Add backup-first duplicate repair

serato_doctor/web.py

@@ -5,7 +5,7 @@ from dataclasses import asdict
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from importlib import resources
 from pathlib import Path
-from typing import Iterable
+from typing import Iterable, Optional
 
 from serato_doctor.crate_parser import load_library_crates
 from serato_doctor.database_parser import parse_database
@@ -16,6 +16,12 @@ from serato_doctor.models.crate import CrateKind
 from serato_doctor.models.duplicate import DuplicateKind
 from serato_doctor.models.library import Library
 from serato_doctor.scanner import scan_filesystem
+from serato_doctor.repair import (
+    BACKUP_FOLDER,
+    apply_duplicate_repair,
+    plan_duplicate_repair,
+    restore_backup,
+)
 
 
 MAX_REQUEST_BYTES = 64 * 1024
@@ -225,6 +231,44 @@ def analyze_paths(
     return result
 
 
+def duplicate_repair(
+    serato: Path,
+    music: Path,
+    keeper: Path,
+    group_files: Iterable[Path],
+    backup_limit: Optional[int],
+    apply: bool = False,
+) -> dict:
+    """Validate a current duplicate group and preview or apply consolidation."""
+    serato = serato.expanduser().resolve()
+    music = music.expanduser().resolve()
+    keeper = keeper.expanduser().resolve()
+    requested = tuple(path.expanduser().resolve() for path in group_files)
+    if not serato.is_dir() or not music.is_dir():
+        raise ValueError("Analyze the library again before repairing duplicates")
+    tracks = scan_filesystem(music).tracks
+    groups = find_duplicate_groups(tracks)
+    valid_groups = [
+        {track.path.resolve() for track in group.tracks} for group in groups
+    ]
+    if set(requested) not in valid_groups:
+        raise ValueError("This duplicate group changed; analyze the library again")
+    plan = plan_duplicate_repair(keeper, requested, serato)
+    result = {
+        "keeper": str(plan.keeper),
+        "replaced": [str(path) for path in plan.replaced],
+        "metadata_backups": len(plan.metadata_files),
+        "strategy": "shortcut",
+        "database_v2_modified": False,
+    }
+    if apply:
+        receipt = apply_duplicate_repair(plan, serato, backup_limit)
+        result.update({"applied": True, "backup": str(receipt.backup)})
+    else:
+        result["applied"] = False
+    return result
+
+
 class SeratoDoctorHandler(BaseHTTPRequestHandler):
     def do_GET(self) -> None:
         asset = STATIC_FILES.get(self.path)
@@ -244,7 +288,13 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
         self.wfile.write(content)
 
     def do_POST(self) -> None:
-        if self.path != "/api/analyze":
+        allowed = {
+            "/api/analyze",
+            "/api/duplicates/preview",
+            "/api/duplicates/apply",
+            "/api/backups/restore",
+        }
+        if self.path not in allowed:
             self._json_response(404, {"error": "Not found"})
             return
         try:
@@ -254,11 +304,37 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
             payload = json.loads(self.rfile.read(length))
             if not isinstance(payload, dict):
                 raise ValueError("Request body must be a JSON object")
-            roots = [Path(value) for value in payload.get("reference_roots", [])]
-            result = analyze_paths(
-                Path(payload["serato"]), Path(payload["music"]), roots
-            )
-        except (KeyError, TypeError, json.JSONDecodeError, ValueError) as error:
+            if self.path == "/api/analyze":
+                roots = [Path(value) for value in payload.get("reference_roots", [])]
+                result = analyze_paths(
+                    Path(payload["serato"]), Path(payload["music"]), roots
+                )
+            elif self.path == "/api/backups/restore":
+                serato = Path(payload["serato"]).expanduser().resolve()
+                backup = Path(payload["backup"]).expanduser().resolve()
+                backup_root = (serato / BACKUP_FOLDER).resolve()
+                if backup.parent != backup_root:
+                    raise ValueError("That backup does not belong to this library")
+                restored = restore_backup(backup)
+                result = {"restored": [str(path) for path in restored]}
+            else:
+                raw_limit = payload.get("backup_limit", 10)
+                backup_limit = None if raw_limit is None else int(raw_limit)
+                result = duplicate_repair(
+                    Path(payload["serato"]),
+                    Path(payload["music"]),
+                    Path(payload["keeper"]),
+                    (Path(value) for value in payload["group_files"]),
+                    backup_limit,
+                    apply=self.path.endswith("/apply"),
+                )
+        except (
+            KeyError,
+            TypeError,
+            OSError,
+            json.JSONDecodeError,
+            ValueError,
+        ) as error:
             self._json_response(400, {"error": str(error)})
             return
         self._json_response(200, result)