//! `T8aD` — the game's 2D UI/HUD texture format.
//!
//! A 32bpp **A8R8G8B8** (Xbox byte order) surface stored as **256×256 raster
//! tiles in row-major order** — each tile prefixed by a 16-byte tile header, edge
//! tiles clipped to the image bounds. Fully reversed 2026-07-17 from the file
//! header and verified against the running game (title screen).
//!
//! ```text
//! 0x00  4         Magic "T8aD"
//! 0x14  4         width  (BE u32)
//! 0x18  4         height (BE u32)
//! 0x1c  4         tile count (BE u32) = ceil(w/256) * ceil(h/256)
//! 0x2c  tiles*4   offset table: absolute byte offset of each row-major tile
//! <off>  16       per-tile header (flags + tile w/h), then:
//! <off+16>        tile_w * tile_h * 4 bytes of A8R8G8B8 pixels, row-major
//! ```
//!
//! Surfaces ≤256px wide are a single tile column, so the first tile's pixels sit
//! at `44 + tiles*4 + 16 = 64` — which is why the old "type→header size 64/84/…"
//! rule (header = 44 + tiles*20) happened to decode small textures correctly: for
//! one tile it lands on the same pixel start. Wide textures were garbled because
//! the offset table + 16-byte per-tile headers weren't accounted for.

/// Magic at the start of every T8aD surface.
pub const T8AD_MAGIC: [u8; 4] = *b"T8aD";

/// A decoded T8aD surface as tightly-packed RGBA8 (row-major, top-left origin).
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct T8adImage {
    pub width: u32,
    pub height: u32,
    pub rgba: Vec<u8>,
}

/// Whether `bytes` starts with the T8aD magic.
pub fn is_t8ad(bytes: &[u8]) -> bool {
    bytes.len() >= 4 && bytes[0..4] == T8AD_MAGIC
}

#[inline]
fn be32(b: &[u8], off: usize) -> u32 {
    u32::from_be_bytes([b[off], b[off + 1], b[off + 2], b[off + 3]])
}

/// Side of the square storage tile, in texels, and the per-tile header size.
const TILE: usize = 256;
const TILE_HDR: usize = 16;

/// Decode a T8aD surface from a slice whose first bytes ARE the magic. Returns
/// `None` for non-T8aD input or a variant we can't decode as RGBA (never guesses).
///
/// Layout (reversed from the header + verified against the running game):
/// a 44-byte base header, then a `tiles`-entry big-endian u32 **offset table** at
/// `0x2c`, where `tiles` = the field at `0x1c` = `ceil(w/256) * ceil(h/256)`.
/// Each entry is the absolute byte offset of a **row-major** 256×256 tile; every
/// tile is a 16-byte tile header followed by `tile_w*tile_h*4` A8R8G8B8 pixels,
/// edge tiles clipped to the image bounds.
pub fn parse(bytes: &[u8]) -> Option<T8adImage> {
    if !is_t8ad(bytes) || bytes.len() < 0x40 {
        return None;
    }
    let width = be32(bytes, 0x14) as usize;
    let height = be32(bytes, 0x18) as usize;
    if !(1..=4096).contains(&width) || !(1..=4096).contains(&height) {
        return None;
    }
    let tiles = be32(bytes, 0x1c) as usize;
    let cols = width.div_ceil(TILE);
    let rows = height.div_ceil(TILE);
    // The field at 0x1c must be the tile count; otherwise it's a variant we don't
    // decode (e.g. DXT / palettized) — defer rather than misdecode.
    if tiles == 0 || tiles != cols * rows {
        return None;
    }
    const TABLE: usize = 0x2c;
    if bytes.len() < TABLE + tiles * 4 {
        return None;
    }

    let mut rgba = vec![0u8; width * height * 4];
    for ty in 0..rows {
        for tx in 0..cols {
            let tile = ty * cols + tx;
            let pixels = be32(bytes, TABLE + tile * 4) as usize + TILE_HDR;
            let tw = TILE.min(width - tx * TILE);
            let th = TILE.min(height - ty * TILE);
            if pixels + tw * th * 4 > bytes.len() {
                return None; // truncated / not the layout we expect
            }
            for row in 0..th {
                let mut s = pixels + row * tw * 4;
                let mut d = ((ty * TILE + row) * width + tx * TILE) * 4;
                for _ in 0..tw {
                    // A8R8G8B8 → RGBA8.
                    rgba[d] = bytes[s + 1];
                    rgba[d + 1] = bytes[s + 2];
                    rgba[d + 2] = bytes[s + 3];
                    rgba[d + 3] = bytes[s];
                    s += 4;
                    d += 4;
                }
            }
        }
    }
    Some(T8adImage {
        width: width as u32,
        height: height as u32,
        rgba,
    })
}

#[cfg(test)]
mod tests {
    use super::*;

    /// Build a synthetic single-tile T8aD (`w,h ≤ 256`) with a known A8R8G8B8
    /// pattern: base header + 1-entry offset table + 16-byte tile header + pixels.
    fn synth(w: u32, h: u32) -> Vec<u8> {
        assert!(w <= 256 && h <= 256);
        let mut b = vec![0u8; 0x2c];
        b[0..4].copy_from_slice(&T8AD_MAGIC);
        b[0x14..0x18].copy_from_slice(&w.to_be_bytes());
        b[0x18..0x1c].copy_from_slice(&h.to_be_bytes());
        b[0x1c..0x20].copy_from_slice(&1u32.to_be_bytes()); // 1 tile
        b.extend_from_slice(&0x30u32.to_be_bytes()); // offset table: tile 0 @ 0x30
        b.extend_from_slice(&[0u8; 16]); // 16-byte tile header → pixels at 0x40
        for i in 0..(w * h) {
            b.extend_from_slice(&[(i & 0xff) as u8, 0x24, 0x63, 0xB2]); // A, R, G, B
        }
        b
    }

    #[test]
    fn decodes_argb_to_rgba() {
        let b = synth(4, 2);
        let img = parse(&b).expect("decodes");
        assert_eq!((img.width, img.height), (4, 2));
        assert_eq!(img.rgba.len(), 4 * 2 * 4);
        // pixel 0: A=0,R=0x24,G=0x63,B=0xB2 → RGBA = 24 63 B2 00
        assert_eq!(&img.rgba[0..4], &[0x24, 0x63, 0xB2, 0x00]);
        // pixel 1: A=1 → alpha byte
        assert_eq!(&img.rgba[4..8], &[0x24, 0x63, 0xB2, 0x01]);
    }

    #[test]
    fn assembles_row_major_tiles_via_offset_table() {
        // 300×1 → 2 tiles: (0,0)=256×1 red, (1,0)=44×1 blue, each +16-byte header.
        let (w, h): (u32, u32) = (300, 1);
        let mut b = vec![0u8; 0x2c];
        b[0..4].copy_from_slice(&T8AD_MAGIC);
        b[0x14..0x18].copy_from_slice(&w.to_be_bytes());
        b[0x18..0x1c].copy_from_slice(&h.to_be_bytes());
        b[0x1c..0x20].copy_from_slice(&2u32.to_be_bytes()); // 2 tiles
        let off0 = 0x2c + 2 * 4; // after the 2-entry table
        let off1 = off0 + 16 + 256 * 4; // tile-0 header + its 256 pixels
        b.extend_from_slice(&(off0 as u32).to_be_bytes());
        b.extend_from_slice(&(off1 as u32).to_be_bytes());
        b.extend_from_slice(&[0u8; 16]);
        b.extend_from_slice(&[0xFF, 0xFF, 0, 0].repeat(256)); // A,R,G,B red
        b.extend_from_slice(&[0u8; 16]);
        b.extend_from_slice(&[0xFF, 0, 0, 0xFF].repeat(44)); // A,R,G,B blue
        let img = parse(&b).expect("decodes");
        assert_eq!((img.width, img.height), (300, 1));
        assert_eq!(&img.rgba[0..4], &[0xFF, 0, 0, 0xFF]); // tile 0 → red
        assert_eq!(&img.rgba[256 * 4..256 * 4 + 4], &[0, 0, 0xFF, 0xFF]); // tile 1 → blue
    }

    #[test]
    fn rejects_wrong_tilecount_and_short() {
        // tile-count field that isn't ceil(w/256)*ceil(h/256) → None
        let mut b = synth(2, 2);
        b[0x1c..0x20].copy_from_slice(&7u32.to_be_bytes());
        assert!(parse(&b).is_none());
        // truncated pixel data → None
        let b = synth(64, 64);
        assert!(parse(&b[..200]).is_none());
        assert!(parse(b"IDXD\0\0\0\0").is_none());
    }
}