fix: make indexing review paths replay-safe

tests/api/test_collections.py

@@ -1,5 +1,6 @@
 from typing import cast
 
+import pytest
 from fastapi import FastAPI
 from fastapi.testclient import TestClient
 
@@ -45,4 +46,24 @@ def test_empty_create_and_rename_do_not_enqueue_jobs(
     client.patch(f"/collections/{collection_id}", json={"name": "Reading"}, headers=headers)
     with cast(FastAPI, client.app).state.database.connect() as connection:
         total = connection.execute("SELECT COUNT(*) FROM jobs").fetchone()[0]
-    assert total == 0
+        assert total == 0
+
+
+def test_delete_rolls_back_when_cleanup_job_cannot_be_written(
+    authenticated: tuple[TestClient, str], monkeypatch: pytest.MonkeyPatch
+) -> None:
+    client, csrf = authenticated
+    collection_id = client.post(
+        "/collections", json={"name": "Books"}, headers={"X-CSRF-Token": csrf}
+    ).json()["id"]
+
+    def fail_id(_size: int) -> str:
+        raise RuntimeError("simulated job ID failure")
+
+    monkeypatch.setattr("recoll_modern.storage.jobs.secrets.token_hex", fail_id)
+    with pytest.raises(RuntimeError, match="simulated job ID failure"):
+        client.delete(
+            f"/collections/{collection_id}", params={"confirmation": "Books"},
+            headers={"X-CSRF-Token": csrf},
+        )
+    assert client.get(f"/collections/{collection_id}").status_code == 200

tests/api/test_documents.py

@@ -34,6 +34,8 @@ def test_text_and_byte_range(authenticated: tuple[TestClient, str], tmp_path: Pa
     assert client.get(
         f"/documents/{digest}/file", headers={"Range": "bytes=99-100"}
     ).status_code == 416
+    suffix = client.get(f"/documents/{digest}/file", headers={"Range": "bytes=-2"})
+    assert suffix.status_code == 206 and suffix.content == b"ef"
 
 
 def test_unknown_and_missing_documents(

tests/api/test_jobs.py

@@ -1,5 +1,8 @@
 import time
+from pathlib import Path
+from typing import cast
 
+from fastapi import FastAPI
 from fastapi.testclient import TestClient
 
 
@@ -22,6 +25,7 @@ def test_retry_refuses_completed_job(authenticated: tuple[TestClient, str]) -> N
         if client.get(f"/jobs/{job_id}").json()["job"]["state"] == "completed":
             break
         time.sleep(0.01)
+        time.sleep(0.01)
     response = client.post(f"/jobs/{job_id}/retry", headers={"X-CSRF-Token": csrf})
     assert response.status_code == 409
     assert response.json()["error"]["code"] == "job_not_retryable"
@@ -32,3 +36,37 @@ def test_job_list_validates_pagination(authenticated: tuple[TestClient, str]) ->
     response = client.get("/jobs", params={"limit": 201})
     assert response.status_code == 422
     assert response.json()["error"]["code"] == "validation_failed"
+
+
+def test_collection_reindex_includes_departed_rule_path(
+    authenticated: tuple[TestClient, str], tmp_path: Path
+) -> None:
+    client, csrf = authenticated
+    books = tmp_path / "docs" / "books"
+    books.mkdir()
+    file = books / "gone.txt"
+    file.write_text("gone")
+    headers = {"X-CSRF-Token": csrf}
+    collection_id = client.post(
+        "/collections", headers=headers, json={"name": "Books"}
+    ).json()["id"]
+    created = client.post(
+        f"/collections/{collection_id}/memberships", headers=headers,
+        json={"sources": [{"type": "directory", "path": "books", "mode": "persistent"}]},
+    )
+    job_id = created.json()["job"]["id"]
+    for _ in range(100):
+        if client.get(f"/jobs/{job_id}").json()["job"]["state"] == "completed":
+            break
+    engine = cast(FastAPI, client.app).state.engine
+    engine.forced_paths.clear()
+    file.unlink()
+    refreshed = client.post(
+        "/jobs/reindex", headers=headers, json={"collections": [collection_id]}
+    )
+    refresh_id = refreshed.json()["job"]["id"]
+    for _ in range(100):
+        if client.get(f"/jobs/{refresh_id}").json()["job"]["state"] == "completed":
+            break
+        time.sleep(0.01)
+    assert any(str(file) in batch for batch in engine.forced_paths)

tests/api/test_memberships.py

@@ -2,6 +2,8 @@ import time
 from pathlib import Path
 from typing import cast
 
+import pytest
+from fastapi import FastAPI
 from fastapi.testclient import TestClient
 
 
@@ -177,3 +179,90 @@ def test_remove_document_creates_override_then_direct_add_restores_it(
     assert len(members) == 1
     assert members[0]["direct"] is True
     assert members[0]["override"] is False
+
+
+def test_rule_deletion_retry_reindexes_removed_membership(
+    authenticated: tuple[TestClient, str], tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    client, csrf = authenticated
+    books = tmp_path / "docs" / "books"
+    books.mkdir()
+    file = books / "a.txt"
+    file.write_text("book")
+    collection_id = _collection(client, csrf)
+    created = client.post(
+        f"/collections/{collection_id}/memberships",
+        headers={"X-CSRF-Token": csrf},
+        json={"sources": [{"type": "directory", "path": "books", "mode": "persistent"}]},
+    )
+    assert _wait(client, created.json()["job"]["id"])["state"] == "completed"
+    rule_id = client.get(f"/collections/{collection_id}/directory-rules").json()["items"][0]["id"]
+    engine = cast(FastAPI, client.app).state.engine
+    original = engine.force_reindex
+    calls: list[tuple[str, ...]] = []
+
+    def fail_once(paths: tuple[str, ...]) -> None:
+        calls.append(paths)
+        if len(calls) == 1:
+            raise RuntimeError("simulated indexing failure")
+        original(paths)
+
+    monkeypatch.setattr(engine, "force_reindex", fail_once)
+    deleted = client.delete(
+        f"/collections/{collection_id}/directory-rules/{rule_id}",
+        headers={"X-CSRF-Token": csrf},
+    )
+    job_id = deleted.json()["job"]["id"]
+    assert _wait(client, job_id)["state"] == "failed"
+    retried = client.post(f"/jobs/{job_id}/retry", headers={"X-CSRF-Token": csrf})
+    assert retried.status_code == 202
+    assert _wait(client, job_id)["state"] == "completed"
+    assert calls == [(str(file),), (str(file),)]
+
+
+def test_rule_patch_retry_reindexes_excluded_member(
+    authenticated: tuple[TestClient, str], tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    client, csrf = authenticated
+    skipped = tmp_path / "docs" / "books" / "skip"
+    skipped.mkdir(parents=True)
+    file = skipped / "a.txt"
+    file.write_text("book")
+    collection_id = _collection(client, csrf)
+    created = client.post(
+        f"/collections/{collection_id}/memberships",
+        headers={"X-CSRF-Token": csrf},
+        json={"sources": [{"type": "directory", "path": "books", "mode": "persistent"}]},
+    )
+    assert _wait(client, created.json()["job"]["id"])["state"] == "completed"
+    rule_id = client.get(f"/collections/{collection_id}/directory-rules").json()["items"][0]["id"]
+    engine = cast(FastAPI, client.app).state.engine
+    original = engine.force_reindex
+    calls: list[tuple[str, ...]] = []
+
+    def fail_once(paths: tuple[str, ...]) -> None:
+        calls.append(paths)
+        if len(calls) == 1:
+            raise RuntimeError("simulated indexing failure")
+        original(paths)
+
+    monkeypatch.setattr(engine, "force_reindex", fail_once)
+    patched = client.patch(
+        f"/collections/{collection_id}/directory-rules/{rule_id}",
+        headers={"X-CSRF-Token": csrf}, json={"excluded_directories": ["books/skip"]},
+    )
+    job_id = patched.json()["job"]["id"]
+    assert _wait(client, job_id)["state"] == "failed"
+    client.post(f"/jobs/{job_id}/retry", headers={"X-CSRF-Token": csrf})
+    assert _wait(client, job_id)["state"] == "completed"
+    assert calls == [(str(file),), (str(file),)]
+
+
+def test_rule_list_validates_pagination(authenticated: tuple[TestClient, str]) -> None:
+    client, csrf = authenticated
+    collection_id = _collection(client, csrf)
+    response = client.get(
+        f"/collections/{collection_id}/directory-rules", params={"limit": 201}
+    )
+    assert response.status_code == 422
+    assert response.json()["error"]["code"] == "validation_failed"