@ingglish/deseret 0.1.0

package/dist/index.cjs

@@ -0,0 +1,298 @@
+"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, {
+  registerDeseret: () => registerDeseret
+});
+module.exports = __toCommonJS(index_exports);
+var import_phonemes2 = require("@ingglish/phonemes");
+
+// src/from-deseret.ts
+var import_dictionary = require("@ingglish/dictionary");
+
+// src/deseret-maps.ts
+var DESERET_CONSONANT_MAP = {
+  B: "\u{1043A}",
+  // U+1043A Bee
+  CH: "\u{1043D}",
+  // U+1043D Chee
+  D: "\u{1043C}",
+  // U+1043C Dee
+  DH: "\u{10444}",
+  // U+10444 Thee
+  F: "\u{10441}",
+  // U+10441 Ef
+  G: "\u{10440}",
+  // U+10440 Gay
+  HH: "\u{10438}",
+  // U+10438 H
+  JH: "\u{1043E}",
+  // U+1043E Jee
+  K: "\u{1043F}",
+  // U+1043F Kay
+  L: "\u{1044A}",
+  // U+1044A El
+  M: "\u{1044B}",
+  // U+1044B Em
+  N: "\u{1044C}",
+  // U+1044C En
+  NG: "\u{1044D}",
+  // U+1044D Eng
+  P: "\u{10439}",
+  // U+10439 Pee
+  R: "\u{10449}",
+  // U+10449 Er
+  S: "\u{10445}",
+  // U+10445 Es
+  SH: "\u{10447}",
+  // U+10447 Esh
+  T: "\u{1043B}",
+  // U+1043B Tee
+  TH: "\u{10443}",
+  // U+10443 Eth
+  V: "\u{10442}",
+  // U+10442 Vee
+  W: "\u{10436}",
+  // U+10436 Wu
+  Y: "\u{10437}",
+  // U+10437 Yee
+  Z: "\u{10446}",
+  // U+10446 Zee
+  ZH: "\u{10448}"
+  // U+10448 Zhee
+};
+var DESERET_VOWEL_MAP = {
+  AA: "\u{1042A}",
+  // U+1042A Long A (palm)
+  AE: "\u{10430}",
+  // U+10430 Short A (trap)
+  AH: "\u{10432}",
+  // U+10432 Short O (strut, stressed default)
+  AO: "\u{1042B}",
+  // U+1042B Long Ah (thought)
+  AW: "\u{10435}",
+  // U+10435 Ow (mouth)
+  // Diphthongs
+  AY: "\u{10434}",
+  // U+10434 Ay (price)
+  EH: "\u{1042F}",
+  // U+1042F Short E (dress)
+  EY: "\u{10429}",
+  // U+10429 Long E (face)
+  IH: "\u{1042E}",
+  // U+1042E Short I (kit)
+  IY: "\u{10428}",
+  // U+10428 Long I (fleece)
+  OW: "\u{1042C}",
+  // U+1042C Long O (goat)
+  OY: "\u{1044E}",
+  // U+1044E Oi (choice)
+  UH: "\u{10433}",
+  // U+10433 Short Oo (foot)
+  UW: "\u{1042D}"
+  // U+1042D Long Oo (goose)
+};
+var DESERET_SCHWA = "\u{10431}";
+var DESERET_EW = "\u{1044F}";
+var ARPABET_TO_DESERET_MAP = {
+  ...DESERET_VOWEL_MAP,
+  ...DESERET_CONSONANT_MAP
+};
+var DESERET_TO_ARPABET_MAP = {
+  // Long vowels
+  "\u{10428}": ["IY"],
+  "\u{10429}": ["EY"],
+  "\u{1042A}": ["AA"],
+  "\u{1042B}": ["AO"],
+  "\u{1042C}": ["OW"],
+  "\u{1042D}": ["UW"],
+  // Short vowels
+  "\u{1042E}": ["IH"],
+  "\u{1042F}": ["EH"],
+  "\u{10430}": ["AE"],
+  "\u{10431}": ["AH"],
+  "\u{10432}": ["AH"],
+  "\u{10433}": ["UH"],
+  // Diphthongs
+  "\u{10434}": ["AY"],
+  "\u{10435}": ["AW"],
+  // Consonants
+  "\u{10436}": ["W"],
+  "\u{10437}": ["Y"],
+  "\u{10438}": ["HH"],
+  "\u{10439}": ["P"],
+  "\u{1043A}": ["B"],
+  "\u{1043B}": ["T"],
+  "\u{1043C}": ["D"],
+  "\u{1043D}": ["CH"],
+  "\u{1043E}": ["JH"],
+  "\u{1043F}": ["K"],
+  "\u{10440}": ["G"],
+  "\u{10441}": ["F"],
+  "\u{10442}": ["V"],
+  "\u{10443}": ["TH"],
+  "\u{10444}": ["DH"],
+  "\u{10445}": ["S"],
+  "\u{10446}": ["Z"],
+  "\u{10447}": ["SH"],
+  "\u{10448}": ["ZH"],
+  "\u{10449}": ["R"],
+  "\u{1044A}": ["L"],
+  "\u{1044B}": ["M"],
+  "\u{1044C}": ["N"],
+  "\u{1044D}": ["NG"],
+  "\u{1044E}": ["OY"],
+  // Ew (expands to Y + UW)
+  "\u{1044F}": ["Y", "UW"]
+};
+
+// src/tokenize.ts
+function isDeseretChar(char) {
+  const cp = char.codePointAt(0);
+  if (cp === void 0) {
+    return false;
+  }
+  return cp >= 66560 && cp <= 66639;
+}
+function tokenizeDeseret(text) {
+  const tokens = [];
+  let current = "";
+  let inWord = false;
+  for (const char of text) {
+    const isDeseret = isDeseretChar(char);
+    if (isDeseret === inWord) {
+      current += char;
+    } else {
+      if (current.length > 0) {
+        tokens.push({ isWord: inWord, text: current });
+      }
+      current = char;
+      inWord = isDeseret;
+    }
+  }
+  if (current.length > 0) {
+    tokens.push({ isWord: inWord, text: current });
+  }
+  return tokens;
+}
+
+// src/from-deseret.ts
+function deseretToArpabet(text) {
+  const result = [];
+  for (const char of text) {
+    if (!isDeseretChar(char)) {
+      continue;
+    }
+    const cp = char.codePointAt(0);
+    const normalized = cp < 66600 ? String.fromCodePoint(cp + 40) : char;
+    const phonemes = DESERET_TO_ARPABET_MAP[normalized];
+    if (phonemes !== void 0) {
+      result.push(...phonemes);
+    }
+  }
+  return result.length > 0 ? result : null;
+}
+function reverseTranslateDeseretText(text) {
+  const tokens = tokenizeDeseret(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateDeseretWord(token.text);
+      return matches[0] ?? token.text;
+    }
+    return token.text;
+  }).join("");
+}
+function reverseTranslateDeseretTextWithMapping(text) {
+  const tokens = tokenizeDeseret(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateDeseretWord(token.text);
+      const translated = matches[0] ?? token.text;
+      return {
+        isWord: true,
+        matched: translated !== token.text,
+        original: token.text,
+        translated
+      };
+    }
+    return { isWord: false, matched: true, original: token.text, translated: token.text };
+  });
+}
+function reverseTranslateDeseretWord(word) {
+  const arpabet = deseretToArpabet(word);
+  if (!arpabet) {
+    return [word];
+  }
+  const key = arpabet.join(" ");
+  const matches = (0, import_dictionary.lookupPhonemeKey)(key);
+  if (!matches || matches.length === 0) {
+    return [word];
+  }
+  return matches.length > 1 ? (0, import_dictionary.sortByFrequency)(matches) : matches;
+}
+
+// src/to-deseret.ts
+var import_phonemes = require("@ingglish/phonemes");
+function arpabetToDeseret(arpabet) {
+  let result = "";
+  const len = arpabet.length;
+  for (let i = 0; i < len; i++) {
+    const phoneme = arpabet[i];
+    const base = (0, import_phonemes.stripStress)(phoneme);
+    if (base === "Y" && i + 1 < len && (0, import_phonemes.stripStress)(arpabet[i + 1]) === "UW") {
+      result += DESERET_EW;
+      i++;
+      continue;
+    }
+    if (base === "ER") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      result += lastChar === 48 ? DESERET_SCHWA : ARPABET_TO_DESERET_MAP.AH;
+      result += ARPABET_TO_DESERET_MAP.R;
+      continue;
+    }
+    if (base === "AH") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      if (lastChar === 48) {
+        result += DESERET_SCHWA;
+        continue;
+      }
+    }
+    result += ARPABET_TO_DESERET_MAP[base] ?? "";
+  }
+  return result;
+}
+
+// src/index.ts
+function registerDeseret() {
+  (0, import_phonemes2.registerFormat)("deseret", {
+    forward: arpabetToDeseret,
+    isLatinScript: false,
+    label: "Deseret",
+    nativeLabel: "\u{10414}\u{1042F}\u{10445}\u{10428}\u{10449}\u{1042F}\u{1043B}",
+    preservesCase: false,
+    reverseText: reverseTranslateDeseretText,
+    reverseTextWithMapping: reverseTranslateDeseretTextWithMapping
+  });
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  registerDeseret
+});

package/dist/index.d.cts

@@ -0,0 +1,3 @@
+declare function registerDeseret(): void;
+
+export { registerDeseret };

package/dist/index.d.ts

@@ -0,0 +1,3 @@
+declare function registerDeseret(): void;
+
+export { registerDeseret };

package/dist/index.js

@@ -0,0 +1,273 @@
+// src/index.ts
+import { registerFormat } from "@ingglish/phonemes";
+
+// src/from-deseret.ts
+import { lookupPhonemeKey, sortByFrequency } from "@ingglish/dictionary";
+
+// src/deseret-maps.ts
+var DESERET_CONSONANT_MAP = {
+  B: "\u{1043A}",
+  // U+1043A Bee
+  CH: "\u{1043D}",
+  // U+1043D Chee
+  D: "\u{1043C}",
+  // U+1043C Dee
+  DH: "\u{10444}",
+  // U+10444 Thee
+  F: "\u{10441}",
+  // U+10441 Ef
+  G: "\u{10440}",
+  // U+10440 Gay
+  HH: "\u{10438}",
+  // U+10438 H
+  JH: "\u{1043E}",
+  // U+1043E Jee
+  K: "\u{1043F}",
+  // U+1043F Kay
+  L: "\u{1044A}",
+  // U+1044A El
+  M: "\u{1044B}",
+  // U+1044B Em
+  N: "\u{1044C}",
+  // U+1044C En
+  NG: "\u{1044D}",
+  // U+1044D Eng
+  P: "\u{10439}",
+  // U+10439 Pee
+  R: "\u{10449}",
+  // U+10449 Er
+  S: "\u{10445}",
+  // U+10445 Es
+  SH: "\u{10447}",
+  // U+10447 Esh
+  T: "\u{1043B}",
+  // U+1043B Tee
+  TH: "\u{10443}",
+  // U+10443 Eth
+  V: "\u{10442}",
+  // U+10442 Vee
+  W: "\u{10436}",
+  // U+10436 Wu
+  Y: "\u{10437}",
+  // U+10437 Yee
+  Z: "\u{10446}",
+  // U+10446 Zee
+  ZH: "\u{10448}"
+  // U+10448 Zhee
+};
+var DESERET_VOWEL_MAP = {
+  AA: "\u{1042A}",
+  // U+1042A Long A (palm)
+  AE: "\u{10430}",
+  // U+10430 Short A (trap)
+  AH: "\u{10432}",
+  // U+10432 Short O (strut, stressed default)
+  AO: "\u{1042B}",
+  // U+1042B Long Ah (thought)
+  AW: "\u{10435}",
+  // U+10435 Ow (mouth)
+  // Diphthongs
+  AY: "\u{10434}",
+  // U+10434 Ay (price)
+  EH: "\u{1042F}",
+  // U+1042F Short E (dress)
+  EY: "\u{10429}",
+  // U+10429 Long E (face)
+  IH: "\u{1042E}",
+  // U+1042E Short I (kit)
+  IY: "\u{10428}",
+  // U+10428 Long I (fleece)
+  OW: "\u{1042C}",
+  // U+1042C Long O (goat)
+  OY: "\u{1044E}",
+  // U+1044E Oi (choice)
+  UH: "\u{10433}",
+  // U+10433 Short Oo (foot)
+  UW: "\u{1042D}"
+  // U+1042D Long Oo (goose)
+};
+var DESERET_SCHWA = "\u{10431}";
+var DESERET_EW = "\u{1044F}";
+var ARPABET_TO_DESERET_MAP = {
+  ...DESERET_VOWEL_MAP,
+  ...DESERET_CONSONANT_MAP
+};
+var DESERET_TO_ARPABET_MAP = {
+  // Long vowels
+  "\u{10428}": ["IY"],
+  "\u{10429}": ["EY"],
+  "\u{1042A}": ["AA"],
+  "\u{1042B}": ["AO"],
+  "\u{1042C}": ["OW"],
+  "\u{1042D}": ["UW"],
+  // Short vowels
+  "\u{1042E}": ["IH"],
+  "\u{1042F}": ["EH"],
+  "\u{10430}": ["AE"],
+  "\u{10431}": ["AH"],
+  "\u{10432}": ["AH"],
+  "\u{10433}": ["UH"],
+  // Diphthongs
+  "\u{10434}": ["AY"],
+  "\u{10435}": ["AW"],
+  // Consonants
+  "\u{10436}": ["W"],
+  "\u{10437}": ["Y"],
+  "\u{10438}": ["HH"],
+  "\u{10439}": ["P"],
+  "\u{1043A}": ["B"],
+  "\u{1043B}": ["T"],
+  "\u{1043C}": ["D"],
+  "\u{1043D}": ["CH"],
+  "\u{1043E}": ["JH"],
+  "\u{1043F}": ["K"],
+  "\u{10440}": ["G"],
+  "\u{10441}": ["F"],
+  "\u{10442}": ["V"],
+  "\u{10443}": ["TH"],
+  "\u{10444}": ["DH"],
+  "\u{10445}": ["S"],
+  "\u{10446}": ["Z"],
+  "\u{10447}": ["SH"],
+  "\u{10448}": ["ZH"],
+  "\u{10449}": ["R"],
+  "\u{1044A}": ["L"],
+  "\u{1044B}": ["M"],
+  "\u{1044C}": ["N"],
+  "\u{1044D}": ["NG"],
+  "\u{1044E}": ["OY"],
+  // Ew (expands to Y + UW)
+  "\u{1044F}": ["Y", "UW"]
+};
+
+// src/tokenize.ts
+function isDeseretChar(char) {
+  const cp = char.codePointAt(0);
+  if (cp === void 0) {
+    return false;
+  }
+  return cp >= 66560 && cp <= 66639;
+}
+function tokenizeDeseret(text) {
+  const tokens = [];
+  let current = "";
+  let inWord = false;
+  for (const char of text) {
+    const isDeseret = isDeseretChar(char);
+    if (isDeseret === inWord) {
+      current += char;
+    } else {
+      if (current.length > 0) {
+        tokens.push({ isWord: inWord, text: current });
+      }
+      current = char;
+      inWord = isDeseret;
+    }
+  }
+  if (current.length > 0) {
+    tokens.push({ isWord: inWord, text: current });
+  }
+  return tokens;
+}
+
+// src/from-deseret.ts
+function deseretToArpabet(text) {
+  const result = [];
+  for (const char of text) {
+    if (!isDeseretChar(char)) {
+      continue;
+    }
+    const cp = char.codePointAt(0);
+    const normalized = cp < 66600 ? String.fromCodePoint(cp + 40) : char;
+    const phonemes = DESERET_TO_ARPABET_MAP[normalized];
+    if (phonemes !== void 0) {
+      result.push(...phonemes);
+    }
+  }
+  return result.length > 0 ? result : null;
+}
+function reverseTranslateDeseretText(text) {
+  const tokens = tokenizeDeseret(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateDeseretWord(token.text);
+      return matches[0] ?? token.text;
+    }
+    return token.text;
+  }).join("");
+}
+function reverseTranslateDeseretTextWithMapping(text) {
+  const tokens = tokenizeDeseret(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateDeseretWord(token.text);
+      const translated = matches[0] ?? token.text;
+      return {
+        isWord: true,
+        matched: translated !== token.text,
+        original: token.text,
+        translated
+      };
+    }
+    return { isWord: false, matched: true, original: token.text, translated: token.text };
+  });
+}
+function reverseTranslateDeseretWord(word) {
+  const arpabet = deseretToArpabet(word);
+  if (!arpabet) {
+    return [word];
+  }
+  const key = arpabet.join(" ");
+  const matches = lookupPhonemeKey(key);
+  if (!matches || matches.length === 0) {
+    return [word];
+  }
+  return matches.length > 1 ? sortByFrequency(matches) : matches;
+}
+
+// src/to-deseret.ts
+import { stripStress } from "@ingglish/phonemes";
+function arpabetToDeseret(arpabet) {
+  let result = "";
+  const len = arpabet.length;
+  for (let i = 0; i < len; i++) {
+    const phoneme = arpabet[i];
+    const base = stripStress(phoneme);
+    if (base === "Y" && i + 1 < len && stripStress(arpabet[i + 1]) === "UW") {
+      result += DESERET_EW;
+      i++;
+      continue;
+    }
+    if (base === "ER") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      result += lastChar === 48 ? DESERET_SCHWA : ARPABET_TO_DESERET_MAP.AH;
+      result += ARPABET_TO_DESERET_MAP.R;
+      continue;
+    }
+    if (base === "AH") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      if (lastChar === 48) {
+        result += DESERET_SCHWA;
+        continue;
+      }
+    }
+    result += ARPABET_TO_DESERET_MAP[base] ?? "";
+  }
+  return result;
+}
+
+// src/index.ts
+function registerDeseret() {
+  registerFormat("deseret", {
+    forward: arpabetToDeseret,
+    isLatinScript: false,
+    label: "Deseret",
+    nativeLabel: "\u{10414}\u{1042F}\u{10445}\u{10428}\u{10449}\u{1042F}\u{1043B}",
+    preservesCase: false,
+    reverseText: reverseTranslateDeseretText,
+    reverseTextWithMapping: reverseTranslateDeseretTextWithMapping
+  });
+}
+export {
+  registerDeseret
+};

package/package.json

@@ -0,0 +1,51 @@
+{
+  "name": "@ingglish/deseret",
+  "version": "0.1.0",
+  "description": "Deseret alphabet conversion for Ingglish",
+  "type": "module",
+  "main": "./dist/index.js",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "source": "./src/index.ts",
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      }
+    }
+  },
+  "files": [
+    "dist"
+  ],
+  "sideEffects": false,
+  "engines": {
+    "node": ">=16"
+  },
+  "scripts": {
+    "build": "tsup",
+    "build:fast": "tsup src/index.ts --format esm",
+    "lint": "eslint --cache src",
+    "test": "vitest run --no-color",
+    "prepublishOnly": "npm run build"
+  },
+  "dependencies": {
+    "@ingglish/phonemes": "^0.1.0",
+    "@ingglish/dictionary": "^0.1.0"
+  },
+  "author": "Paul Tarjan",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/ptarjan/ingglish.git",
+    "directory": "packages/deseret"
+  },
+  "homepage": "https://github.com/ptarjan/ingglish#readme",
+  "bugs": {
+    "url": "https://github.com/ptarjan/ingglish/issues"
+  }
+}