@ingglish/fallback 0.1.0

package/dist/index.js

@@ -0,0 +1,626 @@
+// src/index.ts
+import { getCustomPronunciation } from "@ingglish/dictionary";
+import { wordToArpabetTraced, wordToPhonetic } from "@ingglish/g2p";
+import { arpabetToFormat as arpabetToFormat5 } from "@ingglish/phonemes";
+
+// src/acronyms.ts
+import { arpabetToFormat } from "@ingglish/phonemes";
+var INITIALISM_EXPANSIONS = {
+  ac: ["alternating", "current"],
+  ad: ["anno", "domini"],
+  afk: ["away", "from", "keyboard"],
+  // AI / ML
+  ai: ["artificial", "intelligence"],
+  aka: ["also", "known", "as"],
+  am: ["ante", "meridiem"],
+  api: ["application", "programming", "interface"],
+  asap: ["as", "soon", "as", "possible"],
+  atm: ["automated", "teller", "machine"],
+  aws: ["amazon", "web", "services"],
+  b2b: ["business", "to", "business"],
+  b2c: ["business", "to", "consumer"],
+  bc: ["before", "christ"],
+  bdd: ["behavior", "driven", "development"],
+  brb: ["be", "right", "back"],
+  btw: ["by", "the", "way"],
+  byob: ["bring", "your", "own", "bottle"],
+  cd: ["continuous", "deployment"],
+  cdn: ["content", "delivery", "network"],
+  // Business / titles
+  ceo: ["chief", "executive", "officer"],
+  cfo: ["chief", "financial", "officer"],
+  ci: ["continuous", "integration"],
+  cia: ["central", "intelligence", "agency"],
+  cio: ["chief", "information", "officer"],
+  cli: ["command", "line", "interface"],
+  cmo: ["chief", "marketing", "officer"],
+  cms: ["content", "management", "system"],
+  cnn: ["convolutional", "neural", "network"],
+  coo: ["chief", "operating", "officer"],
+  cors: ["cross", "origin", "resource", "sharing"],
+  cpr: ["cardiopulmonary", "resuscitation"],
+  cpu: ["central", "processing", "unit"],
+  crm: ["customer", "relationship", "management"],
+  crud: ["create", "read", "update", "delete"],
+  cso: ["chief", "security", "officer"],
+  css: ["cascading", "style", "sheets"],
+  csv: ["comma", "separated", "values"],
+  cto: ["chief", "technology", "officer"],
+  dc: ["direct", "current"],
+  ddos: ["distributed", "denial", "of", "service"],
+  dea: ["drug", "enforcement", "administration"],
+  diy: ["do", "it", "yourself"],
+  dj: ["disc", "jockey"],
+  dmv: ["department", "of", "motor", "vehicles"],
+  // Medical / science
+  dna: ["deoxyribonucleic", "acid"],
+  dns: ["domain", "name", "system"],
+  eod: ["end", "of", "day"],
+  epa: ["environmental", "protection", "agency"],
+  er: ["emergency", "room"],
+  erp: ["enterprise", "resource", "planning"],
+  eta: ["estimated", "time", "of", "arrival"],
+  etl: ["extract", "transform", "load"],
+  eu: ["european", "union"],
+  faq: ["frequently", "asked", "questions"],
+  // Government / organizations
+  fbi: ["federal", "bureau", "of", "investigation"],
+  fda: ["food", "and", "drug", "administration"],
+  ftp: ["file", "transfer", "protocol"],
+  fyi: ["for", "your", "information"],
+  gan: ["generative", "adversarial", "network"],
+  gcp: ["google", "cloud", "platform"],
+  gif: ["graphics", "interchange", "format"],
+  gps: ["global", "positioning", "system"],
+  gpt: ["generative", "pre-trained", "transformer"],
+  gpu: ["graphics", "processing", "unit"],
+  gui: ["graphical", "user", "interface"],
+  hdd: ["hard", "disk", "drive"],
+  hiv: ["human", "immunodeficiency", "virus"],
+  hr: ["human", "resources"],
+  html: ["hypertext", "markup", "language"],
+  http: ["hypertext", "transfer", "protocol"],
+  https: ["hypertext", "transfer", "protocol", "secure"],
+  iaas: ["infrastructure", "as", "a", "service"],
+  icu: ["intensive", "care", "unit"],
+  // General / common
+  id: ["identification"],
+  ide: ["integrated", "development", "environment"],
+  idk: ["i", "don't", "know"],
+  imo: ["in", "my", "opinion"],
+  io: ["input", "output"],
+  ip: ["internet", "protocol"],
+  iq: ["intelligence", "quotient"],
+  irs: ["internal", "revenue", "service"],
+  isp: ["internet", "service", "provider"],
+  it: ["information", "technology"],
+  jpeg: ["joint", "photographic", "experts", "group"],
+  // Media
+  jpg: ["joint", "photographic", "experts", "group"],
+  json: ["javascript", "object", "notation"],
+  jwt: ["json", "web", "token"],
+  kpi: ["key", "performance", "indicator"],
+  // Networking
+  lan: ["local", "area", "network"],
+  lcd: ["liquid", "crystal", "display"],
+  led: ["light", "emitting", "diode"],
+  llm: ["large", "language", "model"],
+  mc: ["master", "of", "ceremonies"],
+  // Security
+  mfa: ["multi", "factor", "authentication"],
+  ml: ["machine", "learning"],
+  mp3: ["moving", "picture", "experts", "group", "audio", "layer"],
+  mp4: ["moving", "picture", "experts", "group"],
+  mph: ["miles", "per", "hour"],
+  mri: ["magnetic", "resonance", "imaging"],
+  mvp: ["minimum", "viable", "product"],
+  nasa: ["national", "aeronautics", "space", "administration"],
+  // Acronyms pronounced as words (pass through unchanged like initialisms)
+  nato: ["north", "atlantic", "treaty", "organization"],
+  nda: ["non", "disclosure", "agreement"],
+  nic: ["network", "interface", "card"],
+  nlp: ["natural", "language", "processing"],
+  nosql: ["not", "only", "sql"],
+  nsa: ["national", "security", "agency"],
+  nsfw: ["not", "safe", "for", "work"],
+  nyc: ["new", "york", "city"],
+  omg: ["oh", "my", "god"],
+  ooo: ["out", "of", "office"],
+  // Development
+  oop: ["object", "oriented", "programming"],
+  orm: ["object", "relational", "mapping"],
+  os: ["operating", "system"],
+  otp: ["one", "time", "password"],
+  paas: ["platform", "as", "a", "service"],
+  pc: ["personal", "computer"],
+  pdf: ["portable", "document", "format"],
+  php: ["hypertext", "preprocessor"],
+  pm: ["post", "meridiem"],
+  png: ["portable", "network", "graphics"],
+  pov: ["point", "of", "view"],
+  pr: ["public", "relations"],
+  pto: ["paid", "time", "off"],
+  qa: ["quality", "assurance"],
+  rag: ["retrieval", "augmented", "generation"],
+  ram: ["random", "access", "memory"],
+  rfp: ["request", "for", "proposal"],
+  rip: ["rest", "in", "peace"],
+  rna: ["ribonucleic", "acid"],
+  rnn: ["recurrent", "neural", "network"],
+  roi: ["return", "on", "investment"],
+  rom: ["read", "only", "memory"],
+  rpm: ["revolutions", "per", "minute"],
+  rsvp: ["please", "respond"],
+  rv: ["recreational", "vehicle"],
+  // Cloud / services
+  saas: ["software", "as", "a", "service"],
+  sdk: ["software", "development", "kit"],
+  sftp: ["secure", "file", "transfer", "protocol"],
+  sla: ["service", "level", "agreement"],
+  // Database
+  sql: ["structured", "query", "language"],
+  ssd: ["solid", "state", "drive"],
+  ssh: ["secure", "shell"],
+  ssl: ["secure", "sockets", "layer"],
+  suv: ["sport", "utility", "vehicle"],
+  svg: ["scalable", "vector", "graphics"],
+  tba: ["to", "be", "announced"],
+  tbd: ["to", "be", "determined"],
+  tcp: ["transmission", "control", "protocol"],
+  tdd: ["test", "driven", "development"],
+  tldr: ["too", "long", "didn't", "read"],
+  tls: ["transport", "layer", "security"],
+  tv: ["television"],
+  uat: ["user", "acceptance", "testing"],
+  udp: ["user", "datagram", "protocol"],
+  // User interface / experience
+  ui: ["user", "interface"],
+  uk: ["united", "kingdom"],
+  un: ["united", "nations"],
+  uri: ["uniform", "resource", "identifier"],
+  // Tech / web
+  url: ["uniform", "resource", "locator"],
+  us: ["united", "states"],
+  usa: ["united", "states", "of", "america"],
+  // Hardware
+  usb: ["universal", "serial", "bus"],
+  uv: ["ultraviolet"],
+  ux: ["user", "experience"],
+  vp: ["vice", "president"],
+  vpn: ["virtual", "private", "network"],
+  wan: ["wide", "area", "network"],
+  xml: ["extensible", "markup", "language"],
+  xss: ["cross", "site", "scripting"]
+};
+var MAX_INITIALISM_LENGTH = 5;
+var LETTER_PHONEMES = {
+  a: ["EY1"],
+  b: ["B", "IY1"],
+  c: ["S", "IY1"],
+  d: ["D", "IY1"],
+  e: ["IY1"],
+  f: ["EH1", "F"],
+  g: ["JH", "IY1"],
+  h: ["EY1", "CH"],
+  i: ["AY1"],
+  j: ["JH", "EY1"],
+  k: ["K", "EY1"],
+  l: ["EH1", "L"],
+  m: ["EH1", "M"],
+  n: ["EH1", "N"],
+  o: ["OW1"],
+  p: ["P", "IY1"],
+  q: ["K", "Y", "UW1"],
+  r: ["AA1", "R"],
+  s: ["EH1", "S"],
+  t: ["T", "IY1"],
+  u: ["Y", "UW1"],
+  v: ["V", "IY1"],
+  w: ["D", "AH1", "B", "AH0", "L", "Y", "UW0"],
+  x: ["EH1", "K", "S"],
+  y: ["W", "AY1"],
+  z: ["Z", "IY1"]
+};
+var KNOWN_INITIALISMS = new Set(Object.keys(INITIALISM_EXPANSIONS));
+function isInitialism(word) {
+  if (word.length > MAX_INITIALISM_LENGTH) {
+    return false;
+  }
+  return KNOWN_INITIALISMS.has(word.toLowerCase());
+}
+var INITIALISM_SUFFIXES = ["'s", "s"];
+function parseInitialismWithSuffix(word) {
+  for (const suffix of INITIALISM_SUFFIXES) {
+    if (word.length > suffix.length && word.endsWith(suffix)) {
+      const base = word.slice(0, -suffix.length);
+      if (isInitialism(base)) {
+        return { base, suffix };
+      }
+    }
+  }
+  return null;
+}
+function translateAsAcronym(word, format = "ingglish") {
+  const arpabet = [];
+  for (const char of word.toLowerCase()) {
+    const letterArpabet = LETTER_PHONEMES[char];
+    if (letterArpabet !== void 0) {
+      arpabet.push(...letterArpabet);
+    }
+  }
+  return arpabetToFormat(arpabet, format);
+}
+
+// src/british.ts
+import { lookupPronunciation } from "@ingglish/dictionary";
+import { arpabetToFormat as arpabetToFormat2 } from "@ingglish/phonemes";
+var BRITISH_TO_AMERICAN = [
+  // -isation → -ization (must come before -ise)
+  { pattern: /isation$/, replacement: "ization" },
+  // -ise → -ize (realise→realize, organise→organize)
+  { pattern: /ise$/, replacement: "ize" },
+  // -our → -or (colour→color, favour→favor)
+  { pattern: /our$/, replacement: "or" },
+  // -oured → -ored (coloured→colored, favoured→favored)
+  { pattern: /oured$/, replacement: "ored" },
+  // -ouring → -oring (colouring→coloring)
+  { pattern: /ouring$/, replacement: "oring" },
+  // -ourable → -orable (favourable→favorable)
+  { pattern: /ourable$/, replacement: "orable" },
+  // -re → -er (centre→center, theatre→theater)
+  // Only after consonants to avoid matching normal -re words
+  { pattern: /([a-z])re$/, replacement: "$1er" },
+  // -lled → -led (travelled→traveled, cancelled→canceled)
+  { pattern: /lled$/, replacement: "led" },
+  // -lling → -ling (travelling→traveling, cancelling→canceling)
+  { pattern: /lling$/, replacement: "ling" },
+  // -ller → -ler (traveller→traveler)
+  { pattern: /ller$/, replacement: "ler" },
+  // -ence → -ense (defence→defense, offence→offense)
+  { pattern: /ence$/, replacement: "ense" },
+  // -ogue → -og (catalogue→catalog, dialogue→dialog)
+  { pattern: /ogue$/, replacement: "og" },
+  // -ae- → -e- (anaesthetic→anesthetic, paediatric→pediatric)
+  { pattern: /ae/, replacement: "e" },
+  // -oe- → -e- (foetus→fetus, oestrogen→estrogen)
+  { pattern: /oe/, replacement: "e" },
+  // -ey → -y (curtsey→curtsy)
+  { pattern: /ey$/, replacement: "y" },
+  // grey → gray
+  { pattern: /grey/, replacement: "gray" }
+];
+function matchBritish(word) {
+  const lower = word.toLowerCase();
+  for (const { pattern, replacement } of BRITISH_TO_AMERICAN) {
+    if (pattern.test(lower)) {
+      const american = lower.replace(pattern, replacement);
+      if (american !== lower) {
+        const phonemes = lookupPronunciation(american);
+        if (phonemes) {
+          return { american, phonemes };
+        }
+      }
+    }
+  }
+  return null;
+}
+function translateAsBritish(word, format = "ingglish") {
+  const match = matchBritish(word);
+  if (match === null) {
+    return null;
+  }
+  return arpabetToFormat2(match.phonemes, format);
+}
+
+// src/compounds.ts
+import { lookupPronunciation as lookupPronunciation2, getWordFrequency } from "@ingglish/dictionary";
+import {
+  arpabetToFormat as arpabetToFormat3,
+  getFormatJoinSeparator,
+  getFormatPreservesCase
+} from "@ingglish/phonemes";
+function capitalize(str) {
+  if (str.length === 0) {
+    return str;
+  }
+  return str.charAt(0).toUpperCase() + str.slice(1);
+}
+function isUpperCase(char) {
+  return char === char.toUpperCase() && char !== char.toLowerCase();
+}
+var MIN_PART_LENGTH = 3;
+var MIN_PART_FREQUENCY = 500;
+var MAX_PART_LENGTH = 15;
+function dpDecompose(word) {
+  const n = word.length;
+  const dp = Array.from({
+    length: n + 1
+  });
+  dp[0] = { parts: [], score: 0 };
+  for (let i = MIN_PART_LENGTH; i <= n; i++) {
+    for (let j = Math.max(0, i - MAX_PART_LENGTH); j <= i - MIN_PART_LENGTH; j++) {
+      if (j === 0 && i === n) {
+        continue;
+      }
+      const prev = dp[j];
+      if (prev === void 0) {
+        continue;
+      }
+      const chunk = word.slice(j, i);
+      const phonemes = lookupWord(chunk);
+      if (!phonemes) {
+        continue;
+      }
+      const freq = getWordFrequency(chunk);
+      if (freq === void 0 || freq < MIN_PART_FREQUENCY) {
+        continue;
+      }
+      const newScore = prev.score + freq;
+      const newParts = prev.parts.length + 1;
+      const current = dp[i];
+      if (current === void 0 || newParts < current.parts.length || newParts === current.parts.length && newScore > current.score) {
+        dp[i] = { parts: [...prev.parts, chunk], score: newScore };
+      }
+    }
+  }
+  const result = dp[n];
+  if (result === void 0 || result.parts.length < 2) {
+    return null;
+  }
+  return result.parts;
+}
+function translateAsCompound(word, format = "ingglish") {
+  const lowerWord = word.toLowerCase();
+  if (lowerWord.length < 6) {
+    return null;
+  }
+  const parts = dpDecompose(lowerWord);
+  if (!parts) {
+    return null;
+  }
+  const translations = [];
+  let pos = 0;
+  for (const part of parts) {
+    const phonemes = lookupWord(part);
+    if (!phonemes) {
+      return null;
+    }
+    let translated = arpabetToFormat3(phonemes, format);
+    if (getFormatPreservesCase(format)) {
+      const originalPart = word.slice(pos, pos + part.length);
+      if (originalPart.length > 0 && isUpperCase(originalPart[0])) {
+        translated = capitalize(translated);
+      }
+    }
+    translations.push(translated);
+    pos += part.length;
+  }
+  return translations.join(getFormatJoinSeparator(format));
+}
+function lookupWord(word) {
+  return lookupPronunciation2(word);
+}
+
+// src/stemming.ts
+import { lookupPronunciation as lookupPronunciation3 } from "@ingglish/dictionary";
+import { arpabetToFormat as arpabetToFormat4, stripStress } from "@ingglish/phonemes";
+var VOICELESS = /* @__PURE__ */ new Set(["CH", "F", "HH", "K", "P", "S", "SH", "T", "TH"]);
+var SIBILANTS = /* @__PURE__ */ new Set(["CH", "JH", "S", "SH", "Z", "ZH"]);
+function selectEdPhonemes(lastPhoneme) {
+  const base = stripStress(lastPhoneme);
+  if (base === "T" || base === "D") {
+    return ["IH0", "D"];
+  }
+  if (VOICELESS.has(base)) {
+    return ["T"];
+  }
+  return ["D"];
+}
+function selectSPhonemes(lastPhoneme) {
+  const base = stripStress(lastPhoneme);
+  if (SIBILANTS.has(base)) {
+    return ["IH0", "Z"];
+  }
+  if (VOICELESS.has(base)) {
+    return ["S"];
+  }
+  return ["Z"];
+}
+var INFLECTIONAL_SUFFIXES = /* @__PURE__ */ new Set([
+  "ed",
+  "er",
+  "es",
+  "est",
+  "ification",
+  "ify",
+  "ifying",
+  "ing",
+  "or",
+  "s"
+]);
+var SUFFIX_PHONEMES = [
+  // Long suffixes first (must come before shorter matches: -ification before -tion, -ifying before -ing)
+  { phonemes: ["IH0", "F", "IH0", "K", "EY1", "SH", "AH0", "N"], suffix: "ification" },
+  { phonemes: ["IH0", "F", "AY1", "IH0", "NG"], suffix: "ifying" },
+  { phonemes: ["IH0", "F", "AY1"], suffix: "ify" },
+  // Verb suffixes
+  { phonemes: ["IH0", "NG"], suffix: "ing" },
+  { phonemes: null, suffix: "ed" },
+  // allomorph: T/D/IH0 D (selected dynamically)
+  { phonemes: null, suffix: "es" },
+  // allomorph: same as -s (S/Z/IH0 Z based on stem)
+  { phonemes: null, suffix: "s" },
+  // allomorph: S/Z/IH0 Z (selected dynamically)
+  // Noun suffixes
+  { phonemes: ["SH", "AH0", "N"], suffix: "tion" },
+  { phonemes: ["ZH", "AH0", "N"], suffix: "sion" },
+  { phonemes: ["N", "AH0", "S"], suffix: "ness" },
+  { phonemes: ["M", "AH0", "N", "T"], suffix: "ment" },
+  { phonemes: ["IH0", "T", "IY0"], suffix: "ity" },
+  { phonemes: ["ER0"], suffix: "er" },
+  { phonemes: ["ER0"], suffix: "or" },
+  { phonemes: ["IH0", "S", "T"], suffix: "ist" },
+  { phonemes: ["IH0", "Z", "AH0", "M"], suffix: "ism" },
+  // Adjective suffixes
+  { phonemes: ["L", "IY0"], suffix: "ly" },
+  { phonemes: ["F", "AH0", "L"], suffix: "ful" },
+  { phonemes: ["L", "AH0", "S"], suffix: "less" },
+  { phonemes: ["AH0", "B", "AH0", "L"], suffix: "able" },
+  { phonemes: ["AH0", "B", "AH0", "L"], suffix: "ible" },
+  { phonemes: ["AH0", "S"], suffix: "ous" },
+  { phonemes: ["IH0", "V"], suffix: "ive" },
+  { phonemes: ["AH0", "L"], suffix: "al" },
+  { phonemes: ["IH0", "K"], suffix: "ic" },
+  // Comparative/superlative
+  { phonemes: ["AH0", "S", "T"], suffix: "est" },
+  // Additional suffixes
+  { phonemes: ["AH0", "L", "IY0"], suffix: "ally" },
+  { phonemes: ["AA1", "L", "AH0", "JH", "IY0"], suffix: "ology" },
+  { phonemes: ["AY1", "Z"], suffix: "ize" },
+  { phonemes: ["AY1", "Z"], suffix: "ise" }
+];
+var PREFIX_PHONEMES = [
+  { phonemes: ["AH0", "N"], prefix: "un" },
+  { phonemes: ["R", "IY0"], prefix: "re" },
+  { phonemes: ["P", "R", "IY0"], prefix: "pre" },
+  { phonemes: ["D", "IH0", "S"], prefix: "dis" },
+  { phonemes: ["M", "IH0", "S"], prefix: "mis" },
+  { phonemes: ["OW1", "V", "ER0"], prefix: "over" },
+  { phonemes: ["AH1", "N", "D", "ER0"], prefix: "under" },
+  { phonemes: ["AW1", "T"], prefix: "out" },
+  { phonemes: ["AE1", "N", "T", "IY0"], prefix: "anti" },
+  { phonemes: ["S", "UW1", "P", "ER0"], prefix: "super" }
+];
+function matchStemming(word) {
+  const lowerWord = word.toLowerCase();
+  for (const { phonemes: suffixArpabet, suffix } of SUFFIX_PHONEMES) {
+    if (lowerWord.endsWith(suffix) && lowerWord.length > suffix.length + 2) {
+      const stem = lowerWord.slice(0, -suffix.length);
+      for (const variant of getStemVariants(stem, suffix)) {
+        const baseArpabet = lookupPronunciation3(variant);
+        if (baseArpabet) {
+          const resolvedSuffix = resolveSuffixPhonemes(suffix, suffixArpabet, baseArpabet);
+          return {
+            phonemes: [...baseArpabet, ...resolvedSuffix],
+            stem: variant,
+            suffix
+          };
+        }
+      }
+    }
+  }
+  for (const { phonemes: prefixArpabet, prefix } of PREFIX_PHONEMES) {
+    if (lowerWord.startsWith(prefix) && lowerWord.length > prefix.length + 2) {
+      const stem = lowerWord.slice(prefix.length);
+      const baseArpabet = lookupPronunciation3(stem);
+      if (baseArpabet) {
+        return {
+          phonemes: [...prefixArpabet, ...baseArpabet],
+          prefix,
+          stem
+        };
+      }
+    }
+  }
+  return null;
+}
+function translateWithStemming(word, format = "ingglish") {
+  const match = matchStemming(word);
+  if (match === null) {
+    return null;
+  }
+  return arpabetToFormat4(match.phonemes, format);
+}
+function getStemVariants(stem, suffix) {
+  const variants = [stem];
+  if (INFLECTIONAL_SUFFIXES.has(suffix)) {
+    variants.push(
+      stem + "e",
+      // hoping -> hope
+      stem.length > 1 ? stem.slice(0, -1) : stem,
+      // running -> run (double consonant)
+      stem.length > 0 ? stem + stem.at(-1) : stem
+      // big -> bigg (for adding -er)
+    );
+  }
+  if (stem.endsWith("i")) {
+    variants.push(stem.slice(0, -1) + "y");
+  }
+  variants.push(stem + "y");
+  return variants;
+}
+function resolveSuffixPhonemes(suffix, suffixArpabet, baseArpabet) {
+  if (suffixArpabet !== null) {
+    return suffixArpabet;
+  }
+  const lastPhoneme = baseArpabet.at(-1);
+  if (suffix === "ed") {
+    return selectEdPhonemes(lastPhoneme);
+  }
+  return selectSPhonemes(lastPhoneme);
+}
+
+// src/index.ts
+function diagnoseUnknown(word) {
+  if (/(.)\1\1/.test(word) || !/[aeiouy]/i.test(word)) {
+    return null;
+  }
+  const { strategy } = translateUnknownCore(word, "ingglish");
+  switch (strategy) {
+    case "british": {
+      const m = matchBritish(word);
+      return { americanSpelling: m.american, phonemes: m.phonemes, strategy: "british" };
+    }
+    case "compound": {
+      return { parts: dpDecompose(word.toLowerCase()), strategy: "compound" };
+    }
+    case "custom": {
+      return { phonemes: getCustomPronunciation(word), strategy: "custom" };
+    }
+    case "g2p": {
+      return { strategy: "g2p", trace: wordToArpabetTraced(word) };
+    }
+    case "initialism": {
+      return { strategy: "initialism" };
+    }
+    case "stemming": {
+      const m = matchStemming(word);
+      return { prefix: m.prefix, stem: m.stem, strategy: "stemming", suffix: m.suffix };
+    }
+  }
+}
+function translateUnknown(word, format = "ingglish") {
+  return translateUnknownCore(word, format).translated;
+}
+function translateUnknownCore(word, format) {
+  const customPhonemes = getCustomPronunciation(word);
+  if (customPhonemes !== void 0) {
+    return { strategy: "custom", translated: arpabetToFormat5(customPhonemes, format) };
+  }
+  if (isInitialism(word)) {
+    return { strategy: "initialism", translated: translateAsAcronym(word, format) };
+  }
+  const britishResult = translateAsBritish(word, format);
+  if (britishResult !== null && britishResult.length > 0) {
+    return { strategy: "british", translated: britishResult };
+  }
+  const compoundResult = translateAsCompound(word, format);
+  if (compoundResult !== null && compoundResult.length > 0) {
+    return { strategy: "compound", translated: compoundResult };
+  }
+  const stemmedResult = translateWithStemming(word, format);
+  if (stemmedResult !== null && stemmedResult.length > 0) {
+    return { strategy: "stemming", translated: stemmedResult };
+  }
+  return { strategy: "g2p", translated: wordToPhonetic(word, format) };
+}
+export {
+  KNOWN_INITIALISMS,
+  LETTER_PHONEMES,
+  diagnoseUnknown,
+  isInitialism,
+  matchBritish,
+  parseInitialismWithSuffix,
+  translateAsAcronym,
+  translateUnknown
+};

package/package.json

@@ -0,0 +1,54 @@
+{
+  "name": "@ingglish/fallback",
+  "version": "0.1.0",
+  "description": "Unknown word translation strategies for Ingglish (G2P, stemming, compounds, etc.)",
+  "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",
+    "bench": "vitest bench --no-color",
+    "prepublishOnly": "npm run build"
+  },
+  "dependencies": {
+    "@ingglish/phonemes": "^0.1.0",
+    "@ingglish/ipa": "^0.1.0",
+    "@ingglish/dictionary": "^0.1.0",
+    "@ingglish/g2p": "^0.1.0"
+  },
+  "author": "Paul Tarjan",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/ptarjan/ingglish.git",
+    "directory": "packages/fallback"
+  },
+  "homepage": "https://github.com/ptarjan/ingglish#readme",
+  "bugs": {
+    "url": "https://github.com/ptarjan/ingglish/issues"
+  }
+}