#pragma once
#include <plot/core/status.hpp>
#include <plot/core/types.hpp>
#include <plot/gl/handle.hpp>

namespace plot::render {

/// Per-instance payload of the line pipeline: one segment in data space. It
/// mirrors the interleaved floats `LineBatch::data()` produces, which is why the
/// attribute offsets in vertex_array.cpp come from `offsetof` rather than from
/// hand-written numbers.
struct LineInstance {
  f32 x0;
  f32 y0;
  f32 x1;
  f32 y1;
};

/// Per-instance payload of the text pipeline: one glyph cell.
///
/// - `(x, y)` is the cell's top-left corner in Rect pixels, top-left origin like
///   `plot::Rect`. `TextBatch` already applied the glyph's bearing along the
///   basis, so this is the corner the shader grows the cell from.
/// - `(u, v)` is the glyph rect's **normalised top-left** in the atlas, with `v`
///   increasing *downward* -- the convention `Glyph` states, so `(u, v)` is the
///   rect's top-left texel and the cell spans `(u, v)..(u + w, v + h)`, where
///   `(w, h)` is the glyph cell's normalised size (a per-draw uniform: every
///   glyph a batch stages comes from one atlas and occupies a cell of one size).
/// - `(ax, ay)` is the glyph's local +x axis -- the direction the run advances
///   in -- as a **unit vector in pixels**. It is what rotates the cell: the
///   shader builds it from `(ax, ay)` and its perpendicular, and maps the glyph's
///   rect onto the two the same way round, so a cell is never mirrored. `(1, 0)`
///   is unrotated text, and `(0, -1)` is a run advancing up the screen, i.e. a
///   90 degree counter-clockwise label such as a y-axis title.
///
/// Six floats, so the whole text pipeline still fits one instanced draw call per
/// frame with rotation free: a matrix per glyph would be three times the bytes
/// for the same pixels.
struct TextInstance {
  f32 x;
  f32 y;
  f32 u;
  f32 v;
  f32 ax;
  f32 ay;
};

static_assert(sizeof(LineInstance) == 4 * sizeof(f32), "line instance must stay 4 floats");
static_assert(sizeof(TextInstance) == 6 * sizeof(f32), "text instance must stay 6 floats");

/// How a store's staged instances reach the GPU. Semantics are identical either
/// way -- only the transfer differs, and `Renderer::init()` picks one from
/// `plot::gl::caps()`:
///
/// - `Orphan`: the GL 3.3 baseline. Every upload re-specifies the store with a
///   null `glBufferData` (orphaning it, so the driver never has to wait for the
///   draw that is still reading the previous one) and then refills it.
/// - `PersistentMapped`: GL 4.4 / ARB_buffer_storage. Immutable storage is mapped
///   once and written directly, one slot per upload. A slot is never written
///   twice within a frame, one fence is recorded after the frame's last draw, and
///   the only wait is at the start of the next frame -- so the render thread
///   never synchronises with GPU work it has just issued. The vertex array's
///   attribute pointers move with the slot.
enum class UploadMode { Orphan, PersistentMapped };

namespace detail {

/// The growth half of an instance buffer, shared by both pipelines so neither
/// duplicates the GL ownership or the transfer strategy. This is the one place
/// vertex data is handed to the GPU: `LineBuffer::upload` and
/// `TextBuffer::upload` both land here, and no caller of either can tell which
/// `UploadMode` is live.
class InstanceStore {
 public:
  /// Slots the persistent ring starts with. The floor, not the ring's size: it
  /// grows to cover the uploads a frame actually performs (see `upload()`), and
  /// never shrinks, so a steady workload grows it at most a logarithmic number of
  /// times over the life of the store.
  static constexpr u32 kInitialSlots = 3;
  /// Upper bound on the wait for the previous frame's draws to retire: a driver
  /// that has stopped making progress must not stall the render thread forever.
  static constexpr u64 kFenceWaitNs = 1'000'000'000ull;

  /// Creates the vertex buffer in `mode`. Reports `ErrorCode::Unsupported` while
  /// the GL entry points are unresolved and `GLFailure` if the driver hands out
  /// no name. A caller asking for `PersistentMapped` must already have checked
  /// that the context and the entry points can do it (see Renderer::init): a
  /// store created that way on a machine without them would never draw.
  bool create(UploadMode mode, Status* st = nullptr) noexcept;

  /// Starts a frame: waits, once, for the frame before it to retire the draws
  /// that read the ring, so no slot about to be written can still be being read.
  /// False when that wait timed out -- or when a slot was written without a fence
  /// ever being recorded for it -- in which case the store has dropped to the
  /// baseline path, which has no such hazard, and the caller reports it (see
  /// `Renderer::begin_frame`).
  ///
  /// One wait covers every slot because no slot is written twice within a frame
  /// (`upload()` grows the ring rather than wrapping it), so each slot this frame
  /// touches was last written in the previous frame or earlier -- and the
  /// previous frame's fence sits behind every draw that read one.
  bool begin_frame() noexcept;

  /// Uploads `count` instances of `instance_bytes`. `Orphan` mode orphans and
  /// refills; `PersistentMapped` mode writes the next slot of the ring, growing
  /// the ring first when the frame has already written all of its slots.
  void upload(const void* data, u32 count, usize instance_bytes) noexcept;

  /// Records the frame's single fence, behind every draw that read the ring, so
  /// the next `begin_frame()` can wait for them. Called once per frame, after the
  /// last draw that consumes the store. True in `Orphan` mode, where nothing
  /// reads the store after the orphan, and true when the frame drew nothing from
  /// the ring.
  ///
  /// False when the driver refused the fence: the slots written this frame would
  /// stay unsynchronised, so the store drops the mapped ring for the orphan path
  /// instead of rotating through it (the caller reports the failure -- see
  /// `Renderer::end_frame`).
  bool mark_drawn() noexcept;

  /// Byte offset the current slot's instances start at: 0 in `Orphan` mode,
  /// `slot * slot_bytes` in `PersistentMapped` mode. The vertex array re-points
  /// its attribute pointers whenever `epoch()` changes.
  usize slot_offset() const noexcept {
    return mode_ == UploadMode::PersistentMapped ? usize(slot_) * slot_bytes_ : 0u;
  }

  /// Changes whenever the staged instances moved (a new slot) or the GL buffer
  /// was recreated, i.e. whenever attribute pointers into this store went stale.
  ///
  /// Derived from the two things that can make them stale rather than bumped by
  /// hand at every site that replaces the buffer object: `gl::Buffer::generation()`
  /// advances on every allocation and deletion (so a fallback that re-creates the
  /// buffer cannot leave the vertex array bound to a deleted one), and `slot_epoch_`
  /// advances on every upload that lands in a new slot. Both counters only ever
  /// increase, so their sum changes whenever either does, and never repeats.
  u32 epoch() const noexcept { return buffer_.generation() + slot_epoch_; }

  void bind() const noexcept { buffer_.bind(); }
  bool persistent() const noexcept { return mode_ == UploadMode::PersistentMapped; }

 private:
  /// (Re)allocates the mapped ring with `slots` slots of `bytes` each. False when
  /// the driver refuses the storage or the map, in which case the store has fallen
  /// back to a fresh `Orphan` buffer and the frame still draws.
  bool grow_persistent(usize bytes, u32 slots) noexcept;
  /// Deletes the frame fence, unmaps and releases the GL buffer. `slot_bytes_`
  /// drops to 0 so the next upload regrows.
  void release_storage() noexcept;
  /// Abandons the mapped ring for the baseline path and re-creates the empty
  /// buffer that path needs. Used wherever the ring can no longer be guarded.
  void drop_to_orphan() noexcept;

  gl::Buffer buffer_;
  UploadMode mode_ = UploadMode::Orphan;
  u32 capacity_ = 0;                ///< instances the orphan store can hold
  usize slot_bytes_ = 0;            ///< bytes per slot of the persistent ring
  u32 slot_count_ = kInitialSlots;  ///< slots the ring has; grows, never shrinks
  u32 slot_ = 0;                    ///< slot the last upload wrote
  /// Slots written since this frame began, and the index the next upload takes.
  /// It is the ring index itself, which is what keeps a frame's slots distinct.
  u32 frame_uploads_ = 0;
  /// Times an upload landed in a new slot. Kept apart from the buffer's own
  /// identity (see `epoch()`) so neither has to know about the other.
  u32 slot_epoch_ = 0;
  u8* mapped_ = nullptr;  ///< base of the mapped ring, null in `Orphan` mode
  /// Guards every slot the frame just ended wrote. Recorded once, after its last
  /// draw; waited on once, at the start of the next frame.
  gl::Fence frame_fence_;
};

}  // namespace detail

/// Instance buffer of the line pipeline: one `LineInstance` per segment.
class LineBuffer {
 public:
  bool create(Status* st = nullptr, UploadMode mode = UploadMode::Orphan) noexcept {
    return store_.create(mode, st);
  }
  bool begin_frame() noexcept { return store_.begin_frame(); }
  void upload(const f32* interleaved, u32 count) noexcept {
    store_.upload(interleaved, count, sizeof(LineInstance));
  }
  bool mark_drawn() noexcept { return store_.mark_drawn(); }
  usize slot_offset() const noexcept { return store_.slot_offset(); }
  u32 epoch() const noexcept { return store_.epoch(); }
  bool persistent() const noexcept { return store_.persistent(); }
  void bind() const noexcept { store_.bind(); }

 private:
  detail::InstanceStore store_;
};

/// Instance buffer of the text pipeline: one `TextInstance` per glyph.
class TextBuffer {
 public:
  bool create(Status* st = nullptr, UploadMode mode = UploadMode::Orphan) noexcept {
    return store_.create(mode, st);
  }
  bool begin_frame() noexcept { return store_.begin_frame(); }
  void upload(const f32* interleaved, u32 count) noexcept {
    store_.upload(interleaved, count, sizeof(TextInstance));
  }
  bool mark_drawn() noexcept { return store_.mark_drawn(); }
  usize slot_offset() const noexcept { return store_.slot_offset(); }
  u32 epoch() const noexcept { return store_.epoch(); }
  bool persistent() const noexcept { return store_.persistent(); }
  void bind() const noexcept { store_.bind(); }

 private:
  detail::InstanceStore store_;
};

}  // namespace plot::render