US06-04: Plan and Execute Safe Restores (#80)

photo_pipeline/services/archive_journal.py

@@ -15,6 +15,11 @@ planned → transferring → verified → removing → complete
               ↘             ↘          ↘ failed
 ```
 
+A restore (US06-04) uses the same rows with ``direction='restore'``: it copies from
+the medium back into the library and removes nothing, so it goes ``verified →
+complete`` directly. ``source_path``/``destination_path`` always mean "from"/"to",
+which is why the evidence table below needs no direction of its own.
+
 - ``transferring`` — intent recorded; a temporary copy may exist, the destination
   may or may not have been published. Nothing has been removed.
 - ``verified``     — the archived bytes exist at their final path, hash exactly as
@@ -73,10 +78,22 @@ ALLOWED_TRANSITIONS = {
     ArchiveState.FAILED: {ArchiveState.PLANNED, ArchiveState.TRANSFERRING},
 }
 
+# A restore removes nothing, so it has no ``removing`` step: a verified published
+# copy is the whole job (US06-04). Keeping this as a separate table means the
+# archive direction still cannot reach ``complete`` without going through removal.
+RESTORE_TRANSITIONS = {
+    **ALLOWED_TRANSITIONS,
+    ArchiveState.VERIFIED: {ArchiveState.COMPLETE, ArchiveState.FAILED},
+}
+
 TERMINAL_STATES = frozenset({ArchiveState.COMPLETE})
 # States where this item may already have touched the filesystem.
 UNSAFE_STATES = frozenset({ArchiveState.TRANSFERRING, ArchiveState.VERIFIED, ArchiveState.REMOVING})
 
+# Which way the bytes move. Same rows, same evidence table, opposite direction.
+ARCHIVE = "archive"
+RESTORE = "restore"
+
 RESUMABLE = "resumable"
 FORWARD = "forward"
 MANUAL = "manual"
@@ -94,8 +111,9 @@ class JournalConflict(JournalError):
     """Fencing check failed; a newer owner has taken over this operation."""
 
 
-def can_transition(current: str, target: str) -> bool:
-    return target in ALLOWED_TRANSITIONS.get(current, set())
+def can_transition(current: str, target: str, direction: str = ARCHIVE) -> bool:
+    table = RESTORE_TRANSITIONS if direction == RESTORE else ALLOWED_TRANSITIONS
+    return target in table.get(current, set())
 
 
 def _now() -> datetime:
@@ -119,7 +137,7 @@ class ArchiveJournal:
             if row.journal_state in TERMINAL_STATES:
                 raise InvalidTransition(f"{row.journal_state} is terminal")
             if row.journal_state != ArchiveState.TRANSFERRING and not can_transition(
-                row.journal_state, ArchiveState.TRANSFERRING
+                row.journal_state, ArchiveState.TRANSFERRING, row.direction
             ):
                 raise InvalidTransition(f"{row.journal_state} -> {ArchiveState.TRANSFERRING}")
             if row.journal_state != ArchiveState.TRANSFERRING:
@@ -160,7 +178,7 @@ class ArchiveJournal:
             if row.journal_state == target:
                 session.commit()
                 return _operation_dict(row)  # idempotent
-            if not can_transition(row.journal_state, target):
+            if not can_transition(row.journal_state, target, row.direction):
                 raise InvalidTransition(f"{row.journal_state} -> {target}")
 
             row.journal_state = target
@@ -192,16 +210,18 @@ class ArchiveJournal:
             )
             return [_operation_dict(row) for row in rows]
 
-    def incomplete(self) -> list[dict]:
+    def incomplete(self, *, direction: str | None = None) -> list[dict]:
         """Every operation left in a non-terminal, non-planned state — the work a
-        restart has to reason about."""
+        restart has to reason about. Without ``direction`` this spans archives and
+        restores, because either one half-done blocks the other."""
         with self._session_factory() as session:
+            stmt = select(ArchiveOperation).where(
+                ArchiveOperation.journal_state.not_in([*TERMINAL_STATES, ArchiveState.PLANNED])
+            )
+            if direction is not None:
+                stmt = stmt.where(ArchiveOperation.direction == direction)
             rows = session.scalars(
-                select(ArchiveOperation)
-                .where(
-                    ArchiveOperation.journal_state.not_in([*TERMINAL_STATES, ArchiveState.PLANNED])
-                )
-                .order_by(ArchiveOperation.plan_id, ArchiveOperation.sequence)
+                stmt.order_by(ArchiveOperation.plan_id, ArchiveOperation.sequence)
             )
             return [_operation_dict(row) for row in rows]
 
@@ -231,6 +251,7 @@ class ArchiveJournal:
         return {
             "operation_id": operation_id,
             "plan_id": row["plan_id"],
+            "direction": row["direction"],
             "album": row["album"],
             "asset_id": row["asset_id"],
             "source_path": row["source_path"],
@@ -243,8 +264,8 @@ class ArchiveJournal:
             "destination_matches": destination_matches,
         }
 
-    def classify_all(self) -> list[dict]:
-        return [self.classify(row["id"]) for row in self.incomplete()]
+    def classify_all(self, *, direction: str | None = None) -> list[dict]:
+        return [self.classify(row["id"]) for row in self.incomplete(direction=direction)]
 
     def blocks_mutation(self) -> bool:
         """True when any item may have the library half-archived."""
@@ -317,6 +338,7 @@ def _operation_dict(row: ArchiveOperation) -> dict:
     return {
         "id": row.id,
         "plan_id": row.plan_id,
+        "direction": row.direction,
         "sequence": row.sequence,
         "album": row.album,
         "asset_id": row.asset_id,