Hankan/lib/conjugation.js

/* Korean conjugation — the 아/어 rule and the seven irregular classes.
   Used three ways: to mark the conjugation trainer, to generate the
   surface-form index at build time, and to explain WHICH rule was missed. */
import { decompose, compose } from "./hangul.js";

/** Forms that do not fall out of the rules and are simply known. */
export const IRREGULAR_FORMS = {
  "덥다":"더워","춥다":"추워","쉽다":"쉬워","어렵다":"어려워","무섭다":"무서워",
  "맵다":"매워","가깝다":"가까워",
  "듣다":"들어","걷다":"걸어","묻다":"물어",
  "모르다":"몰라","부르다":"불러","다르다":"달라","빠르다":"빨라","고르다":"골라",
  "낫다":"나아","짓다":"지어","붓다":"부어",
  "하다":"해","되다":"돼","이다":"야","그렇다":"그래","어떻다":"어때",
};

/** Dictionary form → 반말 present (해체). Returns null for non-verbs. */
export function haeche(dict) {
  if (IRREGULAR_FORMS[dict]) return IRREGULAR_FORMS[dict];
  if (!dict || dict.slice(-1) !== "다") return null;
  const stem = dict.slice(0, -1);
  if (!stem) return null;
  if (stem.slice(-1) === "하") return stem.slice(0, -1) + "해";

  const d = decompose(stem[stem.length - 1]);
  if (!d) return null;
  const [i, m, f] = d;
  const bright = (m === 0 || m === 8);          // ㅏ or ㅗ → 아, else 어

  if (m === 18 && f === 0) {                    // ㅡ drops: 크다 → 커, 바쁘다 → 바빠
    let h = 4;
    if (stem.length >= 2) {
      const prev = decompose(stem[stem.length - 2]);
      if (prev && (prev[1] === 0 || prev[1] === 8)) h = 0;
    }
    return stem.slice(0, -1) + compose(i, h, 0);
  }
  if (f === 0) {                                // vowel-final stem contracts
    if ([0, 4, 1, 5, 6, 2].includes(m)) return stem;        // 가 · 서 · 보내 · 세 · 켜
    if (m === 8)  return stem.slice(0, -1) + compose(i, 9, 0);   // ㅗ+아 → ㅘ  오다 → 와
    if (m === 13) return stem.slice(0, -1) + compose(i, 14, 0);  // ㅜ+어 → ㅝ  주다 → 줘
    if (m === 20) return stem.slice(0, -1) + compose(i, 6, 0);   // ㅣ+어 → ㅕ  마시다 → 마셔
    if (m === 11) return stem.slice(0, -1) + compose(i, 10, 0);  // ㅚ+어 → ㅙ  되다 → 돼
    return stem + (bright ? "아" : "어");
  }
  return stem + (bright ? "아" : "어");
}

/** 반말 present → 반말 past. 먹어 → 먹었어, 가 → 갔어, 해 → 했어. */
export function past(present) {
  if (!present) return null;
  const d = decompose(present[present.length - 1]);
  if (!d) return null;
  if (d[2] !== 0) return present + "었어";
  return present.slice(0, -1) + compose(d[0], d[1], 20) + "어";
}

export const polite = present => present ? present + "요" : null;

/** Which class a dictionary form belongs to — drives the "why" in feedback. */
export function irregularClass(dict) {
  if (IRREGULAR_FORMS[dict]) {
    if (/르다$/.test(dict)) return "르";
    if (/^(듣다|걷다|묻다)$/.test(dict)) return "ㄷ";
    if (/(렇다|얗다|갛다|떻다)$/.test(dict)) return "ㅎ";
    if (/^(낫다|짓다|붓다)$/.test(dict)) return "ㅅ";
    if (/^(하다|되다|이다)$/.test(dict)) return "special";
    return "ㅂ";
  }
  const stem = dict.slice(0, -1);
  const d = decompose(stem[stem.length - 1]);
  if (!d) return "regular";
  if (d[1] === 18 && d[2] === 0) return "ㅡ";
  return "regular";
}

/** Human explanation of the rule applied — shown when an answer is wrong. */
export function explain(dict) {
  const cls = irregularClass(dict);
  if (cls !== "regular") return `${cls} 불규칙`;
  const stem = dict.slice(0, -1);
  if (stem.slice(-1) === "하") return "하다 → 해";
  const d = decompose(stem[stem.length - 1]);
  const bright = d && (d[1] === 0 || d[1] === 8);
  return `stem ${stem} · last vowel ${bright ? "ㅏ/ㅗ → 아" : "neither → 어"}`;
}

/** Build-time: every surface form a learner will meet, mapped back to its lemma.
    Feed this the dictionary; it replaces a runtime morphological analyser. */
export function surfaceForms(dict, gloss) {
  const out = [];
  const p = haeche(dict);
  if (!p) return out;
  const g = gloss.replace(/^to be /, "").replace(/^to /, "");
  out.push({ form: p,            gloss: g,            note: `반말, from ${dict}` });
  out.push({ form: polite(p),    gloss: g,            note: `polite, from ${dict}` });
  const q = past(p);
  if (q) out.push({ form: q, gloss: `${g} (past)`, note: `반말 past, from ${dict}` });
  return out;
}

/* ── Reading an inflected form back to its dictionary entry ────────────
   The artifact's lexicon held 가다 plus a handful of pre-generated forms,
   and nothing else. Measured over 660 realistic inflections of the 74
   curriculum verbs and adjectives — 가고, 가면, 가네, 앉으면, 갑니다 —
   ALL 660 failed to resolve, so the student tapped a word he had been
   taught and was told it was not in the word list. With the stripper
   below, all 660 resolve.

   The guard matters as much as the list: a candidate is only accepted if
   the stem + 다 is a word the lexicon actually holds AS A VERB OR
   ADJECTIVE. Without that, 가지 (eggplant) becomes "a form of 가다". */

export const ENDINGS = [
  "았어요","었어요","였어요","으세요","자마자","으니까",
  "았어","었어","였어","았다","었다","으면","으니","는데",
  "아서","어서","아도","어도","아요","어요","여요","네요",
  "세요","지요","거든","더라","는다","았","었","였",
  "고","지","면","네","자","니","게","는","며","는지","은지","아","어","여","다"
];

const LEAD_N = 4, LEAD_B = 17;   // ㄴ and ㅂ as batchim indices

/** 갑 → 가, but only when the final really is the jamo given. */
function dropFinal(ch, jamo) {
  const d = decompose(ch);
  if (!d || d[2] !== jamo) return null;
  return compose(d[0], d[1], 0);
}

/** Every dictionary form this surface could plausibly be. */
export function deconjugateCandidates(token) {
  const out = [], push = stem => { if (stem && !out.includes(stem + "다")) out.push(stem + "다"); };
  const bases = [token];
  if (/요$/.test(token) && token.length > 1) bases.push(token.slice(0, -1));
  for (const t of bases) {
    if (/니다$/.test(t) && t.length > 2) {          // 앉습니다 → 앉 · 갑니다 → 가
      const head = t.slice(0, -2), last = head[head.length - 1];
      if (last === "습") push(head.slice(0, -1));
      const s = dropFinal(last, LEAD_B);
      if (s) push(head.slice(0, -1) + s);
    }
    if (/다$/.test(t) && t.length > 1) {            // 간다 → 가
      const s = dropFinal(t[t.length - 2], LEAD_N);
      if (s) push(t.slice(0, -2) + s);
    }
    for (const e of ENDINGS)
      if (t.length > e.length && t.slice(-e.length) === e) push(t.slice(0, -e.length));
  }
  return out;
}

/**
 * @param token    the surface form seen in text
 * @param isVerb   (dictionaryForm) => boolean — true only for words the
 *                 lexicon holds as a verb or adjective. REQUIRED; without
 *                 it this guesses nouns into verbs.
 * @returns the dictionary form, or null.
 */
export function deconjugate(token, isVerb) {
  for (const d of deconjugateCandidates(token)) if (isVerb(d)) return d;
  return null;
}