UHD_Media_Tool/packages/contracts/test/identify-words.test.ts

import { describe, expect, it } from "vitest";
import {
  compileEntityWords,
  evalEpisodeExpr,
  parseEntityWordLine,
  parseGlobalWordLine,
  parseGlobalWords,
  parseIdentityTag,
  printEntityWord,
  printGlobalWord,
  printIdentityTag,
  pyRegex,
  pySubn,
  rowsToText,
  ruleRowLines,
  updateRuleRow,
  type WordsRow,
  wordsToRows,
} from "../src/index.ts";

// 识别词语法(docs/design/identify-words.md):全局行按 MP __parse_word 拆;作品识别词的解析 / 打印往返、
// 编译(范围、优先级、冲突)、可视化行模型与文本往返(注释、停用、顺序、写错的行都不丢)。

describe("全局识别词(MP 语法)", () => {
  it("四种写法与注释、空行", () => {
    expect(parseGlobalWordLine("国语中字")).toMatchObject({ kind: "block", pattern: "国语中字" });
    expect(parseGlobalWordLine("A => B")).toMatchObject({ kind: "replace", pattern: "A", replacement: "B" });
    expect(parseGlobalWordLine("测试替换 => ")).toMatchObject({
      kind: "replace",
      pattern: "测试替换",
      replacement: "",
    });
    expect(parseGlobalWordLine("第 <> 集 >> EP+1")).toMatchObject({
      kind: "offset",
      front: "第",
      back: "集",
      offset: "EP+1",
    });
    expect(parseGlobalWordLine("旧名 => 新名 && 第 <> 集 >> EP+1")).toMatchObject({
      kind: "replace_offset",
      pattern: "旧名",
      replacement: "新名",
      front: "第",
      back: "集",
      offset: "EP+1",
    });
    expect(parseGlobalWordLine("# 动漫").kind).toBe("comment");
    expect(parseGlobalWordLine("   ").kind).toBe("blank");
  });

  it("打印与解析往返", () => {
    for (const t of ["国语中字", "A => B", "第 <> 集 >> EP+1", "旧名 => 新名 && 第 <> 集 >> 2*EP-1"]) {
      const p = parseGlobalWordLine(t);
      expect(printGlobalWord(p)).toBe(t);
    }
  });

  it("提前报错:正则写错、替换引用了不存在的分组、偏移表达式写错、两个定位词都空", () => {
    expect(parseGlobalWordLine("([ => X").error).toContain("正则");
    expect(parseGlobalWordLine("(a) => \\2").error).toContain("分组");
    expect(parseGlobalWordLine("第 <> 集 >> 2EP").error).toContain("运算符");
    expect(parseGlobalWordLine(" <>  >> EP+1").error).toBeDefined();
    expect(parseGlobalWords("A => B\n\n# x\nC").map((w) => [w.line, w.kind])).toEqual([
      [1, "replace"],
      [2, "blank"],
      [3, "comment"],
      [4, "block"],
    ]);
  });

  it("Python 正则与替换模板", () => {
    expect(pySubn(pyRegex("(?P<n>\\d+)集"), "第\\g<n>话", "12集")).toEqual(["第12话", 1]);
    expect(pySubn(pyRegex("(a)(b)"), "\\2\\1", "abab")).toEqual(["baba", 2]);
    expect(pySubn(pyRegex("(?i)foo"), "bar", "FOO foo")).toEqual(["bar bar", 2]);
    expect(pySubn(pyRegex("x"), "$1\\\\", "x")).toEqual(["$1\\", 1]);
    expect(pySubn(pyRegex("\\p{Han}+"), "中", "ab汉字cd")).toEqual(["ab中cd", 1]);
  });

  it("指定作品标签", () => {
    const t = parseIdentityTag("一念永恒{[tmdbid=107371;type=tv;s=1;g=abc]}S01");
    expect(t).toMatchObject({
      before: "一念永恒",
      after: "S01",
      tag: { tmdbId: "107371", type: "tv", season: "1", extra: ["g=abc"] },
    });
    expect(printIdentityTag(t!.tag)).toBe("{[tmdbid=107371;type=tv;s=1;g=abc]}");
    expect(parseIdentityTag("没有标签")).toBeNull();
  });
});

describe("作品识别词", () => {
  it("季集换算:目标季可省、EP 单独写 = 集号不变、发布组可多个、任意季写 *", () => {
    expect(parseEntityWordLine("S02 >> S01 EP+24")).toMatchObject({
      kind: "map",
      season: 2,
      groups: [],
      targetSeason: 1,
      expr: "EP+24",
    });
    expect(parseEntityWordLine("S03 @ADWeb @MWeb >> S01 EP")).toMatchObject({
      kind: "map",
      season: 3,
      groups: ["ADWeb", "MWeb"],
      targetSeason: 1,
      expr: "EP",
    });
    expect(parseEntityWordLine("S01 @Lilith-Raws >> ep - 12")).toMatchObject({ targetSeason: null, expr: "EP-12" });
    expect(parseEntityWordLine("S02 >> S01")).toMatchObject({ targetSeason: 1, expr: "EP" });
    expect(parseEntityWordLine("* @Judas >> EP*2-1")).toMatchObject({ season: null, groups: ["Judas"] });
    expect(parseEntityWordLine('S01 @"Some Group" >> EP')).toMatchObject({ groups: ["Some Group"] });
  });

  it("单集对照与特别篇", () => {
    expect(parseEntityWordLine("S01E13 >> S00E01")).toMatchObject({
      kind: "table",
      season: 1,
      from: { start: 13, end: 13 },
      to: { season: 0, episode: 1 },
    });
    expect(parseEntityWordLine("S01E27-E28 @Baha >> S02E02")).toMatchObject({
      kind: "table",
      groups: ["Baha"],
      from: { start: 27, end: 28 },
    });
    expect(parseEntityWordLine("E05 >> S00E02")).toMatchObject({ kind: "table", season: null });
    expect(parseEntityWordLine("S00 @SweetSub >> 特别篇")).toMatchObject({ kind: "special", special: "special" });
    expect(parseEntityWordLine("S01 >> 花絮")).toMatchObject({ kind: "special", special: "extra" });
    expect(parseEntityWordLine("S01 >> 忽略")).toMatchObject({ kind: "special", special: "ignore" });
  });

  it("写错的行给出原因", () => {
    expect(parseEntityWordLine("S02 S01 EP+1").error).toContain(">>");
    expect(parseEntityWordLine("Season2 >> EP").error).toContain("不是季号");
    expect(parseEntityWordLine("S02 ADWeb >> EP").error).toContain("@");
    expect(parseEntityWordLine("S02 >> S01 2EP").error).toContain("运算符");
    expect(parseEntityWordLine("S02 >> S01 12").error).toContain("EP");
    expect(parseEntityWordLine("S01E13 >> 第一集").error).toContain("目标季集");
    expect(parseEntityWordLine("S01E13-E10 >> S00E01").error).toContain("写反");
  });

  it("打印与解析往返(规范写法)", () => {
    for (const t of [
      "S02 >> S01 EP+24",
      "S03 @ADWeb @MWeb @黒ネズミたち >> S01 EP",
      "* @Judas >> EP*2-1",
      "S01E13 >> S00E01",
      "S01E27-E28 @Baha >> S02E02",
      "E05 >> S00E02",
      "S01 @SweetSub >> 花絮",
      'S01 @"Some Group" >> EP-1',
    ]) {
      const p = parseEntityWordLine(t);
      expect(p.error).toBeUndefined();
      expect(printEntityWord({ ...p, kind: p.kind, season: p.season ?? null, groups: p.groups ?? [] })).toBe(t);
    }
  });

  it("编译:一行多个发布组拆成多条;单集对照多行合成一张表;同范围冲突报错带行号", () => {
    const c = compileEntityWords(
      [
        "# 药屋",
        "S02 >> S01 EP+24",
        "S03 >> S01 EP+48",
        "S03 @ADWeb @MWeb >> S01 EP",
        "# S03 @Judas >> S01 EP",
        "S01E13 @Baha >> S00E01",
        "S01E14 @Baha >> S00E02",
        "S01E14 @Baha >> S00E03",
        "S01 @Baha >> 忽略",
        "s02 >> EP",
      ].join("\n"),
    );
    expect(c.rules.map((r) => [r.id, r.season, r.releaseGroup, r.kind, r.line])).toEqual([
      ["L0002", 2, null, "expression", 2],
      ["L0003", 3, null, "expression", 3],
      ["L0004", 3, "ADWeb", "expression", 4],
      ["L0004.1", 3, "MWeb", "expression", 4],
      ["L0006", 1, "Baha", "table", 6],
    ]);
    expect(c.rules[4]!.table).toEqual([
      { from: { start: 13, end: 13 }, to: { season: 0, episode: 1 } },
      { from: { start: 14, end: 14 }, to: { season: 0, episode: 2 } },
    ]);
    expect(c.errors).toEqual([
      { line: 8, message: expect.stringContaining("重叠") },
      { line: 9, message: expect.stringContaining("第 6 行已有规则") },
      { line: 10, message: expect.stringContaining("第 2 行已有规则") },
    ]);
  });

  it("集号算术与 MP 一致,EP 必须出现", () => {
    expect(evalEpisodeExpr("EP+24", 1)).toBe(25);
    expect(evalEpisodeExpr("ep*2-1", 3)).toBe(5);
    expect(() => evalEpisodeExpr("5", 1)).toThrow();
  });
});

describe("可视化行模型 ⇄ 文本", () => {
  const ENTITY = [
    "# 药屋少女的呢喃",
    "",
    "# 第二季接着第一季编号",
    "S02 >> S01 EP+24",
    "S03 >> S01 EP+48",
    "# S03 @Judas >> S01 EP",
    "S03 @ADWeb @MWeb >> S01 EP",
    "这一行写错了",
    "",
    "",
    "# 结尾注释",
  ].join("\n");

  it("原文逐字往返(含结尾换行、连续空行、注释、写错的行)", () => {
    for (const text of [ENTITY, `${ENTITY}\n`, "", "S02 >> S01 EP+24", "#x\n#y\n"]) {
      const rows = wordsToRows(text, "entity");
      expect(rowsToText(rows, text.endsWith("\n"))).toBe(text);
    }
  });

  it("备注贴在规则上方;注释掉的规则是停用行;写错的行是原文行", () => {
    const rows = wordsToRows(ENTITY, "entity");
    expect(rows.map((r) => [r.kind, r.kind === "rule" ? [r.enabled, r.note, r.rule] : r.lines])).toEqual([
      ["comment", ["# 药屋少女的呢喃"]],
      ["blank", [""]],
      ["rule", [true, ["第二季接着第一季编号"], "S02 >> S01 EP+24"]],
      ["rule", [true, [], "S03 >> S01 EP+48"]],
      ["rule", [false, [], "S03 @Judas >> S01 EP"]],
      ["rule", [true, [], "S03 @ADWeb @MWeb >> S01 EP"]],
      ["invalid", ["这一行写错了"]],
      ["blank", ["", ""]],
      ["comment", ["# 结尾注释"]],
    ]);
    expect((rows[6] as Extract<WordsRow, { kind: "invalid" }>).error).toContain(">>");
  });

  it("停用 / 启用、改备注、调顺序、删除,其余行原样", () => {
    const rows = wordsToRows(ENTITY, "entity");
    const r2 = rows[3] as Extract<WordsRow, { kind: "rule" }>;
    const r4 = rows[4] as Extract<WordsRow, { kind: "rule" }>;
    const next = [...rows];
    next[3] = updateRuleRow(r2, { enabled: false });
    next[4] = updateRuleRow(r4, { enabled: true, note: ["Judas 接着第一季"] });
    // 交换两行
    [next[3], next[4]] = [next[4]!, next[3]!];
    next.splice(6, 1);
    expect(rowsToText(next)).toBe(
      [
        "# 药屋少女的呢喃",
        "",
        "# 第二季接着第一季编号",
        "S02 >> S01 EP+24",
        "# Judas 接着第一季",
        "S03 @Judas >> S01 EP",
        "# S03 >> S01 EP+48",
        "S03 @ADWeb @MWeb >> S01 EP",
        "",
        "",
        "# 结尾注释",
      ].join("\n"),
    );
    expect(ruleRowLines(["备注"], false, "S01 >> EP")).toEqual(["# 备注", "# S01 >> EP"]);
  });

  it("全局:带运算符的注释是停用的识别词,其余注释是备注;MP 列表原样往返", () => {
    const text = ["#动漫", "Fake => 真", "# 旧名 => 新名", "#屏蔽词也行", "国语中字", "([ => 写错"].join("\n");
    const rows = wordsToRows(text, "global");
    expect(rows.map((r) => [r.kind, r.kind === "rule" ? r.enabled : null])).toEqual([
      ["rule", true],
      ["rule", false],
      ["rule", true],
      ["invalid", null],
    ]);
    expect((rows[0] as Extract<WordsRow, { kind: "rule" }>).note).toEqual(["动漫"]);
    expect((rows[2] as Extract<WordsRow, { kind: "rule" }>).note).toEqual(["屏蔽词也行"]);
    expect(rowsToText(rows)).toBe(text);
  });
});