defmodule MicrowavepropWeb.AboutLive do
  @moduledoc "Static `/about` page — project overview, credits, contact info."
  use MicrowavepropWeb, :live_view

  alias Microwaveprop.Repo

  @impl true
  def mount(_params, _session, socket) do
    {:ok,
     socket
     |> assign(:page_title, "About")
     |> assign(:stats, fetch_stats())}
  end

  @impl true
  def render(assigns) do
    ~H"""
    <Layouts.app flash={@flash} current_scope={@current_scope} max_width="max-w-4xl">
      <.header>
        About NTMS Propagation Prediction
        <:subtitle>What we're building and why.</:subtitle>
      </.header>

      <section class="space-y-8 text-sm leading-relaxed">
        <div class="space-y-3">
          <p>
            Line-of-sight is wrong for the microwave bands. Every operator on
            902 MHz and up has made contacts over hills, through trees, and 200 km
            past the horizon — contacts that shouldn't have worked if LOS were the
            whole story. What's actually going on is the lower atmosphere:
            temperature inversions, humidity gradients, ducting layers, and rain
            cells that bend, trap, and absorb signals in ways that change by the
            hour. The window for a good contact is often minutes, not days.
          </p>
          <p>
            Jim KM5PO started this project to try to predict those windows from
            weather data. Graham W5ISP picked it up and is iterating on it from
            there. The goal: a map that tells you when to get on the air, per
            band, based on real atmospheric conditions and what we've learned
            from the contacts you and everyone else have already made.
          </p>
          <div role="alert" class="alert alert-warning">
            <p>
              <strong>Heads up:</strong>
              the scoring you see is hand-calibrated from the data we have so far.
              It isn't updated in real time — I (Graham) re-fit the weights
              manually when there's enough new data to move the needle. The more
              contacts and beacon reports we collect, the better it gets. See the
              <.link navigate={~p"/algo"} class="link link-hover font-semibold">algorithm page</.link>
              for what's actually under the hood, and please <.link
                navigate={~p"/submit"}
                class="link link-hover font-semibold"
              >submit your contacts</.link>.
            </p>
          </div>
          <div role="alert" class="alert alert-info">
            <p>
              <strong>Coverage:</strong>
              right now this focuses on the continental US. NOAA HRRR, ASOS,
              IEMRE, and the ITU terrain data are CONUS-only. The Canadian HRDPS
              model extends coverage north to 60°N (southern Canada), and SRTM
              terrain tiles cover that range. Hawaii, Alaska, northern Canada,
              and Mexico will need different data sources and aren't wired up yet.
            </p>
          </div>
        </div>

        <div class="space-y-3">
          <h2 class="text-xl font-bold">How it works, roughly</h2>
          <p>
            Two things, paired up. Most propagation tools keep them separate.
          </p>
          <ol class="list-decimal list-outside pl-5 space-y-2">
            <li>
              <strong>The weather.</strong>
              Hourly 3 km NOAA HRRR forecasts give surface fields and pressure-level
              profiles across CONUS, while the Canadian HRDPS model (0.125°
              resolution, 4× daily) extends coverage north to 60°N. We derive
              refractivity profiles, minimum refractivity gradient, ducting
              detection, boundary-layer depth, and precipitable water for every
              grid cell. ASOS surface obs, 12-hourly upper-air soundings, and
              gridded IEMRE reanalysis fill in the gaps. A 10-factor composite
              score is written for every 0.125° cell (~95k across CONUS) across
              23 microwave bands (902 MHz–241 GHz), for each hour of a 48-hour
              forecast.
            </li>
            <li>
              <strong>The contacts.</strong>
              {format_count(@stats.contacts)}+ amateur microwave QSOs, each
              tagged with the atmosphere at both ends of the path (and along it)
              at the time the contact happened. That's a ground-truth dataset we
              can actually fit against — "when you had this score, how far did
              the contact go, and did it happen at all?"
            </li>
          </ol>
          <p>
            The scoring is a weighted sum of ten factors: rain, humidity,
            precipitable water (PWAT), season, refractivity gradient, pressure,
            T–Td depression, sky cover, wind, and time of day — weights
            recalibrated via gradient descent against the contact dataset. The
            physics changes by frequency: humidity helps at 10 GHz (more
            refractivity) and hurts at 24+ GHz (absorption). Refractivity uses
            native HRRR hybrid-sigma levels (10–50 m resolution) for duct
            detection, with a pressure-level fallback (~250 m) when the native
            data isn't available.
          </p>
        </div>

        <div class="space-y-3">
          <h2 class="text-xl font-bold">What we've collected so far</h2>
          <p>Straight from the production database:</p>
          <div class="grid grid-cols-2 md:grid-cols-3 gap-3">
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Contacts</div>
              <div class="stat-value text-xl">{format_count(@stats.contacts)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Weather stations</div>
              <div class="stat-value text-xl">{format_count(@stats.weather_stations)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Surface observations</div>
              <div class="stat-value text-xl">{format_count(@stats.surface_observations)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Upper-air soundings</div>
              <div class="stat-value text-xl">{format_count(@stats.soundings)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">HRRR profiles</div>
              <div class="stat-value text-xl">{format_count(@stats.hrrr_profiles)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">IEMRE gridded obs</div>
              <div class="stat-value text-xl">{format_count(@stats.iemre_observations)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Terrain profiles</div>
              <div class="stat-value text-xl">{format_count(@stats.terrain_profiles)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Beacons</div>
              <div class="stat-value text-xl">{format_count(@stats.beacons)}</div>
            </div>
            <div class="stat bg-base-200 rounded-box">
              <div class="stat-title">Commercial link samples</div>
              <div class="stat-value text-xl">{format_count(@stats.commercial_samples)}</div>
            </div>
          </div>
        </div>

        <div class="space-y-3">
          <h2 class="text-xl font-bold">How it's built</h2>
          <ul class="list-disc list-outside pl-5 space-y-2">
            <li>
              Elixir / Phoenix 1.8 + LiveView for everything web-facing. Ecto
              on Postgres for storage. Oban runs the background pipelines
              (HRRR pulls, terrain, ASOS, soundings, IEMRE, solar indices,
              commercial links).
            </li>
            <li>
              A Rust pipeline (prop-grid-rs) handles the heavy lifting:
              fetching GRIB2 data from NOAA S3, decoding via wgrib2, deriving
              weather scalars, and scoring all 23 bands in a single fused pass
              over ~95k cells. Writes dense binary artifacts (.pgrid profiles,
              .sgrid weather scalars, and per-band .prop score files) to NFS
              for sub-millisecond single-cell reads from Elixir. A full
              forecast-hour chain step runs in ~6 seconds — ~3× faster than
              the previous Elixir-only pipeline.
            </li>
            <li>
              Leaflet + Canvas tile layers for the propagation heatmap — we
              render 0.125° cells at interactive frame rates. Tailwind v4 +
              daisyUI for layout, esbuild for JS bundling.
            </li>
            <li>
              Physics: ITU-R P.526-16 knife-edge + Deygout 3-edge terrain
              diffraction, ITU-R P.838-3 rain attenuation, dynamic k-factor
              from live HRRR refractivity gradients, great-circle geometry,
              FSPL with frequency-dependent O₂ and H₂O absorption.
            </li>
            <li>
              Data sources: NOAA HRRR (AWS S3, hourly analysis + 18 h
              forecasts), Canadian HRDPS (MSC Datamart, 4× daily 48 h
              forecasts), Iowa Environmental Mesonet (ASOS and upper-air
              soundings), IEMRE gridded reanalysis, SRTM 90 m terrain, SNMP
              polling on seven commercial microwave links near DFW at 5-minute
              intervals, and NCEP NARR for pre-2014 contact enrichment.
            </li>
          </ul>
        </div>

        <div class="space-y-3">
          <h2 class="text-xl font-bold">What's next</h2>
          <ul class="list-disc list-outside pl-5 space-y-2">
            <li>
              <strong>Beacon calibration.</strong>
              A distributed network of amateur receivers reporting CW beacon
              signal levels on a schedule. Beacon submissions are already open
              to anyone via the Beacons page.
            </li>
            <li>
              <strong>Weight calibration.</strong>
              Re-fit the 10 factor weights against recorded distances / QSO
              counts per band so the score reflects real propagation, not hand
              tuning. The PSKR spot ingestion pipeline (sampling every 5 min)
              is building the calibration dataset automatically.
            </li>
            <li>
              <strong>Better inputs.</strong> MRMS for precipitation at 24+ GHz where rain attenuation
              dominates, RTMA/URMA surface analysis blending, GOES total
              precipitable water.
            </li>
            <li>
              <strong>Expanded coverage.</strong> The Canadian HRDPS model gives
              us southern Canada (to 60°N). Alaska, Hawaii, Mexico, and the
              Caribbean need their own data sources and scoring pipelines.
            </li>
          </ul>
        </div>
        <div role="alert" class="alert alert-info text-center">
          <p>
            If this tool is useful to you, consider
            <a
              href="https://www.paypal.com/ncp/payment/53VLBD2E67JAE"
              target="_blank"
              class="link font-semibold underline"
            >
              donating to NTMS
            </a>
            to help keep the project running.
          </p>
        </div>
      </section>
    </Layouts.app>
    """
  end

  # For tables that get huge (tens of millions of rows), using count(*) on
  # every About page load is wasteful. We use PostgreSQL's pg_class.reltuples
  # estimate — it's maintained by ANALYZE and is accurate to within a few
  # percent, which is plenty for "big number on a marketing page."
  @estimate_tables ~w(hrrr_profiles surface_observations)

  defp fetch_stats do
    %{
      contacts: count_exact("contacts"),
      weather_stations: count_exact("weather_stations"),
      surface_observations: count_estimate("surface_observations"),
      soundings: count_exact("soundings"),
      hrrr_profiles: count_estimate("hrrr_profiles"),
      iemre_observations: count_exact("iemre_observations"),
      terrain_profiles: count_exact("terrain_profiles"),
      beacons: count_exact("beacons"),
      commercial_samples: count_exact("commercial_samples")
    }
  end

  # Each count is wrapped individually so a missing table in dev (or a
  # transient query failure) never blanks the entire dashboard. The
  # previous outer try/rescue zeroed all 10 numbers if any single one
  # raised — every stat read 0 on environments lacking hrrr_profiles
  # or propagation_scores.
  defp count_exact(table) do
    case Repo.query("SELECT count(*) FROM #{table}") do
      {:ok, %Postgrex.Result{rows: [[count]]}} -> count
      _ -> 0
    end
  end

  defp count_estimate(table) when table in @estimate_tables do
    case Repo.query("SELECT reltuples::bigint FROM pg_class WHERE relname = $1", [table]) do
      {:ok, %Postgrex.Result{rows: [[estimate]]}} -> max(estimate || 0, 0)
      _ -> 0
    end
  end

  defp format_count(n) when is_integer(n) and n >= 1_000_000 do
    "#{Float.round(n / 1_000_000, 1)}M"
  end

  defp format_count(n) when is_integer(n) and n >= 1_000 do
    "#{Float.round(n / 1_000, 1)}k"
  end

  defp format_count(n) when is_integer(n), do: Integer.to_string(n)
  defp format_count(_), do: "—"
end