Sylpheed/crates/sylpheed-formats/tests/ui_screen_vs_fragment_disc.rs

//! Is there a FIELD that says "this bundle is a screen", or only a shape?
//!
//! `is_composable` admits 1 786 more bundles than there are screens, most of
//! them 2–5-element button+glow fragments, and the backlog asks what separates
//! the two. The obvious place to look is the 32-byte bundle header: six words
//! besides the magic and the entry count, none of them read by anything.
//!
//! This sweeps every composable bundle on the disc and asks two questions the
//! same way the `opt `/focus sweeps did — by counting, not by looking at one
//! example:
//!
//!   1. do those six header words ever vary at all?
//!   2. what does the population actually look like — element counts, and how
//!      many carry a full-screen (1280×720) element?
//!
//! A negative on (1) is a real answer: it would mean the file does not label a
//! screen, and a port has to decide by shape or by who references the bundle.

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

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

mod common;
use common::disc_root;

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 the_bundle_header_does_not_label_a_screen() {
    let Some(root) = disc_root() else {
        eprintln!("SKIP: extracted disc not found (set SYLPHEED_DISC to enable)");
        return;
    };

    // header word offset -> value -> how many bundles
    let mut header: HashMap<usize, HashMap<u32, usize>> = HashMap::new();
    let mut bundles = 0usize;
    let mut counts: Vec<usize> = Vec::new();
    let mut with_fullscreen = 0usize;
    // Cross-tabulate the one header word that looks like flags against the two
    // shape signals a "screen" would have: a full-screen element, and size.
    let mut flag_bits: HashMap<u32, (usize, usize, usize)> = HashMap::new(); // bit -> (set, set&fullscreen, set&big)

    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;
        }
        bundles += 1;
        counts.push(build.elements.len());
        if build
            .elements
            .iter()
            .any(|e| (e.pivot_x as u64 * 2, e.pivot_y as u64 * 2) == (1280, 720))
        {
            with_fullscreen += 1;
        }
        let fullscreen = build
            .elements
            .iter()
            .any(|e| (e.pivot_x as u64 * 2, e.pivot_y as u64 * 2) == (1280, 720));
        let big = build.elements.len() >= 10;
        let flags = be32(bytes, 0x10);
        for bit in 0..32u32 {
            if flags & (1 << bit) != 0 {
                let e = flag_bits.entry(bit).or_default();
                e.0 += 1;
                if fullscreen {
                    e.1 += 1;
                }
                if big {
                    e.2 += 1;
                }
            }
        }
        for off in [0x04, 0x08, 0x0c, 0x10, 0x18, 0x1c] {
            *header
                .entry(off)
                .or_default()
                .entry(be32(bytes, off))
                .or_default() += 1;
        }
    });

    counts.sort_unstable();
    let pct = |p: f64| counts[((counts.len() as f64 - 1.0) * p) as usize];
    eprintln!("composable bundles with a real declaration table: {bundles}");
    eprintln!(
        "element counts: min {} p25 {} median {} p75 {} p95 {} max {}",
        counts[0],
        pct(0.25),
        pct(0.50),
        pct(0.75),
        pct(0.95),
        counts[counts.len() - 1]
    );
    eprintln!("bundles carrying a full-screen (1280x720) element: {with_fullscreen}");
    let mut offs: Vec<_> = header.keys().copied().collect();
    offs.sort();
    for off in offs {
        let vals = &header[&off];
        let mut v: Vec<_> = vals.iter().collect();
        v.sort_by_key(|(_, n)| std::cmp::Reverse(**n));
        eprintln!(
            "  header +{off:#04x}: {} distinct value(s), commonest {:?}",
            vals.len(),
            &v[..v.len().min(4)]
        );
    }

    let mut bits: Vec<_> = flag_bits.iter().collect();
    bits.sort();
    eprintln!(
        "  +0x10 bits: bit -> (bundles with it set, of those full-screen, of those >=10 elements)"
    );
    for (bit, (n, fs, big)) in bits {
        eprintln!("     bit {bit:2}: {n:5}  full-screen {fs:5}  big {big:5}");
    }
    eprintln!(
        "  for reference: {bundles} bundles, {with_fullscreen} full-screen, {} with >=10 elements",
        counts.iter().filter(|&&c| c >= 10).count()
    );

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

    // MEASURED 2026-08-24. The question was "does a field say this bundle is a
    // screen"; the answer is no, and the numbers that make it no are asserted.
    //
    // The best any bit of the flags word manages is bit 13, set on 403 bundles
    // of which 179 carry a full-screen element — a 44 % hit rate against a
    // 12.8 % base. Enrichment, not a marker. Bit 15 is set on 91 % of ALL
    // bundles, which is the opposite failure.
    let base = with_fullscreen as f64 / bundles as f64;
    for (bit, (n, fs, _big)) in &flag_bits {
        let rate = *fs as f64 / *n as f64;
        assert!(
            rate < 0.95 || *n < 50,
            "bit {bit} looks like a screen marker after all: {fs}/{n} full-screen \
             against a {base:.3} base — re-open the question"
        );
    }
    // The header is NOT dead space, which is the other half of the result.
    assert!(
        header[&0x18].get(&1280).copied().unwrap_or(0) > bundles * 9 / 10,
        "+0x18 is not the design width after all"
    );
    assert!(
        header[&0x1c].get(&720).copied().unwrap_or(0) > bundles * 9 / 10,
        "+0x1c is not the design height after all"
    );
}