//! XBG7 mesh geometry decoder (geometry resources inside XPR2 containers).
//!
//! ## Clean-room note
//!
//! This format was reverse-engineered **purely by static observation of the
//! retail disc's `hidden/resource3d/*.xpr` files** (hex inspection + geometric
//! validation of the recovered triangles). No game code was decompiled or
//! copied. See `docs/re/structures/xbg7-mesh.md` for the evidence log.
//!
//! ## Where XBG7 lives
//!
//! Ship / weapon / prop models are `XPR2` containers (see [`crate::texture`]).
//! Their resource directory holds `TX2D` texture resources **and** one or more
//! `XBG7` geometry resources.  The `XBG7` *descriptor* (at the resource's
//! `data_offset`) is a scene/material graph; the actual vertex and index
//! buffers live in the container's shared data section (from `header_size`).
//!
//! ## The "simple" layout decoded here (CONFIRMED)
//!
//! For single-stream models (weapons, simple props — 36 of the 166 disc models)
//! the data section is a straight sequence of sub-meshes, each:
//!
//! ```text
//!   [ index buffer  : idx_count × u16 big-endian ]   triangle list
//!   [ 12-byte vertex-buffer header (contents undecoded) ]
//!   [ vertex buffer : vtx_count × stride bytes ]      (declaration-driven)
//!   (pad to 16 bytes → next sub-mesh)
//! ```
//!
//! The vertex layout is **not fixed** — it comes from a **vertex declaration**
//! in the descriptor: a table of `{offset, format-code, usage}` triples (usage
//! `0x00` POSITION `f32×3`, `0x03` NORMAL `f16×4`, `0x05` TEXCOORD `f16×2`).
//! Models omit UV or use fewer elements, so stride varies (20 = pos+normal,
//! 24 = pos+normal+uv, …). Each element is read in naive big-endian component
//! order. Correct alignment is pinned by the recovered normals being exactly
//! unit-length. **Cross-checked against a Canary GPU vertex-fetch capture**,
//! which confirmed the primitive type (triangle list), formats, and offsets —
//! see `docs/re/structures/xbg7-mesh.md`.
//!
//! `vtx_count` / `idx_count` come from per-sub-mesh records in the descriptor:
//! a `[vtx_count:u32][0:u32][idx_count:u32][tail:u32]` tuple (big-endian), read
//! in file order.  Every index is validated to be `< vtx_count`; if any
//! sub-mesh fails to carve cleanly the whole model is rejected
//! ([`MeshError::UnsupportedLayout`]) rather than emitting garbage.
//!
//! ## Not yet decoded
//!
//! The hero-ship *body* meshes (`DeltaSaber_*.xpr` `f004`, and ~100 other
//! models) use a more complex **multi-stream** layout — separate position /
//! attribute streams at descriptor-addressed offsets, quantized positions —
//! which is not handled here and is cleanly declined.

use crate::texture::{Xpr2Header, Xpr2ResourceEntry};
use binrw::BinRead;
use std::io::Cursor;
use thiserror::Error;

#[derive(Debug, Error)]
pub enum MeshError {
    #[error("Not an XPR2 container")]
    NotXpr2,
    #[error("No XBG7 geometry resource in container")]
    NoGeometry,
    #[error("Mesh layout not supported (multi-stream / quantized body mesh)")]
    UnsupportedLayout,
    #[error("Parse error: {0}")]
    Parse(#[from] binrw::Error),
}

/// A decoded 3D mesh ready for Bevy.
#[derive(Debug, Default, Clone)]
pub struct GameMesh {
    /// Vertex positions in model space `[x, y, z]`.
    pub positions: Vec<[f32; 3]>,
    /// Vertex normals `[nx, ny, nz]` — empty when not stored (compute smooth
    /// normals from geometry instead).
    pub normals: Vec<[f32; 3]>,
    /// Texture coordinates `[u, v]`.  **Best-guess channel** (attr halves 0 & 2)
    /// pending in-game visual confirmation — see the module doc.
    pub uvs: Vec<[f32; 2]>,
    /// Triangle-list indices (3 per triangle).
    pub indices: Vec<u32>,
    /// Sub-mesh / node name from the descriptor, when available.
    pub name: Option<String>,
}

/// A model = the set of sub-meshes recovered from one XPR2 container's first
/// XBG7 resource, plus the resource's name.
#[derive(Debug, Default, Clone)]
pub struct Xbg7Model {
    pub name: String,
    pub meshes: Vec<GameMesh>,
}

impl Xbg7Model {
    /// Total vertex / triangle counts across all sub-meshes.
    pub fn totals(&self) -> (usize, usize) {
        let v = self.meshes.iter().map(|m| m.positions.len()).sum();
        let t = self.meshes.iter().map(|m| m.indices.len() / 3).sum();
        (v, t)
    }

    /// Decode the geometry of the first XBG7 resource in an XPR2 container.
    ///
    /// Returns [`MeshError::UnsupportedLayout`] for models whose data section
    /// does not carve cleanly under the simple single-stream layout (the
    /// complex body meshes) — never partial / garbage geometry.
    pub fn from_xpr2(bytes: &[u8]) -> Result<Self, MeshError> {
        if bytes.len() < 16 || &bytes[..4] != b"XPR2" {
            return Err(MeshError::NotXpr2);
        }
        let mut cur = Cursor::new(bytes);
        let header = Xpr2Header::read(&mut cur)?;
        let mut xbg: Option<Xpr2ResourceEntry> = None;
        for _ in 0..header.num_resources {
            let e = Xpr2ResourceEntry::read(&mut cur)?;
            if &e.type_tag == b"XBG7" {
                xbg = Some(e);
                break;
            }
        }
        let xbg = xbg.ok_or(MeshError::NoGeometry)?;

        const DIR_BASE: usize = 0x10;
        let desc = xbg.data_offset as usize + DIR_BASE;
        let desc_end = (desc + xbg.descriptor_size as usize).min(bytes.len());
        if desc >= bytes.len() {
            return Err(MeshError::UnsupportedLayout);
        }

        // Resource name (for labelling).
        let name = read_cstr(bytes, xbg.name_offset as usize + DIR_BASE)
            .unwrap_or_else(|| "XBG7".to_string());

        // Parse the vertex declaration (element offsets/formats + stride). The
        // XBG7 layout is NOT fixed-stride — models omit UV or use fewer elements
        // (stride 20 = pos+normal, stride 24 = pos+normal+uv, …). Confirmed
        // against a Canary GPU vertex-fetch capture (see docs/re/xbg7-mesh.md).
        let decl = parse_vertex_decl(&bytes[desc..desc_end])
            .ok_or(MeshError::UnsupportedLayout)?;

        // Extract the ordered list of sub-mesh (vtx_count, idx_count) records.
        let records = submesh_records(&bytes[desc..desc_end]);
        if records.is_empty() {
            return Err(MeshError::UnsupportedLayout);
        }

        // Carve the data section sequentially.
        let base = header.header_size as usize;
        let mut off = 0usize; // relative to `base`
        let mut meshes = Vec::new();
        for (vtx_count, idx_count) in records {
            // Each sub-mesh block is `[12-byte header][index buffer][vertex
            // buffer]` — the SAME layout as stage resources (see
            // `stage_models`). The header must be skipped: reading indices from
            // the block start instead treats the 12 header bytes as 6 junk
            // indices (2 leading degenerate triangles — the stray-triangle
            // artifact) and drops the last 6 real indices. Skipping it leaves the
            // vertex buffer at the identical offset (`+12 + idx_bytes`), so
            // coverage is unchanged; only the triangle list is corrected.
            let ib = base + off + VERTEX_BUFFER_GAP;
            let ie = ib + idx_count * 2;
            let vb = ie;
            let ve = vb + vtx_count * decl.stride;
            if ve > bytes.len() {
                return Err(MeshError::UnsupportedLayout);
            }

            // Indices (u16 BE), validated against the sub-mesh vertex count.
            let mut indices = Vec::with_capacity(idx_count);
            for k in 0..idx_count {
                let i = be16(bytes, ib + k * 2) as u32;
                if i >= vtx_count as u32 {
                    return Err(MeshError::UnsupportedLayout);
                }
                indices.push(i);
            }

            // Vertices per the declaration. The .xpr stores each element in
            // naive big-endian component order (f32 / f16 read at consecutive
            // offsets) — the GPU's `k8in32` fetch endianness applies to the
            // rearranged guest-memory copy, not to these file bytes.
            let mut positions = Vec::with_capacity(vtx_count);
            let mut normals = Vec::with_capacity(vtx_count);
            let mut uvs = Vec::with_capacity(vtx_count);
            let mut normal_len_sum = 0.0f32;
            for v in 0..vtx_count {
                let o = vb + v * decl.stride;

                // POSITION: f32×3 big-endian.
                let p = o + decl.pos_offset;
                let x = bef(bytes, p);
                let y = bef(bytes, p + 4);
                let z = bef(bytes, p + 8);
                if !(x.is_finite() && y.is_finite() && z.is_finite()) {
                    return Err(MeshError::UnsupportedLayout);
                }
                positions.push([x, y, z]);

                // NORMAL: f16×4 (use xyz).
                if let Some(no) = decl.normal_offset {
                    let nb = o + no;
                    let nx = half(bytes, nb);
                    let ny = half(bytes, nb + 2);
                    let nz = half(bytes, nb + 4);
                    normal_len_sum += (nx * nx + ny * ny + nz * nz).sqrt();
                    normals.push([nx, ny, nz]);
                }

                // TEXCOORD: f16×2.
                if let Some(uo) = decl.uv_offset {
                    let ub = o + uo;
                    uvs.push([half(bytes, ub), half(bytes, ub + 2)]);
                }
            }

            // Sanity gate: when the declaration has a normal element, a correctly
            // aligned vertex buffer yields unit-length normals. A mean far from 1
            // means the layout does not fit (wrong stride / offset) — decline
            // rather than emit garbage.
            if decl.normal_offset.is_some() {
                let mean = normal_len_sum / vtx_count.max(1) as f32;
                if !(0.5..=2.0).contains(&mean) {
                    return Err(MeshError::UnsupportedLayout);
                }
            }

            meshes.push(GameMesh {
                positions,
                normals,
                uvs,
                indices,
                name: None,
            });
            off = align16(ve) - base;
        }

        Ok(Xbg7Model { name, meshes })
    }

    /// Decode **every** locatable XBG7 geometry resource in a container.
    ///
    /// "Stage" containers (`hidden/resource3d/Stage_*.xpr`) are collections of
    /// many enemy / prop sub-models, each an independent XBG7 resource. Unlike
    /// the single-stream weapon layout (index buffer immediately followed by its
    /// vertex buffer), a stage's index buffers and vertex buffers live in
    /// **separate grouped pools**, and the container stores each resource's
    /// buffer *sizes* (index count via the marker, vertex count 32 bytes before
    /// it) but **not** an explicit data offset — the on-disc block layout is a
    /// separate allocation order we have not reversed.
    ///
    /// Rather than guess that order, each resource's `[index buffer][vertex
    /// buffer]` block is located by **content**: the unique offset in the data
    /// section where (a) all `index_count` indices are `< vertex_count`, (b) the
    /// stored normals are unit length, and (c) the resulting triangles are
    /// non-degenerate with a real spatial extent. This signature is strong
    /// enough to pin a block unambiguously in a multi-megabyte file. Resources
    /// that cannot be located and validated this way are **skipped** (never
    /// emitted as garbage) — including the biggest hero bodies, which use the
    /// same quantized/complex layout that [`Xbg7Model::from_xpr2`] declines.
    ///
    /// Returns one [`Xbg7Model`] per decoded resource (empty if none decode).
    pub fn stage_models(bytes: &[u8]) -> Vec<Xbg7Model> {
        let mut out = Vec::new();
        if bytes.len() < 16 || &bytes[..4] != b"XPR2" {
            return out;
        }
        let mut cur = Cursor::new(bytes);
        let header = match Xpr2Header::read(&mut cur) {
            Ok(h) => h,
            Err(_) => return out,
        };
        let data_base = header.header_size as usize;
        if data_base >= bytes.len() {
            return out;
        }

        // ── Collect every XBG7 resource's parameters up front. ──
        const DIR_BASE: usize = 0x10;
        struct Res {
            name: String,
            index_count: usize,
            vtx_count: usize,
            decl: VertexDecl,
        }
        let mut resources: Vec<Res> = Vec::new();
        for _ in 0..header.num_resources {
            let e = match Xpr2ResourceEntry::read(&mut cur) {
                Ok(e) => e,
                Err(_) => break,
            };
            if &e.type_tag != b"XBG7" {
                continue;
            }
            let desc = e.data_offset as usize + DIR_BASE;
            let desc_end = (desc + e.descriptor_size as usize).min(bytes.len());
            if desc >= bytes.len() || desc_end <= desc {
                continue;
            }
            let d = &bytes[desc..desc_end];
            let (mk_rel, index_count) = match find_index_marker(d) {
                Some(m) => m,
                None => continue,
            };
            let decl = match parse_vertex_decl(d) {
                Some(v) => v,
                None => continue,
            };
            // Total vertex count is stored 32 bytes before the index marker.
            if mk_rel < 32 {
                continue;
            }
            let vtx_count = be32(d, mk_rel - 32) as usize;
            if !(3..=400_000).contains(&vtx_count) || index_count < 3 {
                continue;
            }
            // Anchoring relies on the unit-normal signature; skip resources with
            // no NORMAL element (too ambiguous to pin safely).
            if decl.normal_offset.is_none() {
                continue;
            }
            let name = read_cstr(bytes, e.name_offset as usize + DIR_BASE)
                .unwrap_or_else(|| "XBG7".to_string());
            resources.push(Res {
                name,
                index_count,
                vtx_count,
                decl,
            });
        }
        if resources.is_empty() {
            return out;
        }

        // ── One O(file) pass per distinct stride: find vertex-block *starts*. ──
        //
        // Each geometry block is `[12B header][index buffer][vertex buffer]`, and
        // the blocks are scattered among texture data with no stored offset. But
        // a vertex buffer is a run of stride-sized records whose NORMAL (f16×4 at
        // +12) is unit length; a *block start* is the unique offset where that
        // run begins — the previous stride slot is NOT a unit-normal vertex (it's
        // index bytes / header). Collecting those starts turns the per-resource
        // search from O(file) into a scan of a few hundred candidates.
        let mut strides: Vec<usize> = resources.iter().map(|r| r.decl.stride).collect();
        strides.sort_unstable();
        strides.dedup();
        let mut starts_by_stride: std::collections::BTreeMap<usize, Vec<usize>> =
            std::collections::BTreeMap::new();
        for &s in &strides {
            starts_by_stride.insert(s, vertex_run_starts(bytes, data_base, s));
        }

        for r in &resources {
            let starts = &starts_by_stride[&r.decl.stride];
            if let Some(mesh) = anchor_pool_mesh(
                bytes,
                starts,
                r.index_count,
                r.vtx_count,
                &r.decl,
            ) {
                out.push(Xbg7Model {
                    name: r.name.clone(),
                    meshes: vec![mesh],
                });
            }
        }
        out
    }
}

/// Scan the data section for offsets that begin a `stride`-sized unit-normal
/// vertex run (NORMAL is `f16×4` at vertex offset +12). A run *start* is an
/// offset whose normal is unit while the preceding stride slot's is not — i.e.
/// the first vertex of a buffer, not a mid-buffer position. Returns the sorted
/// candidate starts (block vertex-buffer offsets).
fn vertex_run_starts(bytes: &[u8], data_base: usize, stride: usize) -> Vec<usize> {
    const NRM: usize = 12; // POSITION f32×3 occupies [0,12); NORMAL f16×4 follows
    let mut starts = Vec::new();
    if stride < NRM + 8 {
        return starts;
    }
    let is_unit = |o: usize| -> bool {
        if o + NRM + 6 > bytes.len() {
            return false;
        }
        let nx = half(bytes, o + NRM);
        let ny = half(bytes, o + NRM + 2);
        let nz = half(bytes, o + NRM + 4);
        let l = (nx * nx + ny * ny + nz * nz).sqrt();
        (0.85..=1.15).contains(&l)
    };
    // Vertex buffers begin on 4-byte boundaries in practice; step 4.
    let end = bytes.len().saturating_sub(NRM + 6);
    let mut o = data_base;
    while o <= end {
        if is_unit(o) && (o < data_base + stride || !is_unit(o - stride)) {
            starts.push(o);
        }
        o += 4;
    }
    starts
}

/// Locate a stage resource's `[index buffer][vertex buffer]` block among the
/// precomputed vertex-run `starts` (see [`vertex_run_starts`]) and decode it, or
/// return `None` if no candidate validates. A candidate `vb` is accepted when
/// the `index_count` indices ending just before it are all `< vtx_count`,
/// reference (nearly) all vertices, and produce non-degenerate triangles with a
/// real spatial extent — a signature strong enough to pin the block.
fn anchor_pool_mesh(
    bytes: &[u8],
    starts: &[usize],
    index_count: usize,
    vtx_count: usize,
    decl: &VertexDecl,
) -> Option<GameMesh> {
    let stride = decl.stride;
    let idx_bytes = index_count * 2;
    let vtx_bytes = vtx_count.checked_mul(stride)?;

    for &vb in starts {
        // The index buffer sits immediately before the vertex buffer.
        if vb < idx_bytes {
            continue;
        }
        let ib = vb - idx_bytes;
        if vb + vtx_bytes > bytes.len() {
            continue;
        }

        // ── Full index validation: every index in range, uses ~all vertices. ──
        let mut max_idx = 0u32;
        let mut ok = true;
        for k in 0..index_count {
            let i = be16(bytes, ib + k * 2) as u32;
            if i >= vtx_count as u32 {
                ok = false;
                break;
            }
            max_idx = max_idx.max(i);
        }
        if !ok || (max_idx as usize) + 4 < vtx_count {
            continue;
        }

        // ── Triangle quality: finite, non-degenerate, real spatial extent. ──
        let pos = decl.pos_offset;
        let mut lo = [f32::MAX; 3];
        let mut hi = [f32::MIN; 3];
        let mut degenerate = 0usize;
        let mut sampled = 0usize;
        let mut edge_sum = 0.0f32;
        let tris = index_count / 3;
        let tstep = (tris / 96).max(1);
        let mut t = 0;
        let mut bad = false;
        while t < tris {
            let mut p = [[0.0f32; 3]; 3];
            for (c, pc) in p.iter_mut().enumerate() {
                let vi = be16(bytes, ib + (3 * t + c) * 2) as usize;
                let base = vb + vi * stride + pos;
                for (a, slot) in pc.iter_mut().enumerate() {
                    let x = bef(bytes, base + a * 4);
                    if !x.is_finite() || x.abs() > 1.0e6 {
                        bad = true;
                        break;
                    }
                    *slot = x;
                    lo[a] = lo[a].min(x);
                    hi[a] = hi[a].max(x);
                }
                if bad {
                    break;
                }
            }
            if bad {
                break;
            }
            let u = [p[1][0] - p[0][0], p[1][1] - p[0][1], p[1][2] - p[0][2]];
            let w = [p[2][0] - p[0][0], p[2][1] - p[0][1], p[2][2] - p[0][2]];
            let cx = [
                u[1] * w[2] - u[2] * w[1],
                u[2] * w[0] - u[0] * w[2],
                u[0] * w[1] - u[1] * w[0],
            ];
            if 0.5 * (cx[0] * cx[0] + cx[1] * cx[1] + cx[2] * cx[2]).sqrt() < 1.0e-9 {
                degenerate += 1;
            }
            // Sum the triangle's three edge lengths (for the connectivity check).
            let e3 = [p[2][0] - p[1][0], p[2][1] - p[1][1], p[2][2] - p[1][2]];
            edge_sum += (u[0] * u[0] + u[1] * u[1] + u[2] * u[2]).sqrt()
                + (w[0] * w[0] + w[1] * w[1] + w[2] * w[2]).sqrt()
                + (e3[0] * e3[0] + e3[1] * e3[1] + e3[2] * e3[2]).sqrt();
            sampled += 1;
            t += tstep;
        }
        if bad {
            continue;
        }
        let extent = (hi[0] - lo[0]).max(hi[1] - lo[1]).max(hi[2] - lo[2]);
        if extent < 0.5 || sampled == 0 || degenerate * 10 > sampled * 3 {
            continue; // too flat, or >30% degenerate → not this block
        }
        // Connectivity check: a correctly-anchored mesh has triangle edges that
        // are SMALL relative to its overall size (~0.05–0.15 of the bbox
        // diagonal). A wrong anchor / cross-wired index buffer connects distant
        // vertices, so its mean edge spans a large fraction of the model (a spiky
        // mess). Reject those — try another candidate or decline.
        let diag = ((hi[0] - lo[0]).powi(2) + (hi[1] - lo[1]).powi(2) + (hi[2] - lo[2]).powi(2))
            .sqrt()
            .max(1e-6);
        let mean_edge = edge_sum / (sampled as f32 * 3.0);
        if mean_edge / diag > 0.28 {
            continue;
        }

        // ── Accepted: read the full mesh. ──
        return Some(read_pool_mesh(bytes, ib, vb, index_count, vtx_count, decl));
    }
    None
}

/// Read positions / normals / uvs / indices for an anchored stage block.
fn read_pool_mesh(
    bytes: &[u8],
    ib: usize,
    vb: usize,
    index_count: usize,
    vtx_count: usize,
    decl: &VertexDecl,
) -> GameMesh {
    let stride = decl.stride;
    let indices: Vec<u32> = (0..index_count)
        .map(|k| be16(bytes, ib + k * 2) as u32)
        .collect();

    let mut positions = Vec::with_capacity(vtx_count);
    let mut normals = Vec::with_capacity(vtx_count);
    let mut uvs = Vec::with_capacity(vtx_count);
    for v in 0..vtx_count {
        let o = vb + v * stride;
        let p = o + decl.pos_offset;
        positions.push([bef(bytes, p), bef(bytes, p + 4), bef(bytes, p + 8)]);
        if let Some(no) = decl.normal_offset {
            let nb = o + no;
            normals.push([half(bytes, nb), half(bytes, nb + 2), half(bytes, nb + 4)]);
        }
        if let Some(uo) = decl.uv_offset {
            let ub = o + uo;
            uvs.push([half(bytes, ub), half(bytes, ub + 2)]);
        }
    }
    GameMesh {
        positions,
        normals,
        uvs,
        indices,
        name: None,
    }
}

// ── Layout constants ────────────────────────────────────────────────────────

/// Size of the header that precedes each sub-mesh block's index buffer
/// (`[12-byte header][index buffer][vertex buffer]`). Contents not yet decoded.
const VERTEX_BUFFER_GAP: usize = 12;

// ── Vertex declaration ───────────────────────────────────────────────────────

/// The vertex layout for one XBG7 resource, parsed from the descriptor's
/// declaration table (shared by all its sub-meshes).
struct VertexDecl {
    /// Bytes per vertex.
    stride: usize,
    /// Byte offset of the POSITION element (`f32×3`) within a vertex.
    pos_offset: usize,
    /// Byte offset of the NORMAL element (`f16×4`), if present.
    normal_offset: Option<usize>,
    /// Byte offset of the TEXCOORD element (`f16×2`), if present.
    uv_offset: Option<usize>,
}

/// Known element format codes → element size in bytes (from the GPU capture:
/// POSITION `f32×3`, NORMAL `f16×4`, TEXCOORD `f16×2`).
fn decl_code_size(code: u32) -> Option<usize> {
    match code {
        0x2A_23B9 => Some(12), // f32×3  (POSITION)
        0x1A_2360 => Some(8),  // f16×4  (NORMAL)
        0x2C_235F => Some(4),  // f16×2  (TEXCOORD)
        _ => None,
    }
}

/// Parse the XBG7 vertex declaration: a table of `{offset:u32, code:u32,
/// usage<<16:u32}` big-endian triples that follows the `(index_bytes,
/// index_count)` marker, terminated by an `offset == 0x00FF0000` /
/// `code == 0xFFFFFFFF` sentinel. Usage codes: `0` POSITION, `3` NORMAL,
/// `5` TEXCOORD. Stride is the max element extent; unknown element sizes are
/// inferred from the next element's offset.
/// Locate the `(index_bytes, index_count)` marker in a descriptor: the first
/// big-endian pair where `index_bytes == index_count * 2` and `index_count` is a
/// positive multiple of 3. Returns `(rel_offset, index_count)`.
fn find_index_marker(desc: &[u8]) -> Option<(usize, usize)> {
    let mut rel = 0usize;
    while rel + 40 <= desc.len() {
        let a = be32(desc, rel);
        let c = be32(desc, rel + 4);
        if c >= 3 && c % 3 == 0 && c < 400_000 && a == c * 2 {
            return Some((rel, c as usize));
        }
        rel += 4;
    }
    None
}

fn parse_vertex_decl(desc: &[u8]) -> Option<VertexDecl> {
    let mk = find_index_marker(desc)?.0;

    // Read declaration triples.
    let mut elems: Vec<(usize, u32, u32)> = Vec::new(); // (offset, code, usage)
    let mut r = mk + 8;
    for _ in 0..16 {
        if r + 12 > desc.len() {
            break;
        }
        let off = be32(desc, r);
        let code = be32(desc, r + 4);
        let usage = be32(desc, r + 8) >> 16;
        if off == 0x00FF_0000 || code == 0xFFFF_FFFF {
            break;
        }
        if off as usize > 0x1000 {
            break; // out-of-range offset — not a real element
        }
        elems.push((off as usize, code & 0x00FF_FFFF, usage));
        r += 12;
    }
    if elems.is_empty() {
        return None;
    }

    let mut stride = 0usize;
    for (i, &(off, code, _)) in elems.iter().enumerate() {
        let size = decl_code_size(code).unwrap_or_else(|| {
            if i + 1 < elems.len() {
                elems[i + 1].0.saturating_sub(off)
            } else {
                4
            }
        });
        stride = stride.max(off + size);
    }
    if stride == 0 || stride > 256 {
        return None;
    }

    let pos_offset = elems
        .iter()
        .find(|&&(_, c, u)| c == 0x2A_23B9 || u == 0)
        .map(|&(o, _, _)| o)
        .unwrap_or(0);
    let normal_offset = elems.iter().find(|&&(_, _, u)| u == 3).map(|&(o, _, _)| o);
    let uv_offset = elems.iter().find(|&&(_, _, u)| u == 5).map(|&(o, _, _)| o);

    Some(VertexDecl {
        stride,
        pos_offset,
        normal_offset,
        uv_offset,
    })
}

// ── Descriptor sub-mesh record scan ─────────────────────────────────────────

/// Scan an XBG7 descriptor for the ordered list of per-sub-mesh
/// `(vtx_count, idx_count)` records.
///
/// The record is a big-endian tuple `[vtx:u32][0:u32][idx:u32][tail:u32]` with
/// `3 ≤ vtx ≤ 65535`, the second word zero, `idx` a positive multiple of 3, and
/// a small non-zero `tail`.  Found by a sliding 4-byte scan (records are not on
/// a fixed stride in the scene graph).
fn submesh_records(desc: &[u8]) -> Vec<(usize, usize)> {
    let mut out = Vec::new();
    if desc.len() < 16 {
        return out;
    }
    let mut rel = 0usize;
    while rel + 16 <= desc.len() {
        let a = be32(desc, rel);
        let z = be32(desc, rel + 4);
        let c = be32(desc, rel + 8);
        let t = be32(desc, rel + 12);
        if (3..=65535).contains(&a)
            && z == 0
            && c >= 3
            && c <= 200_000
            && c % 3 == 0
            && (1..=64).contains(&t)
        {
            out.push((a as usize, c as usize));
            rel += 16; // consume the record
        } else {
            rel += 4;
        }
    }
    out
}

// ── Little primitive readers ────────────────────────────────────────────────

#[inline]
fn align16(x: usize) -> usize {
    (x + 15) & !15
}
#[inline]
fn be16(b: &[u8], o: usize) -> u16 {
    u16::from_be_bytes([b[o], b[o + 1]])
}
#[inline]
fn be32(b: &[u8], o: usize) -> u32 {
    u32::from_be_bytes([b[o], b[o + 1], b[o + 2], b[o + 3]])
}
#[inline]
fn bef(b: &[u8], o: usize) -> f32 {
    f32::from_be_bytes([b[o], b[o + 1], b[o + 2], b[o + 3]])
}
/// Big-endian IEEE-754 half → f32.
#[inline]
fn half(b: &[u8], o: usize) -> f32 {
    f16_to_f32(be16(b, o))
}

/// Minimal IEEE-754 binary16 → binary32 (no external dep).
fn f16_to_f32(h: u16) -> f32 {
    let sign = (h >> 15) & 1;
    let exp = (h >> 10) & 0x1F;
    let mant = h & 0x3FF;
    let bits: u32 = match exp {
        0 if mant == 0 => (sign as u32) << 31, // ±0
        0 => {
            // subnormal → normalize
            let mut e: i32 = -1;
            let mut m = mant as u32;
            loop {
                e += 1;
                m <<= 1;
                if m & 0x400 != 0 {
                    break;
                }
            }
            let exp32 = (127 - 15 - e) as u32;
            ((sign as u32) << 31) | (exp32 << 23) | ((m & 0x3FF) << 13)
        }
        0x1F => ((sign as u32) << 31) | (0xFF << 23) | ((mant as u32) << 13), // Inf/NaN
        _ => {
            let exp32 = (exp as i32 - 15 + 127) as u32;
            ((sign as u32) << 31) | (exp32 << 23) | ((mant as u32) << 13)
        }
    };
    f32::from_bits(bits)
}

fn read_cstr(b: &[u8], o: usize) -> Option<String> {
    if o >= b.len() {
        return None;
    }
    let end = b[o..].iter().position(|&c| c == 0).map(|p| o + p)?;
    if end == o {
        return None;
    }
    Some(String::from_utf8_lossy(&b[o..end]).into_owned())
}

// ── Tests ───────────────────────────────────────────────────────────────────

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

    #[test]
    fn half_roundtrip_known_values() {
        assert_eq!(f16_to_f32(0x3C00), 1.0); // 1.0
        assert_eq!(f16_to_f32(0x0000), 0.0); // +0
        assert_eq!(f16_to_f32(0xBC00), -1.0); // -1.0
        assert_eq!(f16_to_f32(0x4000), 2.0); // 2.0
        assert!((f16_to_f32(0x3800) - 0.5).abs() < 1e-6); // 0.5
    }

    #[test]
    fn submesh_record_scan_finds_tuple() {
        // [vtx=215][0][idx=1092][tail=4]
        let mut d = vec![0u8; 32];
        d[0..4].copy_from_slice(&215u32.to_be_bytes());
        d[8..12].copy_from_slice(&1092u32.to_be_bytes());
        d[12..16].copy_from_slice(&4u32.to_be_bytes());
        let recs = submesh_records(&d);
        assert_eq!(recs, vec![(215, 1092)]);
    }

    #[test]
    fn rejects_non_xpr2() {
        assert!(matches!(
            Xbg7Model::from_xpr2(b"NOPEnotacontainerXXXXXXXX"),
            Err(MeshError::NotXpr2)
        ));
    }
}