prop/test/microwaveprop/pskr/calibration_sampler_test.exs

defmodule Microwaveprop.Pskr.CalibrationSamplerTest do
  use Microwaveprop.DataCase, async: true

  import Ecto.Query

  alias Microwaveprop.Pskr.CalibrationSample
  alias Microwaveprop.Pskr.CalibrationSampler
  alias Microwaveprop.Pskr.SpotHourly
  alias Microwaveprop.Repo
  alias Microwaveprop.SpaceWeather.GeomagneticObservation
  alias Microwaveprop.Weather.HrrrProfile

  @hour ~U[2026-05-04 18:00:00Z]

  defp insert_spot!(attrs) do
    {:ok, _} =
      %SpotHourly{}
      |> SpotHourly.changeset(
        Map.merge(
          %{
            hour_utc: @hour,
            band: "10000",
            sender_grid: "EM12KL",
            receiver_grid: "DM43ST",
            spot_count: 1,
            midpoint_lat: 33.0,
            midpoint_lon: -97.0,
            distance_km: 200.0,
            modes: ["FT8"]
          },
          attrs
        )
      )
      |> Repo.insert()
  end

  defp insert_hrrr!(attrs) do
    {:ok, _} =
      %HrrrProfile{}
      |> HrrrProfile.changeset(
        Map.merge(
          %{
            valid_time: @hour,
            lat: 33.0,
            lon: -97.0,
            run_time: @hour,
            surface_temp_c: 25.0,
            surface_dewpoint_c: 18.0,
            pwat_mm: 30.0,
            surface_pressure_mb: 1013.0,
            min_refractivity_gradient: -100.0,
            hpbl_m: 500.0,
            ducting_detected: false,
            profile: []
          },
          attrs
        )
      )
      |> Repo.insert()
  end

  defp insert_kp!(value) do
    {:ok, _} =
      %GeomagneticObservation{}
      |> GeomagneticObservation.changeset(%{
        valid_time: DateTime.add(@hour, 60, :second),
        kp_index: value
      })
      |> Repo.insert()
  end

  describe "build_for_hour/1" do
    test "skips and returns zeros when no spots exist for the hour" do
      assert %{upserted: 0, missing_hrrr_cells: 0} = CalibrationSampler.build_for_hour(@hour)
      assert Repo.aggregate(CalibrationSample, :count) == 0
    end

    test "builds one sample per (band, snapped midpoint) cell" do
      insert_spot!(%{midpoint_lat: 33.01, midpoint_lon: -97.02})
      insert_spot!(%{midpoint_lat: 33.04, midpoint_lon: -97.03, sender_grid: "EM13", spot_count: 3})
      # Distinct grid cell (>0.125° away)
      insert_spot!(%{midpoint_lat: 35.0, midpoint_lon: -97.0, sender_grid: "EM15"})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      assert %{upserted: 2} = CalibrationSampler.build_for_hour(@hour)
      [a, b] = CalibrationSample |> Repo.all() |> Enum.sort_by(& &1.midpoint_lat)
      # Two near-midpoints collapsed; one distant cell stayed separate.
      assert a.spot_count == 4
      assert a.distinct_paths == 2
      assert b.spot_count == 1
    end

    test "snaps midpoints to the 0.125° propagation grid" do
      insert_spot!(%{midpoint_lat: 33.06, midpoint_lon: -97.07})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      # 33.06 → nearest 0.125° step → 33.0; -97.07 → -97.125
      assert sample.midpoint_lat == 33.0
      assert sample.midpoint_lon == -97.125
    end

    test "joins HRRR atmospheric features at the midpoint" do
      insert_spot!(%{})

      insert_hrrr!(%{
        lat: 33.0,
        lon: -97.0,
        surface_temp_c: 22.5,
        surface_dewpoint_c: 16.0,
        pwat_mm: 28.0,
        min_refractivity_gradient: -150.0,
        hpbl_m: 420.0,
        ducting_detected: true
      })

      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      assert sample.surface_temp_c == 22.5
      assert sample.surface_dewpoint_c == 16.0
      assert sample.pwat_mm == 28.0
      assert sample.min_refractivity_gradient == -150.0
      assert sample.hpbl_m == 420.0
      assert sample.hrrr_ducting_detected == true
    end

    test "leaves HRRR fields nil when no nearby profile exists" do
      insert_spot!(%{})
      # No HRRR profile inserted at all.
      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      assert sample.surface_temp_c == nil
      assert sample.hpbl_m == nil
      assert sample.hrrr_ducting_detected == nil
    end

    test "enqueues an hrrr_fetch_tasks row when a cell has no nearby HRRR profile" do
      insert_spot!(%{midpoint_lat: 33.0, midpoint_lon: -97.0})

      assert %{upserted: 1, missing_hrrr_cells: 1} = CalibrationSampler.build_for_hour(@hour)

      [task] =
        Repo.all(from(t in "hrrr_fetch_tasks", select: %{points: t.points, status: t.status, valid_time: t.valid_time}))

      assert task.status == "queued"
      assert task.valid_time == DateTime.to_naive(@hour)
      # The cell midpoint, snapped to HRRR grid (0.01° rounding).
      assert task.points == [%{"lat" => 33.0, "lon" => -97.0}]
    end

    test "does not enqueue an hrrr_fetch_tasks row when an HRRR profile already covers the cell" do
      insert_spot!(%{})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      CalibrationSampler.build_for_hour(@hour)

      assert Repo.aggregate(from(t in "hrrr_fetch_tasks"), :count) == 0
    end

    test "deduplicates HRRR enqueue points across bands sharing a midpoint" do
      insert_spot!(%{band: "10000", midpoint_lat: 33.0, midpoint_lon: -97.0})
      insert_spot!(%{band: "24000", midpoint_lat: 33.0, midpoint_lon: -97.0, sender_grid: "EM13"})
      insert_spot!(%{band: "10000", midpoint_lat: 35.0, midpoint_lon: -97.0, sender_grid: "EM15"})

      CalibrationSampler.build_for_hour(@hour)

      [task] = Repo.all(from(t in "hrrr_fetch_tasks", select: %{points: t.points}))
      # Two unique midpoints (33.0,-97.0) and (35.0,-97.0); the second band at the
      # first midpoint must collapse, otherwise the Rust worker double-fetches the
      # same lat/lon for one valid_time.
      assert length(task.points) == 2
      sorted = Enum.sort_by(task.points, & &1["lat"])
      assert sorted == [%{"lat" => 33.0, "lon" => -97.0}, %{"lat" => 35.0, "lon" => -97.0}]
    end

    test "stamps the latest Kp from SpaceWeather on every sample in the hour" do
      insert_spot!(%{})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})
      insert_kp!(5)

      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      assert sample.kp_index == 5
    end

    test "computes median distance across the cell's path mix" do
      insert_spot!(%{distance_km: 100.0, sender_grid: "EM10"})
      insert_spot!(%{distance_km: 200.0, sender_grid: "EM11"})
      insert_spot!(%{distance_km: 300.0, sender_grid: "EM12"})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      assert sample.median_distance_km == 200.0
    end

    test "deduplicates modes across the cell's spots" do
      insert_spot!(%{modes: ["FT8"], sender_grid: "EM10"})
      insert_spot!(%{modes: ["FT4", "FT8"], sender_grid: "EM11"})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      CalibrationSampler.build_for_hour(@hour)
      [sample] = Repo.all(CalibrationSample)
      assert Enum.sort(sample.modes) == ["FT4", "FT8"]
    end

    test "two-pass pipeline: first run NULL+enqueue, second run UPSERTs with HRRR" do
      # End-to-end behaviour the producer was added for: a cell with no
      # nearby HRRR profile gets a sample row written with NULL weather
      # fields *and* a fetch task enqueued; once the Rust hrrr-point-worker
      # delivers the profile (simulated here by directly inserting an
      # hrrr_profiles row), the next sampler pass UPSERTs the same
      # calibration_samples row, this time with non-NULL HRRR fields.
      insert_spot!(%{midpoint_lat: 33.0, midpoint_lon: -97.0})

      # ── Pass 1 ─────────────────────────────────────────────────
      assert %{upserted: 1, missing_hrrr_cells: 1} = CalibrationSampler.build_for_hour(@hour)
      [first_sample] = Repo.all(CalibrationSample)
      assert first_sample.surface_temp_c == nil
      assert first_sample.hpbl_m == nil
      assert Repo.aggregate(from(t in "hrrr_fetch_tasks"), :count) == 1

      # ── Rust worker drains the task (simulated) ────────────────
      insert_hrrr!(%{
        lat: 33.0,
        lon: -97.0,
        surface_temp_c: 24.0,
        surface_dewpoint_c: 18.0,
        pwat_mm: 31.0,
        min_refractivity_gradient: -120.0,
        hpbl_m: 480.0,
        ducting_detected: true
      })

      # ── Pass 2 ─────────────────────────────────────────────────
      assert %{upserted: 1, missing_hrrr_cells: 0} = CalibrationSampler.build_for_hour(@hour)
      [second_sample] = Repo.all(CalibrationSample)

      # Same row, UPSERTed (id preserved, weather populated).
      assert second_sample.id == first_sample.id
      assert second_sample.surface_temp_c == 24.0
      assert second_sample.surface_dewpoint_c == 18.0
      assert second_sample.pwat_mm == 31.0
      assert second_sample.min_refractivity_gradient == -120.0
      assert second_sample.hpbl_m == 480.0
      assert second_sample.hrrr_ducting_detected == true
    end

    test "is idempotent — re-running the same hour upserts the row" do
      insert_spot!(%{})
      insert_hrrr!(%{lat: 33.0, lon: -97.0})

      CalibrationSampler.build_for_hour(@hour)
      first_count = Repo.aggregate(CalibrationSample, :count)

      # Mutate the spot count and re-run; the sample must update, not duplicate.
      Repo.update_all(SpotHourly, set: [spot_count: 99])
      CalibrationSampler.build_for_hour(@hour)
      second_count = Repo.aggregate(CalibrationSample, :count)

      assert first_count == second_count
      [sample] = Repo.all(CalibrationSample)
      assert sample.spot_count == 99
    end
  end
end