feat(identify-words): 识别词——全局识别词(MP 语法)+ 作品识别词(季集换算),规则页「识别词」页签

- 新表 identify_words(0094):全局一块 + 每部作品一块原文,带版本与审计;episode_mapping_rule 转成文本行后删表 - 全局识别词移植 MP WordsMatcher(屏蔽 / 替换 / 集数偏移 / 替换+偏移 / {[tmdbid=…]}),所有按标题 / 文件名识别的地方解析前套用,命中的行记在解析结果上;保存后后台按改动行重新识别 - 作品识别词:S02 >> S01 EP+24 / S01E13 >> S00E01 / S01 @组 >> 忽略,解析器 + 打印器 + 编译;发布组繁简视为同一个 - 去掉规则自动停用:算出来对不上季表只待确认,要停用就注释掉那一行 - 集数待确认的采用 / 忽略与智能体 apply_rule 改为往作品识别词追加一行(带来历注释) - 编辑器可视化 / 文本两种模式改同一份原文,保存前试算;作品页「集数映射」用同一个编辑器 Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-08 17:03:00 +08:00
1 parent 12f8fc59c3
commit 63e94b308e
@@ -0,0 +1,167 @@
+import { type Kysely, sql } from "kysely";
+import { entityTable, execDdl, oneOf } from "../src/migration-helpers.ts";
+
+// 识别词(docs/design/identify-words.md):
+// - identify_words:全局一块(media_entity_id 为空,只能有一行)+ 每部作品一块;原文整块存,version 每次保存 +1;
+//   reresolve 是全局识别词保存后后台重算的进度
+// - 0066 的 episode_mapping_rule 结构化规则逐作品转成作品识别词的文本行后删表:同一作品、同一季、同一换算的
+//   多个发布组合成一行,单集对照一行一条,停用的规则变成注释行。已有文本时只追加还没有的行(可重复执行)
+
+// biome-ignore lint/suspicious/noExplicitAny: 迁移不依赖应用表类型
+type Db = Kysely<any>;
+
+interface RuleRow {
+  media_entity_id: string;
+  season: number | null;
+  release_group: string | null;
+  kind: "expression" | "table" | "special";
+  expression: string | null;
+  target_season: number | null;
+  table_entries: { from: { start: number; end: number }; to: { season: number; episode: number } }[] | null;
+  special: "special" | "extra" | "ignore" | null;
+  status: "active" | "disabled";
+  created_by_type: string;
+  evidence: { reasons?: unknown } | null;
+}
+
+const pad = (n: number) => String(n).padStart(2, "0");
+const SPECIAL = { special: "特别篇", extra: "花絮", ignore: "忽略" } as const;
+const group = (g: string) => (/[\s"]|>>/.test(g) ? `@"${g.replace(/"/g, "")}"` : `@${g}`);
+
+/** 一组同季、同内容的规则 → 文本行(作品识别词语法,与 contracts printEntityWord 一致) */
+function linesOf(rules: RuleRow[]): string[] {
+  const r = rules[0]!;
+  const groups = [...new Set(rules.map((x) => x.release_group?.trim()).filter((g): g is string => !!g))];
+  const g = groups.length ? ` ${groups.map(group).join(" ")}` : "";
+  const scope = `${r.season === null ? "*" : `S${pad(r.season)}`}${g}`;
+  if (r.kind === "table") {
+    return (r.table_entries ?? []).map((e) => {
+      const range = e.from.start === e.from.end ? `E${pad(e.from.start)}` : `E${pad(e.from.start)}-E${pad(e.from.end)}`;
+      return `${r.season === null ? "" : `S${pad(r.season)}`}${range}${g} >> S${pad(e.to.season)}E${pad(e.to.episode)}`;
+    });
+  }
+  if (r.kind === "special") return [`${scope} >> ${SPECIAL[r.special ?? "ignore"]}`];
+  const expr = (r.expression ?? "EP").replace(/\s+/g, "").replace(/(?<![A-Za-z0-9_])ep(?![A-Za-z0-9_])/gi, "EP");
+  return [`${scope} >> ${r.target_season === null ? "" : `S${pad(r.target_season)} `}${expr || "EP"}`];
+}
+
+export function entityWordsText(rows: RuleRow[]): string[] {
+  const buckets = new Map<string, RuleRow[]>();
+  for (const r of rows) {
+    // 有发布组的同内容规则合成一行;没有发布组的单独一行;表格规则各自成行(条目不同)
+    const content =
+      r.kind === "table"
+        ? `table:${r.release_group ?? ""}`
+        : `${r.kind}:${r.expression ?? ""}:${r.target_season ?? ""}:${r.special ?? ""}:${r.release_group ? "g" : "-"}`;
+    const key = `${r.status}|${r.created_by_type === "agent" ? "agent" : "-"}|${r.season ?? "*"}|${content}`;
+    buckets.set(key, [...(buckets.get(key) ?? []), r]);
+  }
+  const ordered = [...buckets.values()].sort((a, b) => {
+    const x = a[0]!;
+    const y = b[0]!;
+    const s = (x.season ?? 9999) - (y.season ?? 9999);
+    if (s) return s;
+    if (!!x.release_group !== !!y.release_group) return x.release_group ? 1 : -1;
+    return x.status === y.status ? 0 : x.status === "active" ? -1 : 1;
+  });
+  const out: string[] = [];
+  for (const b of ordered) {
+    const first = b[0]!;
+    const reasons = b.flatMap((r) =>
+      Array.isArray(r.evidence?.reasons) ? r.evidence.reasons.filter((x): x is string => typeof x === "string") : [],
+    );
+    if (first.created_by_type === "agent") out.push(`# 智能体${reasons.length ? `：${reasons.join("；")}` : ""}`);
+    for (const l of linesOf(b)) out.push(first.status === "active" ? l : `# ${l}`);
+  }
+  return out;
+}
+
+/** 当前 schema 里有没有这张表(测试按 schema 隔离,search_path 后面的 public 不算) */
+const regclass = async (db: Db, name: string) =>
+  (
+    await sql<{
+      t: string | null;
+    }>`select to_regclass(quote_ident(current_schema()) || '.' || ${name})::text as t`.execute(db)
+  ).rows[0]?.t ?? null;
+
+export async function up(db: Db): Promise<void> {
+  if (!(await regclass(db, "identify_words")))
+    await execDdl(
+      db,
+      `${entityTable(
+        "identify_words",
+        `media_entity_id uuid references media_entity (id) on delete cascade,
+       text text not null default '',
+       version integer not null default 0,
+       updated_by_type text ${oneOf("updated_by_type", ["user", "agent", "system", "api_key"])},
+       updated_by_id text,
+       reresolve jsonb`,
+      )}
+    create unique index if not exists identify_words_entity on identify_words (media_entity_id) where media_entity_id is not null;
+    create unique index if not exists identify_words_global on identify_words ((media_entity_id is null)) where media_entity_id is null;`,
+    );
+
+  const rows: RuleRow[] = (await regclass(db, "episode_mapping_rule"))
+    ? ((await db
+        .selectFrom("episode_mapping_rule")
+        .selectAll()
+        .orderBy("media_entity_id")
+        .orderBy("created_at")
+        .execute()) as RuleRow[])
+    : [];
+  const byEntity = new Map<string, RuleRow[]>();
+  for (const r of rows) byEntity.set(r.media_entity_id, [...(byEntity.get(r.media_entity_id) ?? []), r]);
+  for (const [entityId, list] of byEntity) {
+    const lines = entityWordsText(list);
+    const cur = await db
+      .selectFrom("identify_words")
+      .select(["id", "text"])
+      .where("media_entity_id", "=", entityId)
+      .executeTakeFirst();
+    if (!cur) {
+      await db
+        .insertInto("identify_words")
+        .values({ media_entity_id: entityId, text: `${lines.join("\n")}\n`, version: 1, updated_by_type: "system" })
+        .execute();
+      continue;
+    }
+    const have = new Set((cur.text as string).split("\n").map((l) => l.trim()));
+    const missing = lines.filter((l) => !have.has(l.trim()));
+    if (!missing.length) continue;
+    const base = (cur.text as string).replace(/\n*$/, "");
+    await db
+      .updateTable("identify_words")
+      .set({ text: `${base ? `${base}\n` : ""}${missing.join("\n")}\n` })
+      .where("id", "=", cur.id)
+      .execute();
+  }
+  await execDdl(db, `drop table if exists episode_mapping_rule;`);
+}
+
+export async function down(db: Db): Promise<void> {
+  // 文本里的规则不回写成结构化规则:恢复空表结构,识别词原文随表删除
+  await execDdl(
+    db,
+    `${entityTable(
+      "episode_mapping_rule",
+      `media_entity_id uuid not null references media_entity (id) on delete cascade,
+       season integer,
+       release_group text,
+       kind text not null ${oneOf("kind", ["expression", "table", "special"])},
+       expression text,
+       target_season integer,
+       table_entries jsonb,
+       special text ${oneOf("special", ["special", "extra", "ignore"])},
+       status text not null default 'active' ${oneOf("status", ["active", "disabled"])},
+       evidence_level text not null default 'manual' ${oneOf("evidence_level", ["manual", "rule_confirmed", "multi_evidence", "needs_review"])},
+       evidence jsonb not null default '{}'::jsonb,
+       disabled_reason text,
+       created_by_type text not null ${oneOf("created_by_type", ["user", "agent", "system", "api_key"])},
+       created_by_id text`,
+    )}
+    create unique index episode_mapping_rule_active_scope on episode_mapping_rule
+      (media_entity_id, coalesce(season, -1), coalesce(lower(release_group), '')) where status = 'active';
+    create index episode_mapping_rule_entity on episode_mapping_rule (media_entity_id);
+    drop table if exists identify_words;`,
+  );
+}