| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250 |
- """The Report & Release pipeline — the highest-risk behaviour.
- Asserts on exact PPS call kwargs, not just counts: the move-first order, the re-read of
- localguids before every later step (never the cached ones), and the localguid-stability
- rule (release must NOT pass deletedfolder) are all invisible to a call-count check but
- critical to correctness. The last group covers the other half of the design — waiting
- between steps must not block the job queue.
- """
- import pytest
- from conftest import FakePPS
- from pipeline import (
- ALLOWED_STEPS,
- describe_pipeline,
- pipeline_destination,
- run_step,
- )
- from pps_client import PPSError
- def _cfg(steps, move_target="Rep", deleted="Deleted", step_delay=0):
- return {
- "deleted_folder": deleted,
- "list_query": "from=*",
- "default_days_back": 7,
- "chunk_size": 25,
- "report_release": {
- "steps": steps,
- "move_target": move_target,
- "step_delay_seconds": step_delay,
- },
- }
- def _chunk():
- return [
- {"localguid": "6:6:1", "guid": "g1"},
- {"localguid": "6:6:2", "guid": "g2"},
- ]
- def _moved_records():
- """What a search of the move target returns once the messages have landed there."""
- return [{"guid": "g1", "localguid": "R:1"}, {"guid": "g2", "localguid": "R:2"}]
- # ---------------------------------------------------------------- single steps
- def test_first_step_uses_the_job_localguids_without_searching():
- pps = FakePPS()
- folder = run_step(pps, _cfg(["move", "release"]), "move", "Quarantine", _chunk(),
- refresh=False)
- assert folder == "Rep"
- assert pps.searches() == []
- move = pps.acts()[0]
- assert move["action"] == "move" and move["folder"] == "Quarantine"
- assert move["localguids"] == ["6:6:1", "6:6:2"]
- assert move["targetfolder"] == "Rep"
- def test_later_step_rereads_and_never_uses_cached_localguids():
- pps = FakePPS(records=_moved_records())
- folder = run_step(pps, _cfg(["move", "release"]), "release", "Rep", _chunk(),
- refresh=True)
- assert folder == "Rep"
- assert [s["folder"] for s in pps.searches()] == ["Rep"] # re-read in the NEW folder
- release = pps.acts()[0]
- assert release["action"] == "release"
- assert release["folder"] == "Rep"
- assert release["localguids"] == ["R:1", "R:2"] # fresh, not "6:6:*"
- assert release["deletedfolder"] is None # THE stability rule
- def test_release_carries_no_deletedfolder_even_as_first_step():
- pps = FakePPS()
- run_step(pps, _cfg(["release"]), "release", "Quarantine", _chunk(), refresh=False)
- assert pps.acts()[0]["deletedfolder"] is None
- def test_reread_falls_back_to_the_deleted_folder():
- """Some deployments relocate messages to the deleted folder behind our back."""
- class OnlyDeleted(FakePPS):
- def search(self, folder, query, limit=200, days_back=7, enddate=None):
- self.calls.append({"m": "search", "folder": folder, "enddate": enddate})
- return _moved_records() if folder == "Deleted" else []
- pps = OnlyDeleted()
- run_step(pps, _cfg(["move", "release"]), "release", "Rep", _chunk(), refresh=True)
- assert [s["folder"] for s in pps.searches()] == ["Rep", "Deleted"]
- assert pps.acts()[0]["folder"] == "Deleted"
- assert pps.acts()[0]["localguids"] == ["R:1", "R:2"]
- def test_move_retries_once_after_rereading_when_the_stored_handles_are_stale():
- class StaleHandles(FakePPS):
- def act(self, action, folder, localguids, **kw):
- result = super().act(action, folder, localguids, **kw) # record the attempt
- if action == "move" and "6:6:1" in localguids:
- raise PPSError("no such localguid")
- return result
- pps = StaleHandles(records=_moved_records())
- run_step(pps, _cfg(["move"]), "move", "Quarantine", _chunk(), refresh=False)
- assert [s["folder"] for s in pps.searches()] == ["Quarantine"]
- assert [a["localguids"] for a in pps.acts()] == [["6:6:1", "6:6:2"], ["R:1", "R:2"]]
- assert pps.acts()[-1]["targetfolder"] == "Rep"
- def test_reread_without_guids_raises():
- pps = FakePPS()
- with pytest.raises(PPSError):
- run_step(pps, _cfg(["move", "release"]), "release", "Rep",
- [{"localguid": "6:6:1"}], refresh=True) # no guid stored
- # ---------------------------------------------------------------- descriptions
- def test_pipeline_destination():
- assert pipeline_destination(_cfg(["release"])) is None
- assert pipeline_destination(_cfg(["move"])) == "Rep"
- assert pipeline_destination(_cfg(["move", "release"])) == "Rep"
- def test_describe_pipeline_reads_in_execution_order():
- text = describe_pipeline(_cfg(["move", "release"]))
- assert text.index("Rep") < text.index("released")
- def test_allowed_steps_is_canonical_order_and_never_deletes():
- assert ALLOWED_STEPS == ("move", "release")
- # ---------------------------------------------------------------- worker driving
- def _enqueue(queue):
- return queue.enqueue("report_release", "Quarantine", _chunk(), {}, user="dev@x")
- def _run_next(queue):
- """Claim and process one job; returns the claimed job row (None if none is due)."""
- job = queue._claim_next()
- if job is not None:
- queue._process(job)
- return job
- def _job(queue, job_id):
- return next(j for j in queue.recent_jobs(limit=50) if j["id"] == job_id)
- def test_zero_delay_runs_every_step_in_one_pass(make_queue):
- pps = FakePPS(records=_moved_records())
- q = make_queue(pps, _cfg(["move", "release"], step_delay=0))
- job_id = _enqueue(q)
- _run_next(q)
- assert [a["action"] for a in pps.acts()] == ["move", "release"]
- assert _job(q, job_id)["status"] == "done"
- # Even with no wait, the release step re-reads rather than reusing the move's handles.
- assert pps.acts()[1]["localguids"] == ["R:1", "R:2"]
- def test_delay_parks_the_job_instead_of_blocking_the_queue(make_queue):
- pps = FakePPS(records=_moved_records())
- q = make_queue(pps, _cfg(["move", "release"], step_delay=60))
- rr_id = _enqueue(q)
- other_id = q.enqueue("delete", "Quarantine", [{"localguid": "x"}], {}, user="dev@x")
- # First pass: the move, then the job parks itself.
- assert _run_next(q)["id"] == rr_id
- assert [a["action"] for a in pps.acts()] == ["move"]
- parked = _job(q, rr_id)
- assert parked["status"] == "pending" and parked["run_after"]
- # The job queued behind it is NOT blocked by the wait — it runs now.
- assert _run_next(q)["id"] == other_id
- assert [a["action"] for a in pps.acts()] == ["move", "delete"]
- assert _job(q, other_id)["status"] == "done"
- # Nothing else is due while the wait is on.
- assert q._claim_next() is None
- # Once the delay has passed the job is re-claimed and finishes on fresh handles.
- q._conn.execute("UPDATE jobs SET run_after='2000-01-01 00:00:00' WHERE id=?", (rr_id,))
- q._conn.commit()
- assert _run_next(q)["id"] == rr_id
- release = [a for a in pps.acts() if a["action"] == "release"][0]
- assert [s["folder"] for s in pps.searches()] == ["Rep"]
- assert release["folder"] == "Rep" and release["localguids"] == ["R:1", "R:2"]
- assert release["deletedfolder"] is None
- assert _job(q, rr_id)["status"] == "done"
- def test_resume_keeps_the_steps_it_started_with(make_queue):
- """An admin edit during the wait must not change a job already in flight."""
- cfg = _cfg(["move", "release"], step_delay=60)
- pps = FakePPS(records=_moved_records())
- q = make_queue(pps, cfg)
- rr_id = _enqueue(q)
- _run_next(q)
- cfg["report_release"]["steps"] = ["move"] # live config change during the wait
- q._conn.execute("UPDATE jobs SET run_after=NULL WHERE id=?", (rr_id,))
- q._conn.commit()
- _run_next(q)
- # Still released: the plan came from the job's state, not the edited config.
- assert [a["action"] for a in pps.acts()] == ["move", "release"]
- assert _job(q, rr_id)["status"] == "done"
- def test_a_chunk_that_failed_a_step_is_skipped_by_later_steps(make_queue):
- class OneBadMove(FakePPS):
- def act(self, action, folder, localguids, **kw):
- result = super().act(action, folder, localguids, **kw) # record the attempt
- if action == "move" and localguids == ["6:6:2"]:
- raise PPSError("boom")
- return result
- cfg = _cfg(["move", "release"], step_delay=0)
- cfg["chunk_size"] = 1 # one message per chunk
- pps = OneBadMove(records=[{"guid": "g1", "localguid": "R:1"}])
- q = make_queue(pps, cfg)
- rr_id = _enqueue(q)
- _run_next(q)
- # The message whose move failed is never released; the other one is.
- assert [(a["action"], a["localguids"]) for a in pps.acts()] == [
- ("move", ["6:6:1"]), ("move", ["6:6:2"]), ("release", ["R:1"])]
- row = _job(q, rr_id)
- # The failed move re-read first (see the retry above) and couldn't locate it either.
- assert row["status"] == "failed" and "not found" in row["error"]
- assert row["processed"] == 1
- def test_retry_clears_the_parked_state(make_queue):
- pps = FakePPS(records=_moved_records())
- q = make_queue(pps, _cfg(["move", "release"], step_delay=60))
- rr_id = _enqueue(q)
- _run_next(q)
- q._conn.execute("UPDATE jobs SET status='failed' WHERE id=?", (rr_id,))
- q._conn.commit()
- assert q.retry(rr_id) is True
- row = q._conn.execute("SELECT run_after, state FROM jobs WHERE id=?", (rr_id,)).fetchone()
- assert row["run_after"] is None and row["state"] == "{}"
- # ...so it starts over at the first step, on the job's own localguids.
- _run_next(q)
- assert [a["action"] for a in pps.acts()] == ["move", "move"]
|