prop/test/microwaveprop/workers/radar_frame_worker_test.exs
Graham McIntire 733a7f5bf1
fix(review): address code-reviewer findings
Fixes flagged by the code-reviewer agent's pass over the session's
commits (cc9220b..7b78a25):

- Propagation.warm_cache_and_broadcast/2 now uses ScoresFile.read/2
  directly and returns {:ok, :ok} | {:error, :enoent | :invalid_format}.
  Previously it called ScoresFile.read_bounds/3 which silently returns
  [] on missing/corrupt files, poisoning ScoreCache with an empty grid
  that the reconciler couldn't heal.
- NotifyListener.warm_band/2 and ScoreCacheReconciler.warm_one/2 now
  pattern-match {:error, reason} and skip (log, return :error) instead
  of caching empty. rescue clauses kept as defense-in-depth for
  unexpected faults in PubSub.broadcast / ETS writes.
- ScoresFile.extract_points/2 promoted to @doc public — callers that
  need to distinguish missing file from empty grid can feed read/2
  payloads here themselves.
- Weather.build_grid_cache_row/4: replaced || fallbacks with prefer/3
  helper (Map.fetch) so a legitimate persisted ducting_detected: false
  is not clobbered by a derived-from-sounding true.
- Weather.hrrr_data_fully_present?/1 @spec tightened from map() to
  Contact.t() | field-constrained map, plus is_nil(qso_timestamp)
  guard so callers with partial contacts get a clean false rather
  than a HrrrClient.nearest_hrrr_hour/1 crash.
- AdminTaskWorker.native_derive bulk-UPDATE: chunk reduced 2000 → 500
  and wrapped in try/rescue with per-row fallback on Postgrex errors
  so a single bad row doesn't kill the remaining 1999 in its chunk.
- Runbook FM3 rewritten to match the actual code path (no rescue;
  explicit {:error, _} pattern match). FM5 clarifies the surviving
  PropagationGridWorker is a cron-fired seed worker, not a fallback
  compute path.
- Dialyzer: strict flags added (:error_handling, :unknown,
  :unmatched_returns, :extra_return, :missing_return). Baseline
  emitted 130 warnings, mostly discarded Task.start/PubSub/Logger
  returns; a follow-up will tighten those and backfill @specs.

New tests:
- ScoreCacheReconciler GenServer lifecycle: run_on_start true/false,
  interval_ms rescheduling, info-level log line.
- Weather.hrrr_data_fully_present?/1: nil qso_timestamp returns false.
- Weather.build_grid_cache_rows/2: explicit ducting_detected: false
  on profile beats derived true from sounding params.
- RadarFrameWorker: pins the NexradClient "NEXRAD n0q HTTP <code>"
  error string contract so permanent_error?/1 classification doesn't
  silently regress if the client's error format changes.
2026-04-21 10:09:46 -05:00

206 lines
7.6 KiB
Elixir

defmodule Microwaveprop.Workers.RadarFrameWorkerTest do
use Microwaveprop.DataCase, async: false
use Oban.Testing, repo: Microwaveprop.Repo
alias Microwaveprop.Radio.Contact
alias Microwaveprop.Radio.ContactCommonVolumeRadar
alias Microwaveprop.Repo
alias Microwaveprop.Weather.NexradClient
alias Microwaveprop.Workers.RadarFrameWorker
setup do
Req.Test.set_req_test_from_context(%{async: false})
:ok
end
defp insert_contact(attrs \\ %{}) do
default = %{
station1: "W5XD",
station2: "K5TR",
qso_timestamp: ~U[2024-09-15 18:30:00Z],
mode: "CW",
band: Decimal.new("10000"),
grid1: "EM12",
grid2: "EM00",
pos1: %{"lat" => 32.9, "lon" => -97.0},
pos2: %{"lat" => 33.1, "lon" => -96.8},
distance_km: Decimal.new("30")
}
{:ok, contact} =
%Contact{}
|> Contact.changeset(Map.merge(default, attrs))
|> Repo.insert()
contact
end
describe "process_frame/4" do
test "writes a ContactCommonVolumeRadar row and marks :complete for every contact in the batch" do
c1 = insert_contact(%{station1: "A1"})
c2 = insert_contact(%{station1: "A2"})
# In-memory pixel buffer: 10x10 empty frame. The aggregator will
# observe zero echoes but still emit a stats row per contact.
pixels = :binary.copy(<<0>>, 100)
width = 10
frame_ts = ~U[2024-09-15 18:30:00Z]
assert :ok =
RadarFrameWorker.process_frame(
[Repo.reload!(c1), Repo.reload!(c2)],
frame_ts,
pixels,
width
)
assert Repo.get_by(ContactCommonVolumeRadar, contact_id: c1.id)
assert Repo.get_by(ContactCommonVolumeRadar, contact_id: c2.id)
assert %Contact{radar_status: :complete} = Repo.get!(Contact, c1.id)
assert %Contact{radar_status: :complete} = Repo.get!(Contact, c2.id)
end
end
describe "perform/1" do
test "marks every contact in the batch :unavailable when the frame 404s" do
c1 = insert_contact(%{station1: "B1"})
c2 = insert_contact(%{station1: "B2"})
Req.Test.stub(NexradClient, fn conn ->
Plug.Conn.send_resp(conn, 404, "not found")
end)
assert :ok =
perform_job(RadarFrameWorker, %{
"frame_ts" => "2024-09-15T18:30:00Z",
"contact_ids" => [c1.id, c2.id]
})
refute Repo.get_by(ContactCommonVolumeRadar, contact_id: c1.id)
refute Repo.get_by(ContactCommonVolumeRadar, contact_id: c2.id)
assert %Contact{radar_status: :unavailable} = Repo.get!(Contact, c1.id)
assert %Contact{radar_status: :unavailable} = Repo.get!(Contact, c2.id)
end
test "returns {:error, _} and leaves contacts :queued on a 5xx server error (so Oban retries)" do
c1 = insert_contact(%{station1: "S1"})
c2 = insert_contact(%{station1: "S2"})
Req.Test.stub(NexradClient, fn conn ->
Plug.Conn.send_resp(conn, 503, "service unavailable")
end)
assert {:error, _reason} =
perform_job(RadarFrameWorker, %{
"frame_ts" => "2024-09-15T18:30:00Z",
"contact_ids" => [c1.id, c2.id]
})
# Neither contact should be pinned :unavailable — a retry might succeed.
assert %Contact{radar_status: status1} = Repo.get!(Contact, c1.id)
assert %Contact{radar_status: status2} = Repo.get!(Contact, c2.id)
refute status1 == :unavailable
refute status2 == :unavailable
end
test "returns {:error, _} on a transport error without pinning contacts :unavailable" do
c1 = insert_contact(%{station1: "T1"})
Req.Test.stub(NexradClient, fn conn ->
Req.Test.transport_error(conn, :timeout)
end)
assert {:error, _reason} =
perform_job(RadarFrameWorker, %{
"frame_ts" => "2024-09-15T18:30:00Z",
"contact_ids" => [c1.id]
})
assert %Contact{radar_status: status} = Repo.get!(Contact, c1.id)
refute status == :unavailable
end
test "skips contacts already at a terminal status (idempotent replay)" do
c_done = insert_contact(%{station1: "DONE"})
{:ok, _} = c_done |> Ecto.Changeset.change(%{radar_status: :complete}) |> Repo.update()
c_new = insert_contact(%{station1: "NEW"})
Req.Test.stub(NexradClient, fn conn ->
Plug.Conn.send_resp(conn, 404, "not found")
end)
assert :ok =
perform_job(RadarFrameWorker, %{
"frame_ts" => "2024-09-15T18:30:00Z",
"contact_ids" => [c_done.id, c_new.id]
})
# Already-complete contact stays complete; new one is marked unavailable.
assert %Contact{radar_status: :complete} = Repo.get!(Contact, c_done.id)
assert %Contact{radar_status: :unavailable} = Repo.get!(Contact, c_new.id)
end
test "processes every eligible contact in the frame's 5-min bucket, not just contact_ids" do
# Both contacts land in the 18:30 bucket (18:30 ≤ ts < 18:35).
c_passed = insert_contact(%{station1: "PASSED", qso_timestamp: ~U[2024-09-15 18:30:00Z]})
c_omitted = insert_contact(%{station1: "OMITTED", qso_timestamp: ~U[2024-09-15 18:34:00Z]})
# Outside the 18:30 bucket — must not be touched.
c_other_bucket = insert_contact(%{station1: "OTHER", qso_timestamp: ~U[2024-09-15 18:35:00Z]})
Req.Test.stub(NexradClient, fn conn ->
Plug.Conn.send_resp(conn, 404, "not found")
end)
# Only c_passed is explicitly listed, but c_omitted is in the same
# bucket and still :pending — the worker must pick it up too.
assert :ok =
perform_job(RadarFrameWorker, %{
"frame_ts" => "2024-09-15T18:30:00Z",
"contact_ids" => [c_passed.id]
})
assert %Contact{radar_status: :unavailable} = Repo.get!(Contact, c_passed.id)
assert %Contact{radar_status: :unavailable} = Repo.get!(Contact, c_omitted.id)
# Outside-bucket contact stays :pending.
assert %Contact{radar_status: :pending} = Repo.get!(Contact, c_other_bucket.id)
end
end
describe "NexradClient error contract" do
# Pins the exact "NEXRAD n0q HTTP <code>" format emitted by
# NexradClient.fetch_decoded_frame/1 on a non-200 response. RadarFrameWorker
# pattern-matches on this literal prefix in `permanent_error?/1` to
# classify 4xx as permanent (stop retrying) and everything else as
# transient (let Oban retry). A silent format change would quietly turn
# permanent 404s into infinite retries — fail loudly here instead.
test "fetch_decoded_frame/1 returns error starting with \"NEXRAD n0q HTTP \" on 4xx" do
Req.Test.stub(NexradClient, fn conn ->
Plug.Conn.send_resp(conn, 404, "not found")
end)
assert {:error, reason} = NexradClient.fetch_decoded_frame(~U[2024-09-15 18:30:00Z])
assert is_binary(reason)
assert String.starts_with?(reason, "NEXRAD n0q HTTP ")
assert reason == "NEXRAD n0q HTTP 404"
end
end
describe "unique constraint" do
test "rejects a second insert with the same frame_ts while one is pending" do
frame_ts = "2024-09-15T18:30:00Z"
{:ok, first} =
Oban.insert(RadarFrameWorker.new(%{"frame_ts" => frame_ts, "contact_ids" => ["a"]}))
# Second insert with a different contact_ids list but same frame_ts
# must collapse into the existing job — otherwise backfill sweeps
# duplicate 5 MB PNG fetches per frame.
{:ok, second} =
Oban.insert(RadarFrameWorker.new(%{"frame_ts" => frame_ts, "contact_ids" => ["b"]}))
assert first.id == second.id
end
end
end