/// GOP framebuffer driver — renders text via a bitmap font.
///
/// Text surface (cursor, scrolling, colours) lives in `crate::vt`; this
/// module is the low-level rasteriser: glyph blits and pixel shifts on the
/// linear framebuffer.
use crate::font;
use crate::uefi::{GraphicsOutputProtocol, PIXEL_BGR, PIXEL_RGB};
use alloc::boxed::Box;
use alloc::vec;
use alloc::vec::Vec;
use core::fmt;
use core::ptr;
use core::sync::atomic::{AtomicU8, AtomicU64, Ordering};

/// Framebuffer state captured before ExitBootServices.
pub struct Framebuffer {
    base: *mut u8,
    width: usize,
    height: usize,
    pitch: usize, // bytes per scan line
    bytes_per_pixel: usize,
    bg: u32, // packed BGRA or RGBA background colour
    bgr: bool,
}

static mut FB: Option<Framebuffer> = None;

/// Software backbuffer: a RAM copy of the whole framebuffer (same pitch
/// layout, u32 pixels).
///
/// Real-hardware GOP framebuffers are typically mapped uncacheable or
/// write-combining (firmware MTRR/PAT), so *reading* them costs a bus
/// round-trip per cache line — a full-screen scroll shift reads ~4-8 MB
/// and crawls.  Rasterisation therefore writes every pixel to the shadow
/// too, and scrolling is a fast cached memcpy inside the shadow followed
/// by a write-only push to the display: the display is never read.
static mut SHADOW: *mut u32 = core::ptr::null_mut();
static mut SHADOW_WORDS: usize = 0;

/// Initialise the framebuffer from GOP. Call *before* ExitBootServices.
pub fn init(gop: &mut GraphicsOutputProtocol) {
    let mode = unsafe { &*gop.mode };
    let info = unsafe { &*mode.info };
    let base = mode.framebuffer_base as *mut u8;
    let width = info.horizontal_resolution as usize;
    let height = info.vertical_resolution as usize;
    let pitch = info.pixels_per_scan_line as usize * 4; // 32-bit pixel
    let bpp = 4;

    // Pick colours based on pixel format
    let (fg, bg) = match info.pixel_format {
        PIXEL_BGR => (0x00_FF_FF_FFu32, 0x00_00_00_00u32), // white fg, black bg
        PIXEL_RGB => (0x00_FF_FF_FFu32, 0x00_00_00_00u32),
        _ => (0x00_FF_FF_FFu32, 0x00_00_00_00u32),
    };
    let bgr = info.pixel_format == PIXEL_BGR;
    let _ = fg;

    let fb = Framebuffer {
        base,
        width,
        height,
        pitch,
        bytes_per_pixel: bpp,
        bg,
        bgr,
    };

    // Allocate the RAM backbuffer before first paint so every write goes
    // to both the display and the shadow.
    let words = (pitch * height) / 4;
    unsafe {
        if words > 0 {
            let v: Vec<u32> = vec![0; words];
            SHADOW = Box::into_raw(v.into_boxed_slice()) as *mut u32;
            SHADOW_WORDS = words;
        }
    }

    fb.clear();

    unsafe {
        FB = Some(fb);
    }
}

// ---------------------------------------------------------------------------
// Public text API — the text surface now lives in `crate::vt`; these wrappers
// keep callers (shell, macros) unchanged.
// ---------------------------------------------------------------------------

/// Draw a character at the current terminal cursor position and advance.
pub fn put_char(c: char) {
    let b = if (c as u32) < 0x100 { c as u8 } else { b'?' };
    crate::vt::put_char(b);
}

/// Write a string to the terminal.
pub fn write_str(s: &str) {
    crate::vt::write_str(s);
}

/// Clear the terminal and home the cursor.
pub fn clear_screen() {
    crate::vt::clear_all();
}

/// Raw-pointer accessor for the framebuffer static (single-threaded
/// kernel; keeps `static_mut_refs` quiet).
fn fb() -> &'static mut Option<Framebuffer> {
    unsafe { &mut *core::ptr::addr_of_mut!(FB) }
}

/// (cols, rows) of the text surface, from the current framebuffer mode.
pub fn dims() -> (usize, usize) {
    match fb().as_ref() {
        Some(f) => (f.width / 8, f.height / 16),
        None => (0, 0),
    }
}

/// (width, height) of the framebuffer in pixels.
pub fn pixel_dims() -> (usize, usize) {
    match fb().as_ref() {
        Some(f) => (f.width, f.height),
        None => (0, 0),
    }
}

// ---------------------------------------------------------------------------
// Rect primitives + the push path
// ---------------------------------------------------------------------------

/// Copy a shadow rect to the display and composite the mouse cursor on
/// top.  Every display write goes through here (glyph blits, fills,
/// scroll shifts), so the cursor — which lives *only* in this overlay,
/// never in the shadow — stays on top of whatever the content is without
/// any save/restore bookkeeping.  The display is never read.
pub(crate) fn push_rect(x: usize, y: usize, w: usize, h: usize) {
    let Some(fb) = fb().as_ref() else {
        return;
    };
    if unsafe { SHADOW.is_null() } || x >= fb.width || y >= fb.height {
        return;
    }
    let w = w.min(fb.width - x);
    let h = h.min(fb.height - y);
    let row_words = fb.pitch / 4;
    unsafe {
        for dy in 0..h {
            let off = (y + dy) * row_words + x;
            ptr::copy_nonoverlapping(SHADOW.add(off), fb.base.add(off * 4) as *mut u32, w);
        }
    }
    overlay_cursor(x, y, w, h);
}

/// Fill a rectangle in the shadow and push it (with cursor composited).
pub fn fill_rect(x: usize, y: usize, w: usize, h: usize, color: u32) {
    let Some(fb) = fb().as_ref() else {
        return;
    };
    if x >= fb.width || y >= fb.height {
        return;
    }
    let w = w.min(fb.width - x);
    let h = h.min(fb.height - y);
    if unsafe { SHADOW.is_null() } {
        // Degraded: no backbuffer — write the display directly.
        let row_words = fb.pitch / 4;
        unsafe {
            for dy in 0..h {
                let off = (y + dy) * row_words + x;
                for dx in 0..w {
                    ptr::write_volatile(fb.base.add((off + dx) * 4) as *mut u32, color);
                }
            }
        }
        return;
    }
    let row_words = fb.pitch / 4;
    unsafe {
        for dy in 0..h {
            let off = (y + dy) * row_words + x;
            for dx in 0..w {
                *SHADOW.add(off + dx) = color;
            }
        }
    }
    push_rect(x, y, w, h);
}

/// Read one pixel back from the shadow (RAM; cheap).  Test/demo use only.
pub fn shadow_pixel(x: usize, y: usize) -> Option<u32> {
    let fb = fb().as_ref()?;
    if x >= fb.width || y >= fb.height || unsafe { SHADOW.is_null() } {
        return None;
    }
    Some(unsafe { *SHADOW.add(y * (fb.pitch / 4) + x) })
}

/// Read one pixel back from the display (volatile; uncached on real
/// hardware — test/demo use only, never on a hot path).
pub fn display_pixel(x: usize, y: usize) -> Option<u32> {
    let fb = fb().as_ref()?;
    if x >= fb.width || y >= fb.height {
        return None;
    }
    Some(unsafe { ptr::read_volatile(fb.base.add((y * (fb.pitch / 4) + x) * 4) as *mut u32) })
}

// ---------------------------------------------------------------------------
// Mouse cursor — a display overlay, composited by `push_rect`.
// ---------------------------------------------------------------------------

/// Cursor bitmap: 12×16 classic pointer, 1 = opaque.  The hotspot is the
/// top-left corner of the bitmap; the arrow tip sits at (2, 0).  Built by
/// a const fn from explicit column lists (pixel column `dx` = bit `11-dx`)
/// so the shape is auditable instead of hand-mangled bit literals.
const CURSOR_W: usize = 12;
const CURSOR_H: usize = 16;

const fn bmp_row(cols: &[u8]) -> u16 {
    let mut v: u16 = 0;
    let mut i = 0;
    while i < cols.len() {
        v |= 1u16 << (11 - cols[i] as u16);
        i += 1;
    }
    v
}

/// Head: triangle from a 1-px tip at (2,0) widening right to col 11.
/// Tail: 2-px diagonal dropping down-right from the head's base.
const CURSOR_BMP: [u16; CURSOR_H] = [
    bmp_row(&[2]),
    bmp_row(&[2, 3]),
    bmp_row(&[2, 3, 4]),
    bmp_row(&[2, 3, 4, 5]),
    bmp_row(&[2, 3, 4, 5, 6]),
    bmp_row(&[2, 3, 4, 5, 6, 7]),
    bmp_row(&[2, 3, 4, 5, 6, 7, 8]),
    bmp_row(&[2, 3, 4, 5, 6, 7, 8, 9]),
    bmp_row(&[2, 3, 4, 5, 6, 7, 8, 9, 10]),
    bmp_row(&[2, 3, 4, 5, 6, 7, 8, 9, 10, 11]),
    bmp_row(&[8, 9]),
    bmp_row(&[9, 10]),
    bmp_row(&[9, 10]),
    bmp_row(&[10, 11]),
    bmp_row(&[10, 11]),
    bmp_row(&[10, 11]),
];

/// Packed cursor position: x in the high 32 bits, y in the low 32, so a
/// single relaxed load never sees a torn pair.  Written by the cursor
/// task, read by every push (any task).
static CURSOR_POS: AtomicU64 = AtomicU64::new(0);
static CURSOR_BUTTONS: AtomicU8 = AtomicU8::new(0);

fn pack(x: usize, y: usize) -> u64 {
    ((x as u64) << 32) | (y as u64)
}

/// Current cursor position (top-left of the bitmap).
pub fn cursor_pos() -> (usize, usize) {
    let v = CURSOR_POS.load(Ordering::Relaxed);
    ((v >> 32) as usize, (v & 0xFFFF_FFFF) as usize)
}

/// Current button state: bit 0 = left, bit 1 = right, bit 2 = middle.
pub fn cursor_buttons() -> u8 {
    CURSOR_BUTTONS.load(Ordering::Relaxed)
}

pub fn cursor_set_buttons(b: u8) {
    CURSOR_BUTTONS.store(b, Ordering::Relaxed);
}

/// Place the cursor (used at init; centre of the screen).
pub fn cursor_set(x: usize, y: usize) {
    CURSOR_POS.store(pack(x, y), Ordering::Relaxed);
}

/// Move the cursor by a relative delta, clamped to the screen, erasing
/// the old position (a shadow push — the shadow never held the cursor)
/// and drawing the new one.  Returns the new position.
pub fn cursor_move(dx: i16, dy: i16) -> (usize, usize) {
    let Some(fb) = fb().as_ref() else {
        return cursor_pos();
    };
    let (cx, cy) = cursor_pos();
    let max_x = fb.width.saturating_sub(CURSOR_W);
    let max_y = fb.height.saturating_sub(CURSOR_H);
    let nx = (cx as i64 + dx as i64).clamp(0, max_x as i64) as usize;
    let ny = (cy as i64 + dy as i64).clamp(0, max_y as i64) as usize;
    if (nx, ny) == (cx, cy) {
        return (cx, cy);
    }
    CURSOR_POS.store(pack(nx, ny), Ordering::Relaxed);
    // Restore the old rect (overlay now composites at the new position).
    push_rect(cx, cy, CURSOR_W, CURSOR_H);
    // Draw at the new position.
    push_rect(nx, ny, CURSOR_W, CURSOR_H);
    (nx, ny)
}

/// If the cursor overlaps the given rect, composite it (black outline
/// offset +1,+1, white body on top).  Called by `push_rect`.
fn overlay_cursor(x: usize, y: usize, w: usize, h: usize) {
    let (cx, cy) = cursor_pos();
    if x >= cx + CURSOR_W || y >= cy + CURSOR_H {
        return;
    }
    if cx >= x + w || cy >= y + h {
        return;
    }
    draw_bmp(cx + 1, cy + 1, rgb(0, 0, 0));
    draw_bmp(cx, cy, rgb(255, 255, 255));
}

/// Re-composite the cursor where it is (after a scroll shift, which
/// bypasses `push_rect`, and once at init so it is visible over idle
/// cells the diff never re-blits).
pub(crate) fn cursor_redraw() {
    let (cx, cy) = cursor_pos();
    draw_bmp(cx + 1, cy + 1, rgb(0, 0, 0));
    draw_bmp(cx, cy, rgb(255, 255, 255));
}

/// Write the cursor bitmap at (x, y) in one colour — display only, the
/// shadow is never touched (that is what makes the overlay race-free).
fn draw_bmp(x: usize, y: usize, color: u32) {
    let Some(fb) = fb().as_ref() else {
        return;
    };
    let row_words = fb.pitch / 4;
    unsafe {
        for dy in 0..CURSOR_H {
            let yy = y + dy;
            if yy >= fb.height {
                break;
            }
            let row = CURSOR_BMP[dy];
            for dx in 0..CURSOR_W {
                let xx = x + dx;
                if xx >= fb.width {
                    break;
                }
                if row & (1u16 << (11 - dx)) != 0 {
                    let off = yy * row_words + xx;
                    ptr::write_volatile(fb.base.add(off * 4) as *mut u32, color);
                }
            }
        }
    }
}

/// Pack an (r, g, b) colour for the framebuffer's pixel format.
pub fn rgb(r: u8, g: u8, b: u8) -> u32 {
    match fb().as_ref() {
        Some(f) if f.bgr => ((r as u32) << 16) | ((g as u32) << 8) | b as u32,
        _ => ((b as u32) << 16) | ((g as u32) << 8) | r as u32,
    }
}

// ---------------------------------------------------------------------------
// Framebuffer implementation
// ---------------------------------------------------------------------------
impl Framebuffer {
    fn clear(&self) {
        let size = self.pitch * self.height;
        // Fill with background colour (32-bit writes), display + shadow.
        let mut p = self.base;
        let end = unsafe { p.add(size) };
        unsafe {
            while p < end {
                ptr::write_volatile(p as *mut u32, self.bg);
                p = p.add(4);
            }
        }
        if !unsafe { SHADOW.is_null() } {
            for i in 0..unsafe { SHADOW_WORDS } {
                unsafe {
                    *SHADOW.add(i) = self.bg;
                }
            }
        }
    }

    /// Shift the framebuffer content up by `n` text rows (16 pixels each)
    /// and clear the exposed bottom rows.  Called by `vt` when deferred
    /// scrolls are pushed to the display; `n` can batch many scrolls into
    /// one write-only push.
    ///
    /// With the RAM backbuffer, this is a cached shadow memcpy + a
    /// write-only push to the display — the display itself is never read
    /// (reads are uncached on real hardware and dominate the old path).
    pub(crate) fn shift_up_n(&self, n: usize) {
        let n = n.max(1).min(self.height / 16); // sanity
        let row_bytes = self.pitch * 16;
        let total = self.pitch * self.height;
        let row_words = row_bytes / 4;
        let words = total / 4;
        unsafe {
            if SHADOW.is_null() {
                // No shadow (allocation failed): fall back to shifting the
                // display directly.
                ptr::copy(
                    self.base.add(n * row_bytes),
                    self.base,
                    total - n * row_bytes,
                );
                let last_row = self.base.add(total - n * row_bytes);
                for i in 0..(n * row_words) {
                    ptr::write_volatile(last_row.add(i * 4) as *mut u32, self.bg);
                }
                return;
            }
            // Shift the shadow up n rows (cached RAM — fast).
            ptr::copy(SHADOW.add(n * row_words), SHADOW, words - n * row_words);
            // Clear the exposed bottom rows in the shadow.
            for i in (words - n * row_words)..words {
                *SHADOW.add(i) = self.bg;
            }
            // Push the shadow to the display: write-only, no reads.
            // A bulk copy (rep movsb) writes in 64-byte bursts that
            // coalesce well on WC framebuffers — far fewer bus
            // transactions than per-pixel stores.
            ptr::copy_nonoverlapping(SHADOW, self.base as *mut u32, words);
            // The scroll copied the shadow (which never contains the
            // cursor); re-composite it on top of the pushed frame.
            crate::gop::cursor_redraw();
        }
    }
}

/// Blit one glyph cell at (col, row) with explicit fg/bg colours.
/// Procedurally-rendered bitmaps for Unicode glyphs missing from the
/// 256-glyph Latin-1 font: box-drawing (U+2500–U+257F), arrows
/// (U+2190–U+2193) and the em dash (U+2014).  Box drawing is pure
/// geometry, so these are computed, not stored.  Same format as the font:
/// one byte per row, bit 7 = leftmost column.
fn unicode_glyph_bits(ch: u16) -> Option<[u8; 16]> {
    let mut g = [0u8; 16];
    match ch {
        // ─ light horizontal, ━ heavy horizontal
        0x2500 => {
            g[7] = 0xFF;
            g[8] = 0xFF;
        }
        0x2501 => {
            g[7] = 0xFF;
            g[8] = 0xFF;
            g[9] = 0xFF;
        }
        // │ light vertical, ┃ heavy vertical
        0x2502 => {
            for y in 0..16 {
                g[y] = 0x18;
            }
        }
        0x2503 => {
            for y in 0..16 {
                g[y] = 0x3C;
            }
        }
        // corners ┌ ┐ └ ┘
        0x250C => {
            g[7] = 0xF0;
            g[8] = 0xF8;
            for y in 9..16 {
                g[y] = 0x18;
            }
        }
        0x2510 => {
            g[7] = 0x0F;
            g[8] = 0x1F;
            for y in 9..16 {
                g[y] = 0x18;
            }
        }
        0x2514 => {
            for y in 0..7 {
                g[y] = 0x18;
            }
            g[7] = 0xF8;
            g[8] = 0xF0;
        }
        0x2518 => {
            for y in 0..7 {
                g[y] = 0x18;
            }
            g[7] = 0x1F;
            g[8] = 0x0F;
        }
        // T junctions ├ ┤ ┬ ┴ and cross ┼
        0x251C => {
            for y in 0..16 {
                g[y] = 0x18;
            }
            g[7] = 0xF8;
            g[8] = 0xF8;
        }
        0x2524 => {
            for y in 0..16 {
                g[y] = 0x18;
            }
            g[7] = 0x1F;
            g[8] = 0x1F;
        }
        0x252C => {
            g[7] = 0xFF;
            g[8] = 0xFF;
            for y in 9..16 {
                g[y] = 0x18;
            }
        }
        0x2534 => {
            for y in 0..7 {
                g[y] = 0x18;
            }
            g[7] = 0xFF;
            g[8] = 0xFF;
        }
        0x253C => {
            for y in 0..16 {
                g[y] = 0x18;
            }
            g[7] = 0xFF;
            g[8] = 0xFF;
        }
        // ═ double horizontal, ║ double vertical
        0x2550 => {
            g[6] = 0xFF;
            g[9] = 0xFF;
        }
        0x2551 => {
            for y in 0..16 {
                g[y] = 0x24;
            }
        }
        // — em dash
        0x2014 => {
            g[7] = 0xFF;
            g[8] = 0xFF;
        }
        // ← → ↑ ↓
        0x2190 => {
            g[8] = 0xFF;
            g[6] = 0xC0;
            g[7] = 0xC0;
            g[9] = 0xC0;
            g[10] = 0xC0;
        }
        0x2192 => {
            g[8] = 0xFF;
            g[6] = 0x03;
            g[7] = 0x03;
            g[9] = 0x03;
            g[10] = 0x03;
        }
        0x2191 => {
            g[0] = 0x18;
            g[1] = 0x3C;
            g[2] = 0x7E;
            for y in 3..16 {
                g[y] = 0x18;
            }
        }
        0x2193 => {
            for y in 0..13 {
                g[y] = 0x18;
            }
            g[13] = 0x7E;
            g[14] = 0x3C;
            g[15] = 0x18;
        }
        _ => return None,
    }
    Some(g)
}

pub(crate) fn blit_glyph(col: usize, row: usize, ch: u16, fg: (u8, u8, u8), bg: (u8, u8, u8)) {
    if let Some(fb) = fb().as_ref() {
        let glyph = font::GLYPH_8X16;
        let data = if ch < 256 {
            match glyph.get(ch as usize) {
                Some(d) => *d,
                None => return,
            }
        } else if let Some(bits) = unicode_glyph_bits(ch) {
            bits
        } else {
            match glyph.get(32) {
                Some(d) => *d,
                None => return,
            }
        };

        let fg = rgb(fg.0, fg.1, fg.2);
        let bg = rgb(bg.0, bg.1, bg.2);
        let x = col * 8;
        let y = row * 16;

        if unsafe { SHADOW.is_null() } {
            // Degraded: no backbuffer — write the display directly, no
            // cursor overlay.
            for cy in 0..16 {
                let row_bits = data[cy];
                for cx in 0..8 {
                    let offset = (y + cy) * fb.pitch + (x + cx) * fb.bytes_per_pixel;
                    let px = if row_bits & (0x80 >> cx) != 0 { fg } else { bg };
                    unsafe {
                        ptr::write_volatile(fb.base.add(offset) as *mut u32, px);
                    }
                }
            }
            return;
        }

        // Normal path: rasterise into the RAM shadow, then one push
        // copies the cell to the display and composites the cursor.
        for cy in 0..16 {
            let row_bits = data[cy];
            for cx in 0..8 {
                let offset = (y + cy) * fb.pitch + (x + cx) * fb.bytes_per_pixel;
                let px = if row_bits & (0x80 >> cx) != 0 { fg } else { bg };
                unsafe {
                    *SHADOW.add(offset / 4) = px;
                }
            }
        }
        push_rect(x, y, 8, 16);
    }
}

/// Shift the framebuffer content up `n` text rows and clear the exposed
/// bottom rows.  `n` batches deferred scrolls into one push.
pub(crate) fn shift_up_n(n: usize) {
    if let Some(fb) = fb().as_ref() {
        fb.shift_up_n(n);
    }
}

// ---------------------------------------------------------------------------
// fmt::Write wrapper
// ---------------------------------------------------------------------------
pub struct GopWriter;

impl fmt::Write for GopWriter {
    fn write_str(&mut self, s: &str) -> fmt::Result {
        write_str(s);
        Ok(())
    }
}

/// Write a formatted string to the framebuffer.
#[macro_export]
macro_rules! gop_print {
    ($($arg:tt)*) => {{
        use core::fmt::Write;
        let _ = write!(&mut $crate::gop::GopWriter, $($arg)*);
    }};
}

#[macro_export]
macro_rules! gop_println {
    () => { $crate::gop::write_str("\n"); };
    ($($arg:tt)*) => {{
        $crate::gop_print!($($arg)*);
        $crate::gop::write_str("\n");
    }};
}