@ingglish/shavian 0.1.0

package/dist/index.cjs

@@ -0,0 +1,288 @@
+"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, {
+  registerShavian: () => registerShavian
+});
+module.exports = __toCommonJS(index_exports);
+var import_phonemes2 = require("@ingglish/phonemes");
+
+// src/from-shavian.ts
+var import_dictionary = require("@ingglish/dictionary");
+
+// src/shavian-maps.ts
+var SHAVIAN_CONSONANT_MAP = {
+  B: "\u{1045A}",
+  CH: "\u{10457}",
+  D: "\u{1045B}",
+  DH: "\u{1045E}",
+  F: "\u{10453}",
+  G: "\u{1045C}",
+  HH: "\u{10463}",
+  JH: "\u{10461}",
+  K: "\u{10452}",
+  L: "\u{10464}",
+  M: "\u{10465}",
+  N: "\u{1046F}",
+  NG: "\u{10459}",
+  P: "\u{10450}",
+  R: "\u{1046E}",
+  S: "\u{10455}",
+  SH: "\u{10456}",
+  T: "\u{10451}",
+  TH: "\u{10454}",
+  V: "\u{1045D}",
+  W: "\u{10462}",
+  Y: "\u{10458}",
+  Z: "\u{1045F}",
+  ZH: "\u{10460}"
+};
+var SHAVIAN_VOWEL_MAP = {
+  AA: "\u{1046D}",
+  // palm, father
+  AE: "\u{10468}",
+  // trap, cat
+  AH: "\u{10473}",
+  // strut, cup (stressed default)
+  AO: "\u{10477}",
+  // thought, law
+  // Diphthongs
+  AW: "\u{1046C}",
+  // mouth, cow
+  AY: "\u{10472}",
+  // price, my
+  EH: "\u{10467}",
+  // dress, bed
+  ER: "\u{1047B}",
+  // nurse, bird (ligature)
+  EY: "\u{10471}",
+  // face, say
+  IH: "\u{10466}",
+  // kit, sit
+  IY: "\u{10470}",
+  // fleece, see
+  OW: "\u{10474}",
+  // goat, go
+  OY: "\u{10476}",
+  // choice, boy
+  UH: "\u{1046B}",
+  // foot, put
+  UW: "\u{10475}"
+  // goose, too
+};
+var ARPABET_TO_SHAVIAN_MAP = {
+  ...SHAVIAN_VOWEL_MAP,
+  ...SHAVIAN_CONSONANT_MAP
+};
+var SHAVIAN_SCHWA = "\u{10469}";
+var SHAVIAN_R_COLORED = {
+  AA: "\u{10478}",
+  // start (AA+R)
+  AH0: "\u{1047C}",
+  // letter (unstressed AH+R)
+  AO: "\u{10479}",
+  // north/force (AO+R)
+  EH: "\u{1047A}",
+  // square (EH+R)
+  IH: "\u{1047D}"
+  // near (IH+R)
+};
+var SHAVIAN_TO_ARPABET_MAP = {
+  // Consonants
+  "\u{10450}": ["P"],
+  "\u{10451}": ["T"],
+  "\u{10452}": ["K"],
+  "\u{10453}": ["F"],
+  "\u{10454}": ["TH"],
+  "\u{10455}": ["S"],
+  "\u{10456}": ["SH"],
+  "\u{10457}": ["CH"],
+  "\u{10458}": ["Y"],
+  "\u{10459}": ["NG"],
+  "\u{1045A}": ["B"],
+  "\u{1045B}": ["D"],
+  "\u{1045C}": ["G"],
+  "\u{1045D}": ["V"],
+  "\u{1045E}": ["DH"],
+  "\u{1045F}": ["Z"],
+  "\u{10460}": ["ZH"],
+  "\u{10461}": ["JH"],
+  "\u{10462}": ["W"],
+  "\u{10463}": ["HH"],
+  "\u{10464}": ["L"],
+  "\u{10465}": ["M"],
+  "\u{10466}": ["IH"],
+  "\u{10467}": ["EH"],
+  "\u{10468}": ["AE"],
+  // Schwa
+  "\u{10469}": ["AH"],
+  "\u{1046B}": ["UH"],
+  // Diphthongs
+  "\u{1046C}": ["AW"],
+  // Vowels
+  "\u{1046D}": ["AA"],
+  "\u{1046E}": ["R"],
+  "\u{1046F}": ["N"],
+  "\u{10470}": ["IY"],
+  "\u{10471}": ["EY"],
+  "\u{10472}": ["AY"],
+  "\u{10473}": ["AH"],
+  "\u{10474}": ["OW"],
+  "\u{10475}": ["UW"],
+  "\u{10476}": ["OY"],
+  "\u{10477}": ["AO"],
+  // R-colored ligatures (expand to vowel + R)
+  "\u{10478}": ["AA", "R"],
+  "\u{10479}": ["AO", "R"],
+  "\u{1047A}": ["EH", "R"],
+  "\u{1047B}": ["ER"],
+  "\u{1047C}": ["AH", "R"],
+  "\u{1047D}": ["IH", "R"]
+};
+
+// src/tokenize.ts
+function isShavianChar(char) {
+  const cp = char.codePointAt(0);
+  if (cp === void 0) {
+    return false;
+  }
+  return cp >= 66640 && cp <= 66687;
+}
+function tokenizeShavian(text) {
+  const tokens = [];
+  let current = "";
+  let inWord = false;
+  for (const char of text) {
+    const isShavian = isShavianChar(char);
+    if (isShavian === inWord) {
+      current += char;
+    } else {
+      if (current.length > 0) {
+        tokens.push({ isWord: inWord, text: current });
+      }
+      current = char;
+      inWord = isShavian;
+    }
+  }
+  if (current.length > 0) {
+    tokens.push({ isWord: inWord, text: current });
+  }
+  return tokens;
+}
+
+// src/from-shavian.ts
+function reverseTranslateShavianText(text) {
+  const tokens = tokenizeShavian(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateShavianWord(token.text);
+      return matches[0] ?? token.text;
+    }
+    return token.text;
+  }).join("");
+}
+function reverseTranslateShavianTextWithMapping(text) {
+  const tokens = tokenizeShavian(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateShavianWord(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 reverseTranslateShavianWord(word) {
+  const arpabet = shavianToArpabet(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;
+}
+function shavianToArpabet(text) {
+  const result = [];
+  for (const char of text) {
+    if (!isShavianChar(char)) {
+      continue;
+    }
+    const phonemes = SHAVIAN_TO_ARPABET_MAP[char];
+    if (phonemes !== void 0) {
+      result.push(...phonemes);
+    }
+  }
+  return result.length > 0 ? result : null;
+}
+
+// src/to-shavian.ts
+var import_phonemes = require("@ingglish/phonemes");
+function arpabetToShavian(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 (i + 1 < len && arpabet[i + 1] === "R") {
+      const stressKey = base === "AH" ? phoneme : base;
+      const ligature = SHAVIAN_R_COLORED[stressKey] ?? SHAVIAN_R_COLORED[base];
+      if (ligature !== void 0) {
+        result += ligature;
+        i++;
+        continue;
+      }
+    }
+    if (base === "AH") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      if (lastChar === 48) {
+        result += SHAVIAN_SCHWA;
+        continue;
+      }
+    }
+    result += ARPABET_TO_SHAVIAN_MAP[base] ?? "";
+  }
+  return result;
+}
+
+// src/index.ts
+function registerShavian() {
+  (0, import_phonemes2.registerFormat)("shavian", {
+    forward: arpabetToShavian,
+    isLatinScript: false,
+    label: "Shavian",
+    nativeLabel: "\u{10456}\u{10471}\u{1045D}\u{1047E}\u{1046F}",
+    preservesCase: false,
+    reverseText: reverseTranslateShavianText,
+    reverseTextWithMapping: reverseTranslateShavianTextWithMapping
+  });
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  registerShavian
+});

package/dist/index.d.cts

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

package/dist/index.d.ts

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

package/dist/index.js

@@ -0,0 +1,263 @@
+// src/index.ts
+import { registerFormat } from "@ingglish/phonemes";
+
+// src/from-shavian.ts
+import { lookupPhonemeKey, sortByFrequency } from "@ingglish/dictionary";
+
+// src/shavian-maps.ts
+var SHAVIAN_CONSONANT_MAP = {
+  B: "\u{1045A}",
+  CH: "\u{10457}",
+  D: "\u{1045B}",
+  DH: "\u{1045E}",
+  F: "\u{10453}",
+  G: "\u{1045C}",
+  HH: "\u{10463}",
+  JH: "\u{10461}",
+  K: "\u{10452}",
+  L: "\u{10464}",
+  M: "\u{10465}",
+  N: "\u{1046F}",
+  NG: "\u{10459}",
+  P: "\u{10450}",
+  R: "\u{1046E}",
+  S: "\u{10455}",
+  SH: "\u{10456}",
+  T: "\u{10451}",
+  TH: "\u{10454}",
+  V: "\u{1045D}",
+  W: "\u{10462}",
+  Y: "\u{10458}",
+  Z: "\u{1045F}",
+  ZH: "\u{10460}"
+};
+var SHAVIAN_VOWEL_MAP = {
+  AA: "\u{1046D}",
+  // palm, father
+  AE: "\u{10468}",
+  // trap, cat
+  AH: "\u{10473}",
+  // strut, cup (stressed default)
+  AO: "\u{10477}",
+  // thought, law
+  // Diphthongs
+  AW: "\u{1046C}",
+  // mouth, cow
+  AY: "\u{10472}",
+  // price, my
+  EH: "\u{10467}",
+  // dress, bed
+  ER: "\u{1047B}",
+  // nurse, bird (ligature)
+  EY: "\u{10471}",
+  // face, say
+  IH: "\u{10466}",
+  // kit, sit
+  IY: "\u{10470}",
+  // fleece, see
+  OW: "\u{10474}",
+  // goat, go
+  OY: "\u{10476}",
+  // choice, boy
+  UH: "\u{1046B}",
+  // foot, put
+  UW: "\u{10475}"
+  // goose, too
+};
+var ARPABET_TO_SHAVIAN_MAP = {
+  ...SHAVIAN_VOWEL_MAP,
+  ...SHAVIAN_CONSONANT_MAP
+};
+var SHAVIAN_SCHWA = "\u{10469}";
+var SHAVIAN_R_COLORED = {
+  AA: "\u{10478}",
+  // start (AA+R)
+  AH0: "\u{1047C}",
+  // letter (unstressed AH+R)
+  AO: "\u{10479}",
+  // north/force (AO+R)
+  EH: "\u{1047A}",
+  // square (EH+R)
+  IH: "\u{1047D}"
+  // near (IH+R)
+};
+var SHAVIAN_TO_ARPABET_MAP = {
+  // Consonants
+  "\u{10450}": ["P"],
+  "\u{10451}": ["T"],
+  "\u{10452}": ["K"],
+  "\u{10453}": ["F"],
+  "\u{10454}": ["TH"],
+  "\u{10455}": ["S"],
+  "\u{10456}": ["SH"],
+  "\u{10457}": ["CH"],
+  "\u{10458}": ["Y"],
+  "\u{10459}": ["NG"],
+  "\u{1045A}": ["B"],
+  "\u{1045B}": ["D"],
+  "\u{1045C}": ["G"],
+  "\u{1045D}": ["V"],
+  "\u{1045E}": ["DH"],
+  "\u{1045F}": ["Z"],
+  "\u{10460}": ["ZH"],
+  "\u{10461}": ["JH"],
+  "\u{10462}": ["W"],
+  "\u{10463}": ["HH"],
+  "\u{10464}": ["L"],
+  "\u{10465}": ["M"],
+  "\u{10466}": ["IH"],
+  "\u{10467}": ["EH"],
+  "\u{10468}": ["AE"],
+  // Schwa
+  "\u{10469}": ["AH"],
+  "\u{1046B}": ["UH"],
+  // Diphthongs
+  "\u{1046C}": ["AW"],
+  // Vowels
+  "\u{1046D}": ["AA"],
+  "\u{1046E}": ["R"],
+  "\u{1046F}": ["N"],
+  "\u{10470}": ["IY"],
+  "\u{10471}": ["EY"],
+  "\u{10472}": ["AY"],
+  "\u{10473}": ["AH"],
+  "\u{10474}": ["OW"],
+  "\u{10475}": ["UW"],
+  "\u{10476}": ["OY"],
+  "\u{10477}": ["AO"],
+  // R-colored ligatures (expand to vowel + R)
+  "\u{10478}": ["AA", "R"],
+  "\u{10479}": ["AO", "R"],
+  "\u{1047A}": ["EH", "R"],
+  "\u{1047B}": ["ER"],
+  "\u{1047C}": ["AH", "R"],
+  "\u{1047D}": ["IH", "R"]
+};
+
+// src/tokenize.ts
+function isShavianChar(char) {
+  const cp = char.codePointAt(0);
+  if (cp === void 0) {
+    return false;
+  }
+  return cp >= 66640 && cp <= 66687;
+}
+function tokenizeShavian(text) {
+  const tokens = [];
+  let current = "";
+  let inWord = false;
+  for (const char of text) {
+    const isShavian = isShavianChar(char);
+    if (isShavian === inWord) {
+      current += char;
+    } else {
+      if (current.length > 0) {
+        tokens.push({ isWord: inWord, text: current });
+      }
+      current = char;
+      inWord = isShavian;
+    }
+  }
+  if (current.length > 0) {
+    tokens.push({ isWord: inWord, text: current });
+  }
+  return tokens;
+}
+
+// src/from-shavian.ts
+function reverseTranslateShavianText(text) {
+  const tokens = tokenizeShavian(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateShavianWord(token.text);
+      return matches[0] ?? token.text;
+    }
+    return token.text;
+  }).join("");
+}
+function reverseTranslateShavianTextWithMapping(text) {
+  const tokens = tokenizeShavian(text);
+  return tokens.map((token) => {
+    if (token.isWord) {
+      const matches = reverseTranslateShavianWord(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 reverseTranslateShavianWord(word) {
+  const arpabet = shavianToArpabet(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;
+}
+function shavianToArpabet(text) {
+  const result = [];
+  for (const char of text) {
+    if (!isShavianChar(char)) {
+      continue;
+    }
+    const phonemes = SHAVIAN_TO_ARPABET_MAP[char];
+    if (phonemes !== void 0) {
+      result.push(...phonemes);
+    }
+  }
+  return result.length > 0 ? result : null;
+}
+
+// src/to-shavian.ts
+import { stripStress } from "@ingglish/phonemes";
+function arpabetToShavian(arpabet) {
+  let result = "";
+  const len = arpabet.length;
+  for (let i = 0; i < len; i++) {
+    const phoneme = arpabet[i];
+    const base = stripStress(phoneme);
+    if (i + 1 < len && arpabet[i + 1] === "R") {
+      const stressKey = base === "AH" ? phoneme : base;
+      const ligature = SHAVIAN_R_COLORED[stressKey] ?? SHAVIAN_R_COLORED[base];
+      if (ligature !== void 0) {
+        result += ligature;
+        i++;
+        continue;
+      }
+    }
+    if (base === "AH") {
+      const lastChar = phoneme.codePointAt(phoneme.length - 1);
+      if (lastChar === 48) {
+        result += SHAVIAN_SCHWA;
+        continue;
+      }
+    }
+    result += ARPABET_TO_SHAVIAN_MAP[base] ?? "";
+  }
+  return result;
+}
+
+// src/index.ts
+function registerShavian() {
+  registerFormat("shavian", {
+    forward: arpabetToShavian,
+    isLatinScript: false,
+    label: "Shavian",
+    nativeLabel: "\u{10456}\u{10471}\u{1045D}\u{1047E}\u{1046F}",
+    preservesCase: false,
+    reverseText: reverseTranslateShavianText,
+    reverseTextWithMapping: reverseTranslateShavianTextWithMapping
+  });
+}
+export {
+  registerShavian
+};

package/package.json

@@ -0,0 +1,51 @@
+{
+  "name": "@ingglish/shavian",
+  "version": "0.1.0",
+  "description": "Shavian 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/shavian"
+  },
+  "homepage": "https://github.com/ptarjan/ingglish#readme",
+  "bugs": {
+    "url": "https://github.com/ptarjan/ingglish/issues"
+  }
+}