//! How much geometry on the disc was being read one index element late?
//!
//! The pad-scoring fix (2026-08-13) makes `anchor_pool_mesh` choose the pad whose
//! index run is cleanest instead of the first that validates. This measures the
//! blast radius: per container, how many single-block resources now decode from a
//! run that is NOT the old first-match (`pad 0`) one, and how many decoded runs
//! still contain degenerate triangles (the shift signature) afterwards.
//!
//! Usage: pad_shift_audit <resource3d_dir>
use sylpheed_formats::mesh::Xbg7Model;

fn be16(b: &[u8], at: usize) -> u32 {
    ((b[at] as u32) << 8) | b[at + 1] as u32
}

/// Fraction of triangles whose face normal agrees with the stored normals,
/// folded to `max(na, 1-na)` so both authored windings read as ≈1.
fn winding(idx: &[u32], pos: &[[f32; 3]], nrm: &[[f32; 3]]) -> f32 {
    let (mut agree, mut n) = (0usize, 0usize);
    for t in idx.chunks_exact(3) {
        let (a, b, c) = (t[0] as usize, t[1] as usize, t[2] as usize);
        if a == b || b == c || a == c || a.max(b).max(c) >= pos.len() || a >= nrm.len() {
            continue;
        }
        let e1 = [pos[b][0] - pos[a][0], pos[b][1] - pos[a][1], pos[b][2] - pos[a][2]];
        let e2 = [pos[c][0] - pos[a][0], pos[c][1] - pos[a][1], pos[c][2] - pos[a][2]];
        let f = [
            e1[1] * e2[2] - e1[2] * e2[1],
            e1[2] * e2[0] - e1[0] * e2[2],
            e1[0] * e2[1] - e1[1] * e2[0],
        ];
        let nv = nrm[a];
        n += 1;
        if f[0] * nv[0] + f[1] * nv[1] + f[2] * nv[2] > 0.0 {
            agree += 1;
        }
    }
    if n == 0 {
        return 1.0;
    }
    let fr = agree as f32 / n as f32;
    fr.max(1.0 - fr)
}

fn degenerate(idx: &[u32]) -> usize {
    idx.chunks_exact(3)
        .filter(|t| t[0] == t[1] || t[1] == t[2] || t[0] == t[2])
        .count()
}

fn main() {
    let dir = std::env::args().nth(1).expect("resource3d dir");
    let mut files: Vec<_> = std::fs::read_dir(&dir)
        .unwrap()
        .flatten()
        .map(|e| e.path())
        .filter(|p| p.extension().and_then(|s| s.to_str()) == Some("xpr"))
        .collect();
    files.sort();

    let (mut total, mut moved, mut still_degen) = (0usize, 0usize, 0usize);
    let mut weak = 0usize;
    let mut weak_wind: Vec<(f32, f32, String)> = Vec::new();
    let mut worst: Vec<(usize, String, String)> = Vec::new();
    for f in &files {
        let Ok(bytes) = std::fs::read(f) else { continue };
        let where_ = f.file_name().unwrap().to_string_lossy().to_string();
        let mut c_moved = 0usize;
        for m in Xbg7Model::stage_models(&bytes) {
            if m.meshes.len() != 1 {
                continue;
            }
            let sm = &m.meshes[0];
            let Some(vb) = sm.vbuf_offset else { continue };
            let n = sm.indices.len();
            if n < 6 || vb < n * 2 {
                continue;
            }
            total += 1;
            let pad0: Vec<u32> = (0..n).map(|k| be16(&bytes, vb - n * 2 + k * 2)).collect();
            if pad0 != sm.indices {
                moved += 1;
                c_moved += 1;
                // How strong was the evidence for moving? A pad-0 run with
                // degenerate triangles is a decisive shift signature; one with
                // none moved on winding alone, which is weaker.
                if degenerate(&pad0) == 0 {
                    weak += 1;
                    // Record how far apart the two runs' winding is, to see
                    // whether these look like the same shift signature as the
                    // decisive cases (pad-0 winding drifting toward 0.5) or like
                    // noise between two equally clean readings.
                    let w0 = winding(&pad0, &sm.positions, &sm.normals);
                    let w2: f32 = {
                        let l2: Vec<u32> = (0..n).map(|k| be16(&bytes, vb - n * 2 - 2 + k * 2)).collect();
                        winding(&l2, &sm.positions, &sm.normals)
                    };
                    weak_wind.push((w0, w2, m.name.clone()));
                }
            }
            let d = degenerate(&sm.indices);
            if d > 0 {
                still_degen += 1;
                worst.push((d, m.name.clone(), where_.clone()));
            }
        }
        if c_moved > 0 {
            println!("{where_:<24} {c_moved} resources read from a non-pad-0 index run");
        }
    }
    println!("\n{moved} of {total} single-block resources moved off the pad-0 run");
    println!("{still_degen} decoded runs still contain a degenerate triangle");
    println!("of the moved, {weak} had a pad-0 run with no degenerate triangle (moved on winding alone)");
    let clear = weak_wind.iter().filter(|(w0, w2, _)| *w2 - *w0 > 0.15).count();
    let close = weak_wind.iter().filter(|(w0, w2, _)| (*w2 - *w0).abs() <= 0.05).count();
    println!("  of those: {clear} show the shift signature (pad-2 winding > pad-0 by >0.15), {close} are within 0.05 (noise)");
    for (w0, w2, n) in weak_wind.iter().take(8) {
        println!("    {n}: pad0 wind {w0:.3} -> pad2 {w2:.3}");
    }
    worst.sort_by_key(|(d, _, _)| std::cmp::Reverse(*d));
    for (d, n, w) in worst.iter().take(15) {
        println!("  {n} ({w}): {d} degenerate triangles");
    }
}