cizgile 0.1.0 → 0.2.0

package/dist/transliterate.mjs

@@ -1,6 +1,7 @@
-import { C as latin, S as symbols, _ as fold, a as fi, b as stripMarks, c as it, d as nl, f as pt, g as DEFAULT_TABLES, h as vi, i as es, l as latinLocales, m as tr, n as da, o as fr, p as sv, r as de, s as hu, t as az, u as nb, v as lookup, x as transliterate, y as resolveTables } from "./shared/locales-latin-D8enWKzw.mjs";
+import { A as fold, C as sl, D as DEFAULT_TABLES, E as vi, F as symbols, I as latin, M as resolveTables, N as stripMarks, P as transliterate, S as sk, T as tr, _ as nb, a as de, b as pt, c as fi, d as hu, f as is, g as lv, h as lt, i as da, j as lookup, l as fr, m as latinLocales, n as ca, o as es, p as it, r as cs, s as et, t as az, u as hr, v as nl, w as sv, x as ro, y as pl } from "./shared/locales-latin-Bm94HAeL.mjs";
 
 //#region src/transliterate/arabic.ts
+/** Arabic letters to Latin; short vowels are marks and fall away. */
 const arabic = {
 	ء: "e",
 	آ: "a",
@@ -61,6 +62,7 @@ const arabic = {
 	"،": ",",
 	"؛": ";"
 };
+/** Persian letters that differ from Arabic: `پ چ ژ گ` and the Persian yeh and kaf. */
 const persian = {
 	چ: "ch",
 	ک: "k",
@@ -79,6 +81,7 @@ const persian = {
 	"۸": "8",
 	"۹": "9"
 };
+/** Urdu letters that differ from Arabic: `ٹ ڈ ڑ ں ے`. */
 const urdu = {
 	ٹ: "t",
 	ڈ: "d",
@@ -88,6 +91,7 @@ const urdu = {
 	ھ: "h",
 	ے: "e"
 };
+/** Pashto letters that differ from Arabic: `ټ ډ ړ ږ ښ ڼ`. */
 const pashto = {
 	ټ: "t",
 	ځ: "z",
@@ -105,6 +109,7 @@ const pashto = {
 
 //#endregion
 //#region src/transliterate/armenian.ts
+/** Armenian to Latin; `ե` and `ո` take their word-initial spelling on the capital. */
 const armenian = {
 	ու: "u",
 	Ու: "U",
@@ -195,6 +200,7 @@ const armenian = {
 
 //#endregion
 //#region src/transliterate/cyrillic.ts
+/** Cyrillic to Latin, the simov/slugify values, covering Russian, Kazakh, Belarusian and the other national alphabets. */
 const cyrillic = {
 	А: "A",
 	а: "a",
@@ -323,6 +329,7 @@ const cyrillic = {
 	Ѵ: "I",
 	ѵ: "i"
 };
+/** Ukrainian refinements: `г` is `h`, `и` is `y`, `є ї й ю я` take their word-initial spelling on the capital. */
 const cyrillicUk = {
 	Г: "H",
 	г: "h",
@@ -341,6 +348,7 @@ const cyrillicUk = {
 	Я: "Ya",
 	я: "ia"
 };
+/** Bulgarian refinements: `щ` is `sht`, `ъ` is `a`. */
 const cyrillicBg = {
 	Й: "Y",
 	й: "y",
@@ -353,6 +361,7 @@ const cyrillicBg = {
 	Ь: "Y",
 	ь: "y"
 };
+/** Macedonian refinements: `ѓ ќ ѕ џ љ њ`. */
 const cyrillicMk = {
 	Х: "H",
 	х: "h",
@@ -365,6 +374,7 @@ const cyrillicMk = {
 	Ш: "S",
 	ш: "s"
 };
+/** Serbian refinements: `ђ ћ џ љ њ`, `х` is `h`. */
 const cyrillicSr = {
 	Х: "H",
 	х: "h",
@@ -386,11 +396,13 @@ const cyrillicSr = {
 
 //#endregion
 //#region src/transliterate/define.ts
+/** One table from many; later tables win. Returns a new object. */
 function mergeTables(...tables) {
 	const out = {};
 	for (const table of tables) Object.assign(out, table);
 	return out;
 }
+/** A new locale from `base` with `overrides` merged in; neither object is mutated. */
 function defineLocale(base, overrides = {}) {
 	const out = {
 		id: overrides.id ?? base.id,
@@ -405,6 +417,7 @@ function defineLocale(base, overrides = {}) {
 
 //#endregion
 //#region src/transliterate/dhivehi.ts
+/** Thaana (Dhivehi) to Latin, the sindresorhus/transliterate values. */
 const dhivehi = {
 	ހ: "h",
 	ށ: "sh",
@@ -459,6 +472,7 @@ const dhivehi = {
 
 //#endregion
 //#region src/transliterate/georgian.ts
+/** Georgian Mkhedruli to Latin. */
 const georgian = {
 	ა: "a",
 	ბ: "b",
@@ -503,6 +517,7 @@ const georgian = {
 
 //#endregion
 //#region src/transliterate/greek.ts
+/** Modern Greek to Latin: `η` and `ι` are `i`, `β` is `v`, `θ` is `th`. */
 const greek = {
 	α: "a",
 	β: "v",
@@ -563,28 +578,484 @@ const greek = {
 	Ϲ: "S"
 };
 
+//#endregion
+//#region src/transliterate/hangul.ts
+/** Hangul jamo to Revised Romanization, jamo by jamo; precomposed syllables reach it through NFD, with no sound-change rules across syllables. */
+const hangul = {
+	ᄀ: "g",
+	ᄁ: "kk",
+	ᄂ: "n",
+	ᄃ: "d",
+	ᄄ: "tt",
+	ᄅ: "r",
+	ᄆ: "m",
+	ᄇ: "b",
+	ᄈ: "pp",
+	ᄉ: "s",
+	ᄊ: "ss",
+	ᄋ: "",
+	ᄌ: "j",
+	ᄍ: "jj",
+	ᄎ: "ch",
+	ᄏ: "k",
+	ᄐ: "t",
+	ᄑ: "p",
+	ᄒ: "h",
+	ᅡ: "a",
+	ᅢ: "ae",
+	ᅣ: "ya",
+	ᅤ: "yae",
+	ᅥ: "eo",
+	ᅦ: "e",
+	ᅧ: "yeo",
+	ᅨ: "ye",
+	ᅩ: "o",
+	ᅪ: "wa",
+	ᅫ: "wae",
+	ᅬ: "oe",
+	ᅭ: "yo",
+	ᅮ: "u",
+	ᅯ: "wo",
+	ᅰ: "we",
+	ᅱ: "wi",
+	ᅲ: "yu",
+	ᅳ: "eu",
+	ᅴ: "ui",
+	ᅵ: "i",
+	ᆨ: "k",
+	ᆩ: "k",
+	ᆪ: "k",
+	ᆫ: "n",
+	ᆬ: "n",
+	ᆭ: "n",
+	ᆮ: "t",
+	ᆯ: "l",
+	ᆰ: "k",
+	ᆱ: "m",
+	ᆲ: "l",
+	ᆳ: "l",
+	ᆴ: "l",
+	ᆵ: "p",
+	ᆶ: "l",
+	ᆷ: "m",
+	ᆸ: "p",
+	ᆹ: "p",
+	ᆺ: "t",
+	ᆻ: "t",
+	ᆼ: "ng",
+	ᆽ: "t",
+	ᆾ: "t",
+	ᆿ: "k",
+	ᇀ: "t",
+	ᇁ: "p",
+	ᇂ: "t",
+	ㄱ: "g",
+	ㄲ: "kk",
+	ㄳ: "gs",
+	ㄴ: "n",
+	ㄵ: "nj",
+	ㄶ: "nh",
+	ㄷ: "d",
+	ㄸ: "tt",
+	ㄹ: "r",
+	ㄺ: "lg",
+	ㄻ: "lm",
+	ㄼ: "lb",
+	ㄽ: "ls",
+	ㄾ: "lt",
+	ㄿ: "lp",
+	ㅀ: "lh",
+	ㅁ: "m",
+	ㅂ: "b",
+	ㅃ: "pp",
+	ㅄ: "bs",
+	ㅅ: "s",
+	ㅆ: "ss",
+	ㅇ: "ng",
+	ㅈ: "j",
+	ㅉ: "jj",
+	ㅊ: "ch",
+	ㅋ: "k",
+	ㅌ: "t",
+	ㅍ: "p",
+	ㅎ: "h",
+	ㅏ: "a",
+	ㅐ: "ae",
+	ㅑ: "ya",
+	ㅒ: "yae",
+	ㅓ: "eo",
+	ㅔ: "e",
+	ㅕ: "yeo",
+	ㅖ: "ye",
+	ㅗ: "o",
+	ㅘ: "wa",
+	ㅙ: "wae",
+	ㅚ: "oe",
+	ㅛ: "yo",
+	ㅜ: "u",
+	ㅝ: "wo",
+	ㅞ: "we",
+	ㅟ: "wi",
+	ㅠ: "yu",
+	ㅡ: "eu",
+	ㅢ: "ui",
+	ㅣ: "i"
+};
+
+//#endregion
+//#region src/transliterate/hebrew.ts
+/** Hebrew consonants to Latin, final forms and Yiddish ligatures included; vowel points fall away. */
+const hebrew = {
+	א: "",
+	ב: "b",
+	ג: "g",
+	ד: "d",
+	ה: "h",
+	ו: "v",
+	ז: "z",
+	ח: "ch",
+	ט: "t",
+	י: "y",
+	כ: "k",
+	ך: "k",
+	ל: "l",
+	מ: "m",
+	ם: "m",
+	נ: "n",
+	ן: "n",
+	ס: "s",
+	ע: "",
+	פ: "p",
+	ף: "f",
+	צ: "ts",
+	ץ: "ts",
+	ק: "k",
+	ר: "r",
+	ש: "sh",
+	ת: "t",
+	װ: "v",
+	ױ: "oy",
+	ײ: "ey",
+	"׳": "",
+	"״": "",
+	"־": " ",
+	"׀": " ",
+	"׆": ""
+};
+
+//#endregion
+//#region src/transliterate/kana.ts
+/** Hiragana and katakana to Hepburn, digraphs and foreign-sound combinations included; the long-vowel mark and sokuon are dropped, kanji is left alone. */
+const kana = {
+	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: "o",
+	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: "ji",
+	づ: "zu",
+	で: "de",
+	ど: "do",
+	ば: "ba",
+	び: "bi",
+	ぶ: "bu",
+	べ: "be",
+	ぼ: "bo",
+	ぱ: "pa",
+	ぴ: "pi",
+	ぷ: "pu",
+	ぺ: "pe",
+	ぽ: "po",
+	ゔ: "vu",
+	ぁ: "a",
+	ぃ: "i",
+	ぅ: "u",
+	ぇ: "e",
+	ぉ: "o",
+	ゃ: "ya",
+	ゅ: "yu",
+	ょ: "yo",
+	ゎ: "wa",
+	っ: "",
+	ゕ: "ka",
+	ゖ: "ke",
+	ゝ: "",
+	ゞ: "",
+	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",
+	ぢゃ: "ja",
+	ぢゅ: "ju",
+	ぢょ: "jo",
+	びゃ: "bya",
+	びゅ: "byu",
+	びょ: "byo",
+	ぴゃ: "pya",
+	ぴゅ: "pyu",
+	ぴょ: "pyo",
+	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: "o",
+	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: "ji",
+	ヅ: "zu",
+	デ: "de",
+	ド: "do",
+	バ: "ba",
+	ビ: "bi",
+	ブ: "bu",
+	ベ: "be",
+	ボ: "bo",
+	パ: "pa",
+	ピ: "pi",
+	プ: "pu",
+	ペ: "pe",
+	ポ: "po",
+	ヴ: "vu",
+	ァ: "a",
+	ィ: "i",
+	ゥ: "u",
+	ェ: "e",
+	ォ: "o",
+	ャ: "ya",
+	ュ: "yu",
+	ョ: "yo",
+	ヮ: "wa",
+	ッ: "",
+	ヵ: "ka",
+	ヶ: "ke",
+	ヽ: "",
+	ヾ: "",
+	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",
+	ヂャ: "ja",
+	ヂュ: "ju",
+	ヂョ: "jo",
+	ビャ: "bya",
+	ビュ: "byu",
+	ビョ: "byo",
+	ピャ: "pya",
+	ピュ: "pyu",
+	ピョ: "pyo",
+	ヷ: "va",
+	ヸ: "vi",
+	ヹ: "ve",
+	ヺ: "vo",
+	ー: "",
+	"・": " ",
+	ファ: "fa",
+	フィ: "fi",
+	フェ: "fe",
+	フォ: "fo",
+	フュ: "fyu",
+	ティ: "ti",
+	ディ: "di",
+	トゥ: "tu",
+	ドゥ: "du",
+	ウィ: "wi",
+	ウェ: "we",
+	ウォ: "wo",
+	ヴァ: "va",
+	ヴィ: "vi",
+	ヴェ: "ve",
+	ヴォ: "vo",
+	シェ: "she",
+	ジェ: "je",
+	チェ: "che",
+	ツァ: "tsa",
+	ツィ: "tsi",
+	ツェ: "tse",
+	ツォ: "tso",
+	デュ: "dyu",
+	テュ: "tyu",
+	イェ: "ye"
+};
+
 //#endregion
 //#region src/transliterate/locales-cyrillic.ts
+/** Russian: the Cyrillic table, `&` becomes `i`. */
 const ru = {
 	id: "ru",
 	table: { "&": " i " },
 	tables: [cyrillic]
 };
+/** Ukrainian: the Ukrainian overlay on the Cyrillic table, `&` becomes `ta`. */
 const uk = {
 	id: "uk",
 	table: { "&": " ta " },
 	tables: [cyrillicUk, cyrillic]
 };
+/** Bulgarian: the Bulgarian overlay on the Cyrillic table, `&` becomes `i`. */
 const bg = {
 	id: "bg",
 	table: { "&": " i " },
 	tables: [cyrillicBg, cyrillic]
 };
+/** Macedonian: the Macedonian overlay on the Cyrillic table, `&` becomes `i`. */
 const mk = {
 	id: "mk",
 	table: { "&": " i " },
 	tables: [cyrillicMk, cyrillic]
 };
+/** Serbian: the Serbian overlay on the Cyrillic table, Latin `đ` becomes `dj`, `&` becomes `i`. */
 const sr = {
 	id: "sr",
 	table: {
@@ -594,16 +1065,66 @@ const sr = {
 	},
 	tables: [cyrillicSr, cyrillic]
 };
+/** Kazakh: the Cyrillic table, `&` becomes `zhane`. */
+const kk = {
+	id: "kk",
+	table: { "&": " zhane " },
+	tables: [cyrillic]
+};
+/** Belarusian: the Cyrillic table, `&` becomes `i`. */
+const be = {
+	id: "be",
+	table: { "&": " i " },
+	tables: [cyrillic]
+};
+/** The Cyrillic-script locales by id. */
 const cyrillicLocales = {
+	be,
 	bg,
+	kk,
 	mk,
 	ru,
 	sr,
 	uk
 };
 
+//#endregion
+//#region src/transliterate/locales-other.ts
+/** Greek: the Greek table, `&` becomes `kai`. */
+const el = {
+	id: "el",
+	table: { "&": " kai " },
+	tables: [greek]
+};
+/** Hebrew: the Hebrew table, `&` becomes `ve`. */
+const he = {
+	id: "he",
+	table: { "&": " ve " },
+	tables: [hebrew]
+};
+/** Japanese: the kana table, `&` becomes `to`; kanji is left alone. */
+const ja = {
+	id: "ja",
+	table: { "&": " to " },
+	tables: [kana]
+};
+/** Korean: the Hangul table, `&` becomes `mit`. */
+const ko = {
+	id: "ko",
+	table: { "&": " mit " },
+	tables: [hangul]
+};
+/** The Greek, Hebrew, Japanese and Korean locales by id. */
+const otherLocales = {
+	el,
+	he,
+	ja,
+	ko
+};
+
 //#endregion
 //#region src/transliterate.ts
+/** Every script table; pass as `tables` when the input language is unknown. */
 const allScripts = [
 	latin,
 	symbols,
@@ -615,23 +1136,44 @@ const allScripts = [
 	pashto,
 	armenian,
 	georgian,
-	dhivehi
+	dhivehi,
+	hebrew,
+	hangul,
+	kana
 ];
+/** Every locale object by id. */
 const locales = {
 	az,
+	be,
 	bg,
+	ca,
+	cs,
 	da,
 	de,
+	el,
 	es,
+	et,
 	fi,
 	fr,
+	he,
+	hr,
 	hu,
+	is,
 	it,
+	ja,
+	kk,
+	ko,
+	lt,
+	lv,
 	mk,
 	nb,
 	nl,
+	pl,
 	pt,
+	ro,
 	ru,
+	sk,
+	sl,
 	sr,
 	sv,
 	tr,
@@ -640,4 +1182,4 @@ const locales = {
 };
 
 //#endregion
-export { DEFAULT_TABLES, allScripts, arabic, armenian, az, bg, cyrillic, cyrillicBg, cyrillicLocales, cyrillicMk, cyrillicSr, cyrillicUk, da, de, defineLocale, dhivehi, es, fi, fold, fr, georgian, greek, hu, it, latin, latinLocales, locales, lookup, mergeTables, mk, nb, nl, pashto, persian, pt, resolveTables, ru, sr, stripMarks, sv, symbols, tr, transliterate, uk, urdu, vi };
+export { DEFAULT_TABLES, allScripts, arabic, armenian, az, be, bg, ca, cs, cyrillic, cyrillicBg, cyrillicLocales, cyrillicMk, cyrillicSr, cyrillicUk, da, de, defineLocale, dhivehi, el, es, et, fi, fold, fr, georgian, greek, hangul, he, hebrew, hr, hu, is, it, ja, kana, kk, ko, latin, latinLocales, locales, lookup, lt, lv, mergeTables, mk, nb, nl, otherLocales, pashto, persian, pl, pt, resolveTables, ro, ru, sk, sl, sr, stripMarks, sv, symbols, tr, transliterate, uk, urdu, vi };