//! Do our decoded triangle indices equal the ones the GPU actually read?
//!
//! `capture_ib_truth` established *where* a block's index buffer lives and that
//! its length matches ours. This asks the stronger question: are the index VALUES
//! the same, in the same order? The capture prints the first 24 indices of every
//! draw batch verbatim (`idx: …`), and a batch's `ibase` locates it inside the
//! block's index buffer — so for each drawn buffer we can line the captured run
//! up against `GameMesh::indices` at the right offset and compare element by
//! element. That tests the whole index path at once: the anchor, the u16
//! big-endian read, the triangle-list interpretation (a strip would disagree
//! immediately), and the sub-mesh carve.
//!
//! Usage:
//!   cargo run --release --example capture_index_bytes -- <Stage_SNN.xpr> <capture.log>...
use sylpheed_formats::mesh::Xbg7Model;
use sylpheed_formats::ship_capture::{parse_capture, CapturedDraw};
use std::collections::HashMap;

fn q(v: f32) -> i64 {
    (v as f64 * 1e4).round() as i64
}

fn main() {
    let a: Vec<String> = std::env::args().collect();
    if a.len() < 3 {
        eprintln!("usage: capture_index_bytes <container.xpr> <capture.log>...");
        std::process::exit(2);
    }
    let bytes = std::fs::read(&a[1]).expect("container");

    let mut draws: Vec<CapturedDraw> = Vec::new();
    let mut seen = std::collections::HashSet::new();
    for log in &a[2..] {
        let text = std::fs::read_to_string(log).expect("log");
        for d in parse_capture(&text) {
            let k = d.ib.map(|i| (i.ibase, i.icount)).unwrap_or((0, 0));
            if d.ib.map_or(false, |i| i.head_len > 0) && d.pos.len() >= 4 && seen.insert((log.clone(), d.vbase, k)) {
                draws.push(d);
            }
        }
    }
    eprintln!("{} draw batches with an index head", draws.len());

    // Place each drawn buffer in the file by its dumped positions (see
    // capture_ib_truth for the method) and keep the modal load constant.
    let be = |at: usize| f32::from_be_bytes(bytes[at..at + 4].try_into().unwrap());
    let mut index: HashMap<(i64, i64, i64), Vec<u32>> = HashMap::new();
    let mut o = 0usize;
    while o + 12 <= bytes.len() {
        let (x, y, z) = (be(o), be(o + 4), be(o + 8));
        if x.is_finite() && y.is_finite() && z.is_finite() && x.abs() < 1e6 && y.abs() < 1e6 && z.abs() < 1e6 {
            index.entry((q(x), q(y), q(z))).or_default().push(o as u32);
        }
        o += 4;
    }
    let mut deltas: HashMap<i64, usize> = HashMap::new();
    let mut hits: Vec<(i64, usize, &CapturedDraw)> = Vec::new();
    for d in &draws {
        let k = (q(d.pos[0][0]), q(d.pos[0][1]), q(d.pos[0][2]));
        for dx in -1..=1i64 {
            for dy in -1..=1i64 {
                for dz in -1..=1i64 {
                    let Some(cands) = index.get(&(k.0 + dx, k.1 + dy, k.2 + dz)) else { continue };
                    for &off in cands {
                        for stride in (12..=64).step_by(4) {
                            let ok = (1..4).all(|j| {
                                let at = off as usize + j * stride;
                                at + 12 <= bytes.len()
                                    && (0..3).all(|c| (be(at + c * 4) - d.pos[j][c]).abs() <= 1e-4)
                            });
                            if ok {
                                *deltas.entry(d.vbase as i64 - off as i64).or_default() += 1;
                                hits.push((d.vbase as i64 - off as i64, off as usize, d));
                                break;
                            }
                        }
                    }
                }
            }
        }
    }
    let Some((&base_delta, _)) = deltas.iter().max_by_key(|(_, n)| **n) else {
        eprintln!("no draw could be placed in this container");
        std::process::exit(1);
    };
    println!("load constant 0x{base_delta:X}");

    // Our decode, indexed by vertex offset. A model may hold several sub-meshes;
    // compare against the one whose vertex count matches the draw.
    let models = Xbg7Model::stage_models(&bytes);
    let mut by_off: HashMap<usize, Vec<(String, usize, Vec<u32>)>> = HashMap::new();
    for m in &models {
        for sm in &m.meshes {
            if let Some(off) = sm.vbuf_offset {
                by_off
                    .entry(off)
                    .or_default()
                    .push((m.name.clone(), sm.positions.len(), sm.indices.clone()));
            }
        }
    }

    // Where does each buffer's index data START? Take it from the capture, not
    // from an assumed pad: `capture_ib_truth` established that a buffer's batches
    // tile its index buffer exactly (sum of counts == our idx_count, span ==
    // 2*count), so the lowest `ibase` over a buffer's batches IS the block's
    // index start. Assuming `vb - 2*len` instead is wrong for the buffers that
    // sit at pad 2 and shifts the whole comparison by one element.
    let mut ib_start: HashMap<u32, i64> = HashMap::new();
    for (delta, _, d) in &hits {
        if *delta != base_delta {
            continue;
        }
        let ibase = d.ib.unwrap().ibase as i64;
        ib_start.entry(d.vbase).and_modify(|e| *e = (*e).min(ibase)).or_insert(ibase);
    }

    let (mut agree, mut disagree, mut unmatched, mut nooverlap) = (0usize, 0usize, 0usize, 0usize);
    let mut bad: Vec<String> = Vec::new();
    let mut checked_elems = 0usize;
    let mut done: std::collections::HashSet<(u32, u32)> = std::collections::HashSet::new();
    for (delta, voff, d) in &hits {
        if *delta != base_delta {
            continue;
        }
        let ib = d.ib.unwrap();
        if !done.insert((d.vbase, ib.ibase)) {
            continue;
        }
        let Some(cands) = by_off.get(voff) else {
            unmatched += 1;
            continue;
        };
        let Some((name, _, ours)) = cands.iter().find(|(_, p, _)| *p as u32 == d.vcount) else {
            unmatched += 1;
            continue;
        };
        // Element 0 of our index list is the block's index start, as observed.
        let ours_start = ib_start[&d.vbase] - base_delta;
        let batch_off = ib.ibase as i64 - base_delta - ours_start;
        if batch_off < 0 || batch_off % 2 != 0 {
            nooverlap += 1;
            continue;
        }
        let first = (batch_off / 2) as usize;
        let n = (ib.head_len as usize).min(ours.len().saturating_sub(first));
        if n == 0 {
            nooverlap += 1;
            continue;
        }
        let mism = (0..n).find(|&k| ours[first + k] != ib.head[k]);
        checked_elems += n;
        match mism {
            None => agree += 1,
            Some(k) => {
                disagree += 1;
                if bad.len() < 8 {
                    bad.push(format!(
                        "{name} vb 0x{:07X} batch@{first}: ours {:?} != captured {:?} (first differs at {k})",
                        voff,
                        &ours[first..first + n.min(12)],
                        &ib.head[..n.min(12)]
                    ));
                }
            }
        }
    }
    println!(
        "index runs compared: {agree} identical · {disagree} differing · {unmatched} no decoded resource · {nooverlap} batch outside our buffer"
    );
    println!("{checked_elems} index elements checked against the GPU");
    for b in &bad {
        println!("  MISMATCH {b}");
    }
}