪ", "ヌー": "NŪ", "ネー": "NĒ", "ノー": "NŌ",
"ハー": "HĀ", "ヒー": "HĪ", "フー": "FŪ", "ヘー": "HĒ", "ホー": "HŌ",
"マー": "MĀ", "ミー": "MĪ", "ムー": "MŪ", "メー": "MĒ", "モー": "MŌ",
"ヤー": "YĀ", "ユー": "YŪ", "ヨー": "YŌ",
"ラー": "RĀ", "リー": "RĪ", "ルー": "RŪ", "レー": "RĒ", "ロー": "RŌ",
"ワー": "WĀ", "ヰー": "WĪ", "ヱー": "WĒ", "ヲー": "WŌ", "ンー": "N",
"ガー": "GĀ", "ギー": "GĪ", "グー": "GŪ", "ゲー": "GĒ", "ゴー": "GŌ",
"ザー": "ZĀ", "ジー": "JĪ", "ズー": "ZŪ", "ゼー": "ZĒ", "ゾー": "ZŌ",
"ダー": "DĀ", "ヂー": "DJĪ", "ヅー": "DZŪ", "デー": "DĒ", "ドー": "DŌ",
"バー": "BĀ", "ビー": "BĪ", "ブー": "BŪ", "ベー": "BĒ", "ボー": "BŌ",
"パー": "PĀ", "ピー": "PĪ", "プー": "PŪ", "ペー": "PĒ", "ポー": "PŌ",
"キャ": "KYA", "キュ": "KYU", "キョ": "KYO",
"シャ": "SHA", "シュ": "SHU", "ショ": "SHO",
"チャ": "CHA", "チュ": "CHU", "チョ": "CHO",
"ニャ": "NYA", "ニュ": "NYU", "ニョ": "NYO",
"ヒャ": "HYA", "ヒュ": "HYU", "ヒョ": "HYO",
"ミャ": "MYA", "ミュ": "MYU", "ミョ": "MYO",
"リャ": "RYA", "リュ": "RYU", "リョ": "RYO",
"ギャ": "GYA", "ギュ": "GYU", "ギョ": "GYO",
"ジャ": "JA", "ジュ": "JU", "ジョ": "JO",
"ビャ": "BYA", "ビュ": "BYU", "ビョ": "BYO",
"ピャ": "PYA", "ピュ": "PYU", "ピョ": "PYO",
"クヮ": "KWA", "クィ": "KWI", "クェ": "KWE", "クォ": "KWO",
"グヮ": "GWA", "スィ": "SI", "シェ": "SHE", "ズィ": "ZI", "ジェ": "JE",
"ティ": "TI", "トゥ": "TU", "テュ": "TYU", "チェ": "CHE",
"ツァ": "TSA", "ツィ": "TSI", "ツェ": "TSE", "ツォ": "TSO",
"ディ": "DI" , "ドゥ": "DU", "デュ": "DYU", "ホゥ": "HU",
"ファ": "FA", "フィ": "FI", "フェ": "FE", "フォ": "FO", "フュ": "FYU",
"イィ": "YI", "イェ": "YE",
"ウィ": "WI", "ウゥ": "WU", "ウェ": "WE", "ウォ": "WO",
"ヴァ": "VA", "ヴィ": "VI", "ヴ": "VU", "ヴェ": "VE", "ヴォ": "VO", "ヴュ": "VYU"
};
var katakanaTrigraphs = {
"キャー": "KYĀ", "キュー": "KYŪ", "キョー": "KYŌ",
"シャー": "SHĀ", "シュー": "SHŪ", "ショー": "SHŌ",
"チャー": "CHĀ", "チュー": "CHŪ", "チョー": "CHŌ",
"ニャー": "NYĀ", "ニュー": "NYŪ", "ニョー": "NYŌ",
"ヒャー": "HYĀ", "ヒュー": "HYŪ", "ヒョー": "HYŌ",
"ミャー": "MYĀ", "ミュー": "MYŪ", "ミョー": "MYŌ",
"リャー": "RYĀ", "リュー": "RYŪ", "リョー": "RYŌ",
"ギャー": "GYĀ", "ギュー": "GYŪ", "ギョー": "GYŌ",
"ジャー": "JĀ", "ジュー": "JŪ", "ジョー": "JŌ",
"ビャー": "BYĀ", "ビュー": "BYŪ", "ビョー": "BYŌ",
"ピャー": "PYĀ", "ピュー": "PYŪ", "ピョー": "PYŌ"
};
var katakanaHalfwidths = {
"ｱ": "ア", "ｲ": "イ", "ｳ": "ウ", "ｴ": "エ", "ｵ": "オ",
"ｶ": "カ", "ｷ": "キ", "ｸ": "ク", "ｹ": "ケ", "ｺ": "コ",
"ｻ": "サ", "ｼ": "シ", "ｽ": "ス", "ｾ": "セ", "ｿ": "ソ",
"ﾀ": "タ", "ﾁ": "チ", "ﾂ": "ツ", "ﾃ": "テ", "ﾄ": "ト",
"ﾅ": "ナ", "ﾆ": "ニ", "ﾇ": "ヌ", "ﾈ": "ネ", "ﾉ": "ノ",
"ﾊ": "ハ", "ﾋ": "ヒ", "ﾌ": "フ", "ﾍ": "ヘ", "ﾎ": "ホ",
"ﾏ": "マ", "ﾐ": "ミ", "ﾑ": "ム", "ﾒ": "メ", "ﾓ": "モ",
"ﾔ": "ヤ", "ﾕ": "ユ", "ﾖ": "ヨ",
"ﾗ": "ラ", "ﾘ": "リ", "ﾙ": "ル", "ﾚ": "レ", "ﾛ": "ロ",
"ﾜ": "ワ", "ｦ": "ヲ", "ﾝ": "ン",
"ｶﾞ": "ガ", "ｷﾞ": "ギ", "ｸﾞ": "グ", "ｹﾞ": "ゲ", "ｺﾞ": "ゴ",
"ｻﾞ": "ザ", "ｼﾞ": "ジ", "ｽﾞ": "ズ", "ｾﾞ": "ゼ", "ｿﾞ": "ゾ",
"ﾀﾞ": "ダ", "ﾁﾞ": "ヂ", "ﾂﾞ": "ヅ", "ﾃﾞ": "デ", "ﾄﾞ": "ド",
"ﾊﾞ": "バ", "ﾋﾞ": "ビ", "ﾌﾞ": "ブ", "ﾍﾞ": "ベ", "ﾎﾞ": "ボ",
"ﾊﾟ": "パ", "ﾋﾟ": "ピ", "ﾌﾟ": "プ", "ﾍﾟ": "ペ", "ﾎﾟ": "ポ",
"ｧ": "ァ", "ｨ": "ィ", "ｩ": "ゥ", "ｪ": "ェ", "ｫ": "ォ",
"ｬ": "ャ", "ｭ": "ュ", "ｮ": "ョ",
"ｯ": "ッ", "ｰ": "ー"
}
var katakanaHalfwidthsCombined = {
"ｶﾞ": "ガ", "ｷﾞ": "ギ", "ｸﾞ": "グ", "ｹﾞ": "ゲ", "ｺﾞ": "ゴ",
"ｻﾞ": "ザ", "ｼﾞ": "ジ", "ｽﾞ": "ズ", "ｾﾞ": "ゼ", "ｿﾞ": "ゾ",
"ﾀﾞ": "ダ", "ﾁﾞ": "ヂ", "ﾂﾞ": "ヅ", "ﾃﾞ": "デ", "ﾄﾞ": "ド",
"ﾊﾞ": "バ", "ﾋﾞ": "ビ", "ﾌﾞ": "ブ", "ﾍﾞ": "ベ", "ﾎﾞ": "ボ",
"ﾊﾟ": "パ", "ﾋﾟ": "ピ", "ﾌﾟ": "プ", "ﾍﾟ": "ペ", "ﾎﾟ": "ポ"
}
var choonpu = "ー";
var yoonHiragana = "ぁぃぅぇぉゃゅょゎゕ";
var yoonKatakana = "ァィゥェォャュョヮヵ";
var sokuonHiragana = "っ";
var sokuonKatakana = "ッ";
var sokuons = sokuonKatakana + sokuonHiragana;
var katakanaSplitCombinators = choonpu + yoonKatakana + sokuonKatakana;
var hiraganaSplitCombinators = choonpu + yoonHiragana + sokuonHiragana;
var kanaSplitCombinators = katakanaSplitCombinators + hiraganaSplitCombinators;
// Used to convert old Nihon-Shiki style romaji into the modern Hepburn form.
// Source: http://nayuki.eigenstate.org/page/variations-on-japanese-romanization
var nihonShiki = {
"SI": "SHI",
"ZI": "JI",
"TI": "CHI",
"DI": "JI",
"TU": "TSU",
"DU": "ZU",
"SHU": "SHU", // Prevent HU from accidentally converting
"CHU": "CHU",
"HU": "FU",
"CYA": "CHA",
"CYO": "CHO",
"CYU": "CHU",
"CHY": "CH",
"SYA": "SHA",
"SYU": "SHU",
"SYO": "SHO",
"SHY": "SH",
"ZYA": "JA",
"ZYU": "JU",
"ZYO": "JO",
"TYA": "CHA",
"TYU": "CHU",
"TYO": "CHO",
"DYA": "JA",
"DYU": "JU",
"DYO": "JO"
};
function keysToRegex(obj) {
return new RegExp(Object.keys(obj).join('|'), "g");
}
// For use with toHiragana
var hiraganaMap = {};
Object.keys(hiraganaMonographs).forEach(function(key) {
var value = hiraganaMonographs[key];
if (!(value in hiraganaMap)) {
hiraganaMap[value] = key;
}
});
Object.keys(hiraganaDigraphs).forEach(function(key) {
var value = hiraganaDigraphs[key];
if (!(value in hiraganaMap)) {
hiraganaMap[value] = key;
}
});
var hiraganaRegex = new RegExp(Object.keys(hiraganaMap).sort(function(a, b) {
return b.length - a.length;
}).join("|"), "g");
var hiraganaMonographsRegex = keysToRegex(hiraganaMonographs);
var hiraganaDigraphsRegex = keysToRegex(hiraganaDigraphs);
// For use with toKatakana
var katakanaMap = {};
Object.keys(katakanaMonographs).forEach(function(key) {
var value = katakanaMonographs[key];
if (!(value in katakanaMap)) {
katakanaMap[value] = key;
}
});
Object.keys(katakanaDigraphs).forEach(function(key) {
var value = katakanaDigraphs[key];
if (!(value in katakanaMap)) {
katakanaMap[value] = key;
}
});
Object.keys(katakanaTrigraphs).forEach(function(key) {
var value = katakanaTrigraphs[key];
if (!(value in katakanaMap)) {
katakanaMap[value] = key;
}
});
var katakanaRegex = new RegExp(Object.keys(katakanaMap).sort(function(a, b) {
return b.length - a.length;
}).join("|"), "g");
var katakanaMonographsRegex = keysToRegex(katakanaMonographs);
var katakanaDigraphsRegex = keysToRegex(katakanaDigraphs);
var katakanaHalfwidthsCombinedRegex = keysToRegex(katakanaHalfwidthsCombined);
var katakanaHalfwidthsRegex = keysToRegex(katakanaHalfwidths);
var nihonShikiRegex = keysToRegex(nihonShiki);
// API
exports.fromKana = function(str) {
// Initial transliteration
str = bulkReplace(str, katakanaHalfwidthsCombinedRegex, katakanaHalfwidthsCombined);
str = bulkReplace(str, katakanaHalfwidthsRegex, katakanaHalfwidths);
str = bulkReplace(str, hiraganaDigraphsRegex, hiraganaDigraphs);
str = bulkReplace(str, katakanaDigraphsRegex, katakanaDigraphs);
str = bulkReplace(str, hiraganaMonographsRegex, hiraganaMonographs);
str = bulkReplace(str, katakanaMonographsRegex, katakanaMonographs);
// Correct use of sokuon
str = str.replace(/[っッ]C/g, "TC").replace(/[っッ](.)/g, "$1$1");
// Correct usage of N' (M' is a common mistake)
str = str.replace(/[NM]'([^YAEIOU]|$)/g, "N$1");
// Correct use of choonpu
str = str.replace(/Aー/g, "Ā");
str = str.replace(/Iー/g, "Ī");
str = str.replace(/Uー/g, "Ū");
str = str.replace(/Eー/g, "Ē");
str = str.replace(/Oー/g, "Ō");
return str;
};
exports.toHiragana = function(str) {
// All conversion is done in upper-case
str = str.toUpperCase();
// Correct use of sokuon
str = str.replace(/TC/g, "っC");
str = str.replace(/([^AEIOUN])\1/g, "っ$1");
// Transliteration
str = bulkReplace(str, hiraganaRegex, hiraganaMap);
// Fix any remaining N/M usage (that isn't a N' usage)
str = str.replace(/N|M/g, "ん");
return str;
};
exports.toKatakana = function(str) {
// All conversion is done in upper-case
str = str.toUpperCase();
// Correct use of sokuon
str = str.replace(/TC/g, "ッC");
str = str.replace(/([^AEIOUN])\1/g, "ッ$1");
// Transliteration
str = bulkReplace(str, katakanaRegex, katakanaMap);
// Fix any remaining N/M usage (that isn't a N' usage)
str = str.replace(/N|M/g, "ン");
return str;
};
exports.cleanRomaji = function(str) {
// Follows many of the suggestions from:
// http://nayuki.eigenstate.org/page/variations-on-japanese-romanization
// All conversion is done in upper-case
str = str.toUpperCase();
// Should be using N instead of M
str = str.replace(/(\w)M([^AEIOUY]|$)/g, "$1N$2");
// Convert the NN form into the more common N'
str = str.replace(/NN/g, "N'");
// Convert usage of OU into the more common OO
// Handle cases like Toukyou
str = str.replace(/OU/g, "OO");
// Fix antiquated usage of OH to mean OO
// (handle ambiguous cases like 'Kohusai' vs. 'Tohkyoh')
str = str.replace(/OH([^AIEO]|$)/g, "OO$1");
// Replace old Nihon-shiki usage with modern Hepburn form
str = bulkReplace(str, nihonShikiRegex, nihonShiki);
return str;
};
exports.splitKana = function(str) {
return str.split("").reduce(function(r, h) {
// if current kana is a combinator
// or previous syllable and current character both aren't kanas
// then merge with previous syllable if any
if (
r[r.length - 1] && h.trim() &&
(kanaSplitCombinators.includes(h) ||
(!exports.containsHiragana(r[r.length - 1]) &&
!exports.containsKatakana(r[r.length - 1]) &&
(!exports.containsHiragana(h) && !exports.containsKatakana(h))))
) {
r[r.length - 1] += h;
} else {
r.push(h);
}
return r;
}, []);
};
// known issue: unclean romaji might get too chopped up
// e.g. "CHYA" becomes ["C", "HYA"]
exports.splitRomaji = function(str) {
return exports.splitKana(exports.toKatakana(str)).map((k, i, ks) => {
// if syllable's last character is a sokuon
// add the first letter of the following syllable if any
// to the end of current syllable
if (i < ks.length - 1 && sokuons.includes(k.slice(-1)[0])) {
const next = ks[i + 1];
const nextRomaji =
exports.containsHiragana(next) || exports.containsKatakana(next)
? exports.fromKana(next)
: next;
var nextLetter = nextRomaji[0]
// correct CC/TC use of sokuon
if (nextLetter === 'C') {
nextLetter = 'T'
}
const r = exports.fromKana(k.slice(0, -1)) + nextLetter;
return r;
}
return exports.fromKana(k);
})
}
exports.containsHiragana = function(str) {
hiraganaMonographsRegex.lastIndex = 0;
return hiraganaMonographsRegex.test(str);
};
exports.containsKatakana = function(str) {
katakanaMonographsRegex.lastIndex = katakanaHalfwidthsRegex.lastIndex = 0;
return katakanaMonographsRegex.test(str) || katakanaHalfwidthsRegex.test(str);
};
exports.containsKana = function(str){
return (exports.containsHiragana(str) || exports.containsKatakana(str));
};
exports.containsKanji = function(str){
return /[\u4e00-\u9fcf\uf900-\ufaff\u3400-\u4dbf]/.test(str);
}