Add batch duplicate review workflow

This commit is contained in:
Philip Guzman
2026-07-01 16:18:30 -07:00
parent 4315d8d4d4
commit f3cfed316d
8 changed files with 391 additions and 36 deletions
+40 -10
View File
@@ -83,8 +83,28 @@ def apply_duplicate_repair(
backup_limit: Optional[int] = 10,
) -> RepairReceipt:
"""Create a complete rollback snapshot, then replace extras with symlinks."""
return apply_duplicate_repair_batch((plan,), serato_root, backup_limit)
def apply_duplicate_repair_batch(
plans: Iterable[DuplicateRepairPlan],
serato_root: Path,
backup_limit: Optional[int] = 10,
) -> RepairReceipt:
"""Apply several approved duplicate choices as one atomic backup."""
plans = tuple(plans)
if not plans:
raise ValueError("Choose at least one duplicate group")
if backup_limit is not None and backup_limit < 1:
raise ValueError("Backup limit must be at least 1, or unlimited")
replaced_paths = tuple(
path for plan in plans for path in plan.replaced
)
if len(set(replaced_paths)) != len(replaced_paths):
raise ValueError("The same file appears in more than one repair choice")
keepers = {plan.keeper for plan in plans}
if keepers.intersection(replaced_paths):
raise ValueError("A selected keeper cannot be removed by another choice")
backup_root = serato_root.expanduser().resolve() / BACKUP_FOLDER
backup = backup_root / _backup_name()
files_root = backup / "files"
@@ -93,35 +113,45 @@ def apply_duplicate_repair(
entries = []
try:
for path in plan.replaced:
destination = files_root / _safe_backup_path(path)
destination.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(path, destination)
entries.append({"original": str(path), "backup": str(destination)})
for path in plan.metadata_files:
for plan in plans:
for path in plan.replaced:
destination = files_root / _safe_backup_path(path)
destination.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(path, destination)
entries.append(
{
"original": str(path),
"backup": str(destination),
"keeper": str(plan.keeper),
}
)
for path in plans[0].metadata_files:
relative = path.relative_to(serato_root.expanduser().resolve())
destination = metadata_root / relative
destination.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(path, destination)
manifest = {
"created_at": datetime.now(timezone.utc).isoformat(),
"keeper": str(plan.keeper),
"keeper": str(plans[0].keeper),
"keepers": [str(plan.keeper) for plan in plans],
"choice_count": len(plans),
"replaced": entries,
"strategy": "symlink",
}
(backup / "manifest.json").write_text(
json.dumps(manifest, indent=2), encoding="utf-8"
)
for path in plan.replaced:
for entry in entries:
path = Path(entry["original"])
path.unlink()
path.symlink_to(plan.keeper)
path.symlink_to(Path(entry["keeper"]))
except Exception:
_rollback_entries(entries)
shutil.rmtree(backup, ignore_errors=True)
raise
rotate_backups(backup_root, backup_limit)
return RepairReceipt(backup, plan.keeper, plan.replaced)
return RepairReceipt(backup, plans[0].keeper, replaced_paths)
def restore_backup(backup: Path) -> Tuple[Path, ...]: