// EL512Panel - refresh driver for the Planar EL512.256-H on an ESP32.
//
// Uses only ESP-IDF APIs, so the same code builds for Arduino/PlatformIO
// (lib/EL512) and for the ESPHome component in this folder.
//
// The panel has no frame memory: it must be refreshed continuously. I2S0 in
// 8-bit parallel (LCD) mode streams the signals by DMA from a small ring of
// encoded lines (CHUNK_COUNT chunks of LINES_PER_CHUNK lines). When a chunk has
// been sent, the DMA EOF interrupt re-encodes it with the lines that come
// RING_LINES later, so the ring stays ~1.7 ms ahead of the panel.
//
//   byte bit 0 = VID   (even columns 2..512 = x 1, 3, ..., 511)
//   byte bit 1 = TVID  (odd columns 1..511 = x 0, 2, ..., 510)
//   byte bit 2 = HS    (high while the 256 data clocks of a row are sent)
//   byte bit 3 = VS    (marks the top row)
//   I2S BCK   -> VCLK  (inverted, see the .cpp)
//
// BCK rises once per two stream bytes (measured with PCNT), so every VCLK
// period is two identical bytes; the I2S byte rate is 10 MHz for a 5 MHz VCLK.
// In 8-bit LCD mode the I2S emits each 32-bit DMA word as bytes 2, 3, 0, 1, so
// stream byte i is stored at index i ^ 2.
//
// Panel in two-bit parallel mode (PS1 jumper 2 removed, datasheet Table 3):
//   272 clocks per row (256 data + 16 blanking), 261 rows per frame
//   (256 visible + 5 blanking) -> 5e6 / (272 * 261) ~= 70.4 Hz.
//
// Drawing goes into a back buffer; show() copies it to the displayed buffer at
// the start of the next frame, so a redraw never shows half-drawn.
#pragma once

#include <stddef.h>
#include <stdint.h>

struct lldesc_s;           // ESP32 DMA descriptor
struct intr_handle_data_t;  // esp_intr_alloc handle

struct EL512Pins {
  int8_t vclk;
  int8_t vid;
  int8_t tvid;
  int8_t hs;
  int8_t vs;
  int8_t enable;    // -1 if not connected (panel pulls it high)
  int8_t lowpwr_n;  // -1 if not connected (panel pulls it high)
};

class EL512Panel {
 public:
  static constexpr uint16_t WIDTH = 512;
  static constexpr uint16_t HEIGHT = 256;

  // Timing (two-bit parallel mode)
  static constexpr uint32_t PIXEL_CLOCK_HZ = 5000000;
  static constexpr uint16_t DATA_CLOCKS_PER_ROW = WIDTH / 2;  // 2 px per VCLK
  static constexpr uint16_t CLOCKS_PER_ROW = 272;
  static constexpr uint16_t BLANK_CLOCKS_PER_ROW = CLOCKS_PER_ROW - DATA_CLOCKS_PER_ROW;
  static constexpr uint16_t LINES_PER_FRAME = 261;
  static constexpr uint16_t BLANK_LINES = LINES_PER_FRAME - HEIGHT;

  // DMA stream byte bits
  static constexpr uint8_t BIT_VID = 1 << 0;
  static constexpr uint8_t BIT_TVID = 1 << 1;
  static constexpr uint8_t BIT_HS = 1 << 2;
  static constexpr uint8_t BIT_VS = 1 << 3;

  // Stream bytes per VCLK period (BCK runs at half the I2S byte rate).
  static constexpr uint8_t BYTES_PER_CLOCK = 2;
  static constexpr uint16_t ROW_BYTES = CLOCKS_PER_ROW * BYTES_PER_CLOCK;

  // DMA ring: CHUNK_COUNT descriptors of LINES_PER_CHUNK lines each.
  static constexpr uint16_t LINES_PER_CHUNK = 4;
  static constexpr uint16_t CHUNK_COUNT = 8;
  static constexpr uint16_t RING_LINES = LINES_PER_CHUNK * CHUNK_COUNT;
  static constexpr size_t RING_BYTES = (size_t)RING_LINES * ROW_BYTES;

  static constexpr size_t FRAMEBUFFER_BYTES = (size_t)WIDTH * HEIGHT / 8;

  explicit EL512Panel(const EL512Pins& pins);
  ~EL512Panel();

  // Allocates buffers, sets up control GPIOs and starts the I2S DMA refresh.
  bool begin();
  void end();
  bool running() const { return _running; }

  // Display on/off (ENABLE) and low-power mode (_LOWPWR, active low).
  void setEnabled(bool on);
  void setLowPower(bool on);
  bool enabled() const { return _enabled; }
  bool lowPower() const { return _lowPower; }

  // 1 bpp drawing buffer, row-major, MSB = leftmost pixel.
  uint8_t* framebuffer() { return _fb; }
  void setPixel(int16_t x, int16_t y, bool on);
  bool getPixel(int16_t x, int16_t y) const;
  void clear(bool on = false);

  // Hand the drawing buffer to the refresh. Copies it at the start of the next
  // frame and waits for that (at most one frame, ~14 ms).
  void show();

  // Encode one scan line (0..LINES_PER_FRAME-1) of the displayed buffer into
  // ROW_BYTES bytes in DMA order. Lines >= HEIGHT produce blanking.
  void encodeRow(uint16_t line, uint8_t* out) const;

  // Frame refresh rate implied by the timing constants.
  static constexpr float refreshHz() {
    return (float)PIXEL_CLOCK_HZ / ((float)CLOCKS_PER_ROW * LINES_PER_FRAME);
  }

 private:
  bool startI2S();
  void stopI2S();
  void fillChunk(uint16_t chunk);
  static void isr(void* arg);

  EL512Pins _pins;
  uint8_t* _fb = nullptr;     // drawing buffer
  uint8_t* _front = nullptr;  // buffer being displayed
  uint8_t* _ring = nullptr;   // RING_BYTES, DMA-capable
  lldesc_s* _desc = nullptr;  // CHUNK_COUNT descriptors, circular
  intr_handle_data_t* _intr = nullptr;
  uint16_t _chunkLine[CHUNK_COUNT] = {};  // first line currently in each chunk
  volatile bool _swapPending = false;
  bool _running = false;
  bool _enabled = false;
  bool _lowPower = false;
};