#pragma once
#include <span>
#include <vector>

#include <plot/core/color.hpp>
#include <plot/core/rect.hpp>
#include <plot/core/status.hpp>
#include <plot/core/types.hpp>
#include <plot/math/vec2.hpp>
#include <plot/plot/plot.hpp>
#include <plot/render/embedded_mono_font.hpp>
#include <plot/render/buffer.hpp>
#include <plot/render/primitives.hpp>
#include <plot/render/program.hpp>
#include <plot/render/style.hpp>
#include <plot/render/text_atlas.hpp>
#include <plot/render/vertex_array.hpp>

namespace plot {

/// What one frame staged and drew. It exists because pixels alone cannot say
/// which of the two rasterisation paths a trace took: a 1M-sample series drawn
/// from the LOD pyramid and one drawn from raw samples can cover the same
/// columns, so the smoke test asserts the path here and the pixels there.
struct FrameStats {
  u32 raw_traces = 0;        ///< traces drawn from raw samples (level 0)
  u32 lod_traces = 0;        ///< traces drawn from a min/max pyramid level
  u64 visible_samples = 0;   ///< samples the gathered windows covered, summed
  u32 staged_segments = 0;   ///< line segments staged, all colour groups
  u32 draw_calls = 0;        ///< draw calls issued, line and text
};

/// Draws a `Plot` into whatever framebuffer is bound.
///
/// The renderer never creates, binds or resizes a framebuffer: `begin_frame()`
/// takes the framebuffer size for the projection and a `Rect` for the region the
/// plot occupies, clears exactly that region (`GL_SCISSOR_TEST` around the clear,
/// so a host that has already painted the rest of its surface keeps it) and sets
/// `glViewport` to the flipped rect. That is the whole embedding contract of the
/// adapters (Qt/GTK/ImGui widgets).
///
/// Two properties drive the rest of the design:
///
/// - **Only the visible window is gathered.** A trace's x range is mapped onto
///   sample indices and `Series::gather` is asked for that window -- never the
///   whole series -- at `pyramid().level_for(n, samples_per_pixel)` whenever a
///   pixel covers `dense_threshold_spp` samples or more. A 100M-sample series
///   therefore stages O(pixels) vertices, and `FrameStats` records which way each
///   trace went.
/// - **Vertex data stays in data space.** Segments are staged in data
///   coordinates and mapped to pixels by the line program's `u_scale`/`u_offset`
///   uniforms, so nothing is ever baked into screen space per primitive; a log
///   axis is staged in the transform's pre-affine coordinate (`log10`), which is
///   what the affine part expects. Pan and zoom are uniform updates.
///
/// The vertex transfer itself is one of two strategies, chosen once in `init()`
/// from `plot::gl::caps()` and invisible to every caller afterwards: a
/// persistent-mapped, fence-guarded ring on 4.3+/ARB_buffer_storage, and the
/// orphan-and-refill baseline on 3.3. Setting `PLOT_FORCE_GL33_UPLOAD=1` in the
/// environment forces the baseline path, which is how both are exercised on one
/// machine. A driver that refuses the storage, a map or a fence drops the store
/// that hit it to the baseline path -- the ring is never rotated through without
/// a guard -- and the frame reports it (see `last_frame_had_gl_error()`).
///
/// Not thread-safe, and confined to the thread that owns the current context.
class Renderer {
 public:
  Renderer() noexcept = default;
  ~Renderer() = default;
  Renderer(const Renderer&) = delete;
  Renderer& operator=(const Renderer&) = delete;

  /// Compiles both programs, uploads the font's atlas and allocates the vertex
  /// buffers. The calling thread must have the context current and
  /// `plot::gl::load()` must have succeeded, otherwise the returned `Status` is
  /// `Unsupported`; anything the driver refuses is `GLFailure` plus its log.
  bool init(Status* st = nullptr) noexcept;

  /// Starts a frame: records `fb_w` x `fb_h` for the projection, flips
  /// `viewport_px` (top-left origin, like every `Rect` in this library) into GL's
  /// bottom-left origin once, clears that region to `style().background` and
  /// empties the staging batches.
  ///
  /// It is also where the instance stores wait -- once each -- for the previous
  /// frame's draws to retire the ring they read, before this frame writes any
  /// slot (see `InstanceStore::begin_frame`): a frame never synchronises with the
  /// work it issued itself. A store that cannot retire that frame drops to the
  /// baseline path, which this frame reports (see `last_frame_had_gl_error()`).
  void begin_frame(u32 fb_w, u32 fb_h, Rect viewport_px) noexcept;

  /// Draws `plot`, refreshing its layout, ticks and grid first.
  ///
  /// The renderer owns the presentation, style and text both: `draw()` copies
  /// `style()` into the plot, hands it the style's `ui_scale` *before* it lays out
  /// (`Plot::set_ui_scale()`) and installs its own font backend on it, so the strips
  /// and tick densities the plot lays out with are the values the renderer draws
  /// with -- set colours and metrics here, not on the plot, and expect a backend
  /// set with `Plot::set_text_backend()` to be replaced on the first frame (a
  /// debug build names the one it dropped). The renderer must therefore outlive the
  /// plot's use of it.
  ///
  /// Every metric in `style()` is a logical unit, so this is also where the scale
  /// becomes pixels: the font is reset at `style().device(axis_font_px)` and each
  /// stroke and padding is converted through the same call. A host therefore states
  /// its display once, in `style().ui_scale`, and the frame it gets back is the same
  /// physical size on a 1x panel and a 2x one.
  ///
  /// `Plot::layout()` is computed exactly once, here, and handed to every helper:
  /// it runs the auto scale, the strip fixed-point loop, the grid build and the
  /// region geometry, so re-deriving it per helper would rebuild all of that per
  /// helper.
  ///
  /// The handles a pointer is on are drawn highlighted -- a cursor marker is widened
  /// into a tab, a region bound is drawn in the style's cursor colour at the width
  /// `PlotLayout` sized its handle at -- and what is hot comes from
  /// `Plot::hot_handles()`, which the input layer publishes. The renderer therefore
  /// never sees a pointer, a button or a gesture: it draws what the plot says is
  /// being manipulated, and only when a host drives the plot with a controller is
  /// anything ever hot.
  ///
  /// A legend the plot has is part of the frame: the panel and its swatches are
  /// line geometry staged with everything else, the names are glyphs on the text
  /// path, and both read the boxes `PlotLayout::legend` measured. It is the last
  /// line batch, so the legend cannot be drawn under a trace, and it leaves no GL
  /// state of its own -- the frame's blend and its neighbours' scissor already say
  /// everything a fill and a hairline border need (see end_frame's residue list).
  ///
  /// Regions are part of that same evidence: the fill is one instance of the line
  /// pipeline (`fill_pixels()`, the primitive the legend panel uses), the bounds are
  /// vertical strokes and the label is a staged glyph run, so a frame with regions
  /// leaves behind exactly what a frame without them does.
  void draw(Plot& plot);

  /// Ends the frame, draining `glGetError()` in a loop so a stale error cannot be
  /// attributed to a later frame (see `last_frame_had_gl_error()`).
  ///
  /// It also records each instance store's single fence for the frame, behind
  /// every draw that read the ring, which is what the next `begin_frame()` waits
  /// on (see `InstanceStore::mark_drawn`).
  ///
  /// The GL state it leaves behind, so a host can embed the plot without guessing:
  /// vertex array 0, program 0, `GL_ARRAY_BUFFER` 0, texture unit 0 active and
  /// nothing bound to `GL_TEXTURE_2D` on it, blending off, scissoring off, and the
  /// viewport left at the frame's rect (the caller sets its own for the next pass).
  /// The one piece of global state the frame *changed* is handed back rather than
  /// left where the frame wanted it: the clear colour, which is
  /// `style().background` only for the duration of the frame. GL keeps no history
  /// for it, so the host's value is queried on the first `begin_frame()`; that
  /// first value is what comes back here, so a colour the host changes after the
  /// first frame is restored over by it.
  ///
  /// `GL_UNPACK_ALIGNMENT` is deliberately not in that list any more: the atlas
  /// upload needs it at 1 for single-channel rows, and `render::TextAtlas` saves
  /// and restores it around every upload it performs, so no frame -- initial or
  /// mid-run -- leaves it moved for the host's own uploads to inherit.
  /// The framebuffer binding is never touched -- it is the caller's, and so is the
  /// pixel-pack alignment if `dump_frame_ppm()` ran.
  void end_frame() noexcept;

  /// The frame's colours and metrics; `draw()` hands them to the plot as well --
  /// style and `ui_scale` both -- so the layout it computes matches what is drawn.
  /// Every metric here is a logical unit (`Style`'s unit rule): the host writes
  /// `ui_scale` from the display it is on and this converts each metric with
  /// `device()`. `line_width_px` is the width of the strokes framing the data (axis
  /// lines, cursor markers); the grid carries a width *per class*
  /// (`grid_major_width` / `grid_minor_width`) and every trace its own, and a grid
  /// class the style switches off stages no geometry at all.
  render::Style& style() noexcept { return style_; }
  const render::Style& style() const noexcept { return style_; }

  /// True when the last frame reported a GL failure: an error drained from
  /// `glGetError()` in `end_frame()`, or a fence the driver refused, which the
  /// store reports when the frame's fence is recorded or waited on (such a
  /// frame has already fallen back to the baseline path). Errors are drained in a
  /// loop, so a stale one cannot be attributed to a later frame.
  bool last_frame_had_gl_error() const noexcept { return gl_error_; }

  /// Statistics of the most recently drawn frame.
  const FrameStats& stats() const noexcept { return stats_; }

  bool ready() const noexcept { return ready_; }
  /// True while both pipelines are uploading through the persistent-mapped ring:
  /// `init()` selects it from the caps and the entry points (4.3+ with
  /// ARB_buffer_storage, and `PLOT_FORCE_GL33_UPLOAD` unset), and a driver failure
  /// later -- a refused map or fence -- leaves the store that hit it on the
  /// baseline path, which this then says.
  bool using_persistent_upload() const noexcept {
    return line_vao_.persistent() && text_vao_.persistent();
  }
  /// The axis text size the renderer actually draws with, in **device** pixels: the
  /// on-screen cell height of the backend it draws with, which is
  /// `style().device(Style::axis_font_px)`'s own cell rather than the logical request
  /// itself. `Style::axis_font_px` is an em size, so with an ascent-to-descent cell
  /// it is this that a host reads back as the line height it got -- and it is the
  /// backend's own `height()` scaled, so it always agrees with the metrics the plot
  /// laid the labels out with.
  f32 axis_font_px() const noexcept { return font_backend_.cell_px(); }

  /// Writes the framebuffer's viewport region as a binary PPM (P6, 8 bits per
  /// channel, rows top-down) so a headless render can be looked at without a
  /// window. Reads the framebuffer that is bound now, which is the one the frame
  /// was drawn into. Returns false, with `st` filled in, on a bad argument or an
  /// unreadable pixel.
  ///
  /// The one entry point here that is not `noexcept`: it sizes its readback hole
  /// and its output row, so an allocation failure propagates `std::bad_alloc`
  /// rather than terminating a process that could have carried on without a
  /// screenshot. A dump is a diagnostic, and no `Status` code could say more than
  /// the exception already does.
  bool dump_frame_ppm(const char* path, Status* st = nullptr) const;

 private:
  /// The backend the plot layer sees, at the size the text pipeline draws it:
  /// `measure`/`height`/`ascent` scale with the run, so a label can never be laid
  /// out for one size and drawn at another.
  ///
  /// It wraps a `TextBackend` and nothing more: the scale is
  /// `axis_font_px / em_px()`, a plain ratio, so an anti-aliased face is drawn at
  /// the size the style asked for rather than at a whole multiple of its cell,
  /// and any backend -- the embedded font, a host's TrueType face -- is drawn the
  /// same way. It forwards the whole interface: the metrics and the glyph
  /// bearings and advances are scaled, while the artwork itself -- the atlas
  /// bytes, its size and its revision -- is the backend's own and passes through
  /// untouched.
  class AxisFont final : public render::TextBackend {
   public:
    void reset(const render::TextBackend& font, f32 requested_px) noexcept;
    f32 measure(const char* utf8) const override;
    f32 height() const override;
    f32 ascent() const override;
    f32 em_px() const override;
    /// The font's glyph at this wrapper's scale: the atlas rect is unchanged (it
    /// is scale-free) and the bearing and advance are multiplied by it, so one
    /// `Glyph` describes the glyph this backend draws. The result lives in the
    /// wrapper until the next call, which is enough for a caller measuring or
    /// laying out one glyph at a time.
    const render::Glyph* glyph(u32 codepoint) const override;
    /// The font's cell: the atlas is the font's own, and a cell's size is a
    /// property of the atlas, not of the size text is drawn at, so this forwards
    /// unchanged -- which is what makes it the authoritative value the staging
    /// path declares and the draw is told.
    Vec2 cell_uv() const override;
    const u8* atlas_pixels() const override;
    u32 atlas_width() const override;
    u32 atlas_height() const override;
    u32 revision() const override;
    /// On-screen size of one glyph cell, in pixels.
    f32 cell_px() const noexcept { return cell_px_; }
    /// On-screen pixels per font pixel: the factor `measure()` and `glyph()` are
    /// scaled by, and what `TextBatch::add_text` is handed as its size.
    f32 scale() const noexcept { return scale_; }

   private:
    const render::TextBackend* font_ = nullptr;
    f32 cell_px_ = 1.0f;
    f32 scale_ = 1.0f;
    /// `glyph()`'s scaled result, returned by pointer because the interface is
    /// `const Glyph*` and the scale is the one thing this wrapper adds.
    mutable render::Glyph scaled_{};
  };

  /// One axis pair's data -> pixel mapping, already shifted so the viewport's
  /// top-left corner is the origin (the shaders emit NDC relative to the GL
  /// viewport, not the framebuffer).
  struct Mapping {
    Vec2 scale{1.0f, 1.0f};
    Vec2 offset{0.0f, 0.0f};
  };

  Mapping mapping(const Plot& plot, u32 axis_x, u32 axis_y) const noexcept;
  /// The identity mapping for geometry already staged in viewport pixels.
  Mapping pixel_mapping() const noexcept;
  /// Shifts one framebuffer-space pixel position into viewport space.
  Vec2 to_viewport(Vec2 px) const noexcept;

  /// The single transfer point of the line pipeline: the staged `LineBatch`
  /// payload (four floats per instance) goes to whichever strategy `init()`
  /// selected. Callers of this helper never see which one is live.
  void upload_vertices(std::span<const f32> interleaved) noexcept;
  /// Same, for the text pipeline's four-float glyph instances.
  void upload_text_vertices(std::span<const f32> interleaved) noexcept;

  /// Uploads the staged line batch, maps it with (`scale`, `offset`), rasterises
  /// it in one colour and empties the batch. A no-op for an empty batch, so the
  /// caller can flush unconditionally.
  void flush_lines(const Mapping& map, Color color, f32 width) noexcept;
  /// Draws every staged glyph in `style().axis_text` and empties the batch. Text
  /// is texture-bound, so this runs once per frame, after all line geometry.
  void flush_text() noexcept;

  /// Fills `rect` -- in framebuffer pixels, like `Rect` -- with `color`, in one
  /// instance: a horizontal stroke whose width is the rect's height *is* the rect,
  /// because a stroke's quad is its perpendicular width and the fragment shader
  /// ramps on that perpendicular alone -- the ends are not capped (see
  /// `fill_pixels()` in the implementation for why a per-column fill, the way the
  /// measurement band fills, is the wrong primitive here). A rect with no width or
  /// no height stages nothing.
  void fill_pixels(const Rect& rect, Color color);
  /// Stages one data-space segment, taking the two axes' log flags into account.
  void stage_segment(f64 x0, f64 y0, f64 x1, f64 y1, bool log_x, bool log_y);
  /// Stages `n` interleaved `x,y` data-space points (a gathered window).
  void stage_xy(const f32* xy, u32 n, bool log_x, bool log_y);
  /// Lays one run of text out at a framebuffer position and stages it, shifting
  /// it into viewport space. Returns the pen past the run.
  Vec2 stage_text(Vec2 pos_px, const char* utf8);
  /// Width of the longest prefix of `utf8` that fits `budget_px` along `axis`, at
  /// the size the text pipeline draws with: exactly what `stage_text_clipped()`
  /// stages.
  f32 clipped_text_width(const char* utf8, f32 budget_px, Vec2 axis) const;
  /// Stages as much of `utf8` as fits `budget_px` along `axis` at `pos_px` and
  /// returns the length it staged. Titles are the runs that need this: a title
  /// longer than the strip the layout reserved for it is cut there, rather than
  /// being allowed to grow the strip (which would shrink the plot) or to spill
  /// over the tick labels and the data (which is the defect the strips exist to
  /// prevent).
  ///
  /// `axis` is the run's own direction and a unit vector: (1, 0) for the
  /// horizontal x title, which spends the strip's width, and (0,-1) for the y
  /// title, which reads bottom-to-top and spends the strip's height. `pos_px` is
  /// the pen -- for the rotated run, the bottom-left corner of its first cell.
  f32 stage_text_clipped(Vec2 pos_px, const char* utf8, f32 budget_px, Vec2 axis);

  void draw_grid(const Plot& plot);
  void draw_axis_lines(const Plot& plot);
  /// The chrome helpers take the frame's layout: `plot.layout()` recomputes the
  /// ticks, the strips and the grid, so it belongs to `draw()` alone.
  void draw_tick_labels(const Plot& plot, const PlotLayout& layout);
  void draw_titles(const Plot& plot, const PlotLayout& layout);
  /// The data helpers take it too; they read the axes rect and the transforms it
  /// pins.
  void draw_traces(const Plot& plot, const PlotLayout& layout);
  void draw_cursors(const Plot& plot, const PlotLayout& layout);
  /// The regions: the fill, one bound per edge, the optional label. Every rect comes
  /// from `PlotLayout::regions` -- the same geometry the controller hit-tests -- so
  /// a region is drawn where it can be grabbed, and neither side derives the other's
  /// rects.
  void draw_regions(const Plot& plot, const PlotLayout& layout);
  /// One region bound: a vertical stroke of `width` down the tab's own column, in
  /// `color`. The column is `handle_column()` of the tab -- the bound the layout
  /// placed -- and a bound outside the axes' columns is skipped, exactly as a cursor
  /// marker out of the visible window is.
  void draw_region_edge(const Rect& tab, const Rect& axes, Color color, f32 width);
  void draw_measures(const Plot& plot, const PlotLayout& layout);
  void draw_annotations(const Plot& plot);
  /// The legend: the panel and its swatches as line geometry, the names on the text
  /// path. It reads the boxes `Plot::layout()` measured rather than deriving any of
  /// them again, so the panel a test asserts and the panel this draws are the same
  /// numbers.
  void draw_legend(const Plot& plot, const PlotLayout& layout);

  /// The built-in backend the renderer owns. Every use of it goes through the
  /// `TextBackend` interface -- `self`-typed nowhere -- so swapping it for
  /// another face is a change to this member alone.
  render::EmbeddedMonoFont default_font_;
  AxisFont font_backend_;
  render::Style style_;

  render::TextAtlas atlas_;
  render::LineProgram line_program_;
  render::TextProgram text_program_;
  render::LineVertexArray line_vao_;
  render::TextVertexArray text_vao_;

  render::LineBatch lines_;
  render::TextBatch glyphs_;
  std::vector<f32> gather_;   ///< scratch for one gathered window, re-used
  mutable std::vector<u8> readback_;  ///< dump_frame_ppm's row buffer

  /// The host's `GL_COLOR_CLEAR_VALUE`, queried on the first `begin_frame()` (GL
  /// has no other way to recover it once the frame has set it) and handed back by
  /// `end_frame()`.
  Color host_clear_{};
  bool host_clear_saved_ = false;

  Rect viewport_;      ///< the frame's region, top-left origin, framebuffer px
  Rect gl_viewport_;   ///< the same rect flipped for GL, and for readback
  u32 fb_w_ = 0;
  u32 fb_h_ = 0;
  bool ready_ = false;
  bool gl_error_ = false;
  FrameStats stats_{};
};

}  // namespace plot