@lunarisapp/language/dist/index.js

A utility library for core linguistic breakdown: vowels, consonants, words, and sentences.

"use strict";
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);

// src/index.ts
var index_exports = {};
__export(index_exports, {
  consonants: () => consonants,
  contractionsRegexSeq: () => contractionsRegexSeq,
  getSentences: () => getSentences,
  getWords: () => getWords,
  languages: () => languages,
  removePunctuation: () => removePunctuation,
  vowels: () => vowels
});
module.exports = __toCommonJS(index_exports);

// src/features/languages.ts
var languages = [
  "af",
  "as",
  "be",
  "bg",
  "ca",
  "da",
  "de",
  "de_DE",
  "de_CH",
  "de_AT",
  "en",
  "en_US",
  "en_GB",
  "eo",
  "es",
  "et",
  "fr",
  "gl",
  "hr",
  "hu",
  "id",
  "is",
  "it",
  "kn",
  "lt",
  "lv",
  "mn",
  "mr",
  "nb",
  "nl",
  "nn",
  "pa",
  "pl",
  "pt",
  "pt_PT",
  "pt_BR",
  "ro",
  "ru",
  "sa",
  "sk",
  "sl",
  "sq",
  "sr",
  "sr_Latn",
  "sv",
  "te",
  "th",
  "uk",
  "zu"
];

// src/features/vowels.ts
var VOWEL_LATIN_GROUP = ["a", "e", "i", "o", "u"];
var VOWEL_GERMANIC_UMLAUTS_GROUP = [
  ...VOWEL_LATIN_GROUP,
  "\xE4",
  "\xF6",
  "\xFC",
  "y"
];
var vowels = {
  af: VOWEL_LATIN_GROUP,
  as: ["\u0985", "\u0986", "\u0987", "\u0988", "\u0989", "\u098A", "\u098B", "\u098F", "\u0990", "\u0993", "\u0994"],
  be: ["\u0430", "\u0435", "\u0451", "\u0456", "\u043E", "\u0443", "\u044B", "\u044D", "\u044E", "\u044F"],
  bg: ["\u0430", "\u044A", "\u043E", "\u0443", "\u0435", "\u0438", "\u044E", "\u044F"],
  ca: VOWEL_LATIN_GROUP,
  da: [...VOWEL_LATIN_GROUP, "y", "\xE6", "\xF8", "\xE5"],
  de: VOWEL_GERMANIC_UMLAUTS_GROUP,
  de_DE: VOWEL_GERMANIC_UMLAUTS_GROUP,
  de_CH: VOWEL_GERMANIC_UMLAUTS_GROUP,
  de_AT: VOWEL_GERMANIC_UMLAUTS_GROUP,
  en: VOWEL_LATIN_GROUP,
  en_US: VOWEL_LATIN_GROUP,
  en_GB: VOWEL_LATIN_GROUP,
  eo: VOWEL_LATIN_GROUP,
  es: [...VOWEL_LATIN_GROUP, "\xE1", "\xE9", "\xED", "\xF3", "\xFA", "\xFC"],
  et: [...VOWEL_LATIN_GROUP, "\xF5", "\xE4", "\xF6", "\xFC"],
  fr: [
    "a",
    "e",
    "i",
    "o",
    "u",
    "y",
    "\xE0",
    "\xE2",
    "\xE6",
    "\xE8",
    "\xE9",
    "\xEA",
    "\xEB",
    "\xEE",
    "\xEF",
    "\xF4",
    "\u0153",
    "\xF9",
    "\xFB",
    "\xFC"
  ],
  gl: VOWEL_LATIN_GROUP,
  hr: VOWEL_LATIN_GROUP,
  hu: [...VOWEL_LATIN_GROUP, "\xF6", "\xFC"],
  id: VOWEL_LATIN_GROUP,
  is: [
    "a",
    "e",
    "i",
    "o",
    "u",
    "y",
    "\xE1",
    "\xF0",
    "\xE9",
    "\xED",
    "\xF3",
    "\xFA",
    "\xFD",
    "\xE6",
    "\xF6"
  ],
  it: VOWEL_LATIN_GROUP,
  kn: [
    "\u0C85",
    "\u0C86",
    "\u0C87",
    "\u0C88",
    "\u0C89",
    "\u0C8A",
    "\u0C8B",
    "\u0C8E",
    "\u0C8F",
    "\u0C90",
    "\u0C92",
    "\u0C93",
    "\u0C94"
  ],
  lt: [...VOWEL_LATIN_GROUP, "\u0105", "\u0119", "\u0117", "\u012F", "\u0173", "\u016B"],
  lv: VOWEL_LATIN_GROUP,
  mn: ["\u0430", "\u0435", "\u0438", "\u043E", "\u0443", "\u04AF", "\u04E9", "\u044D", "\u044F", "\u0451", "\u044E"],
  mr: ["\u0905", "\u0906", "\u0907", "\u0908", "\u0909", "\u090A", "\u090B", "\u090F", "\u0910", "\u0913", "\u0914"],
  nb: [...VOWEL_LATIN_GROUP, "y", "\xE6", "\xF8", "\xE5"],
  nl: VOWEL_LATIN_GROUP,
  nn: [...VOWEL_LATIN_GROUP, "y", "\xE6", "\xF8", "\xE5"],
  pa: ["\u0A05", "\u0A06", "\u0A07", "\u0A08", "\u0A09", "\u0A0A", "\u0A0F", "\u0A10", "\u0A13", "\u0A14"],
  pl: ["a", "\u0105", "e", "\u0119", "i", "o", "\xF3", "u", "y"],
  pt: VOWEL_LATIN_GROUP,
  pt_PT: VOWEL_LATIN_GROUP,
  pt_BR: VOWEL_LATIN_GROUP,
  ro: [...VOWEL_LATIN_GROUP, "\u0103", "\xE2", "\xEE"],
  ru: ["\u0430", "\u0435", "\u0451", "\u0438", "\u043E", "\u0443", "\u044B", "\u044D", "\u044E", "\u044F"],
  sa: ["\u0905", "\u0906", "\u0907", "\u0908", "\u0909", "\u090A", "\u090B", "\u090F", "\u0910", "\u0913", "\u0914"],
  sk: [...VOWEL_LATIN_GROUP, "y", "\xE4", "\xF4"],
  sl: VOWEL_LATIN_GROUP,
  sq: [...VOWEL_LATIN_GROUP, "y", "\xEB"],
  sr: ["\u0430", "\u0435", "\u0438", "\u043E", "\u0443"],
  sr_Latn: VOWEL_LATIN_GROUP,
  sv: [...VOWEL_LATIN_GROUP, "y", "\xE5", "\xE4", "\xF6"],
  te: [
    "\u0C05",
    "\u0C06",
    "\u0C07",
    "\u0C08",
    "\u0C09",
    "\u0C0A",
    "\u0C0B",
    "\u0C0E",
    "\u0C0F",
    "\u0C10",
    "\u0C12",
    "\u0C13",
    "\u0C14"
  ],
  th: [
    "\u0E30",
    "\u0E32",
    "\u0E34",
    "\u0E35",
    "\u0E36",
    "\u0E37",
    "\u0E38",
    "\u0E39",
    "\u0E40",
    "\u0E41",
    "\u0E42",
    "\u0E43",
    "\u0E44",
    "\u0E45"
  ],
  uk: ["\u0430", "\u0435", "\u0454", "\u0438", "\u0456", "\u0457", "\u043E", "\u0443", "\u044E", "\u044F"],
  zu: VOWEL_LATIN_GROUP
};

// src/features/consonants.ts
var CONSONANT_LATIN_GROUP = [
  "b",
  "c",
  "d",
  "f",
  "g",
  "h",
  "j",
  "k",
  "l",
  "m",
  "n",
  "p",
  "q",
  "r",
  "s",
  "t",
  "v",
  "w",
  "x",
  "z"
];
var CONSONANT_CYRILLIC_GROUP = [
  "\u0431",
  "\u0432",
  "\u0433",
  "\u0434",
  "\u0436",
  "\u0437",
  "\u0439",
  "\u043A",
  "\u043B",
  "\u043C",
  "\u043D",
  "\u043F",
  "\u0440",
  "\u0441",
  "\u0442",
  "\u0444",
  "\u0445",
  "\u0446",
  "\u0447",
  "\u0448",
  "\u0449"
];
var consonants = {
  af: CONSONANT_LATIN_GROUP,
  as: [
    "\u0995",
    "\u0996",
    "\u0997",
    "\u0998",
    "\u0999",
    "\u099A",
    "\u099B",
    "\u099C",
    "\u099D",
    "\u099E",
    "\u099F",
    "\u09A0",
    "\u09A1",
    "\u09A2",
    "\u09A3",
    "\u09A4",
    "\u09A5",
    "\u09A6",
    "\u09A7",
    "\u09A8",
    "\u09AA",
    "\u09AB",
    "\u09AC",
    "\u09AD",
    "\u09AE",
    "\u09AF",
    "\u09B0",
    "\u09B2",
    "\u09B6",
    "\u09B7",
    "\u09B8",
    "\u09B9"
  ],
  be: CONSONANT_CYRILLIC_GROUP,
  bg: CONSONANT_CYRILLIC_GROUP,
  ca: CONSONANT_LATIN_GROUP,
  da: [...CONSONANT_LATIN_GROUP, "\xF0"],
  de: [...CONSONANT_LATIN_GROUP, "\xDF"],
  de_AT: [...CONSONANT_LATIN_GROUP, "\xDF"],
  de_CH: [...CONSONANT_LATIN_GROUP, "\xDF"],
  de_DE: [...CONSONANT_LATIN_GROUP, "\xDF"],
  en: CONSONANT_LATIN_GROUP,
  en_GB: CONSONANT_LATIN_GROUP,
  en_US: CONSONANT_LATIN_GROUP,
  eo: CONSONANT_LATIN_GROUP,
  es: [...CONSONANT_LATIN_GROUP, "\xF1"],
  et: CONSONANT_LATIN_GROUP,
  fr: [...CONSONANT_LATIN_GROUP, "\xE7"],
  gl: CONSONANT_LATIN_GROUP,
  hr: [...CONSONANT_LATIN_GROUP, "\u010D", "\u0107", "\u0111", "\u0161", "\u017E"],
  hu: [
    ...CONSONANT_LATIN_GROUP,
    "cs",
    "dz",
    "gy",
    "ly",
    "ny",
    "sz",
    "ty",
    "zs"
  ],
  id: CONSONANT_LATIN_GROUP,
  is: [...CONSONANT_LATIN_GROUP, "\xF0", "\xFE"],
  it: CONSONANT_LATIN_GROUP,
  kn: [
    "\u0C95",
    "\u0C96",
    "\u0C97",
    "\u0C98",
    "\u0C99",
    "\u0C9A",
    "\u0C9B",
    "\u0C9C",
    "\u0C9D",
    "\u0C9E",
    "\u0C9F",
    "\u0CA0",
    "\u0CA1",
    "\u0CA2",
    "\u0CA3",
    "\u0CA4",
    "\u0CA5",
    "\u0CA6",
    "\u0CA7",
    "\u0CA8",
    "\u0CAA",
    "\u0CAB",
    "\u0CAC",
    "\u0CAD",
    "\u0CAE",
    "\u0CAF",
    "\u0CB0",
    "\u0CB2",
    "\u0CB5",
    "\u0CB6",
    "\u0CB7",
    "\u0CB8",
    "\u0CB9"
  ],
  lt: [...CONSONANT_LATIN_GROUP, "\u010D", "\u0161", "\u017E"],
  lv: CONSONANT_LATIN_GROUP,
  mr: [
    "\u0915",
    "\u0916",
    "\u0917",
    "\u0918",
    "\u0919",
    "\u091A",
    "\u091B",
    "\u091C",
    "\u091D",
    "\u091E",
    "\u091F",
    "\u0920",
    "\u0921",
    "\u0922",
    "\u0923",
    "\u0924",
    "\u0925",
    "\u0926",
    "\u0927",
    "\u0928",
    "\u092A",
    "\u092B",
    "\u092C",
    "\u092D",
    "\u092E",
    "\u092F",
    "\u0930",
    "\u0932",
    "\u0935",
    "\u0936",
    "\u0937",
    "\u0938",
    "\u0939",
    "\u0933",
    "\u0915\u094D\u200D\u0937",
    "\u0924\u094D\u0930",
    "\u091C\u094D\u091E"
  ],
  mn: [
    "\u0431",
    "\u0432",
    "\u0433",
    "\u0434",
    "\u0436",
    "\u0437",
    "\u0439",
    "\u043A",
    "\u043B",
    "\u043C",
    "\u043D",
    "\u043F",
    "\u0440",
    "\u0441",
    "\u0442",
    "\u0444",
    "\u0445",
    "\u0446",
    "\u0447",
    "\u0448"
  ],
  nb: [...CONSONANT_LATIN_GROUP, "\xE7"],
  nn: [...CONSONANT_LATIN_GROUP, "\xE7"],
  nl: CONSONANT_LATIN_GROUP,
  pa: [
    "\u0A15",
    "\u0A16",
    "\u0A17",
    "\u0A18",
    "\u0A19",
    "\u0A1A",
    "\u0A1B",
    "\u0A1C",
    "\u0A1D",
    "\u0A1E",
    "\u0A1F",
    "\u0A20",
    "\u0A21",
    "\u0A22",
    "\u0A23",
    "\u0A24",
    "\u0A25",
    "\u0A26",
    "\u0A27",
    "\u0A28",
    "\u0A2A",
    "\u0A2B",
    "\u0A2C",
    "\u0A2D",
    "\u0A2E",
    "\u0A2F",
    "\u0A30",
    "\u0A32",
    "\u0A35",
    "\u0A36",
    "\u0A5B",
    "\u0A38",
    "\u0A39"
  ],
  pl: [...CONSONANT_LATIN_GROUP, "\u0142", "\u0144", "\u015B", "\u017A", "\u017C", "\u0107"],
  pt: CONSONANT_LATIN_GROUP,
  pt_BR: CONSONANT_LATIN_GROUP,
  pt_PT: CONSONANT_LATIN_GROUP,
  ro: [...CONSONANT_LATIN_GROUP, "\u021B", "\u0219"],
  ru: CONSONANT_CYRILLIC_GROUP,
  sa: [
    "\u0915",
    "\u0916",
    "\u0917",
    "\u0918",
    "\u0919",
    "\u091A",
    "\u091B",
    "\u091C",
    "\u091D",
    "\u091E",
    "\u091F",
    "\u0920",
    "\u0921",
    "\u0922",
    "\u0923",
    "\u0924",
    "\u0925",
    "\u0926",
    "\u0927",
    "\u0928",
    "\u092A",
    "\u092B",
    "\u092C",
    "\u092D",
    "\u092E",
    "\u092F",
    "\u0930",
    "\u0932",
    "\u0935",
    "\u0936",
    "\u0937",
    "\u0938",
    "\u0939",
    "\u0933",
    "\u0915\u094D\u200D\u0937",
    "\u0924\u094D\u0930",
    "\u091C\u094D\u091E"
  ],
  sk: [...CONSONANT_LATIN_GROUP, "\u010D", "\u010F", "\u013E", "\u0148", "\u0161", "\u0165", "\u017E"],
  sl: [...CONSONANT_LATIN_GROUP, "\u010D", "\u0161", "\u017E"],
  sq: [...CONSONANT_LATIN_GROUP, "\xE7"],
  sr: [
    "\u0431",
    "\u0432",
    "\u0433",
    "\u0434",
    "\u0436",
    "\u0437",
    "\u0458",
    "\u043A",
    "\u043B",
    "\u0459",
    "\u043C",
    "\u043D",
    "\u045A",
    "\u043F",
    "\u0440",
    "\u0441",
    "\u0442",
    "\u045B",
    "\u0443",
    "\u0444",
    "\u0445",
    "\u0446",
    "\u0447",
    "\u045F",
    "\u0448"
  ],
  sr_Latn: [...CONSONANT_LATIN_GROUP, "\u010D", "\u0107", "\u0111", "\u0161", "\u017E"],
  sv: CONSONANT_LATIN_GROUP,
  te: [
    "\u0C15",
    "\u0C16",
    "\u0C17",
    "\u0C18",
    "\u0C19",
    "\u0C1A",
    "\u0C1B",
    "\u0C1C",
    "\u0C1D",
    "\u0C1E",
    "\u0C1F",
    "\u0C20",
    "\u0C21",
    "\u0C22",
    "\u0C23",
    "\u0C24",
    "\u0C25",
    "\u0C26",
    "\u0C27",
    "\u0C28",
    "\u0C2A",
    "\u0C2B",
    "\u0C2C",
    "\u0C2D",
    "\u0C2E",
    "\u0C2F",
    "\u0C30",
    "\u0C32",
    "\u0C35",
    "\u0C36",
    "\u0C37",
    "\u0C38",
    "\u0C39"
  ],
  th: [
    "\u0E01",
    "\u0E02",
    "\u0E03",
    "\u0E04",
    "\u0E05",
    "\u0E06",
    "\u0E07",
    "\u0E08",
    "\u0E09",
    "\u0E0A",
    "\u0E0B",
    "\u0E0C",
    "\u0E0D",
    "\u0E0E",
    "\u0E0F",
    "\u0E10",
    "\u0E11",
    "\u0E12",
    "\u0E13",
    "\u0E14",
    "\u0E15",
    "\u0E16",
    "\u0E17",
    "\u0E18",
    "\u0E19",
    "\u0E1A",
    "\u0E1B",
    "\u0E1C",
    "\u0E1D",
    "\u0E1E",
    "\u0E1F",
    "\u0E20",
    "\u0E21",
    "\u0E22",
    "\u0E23",
    "\u0E25",
    "\u0E27",
    "\u0E28",
    "\u0E29",
    "\u0E2A",
    "\u0E2B",
    "\u0E2C",
    "\u0E2D",
    "\u0E2E"
  ],
  uk: CONSONANT_CYRILLIC_GROUP,
  zu: CONSONANT_LATIN_GROUP
};

// src/features/contractions.ts
var contractionsRegexSeq = {
  en: "[tsd]\\b|ve\\b|ll\\b|re\\b",
  // it's, don't, you've, I'll
  fr: "\\b[cjntlsd]'\\b",
  // c', j', n', l', d' (e.g., c'est, j'aime)
  es: "\\b(pa')\\b",
  // pa' (e.g., pa'lante)
  it: "\\b(l'|un'|da')\\b",
  // l', un', da' (e.g., l'amico, un'amica)
  ca: "\\b(l'|d'|m'|s'|t'|n')\\b",
  // l', d', m', s' (e.g., l'amor, d'aigua)
  gl: "\\b(d'|n'|t'|v'|ll'|m'|s')\\b",
  // d', n', t' (e.g., d'aquela, n'hai)
  ro: "\\b(l|m|s|\u0163i|d|c|a)-(am|ai|a|au|om|i|em|\u0163i)\\b",
  // l-am, m-a, s-a
  nl: "\\b('t|m\u2019n|d\u2019r|'n)\\b"
  // 't huis, m'n, d'r, 'n
};

// src/features/removePunctuation.ts
function removePunctuation(text, ignoreContractions = false) {
  if (ignoreContractions) {
    const contractions = Object.values(contractionsRegexSeq).join("|");
    if (contractions) {
      const antiContractionsRegex = new RegExp(`'(?!${contractions})`, "g");
      text = text.replace(antiContractionsRegex, '"');
      return text.replace(/[^\p{L}\p{N}\s']/gu, "");
    }
  }
  return text.replace(/[^\p{L}\p{N}\s]/gu, "");
}

// src/features/parsers.ts
function getWords(text, isRemovePunctuation = true) {
  if (isRemovePunctuation) {
    text = removePunctuation(text, true);
  }
  return text.toLowerCase().split(/\s+/g);
}
function getSentences(text) {
  return text.match(/[^.!?。！？\n\r]+[.!?。！？]*[\n\r]*/gu) || [];
}
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
  consonants,
  contractionsRegexSeq,
  getSentences,
  getWords,
  languages,
  removePunctuation,
  vowels
});