feat(curator): vendor the application backend as the scenario's tracked source

The curator Python backend (package, tests, systemd units, config templates, scripts) now lives under scenarios/curator/backend and is the single source of truth; the live checkout at the workspace path is a runtime copy. Exported from the app repo's tracked tree via git archive (no history, .pi/venv/caches excluded). 149 unit tests pass from the new location. profile.toml backend is now repo-relative (scenarios/curator/backend); verify-generated.sh resolves a relative backend against REPO_ROOT. verify-no-secrets ASSIGN heuristic now requires value entropy so vendored kwargs like token=extraction_token no longer false-positive. README documents the backend/ layout and the operator-owned app rollout step.
2026-08-30 18:49:10 -07:00
parent 14c97d88cf
commit 88b06d782f
57 changed files with 14236 additions and 9 deletions
@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sqlite3
+from datetime import UTC, datetime
+from pathlib import Path
+
+from curator.db import Database, normalize
+from curator.epub import inspect_epub
+from curator.library import safe_component, safe_filename
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Repair a Curator EPUB from its embedded metadata")
+    parser.add_argument("database", type=Path)
+    parser.add_argument("asset_id", type=int)
+    parser.add_argument("--apply", action="store_true")
+    args = parser.parse_args()
+
+    connection = sqlite3.connect(args.database)
+    connection.row_factory = sqlite3.Row
+    row = connection.execute(
+        """SELECT a.*, e.id AS edition_id, e.work_id, e.variant
+           FROM assets a JOIN editions e ON e.id=a.edition_id WHERE a.id=?""",
+        (args.asset_id,),
+    ).fetchone()
+    if not row or row["format"] != "epub":
+        raise SystemExit("asset must be an existing EPUB")
+    old_path = Path(row["path"])
+    info = inspect_epub(old_path)
+    filename = safe_filename(row["filename"], "book.epub")
+    root = old_path.parents[3]
+    destination = (
+        root / safe_component(info.author, "Unknown Author") / safe_component(info.title, "Untitled")
+        / safe_component(f"{info.language}-{row['variant']}", "und-original") / filename
+    )
+    metadata = json.loads(row["metadata_json"] or "{}")
+    metadata.update({
+        "display_title": info.display_title,
+        "title_aliases": list(info.title_aliases),
+        "declared_language": info.declared_language,
+        "identifiers": list(info.identifiers),
+        "source_identifiers": list(info.source_identifiers),
+    })
+    plan = {"work_id": row["work_id"], "asset_id": row["id"], "title": info.title, "author": info.author,
+            "language": info.language, "isbn": info.isbn, "old": str(old_path), "new": str(destination)}
+    print(json.dumps(plan, ensure_ascii=False, indent=2))
+    if not args.apply:
+        return
+
+    backup = args.database.with_name(f"{args.database.stem}-before-repair-{datetime.now(UTC).strftime('%Y%m%dT%H%M%SZ')}.sqlite3")
+    with sqlite3.connect(backup) as backup_connection:
+        connection.backup(backup_connection)
+    moved = False
+    try:
+        connection.execute("PRAGMA foreign_keys=ON")
+        connection.execute("BEGIN IMMEDIATE")
+        destination.parent.mkdir(parents=True, exist_ok=True)
+        if destination.exists() and destination != old_path:
+            raise FileExistsError(destination)
+        if destination != old_path:
+            os.replace(old_path, destination)
+            moved = True
+        stamp = datetime.now(UTC).replace(microsecond=0).isoformat()
+        connection.execute(
+            """UPDATE works SET title=?, author=?, normalized_title=?, normalized_author=?, updated_at=? WHERE id=?""",
+            (info.title, info.author, normalize(info.title), normalize(info.author), stamp, row["work_id"]),
+        )
+        connection.execute(
+            "UPDATE editions SET language=?, isbn=?, publisher=? WHERE id=?",
+            (info.language, info.isbn, info.publisher, row["edition_id"]),
+        )
+        connection.execute(
+            "UPDATE assets SET filename=?, path=?, metadata_json=? WHERE id=?",
+            (filename, str(destination), json.dumps(metadata, ensure_ascii=False, sort_keys=True), row["id"]),
+        )
+        connection.execute(
+            "UPDATE activity_jobs SET detail=?, updated_at=? WHERE kind='book-import' AND detail LIKE '%�%'",
+            (f"{info.title} · {info.author or '未知作者'} · 已校验并入库", stamp),
+        )
+        connection.commit()
+    except Exception:
+        connection.rollback()
+        if moved:
+            old_path.parent.mkdir(parents=True, exist_ok=True)
+            os.replace(destination, old_path)
+        raise
+    finally:
+        connection.close()
+    Database(args.database).reconcile_imported_book(info.title, info.author)
+    print(f"backup={backup}")
+
+
+if __name__ == "__main__":
+    main()