Sylpheed/crates/sylpheed-formats/examples/capture_ib_truth.rs

//! Where does a drawn block's INDEX buffer really live?
//!
//! Our XBG7 anchor scan only ever *assumes* the layout `[index buffer][vertex
//! buffer]` with a pad of at most 3 bytes between them (`anchor_pool_mesh`:
//! `ib = vb - idx_count*2 - pad`). Nothing on disc states it, and it is the gate
//! that rejected the capture-proven `e106_eng_02_l` block
//! (docs/re/captures/…): the block's index data was not where the decoder
//! looked. The F10 ship capture was extended on 2026-08-13 to log each draw's
//! index-buffer base, count and min/max index value, so the assumption is now
//! directly checkable:
//!
//!   * `vbase - ibase` is the real gap in guest memory, and a stage container is
//!     uploaded contiguously (see `shared_vbase_check`), so the same difference
//!     holds in the file;
//!   * `max index vs vcount` says whether a draw covers its whole vertex pool —
//!     the "buffer not covered" miss class is a *sub-range draw* if it does not.
//!
//! Usage:
//!   cargo run --release --example capture_ib_truth -- <Stage_SNN.xpr> <capture.log>...
use std::collections::HashMap;
use sylpheed_formats::mesh::{debug_resource_params, xbg7_resource_names, Xbg7Model};
use sylpheed_formats::ship_capture::{parse_capture, CapturedDraw};

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_ib_truth <container.xpr> <capture.log>...");
        std::process::exit(2);
    }
    let bytes = std::fs::read(&a[1]).expect("container");

    // One entry per (log, vbase): the capture already de-dups per placement, and
    // a buffer drawn at several transforms has the same index buffer each time.
    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) {
            // One entry per (log, vbase, index range): the engine issues SEVERAL
            // draws over one vertex buffer, each with its own index sub-range, and
            // it is their UNION that describes the block. (Captures taken before
            // 2026-08-13 de-dup by (vbase, transform) and so hold only the first
            // batch — such a log reads as a mysteriously short draw.)
            let k = d.ib.map(|i| (i.ibase, i.icount)).unwrap_or((0, 0));
            if d.ib.is_some() && d.pos.len() >= 4 && seen.insert((log.clone(), d.vbase, k)) {
                draws.push(d);
            }
        }
    }
    eprintln!("{} drawn buffers with an index buffer", draws.len());

    // ── Place the drawn buffers in the file: POSITION is f32×3 big-endian at
    // vertex offset 0, so the dumped positions are a literal byte pattern.
    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(); // (delta, file offset, draw)
    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 {
                                let delta = d.vbase as i64 - off as i64;
                                *deltas.entry(delta).or_default() += 1;
                                hits.push((delta, off as usize, d));
                                break;
                            }
                        }
                    }
                }
            }
        }
    }
    let Some((&base_delta, &n)) = deltas.iter().max_by_key(|(_, n)| **n) else {
        eprintln!("no draw could be placed in this container");
        std::process::exit(1);
    };
    println!(
        "container load constant: vbase - file_offset = 0x{base_delta:X}  ({n} buffers agree)"
    );

    // ── Our decoder's view of the same container.
    let models = Xbg7Model::stage_models(&bytes);
    let mut by_off: HashMap<usize, Vec<(String, usize, usize)>> = 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.len(),
                ));
            }
        }
    }
    println!(
        "decoded {} resources, {} distinct vertex offsets\n",
        models.len(),
        by_off.len()
    );

    // Declared-but-not-decoded resources, indexed by their first marker's
    // (vertex, index) counts. A drawn buffer our decoder cannot name is the one
    // thing a capture can give the residual misses: ground truth for where the
    // block actually is. Matching on counts is enough to propose an identity —
    // then `debug_try_anchor` at that offset says which gate rejects it.
    let decoded_names: std::collections::HashSet<String> =
        models.iter().map(|m| m.name.clone()).collect();
    let mut undecoded_by_counts: HashMap<(usize, usize), Vec<String>> = HashMap::new();
    for n in xbg7_resource_names(&bytes) {
        if decoded_names.contains(&n) {
            continue;
        }
        if let Some((markers, _)) = debug_resource_params(&bytes, &n) {
            if let Some(&(v, i)) = markers.first() {
                undecoded_by_counts.entry((v, i)).or_default().push(n);
            }
        }
    }

    // ── The report: one row per drawn BUFFER, aggregating its index batches.
    let mut per_buf: HashMap<
        u32,
        (
            usize,
            Vec<sylpheed_formats::ship_capture::CapturedIndexBuffer>,
            u32,
        ),
    > = HashMap::new();
    for (delta, voff, d) in &hits {
        if *delta != base_delta {
            continue;
        }
        let e = per_buf
            .entry(d.vbase)
            .or_insert((*voff, Vec::new(), d.vcount));
        let ib = d.ib.unwrap();
        if !e.1.contains(&ib) {
            e.1.push(ib);
        }
    }

    let (mut pad0, mut pad_small, mut pad_off, mut unnamed) = (0usize, 0usize, 0usize, 0usize);
    let (mut cover_exact, mut cover_short, mut idx_equal, mut idx_partial) =
        (0usize, 0usize, 0usize, 0usize);
    let mut rows: Vec<(usize, String)> = Vec::new();
    for (voff, ibs, vcount) in per_buf.values() {
        let batches = ibs.len();
        let total: u32 = ibs.iter().map(|i| i.icount).sum();
        let lo = ibs.iter().map(|i| i.ibase).min().unwrap() as i64 - base_delta;
        let hi = ibs.iter().map(|i| i.ibase + i.icount * 2).max().unwrap() as i64 - base_delta;
        let umax = ibs.iter().map(|i| i.imax).max().unwrap();
        let gap = *voff as i64 - hi; // bytes from the end of the index data to the vertex buffer
        let names = by_off.get(voff);
        let dec_idx = names.and_then(|v| {
            v.iter()
                .find(|(_, p, _)| *p as u32 == *vcount)
                .map(|(_, _, i)| *i as u32)
        });
        // The decoder's assumption, scored: it expects the whole index buffer at
        // `vb - 2*idx_count - pad`, pad ≤ 3.
        let dec_pad = dec_idx.map(|i| *voff as i64 - (i as i64) * 2 - lo);
        match dec_pad {
            Some(0) => pad0 += 1,
            Some(p) if (1..=3).contains(&p) => pad_small += 1,
            Some(_) => pad_off += 1,
            None => unnamed += 1,
        }
        if umax + 1 == *vcount {
            cover_exact += 1;
        } else {
            cover_short += 1;
        }
        match dec_idx {
            Some(i) if i == total => idx_equal += 1,
            Some(_) => idx_partial += 1,
            None => {}
        }
        rows.push((
            *voff,
            format!(
                "vb 0x{:07X} v={:<6} batches {:<3} idx {:<6} span {:<7} gap {:<8} decpad {:<7} cover {:<10} {}",
                voff,
                vcount,
                batches,
                total,
                hi - lo,
                gap,
                dec_pad.map(|p| p.to_string()).unwrap_or_else(|| "?".into()),
                if umax + 1 == *vcount { "exact".to_string() } else { format!("{}/{}", umax, vcount - 1) },
                names
                    .map(|v| v
                        .iter()
                        .map(|(n, p, i)| format!("{n}(v{p},i{i})"))
                        .collect::<Vec<_>>()
                        .join(" "))
                    .unwrap_or_else(|| {
                        // Nothing of ours sits here — is it a resource that never
                        // decodes? Propose it by (vertex, index) counts.
                        undecoded_by_counts
                            .get(&(*vcount as usize, total as usize))
                            .map(|v| format!("MISSED? {}", v.join(" ")))
                            .unwrap_or_else(|| "-".into())
                    })
            ),
        ));
    }
    rows.sort();
    for (_, r) in &rows {
        println!("{r}");
    }
    println!("\nplaced {} drawn buffers in this container", rows.len());
    println!(
        "DECODER layout assumption — whole index buffer at vb - 2*idx_count - pad:  pad 0 {pad0} · pad 1..3 {pad_small} · elsewhere {pad_off} · not decoded here {unnamed}"
    );
    println!(
        "index extent: our idx_count == sum of captured batches for {idx_equal} buffers, differs for {idx_partial}"
    );
    println!(
        "vertex-pool coverage by the union of batches: exact {cover_exact} · short {cover_short}"
    );
}