#include "harness.hpp"
#include <plot/data/array_series.hpp>
#include <plot/data/stream_series.hpp>
#include <algorithm>
#include <cmath>
#include <random>
#include <thread>
#include <vector>

PLOT_TEST(array_series_bounds_and_gather) {
  std::vector<f32> y{1, 5, -2, 3};
  plot::data::ArraySeries s(std::move(y), /*x0=*/10.0, /*dx=*/0.5);
  PLOT_CHECK(s.size() == 4);
  PLOT_CHECK_NEAR(s.x_bounds().min, 10.0, 1e-9);
  PLOT_CHECK_NEAR(s.x_bounds().max, 11.5, 1e-9);
  PLOT_CHECK_NEAR(s.y_bounds().min, -2.0, 1e-6);
  std::vector<f32> out;
  s.gather(0, 0, 4, out);
  PLOT_CHECK(out.size() == 8);             // interleaved x,y
  PLOT_CHECK_NEAR(out[0], 10.0, 1e-6);
  PLOT_CHECK_NEAR(out[1], 1.0, 1e-6);
  PLOT_CHECK_NEAR(out[6], 11.5, 1e-6);
}

PLOT_TEST(stream_series_acquire_publishes_snapshot) {
  plot::data::StreamSeries s(1 << 12, /*x0=*/0.0, /*dx=*/1e-6);
  for (int i = 0; i < 100; ++i) s.push(f32(i));
  PLOT_CHECK(s.produced() == 100);
  s.acquire();
  PLOT_CHECK(s.size() == 100);
  // Pyramid must track the published samples.
  PLOT_CHECK_NEAR(s.pyramid().reduce(0, 100).max, 99.0, 1e-4);
  for (int i = 100; i < 250; ++i) s.push(f32(i));
  s.acquire();
  PLOT_CHECK(s.size() == 250);
}

PLOT_TEST(stream_series_drops_oldest_when_full) {
  plot::data::StreamSeries s(256, 0.0, 1.0);
  for (int i = 0; i < 1000; ++i) s.push(f32(i));
  s.acquire();
  PLOT_CHECK(s.size() <= 256);
  PLOT_CHECK_NEAR(s.y_bounds().max, 999.0, 1e-4);
}

PLOT_TEST(array_series_exact_range_queries_match_bruteforce) {
  // The strong test for the exactness split: arbitrary, deliberately
  // unaligned ranges must match a brute-force scan of the raw samples.
  std::mt19937 rng(7);
  std::uniform_real_distribution<float> d(-5.0f, 5.0f);
  std::vector<f32> y(4000);
  for (auto& v : y) v = d(rng);
  plot::data::ArraySeries s(y, 0.0, 1.0);
  for (u64 a = 0; a < 4000; a += 173) {
    for (u64 b = a + 1; b <= 4000; b += 331) {
      float lo = y[a], hi = y[a];
      double sum = 0.0, sq = 0.0;
      for (u64 i = a; i < b; ++i) {
        lo = std::min(lo, y[i]); hi = std::max(hi, y[i]);
        sum += y[i]; sq += double(y[i]) * double(y[i]);
      }
      const plot::Range r = s.reduce(a, b);
      PLOT_CHECK_NEAR(r.min, lo, 1e-4);
      PLOT_CHECK_NEAR(r.max, hi, 1e-4);
      PLOT_CHECK_NEAR(s.sum(a, b), sum, 1e-2);
      PLOT_CHECK_NEAR(s.sumsq(a, b), sq, 1e-1);
    }
  }
}

PLOT_TEST(stream_series_exact_queries_survive_ring_wrap) {
  plot::data::StreamSeries s(1u << 10, 0.0, 1.0);
  constexpr u64 kPushes = 3000;
  constexpr u64 kFirstRetained = kPushes - (1u << 10);  // 1976
  for (u64 i = 0; i < kPushes; ++i) s.push(f32(i % 97));   // wraps the ring twice
  s.acquire();
  const u64 n = s.size();
  PLOT_CHECK(n == 1u << 10);
  PLOT_CHECK_NEAR(s.x0(), 1976.0, 1e-9);
  PLOT_CHECK(s.x_bounds().min == s.x0());
  PLOT_CHECK(s.pyramid().size() == n);

  const plot::Range r = s.reduce(0, n);                 // retained window, wrapped
  PLOT_CHECK_NEAR(r.max, 96.0, 1e-4);
  PLOT_CHECK_NEAR(r.min, 0.0, 1e-4);

  double sum = 0.0, sumsq = 0.0;
  for (u64 i = kFirstRetained; i < kPushes; ++i) {
    const double v = static_cast<double>(i % 97);
    sum += v;
    sumsq += v * v;
  }
  PLOT_CHECK_NEAR(s.sum(0, n), sum, 1e-2);
  PLOT_CHECK_NEAR(s.sumsq(0, n), sumsq, 1e-1);

  std::vector<f32> out;
  s.gather(0, 0, n, out);                               // level 0: raw samples
  PLOT_CHECK(out.size() == 2 * n);
  PLOT_CHECK_NEAR(out[0], s.x0(), 1e-6);
  PLOT_CHECK_NEAR(out[1], f32(kFirstRetained % 97), 1e-6);
  PLOT_CHECK_NEAR(out[2 * n - 2], s.x0() + f64(n - 1), 1e-6);
}

PLOT_TEST(stream_series_push_and_read_are_race_free) {
  // The ring overwrites, so the producer reuses the slot of the snapshot's oldest
  // retained sample while the consumer may still be reading it. Relaxed atomic
  // slots make that defined; nothing else in the suite has two threads, so this
  // is the case ThreadSanitizer actually flags when that is not the case.
  plot::data::StreamSeries s(1u << 8, 0.0, 1.0);
  constexpr u64 kPushes = 50'000;
  std::thread producer([&s] {
    for (u64 i = 0; i < kPushes; ++i) s.push(f32(i % 971));
  });
  u64 reads = 0;
  while (s.produced() < kPushes) {
    s.acquire();
    const u64 n = s.size();
    if (n == 0) continue;
    (void)s.reduce(0, n);
    (void)s.sum(0, n);
    (void)s.sumsq(0, n);
    std::vector<f32> out;
    s.gather(0, 0, n, out);                             // reads the oldest edge
    PLOT_CHECK(out.size() == 2 * n);
    ++reads;
  }
  producer.join();
  PLOT_CHECK(s.produced() == kPushes);
  PLOT_CHECK(reads > 0);
}