Hankan/test/lib/lexicon.test.ts

/* Golden tests pinning lib/lexicon.js — the one resolver shared by word
   lookup and the gate. It ships unchanged. */

import { describe, it, expect } from "vitest";
import { readFileSync } from "node:fs";
import { buildLexicon, Lexicon, PARTICLES } from "@lib/lexicon.js";
import { haeche, past } from "@lib/conjugation.js";
import { flatten } from "@lib/gate.js";
import type { Curriculum } from "@lib/gate.js";

const conj = { haeche, past };

describe("ORDER MATTERS — roadmap words are entered first", () => {
  /* 마셔 belongs to unit 2.3. Expanded from the deck first, it becomes a form
     of 마시다 and inherits that stem's permission, so a unit-2.3 word turns
     legal in Phase 1. In the fixture corpus that is four messages of
     violations that stop being reported. */
  it("keeps a scheduled form its own head", () => {
    const lex = buildLexicon(
      { roadmapWords: ["마셔"], deck: [{ ko: "마시다", en: "to drink", pos: "verb" }] },
      conj,
    );
    expect(lex.heads("마셔")).toEqual(["마셔"]);
    expect(lex.get("마셔")).toMatchObject({ src: "roadmap", base: "" });
  });

  it("links it to the stem when the deck got there first", () => {
    const lex = buildLexicon({ deck: [{ ko: "마시다", en: "to drink", pos: "verb" }] }, conj);
    expect(lex.heads("마셔")).toEqual(["마셔", "마시다"]);
  });
});

describe("heads — every route, best first", () => {
  const lex = buildLexicon(
    {
      roadmapWords: ["닭"],
      deck: [
        { ko: "마시다", en: "to drink", pos: "verb" },
        { ko: "친구", en: "friend", pos: "noun" },
      ],
      glossExtra: [["이야", "it is"]],
      sfx: [["쿵", "thud"]],
    },
    conj,
  );

  it("strips a particle", () => {
    expect(lex.heads("닭이")).toEqual(["닭"]);
    expect(lex.heads("친구가")).toEqual(["친구"]);
  });

  it("follows a generated form back to its stem", () => {
    expect(lex.heads("마셨어")).toEqual(["마셨어", "마시다"]);
  });

  it("deconjugates a form nobody generated, but only onto a known verb", () => {
    expect(lex.heads("마시면")).toEqual(["마시다"]);
  });

  it("returns nothing for a word it cannot place", () => {
    expect(lex.heads("없는말")).toEqual([]);
  });
});

describe("lookup — what the student sees on a tap", () => {
  const lex = buildLexicon(
    { deck: [{ ko: "마시다", en: "to drink", pos: "verb" }, { ko: "친구", en: "friend", pos: "noun" }] },
    conj,
  );

  it("notes the particle", () => {
    expect(lex.lookup("친구가")).toMatchObject({ ko: "친구가", gloss: "friend", note: "with 조사 가" });
  });

  it("notes the dictionary form", () => {
    expect(lex.lookup("마시면")).toMatchObject({ gloss: "to drink", note: "a form of 마시다" });
  });

  it("is null for an unknown word", () => {
    expect(lex.lookup("없는말")).toBeNull();
  });
});

describe("Lexicon", () => {
  it("never replaces an existing entry — the first writer wins", () => {
    const lex = new Lexicon();
    lex.add("밥", "rice");
    lex.add("밥", "meal");
    expect(lex.get("밥")!.gloss).toBe("rice");
  });

  it("strips the longer particle forms", () => {
    expect(PARTICLES).toEqual(expect.arrayContaining(["에서", "한테", "까지", "처럼"]));
  });
});

describe("the shipped data", () => {
  const read = (f: string) => JSON.parse(readFileSync(new URL(`../../data/${f}`, import.meta.url), "utf8"));
  const curriculum = read("curriculum.json") as Curriculum;
  const deck = read("deck.json") as { topics: Record<string, [string, string, string, string][]> };
  const glossExtra = read("gloss-extra.json") as { entries: { ko: string; en: string; note?: string }[] };
  const sentences = read("sentences.json") as { sentences: { parts: [string, string][] }[] };
  const sfx = read("sfx.json") as { items: { ko: string; en: string }[] };

  const units = flatten(curriculum);
  const lex = buildLexicon(
    {
      roadmapWords: units.flatMap((u) => u.words ?? []),
      deck: Object.values(deck.topics)
        .flat()
        .map(([ko, , en, pos]) => ({ ko, en, pos })),
      glossExtra: glossExtra.entries.map((g) => [g.ko, g.en, g.note] as const),
      sentences: sentences.sentences,
      sfx: sfx.items.map((i) => [i.ko, i.en] as const),
    },
    conj,
  );

  it("resolves every roadmap word", () => {
    const missing = units.flatMap((u) => u.words ?? []).filter((w) => !lex.lookup(w));
    expect(missing).toEqual([]);
  });
});