Syplheed-Reborn/crates/sylpheed-formats/tests/ui_header_time_disc.rs

//! Is the bundle header's `+0x08` really an animation **duration in frames**?
//!
//! The header sweep found `+0x04` takes only `0x3C0000` and `0x1E0000` — exactly
//! `60.0` and `30.0` in 16.16 — and `+0x08` takes 30 / 1200 / 120 / 60, which
//! *looks* like a frame rate and a length. That reading came from the values
//! alone, and this checks it against something the file states independently:
//! the **keyframe times** in the placement region.
//!
//! If `+0x08` is the length of the bundle's animation, the largest keyframe time
//! in the bundle should never exceed it, and should reach it on bundles that
//! animate all the way through. If instead the times run past it, the reading is
//! wrong and the amber has to come off the other way.

use std::collections::HashMap;
use std::path::{Path, PathBuf};

use sylpheed_formats::{pak::PakArchive, ratc, ui_layout};

fn disc_root() -> Option<PathBuf> {
    if let Ok(p) = std::env::var("SYLPHEED_DISC") {
        let p = PathBuf::from(p);
        if p.join("dat").is_dir() {
            return Some(p);
        }
    }
    let default = Path::new(
        "/home/fabi/RE - Project Sylpheed/Project Sylpheed - Arc of Deception (USA, Europe) (En,Ja)",
    );
    if default.join("dat").is_dir() {
        return Some(default.to_path_buf());
    }
    None
}

fn for_each_build(root: &Path, mut f: impl FnMut(&str, &[u8])) {
    let mut paks: Vec<PathBuf> = std::fs::read_dir(root.join("dat"))
        .expect("dat/")
        .flatten()
        .map(|e| e.path())
        .filter(|p| p.extension().and_then(|s| s.to_str()) == Some("pak"))
        .collect();
    paks.sort();
    for p in &paks {
        let name = p.file_name().unwrap().to_string_lossy().to_string();
        let Ok(arc) = PakArchive::open(p) else { continue };
        for e in arc.entries() {
            let Ok(bytes) = arc.read(e) else { continue };
            if ratc::is_ratc(&bytes) {
                f(&name, &bytes);
            }
        }
    }
}

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

#[test]
fn header_0x08_against_the_keyframe_times() {
    let Some(root) = disc_root() else {
        eprintln!("SKIP: extracted disc not found (set SYLPHEED_DISC to enable)");
        return;
    };

    let (mut animated, mut within, mut exact, mut over) = (0usize, 0, 0, 0);
    let mut worst: Vec<String> = Vec::new();
    // How the ratio max_time / header_0x08 is distributed, in tenths.
    let mut ratio: HashMap<u32, usize> = HashMap::new();
    // Does the rate word co-vary with anything?
    let mut by_rate: HashMap<u32, (usize, u32)> = HashMap::new(); // rate -> (bundles, max seen 0x08)
    // The 16.16 frame-rate reading rests on twelve bundles at 30.0. If those are
    // VARIANTS of 60.0 bundles - same elements, different rate - the reading
    // gains a real discriminator; if they are unrelated one-offs it does not.
    let mut odd_rate: Vec<String> = Vec::new();

    for_each_build(&root, |pak, bytes| {
        if bytes.len() < 0x20 {
            return;
        }
        let Some(build) = ui_layout::parse_build(bytes) else {
            return;
        };
        if build.from_fallback {
            return;
        }
        let dur = be32(bytes, 0x08);
        let rate = be32(bytes, 0x04);
        let e = by_rate.entry(rate).or_default();
        e.0 += 1;
        e.1 = e.1.max(dur);

        if rate != 0x3C_0000 && odd_rate.len() < 20 {
            let names: Vec<&str> = build.elements.iter().map(|e| e.name.as_str()).take(6).collect();
            odd_rate.push(format!(
                "{pak}: rate {rate:#x} dur {dur} elements {} {:?}",
                build.elements.len(),
                names
            ));
        }
        let max_time = build
            .elements
            .iter()
            .flat_map(|el| el.keyframes.iter())
            .filter_map(|k| k.time)
            .max();
        let Some(max_time) = max_time else { return };
        if dur == 0 {
            return;
        }
        animated += 1;
        if max_time <= dur {
            within += 1;
            if max_time == dur {
                exact += 1;
            }
        } else {
            over += 1;
            if worst.len() < 10 {
                worst.push(format!("{pak}: max keyframe {max_time} > header {dur}"));
            }
        }
        let r = ((max_time as f64 / dur as f64) * 10.0).round() as u32;
        *ratio.entry(r.min(30)).or_default() += 1;
    });

    eprintln!("bundles with keyframe times and a non-zero +0x08: {animated}");
    eprintln!("  max keyframe time <= +0x08: {within}   of which EXACTLY equal: {exact}");
    eprintln!("  max keyframe time  > +0x08: {over}");
    let mut r: Vec<_> = ratio.iter().collect();
    r.sort();
    eprintln!("  ratio max_time/+0x08 (tenths -> bundles): {r:?}");
    let mut br: Vec<_> = by_rate.iter().collect();
    br.sort();
    eprintln!("  +0x04 rate word -> (bundles, largest +0x08 seen): {br:?}");
    for w in &worst {
        eprintln!("  over: {w}");
    }
    for o in &odd_rate {
        eprintln!("  non-60 rate: {o}");
    }

    assert!(animated > 0, "no animated bundles — the sweep is broken");

    // MEASURED 2026-08-24. +0x08 bounds the keyframe times in EVERY one of the
    // 2313 bundles that have both, and 444 of them reach it exactly. The
    // spread-out ratio histogram is what rules out the boring explanation: a
    // large unrelated constant would bound everything too, but then the ratios
    // would pile up near zero instead of peaking at 1.0.
    assert_eq!(over, 0, "a keyframe time runs past the header's +0x08");
    assert!(exact > 400, "the bound is never attained — it may be unrelated");
    let near_one = ratio.get(&10).copied().unwrap_or(0);
    let near_zero = ratio.get(&0).copied().unwrap_or(0);
    assert!(
        near_one > near_zero * 4,
        "the max_time/+0x08 ratio does not peak at 1.0 — the bound may be vacuous"
    );
}