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

//! Real-disc test for the movie manifest → voice binding. Skipped without
//! `SYLPHEED_DISC`.

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

use sylpheed_formats::movie_manifest;
use sylpheed_formats::slb::VoiceLang;
use sylpheed_formats::PakArchive;

fn disc_root() -> Option<PathBuf> {
    let p = PathBuf::from(std::env::var("SYLPHEED_DISC").ok()?);
    p.join("dat").is_dir().then_some(p)
}

/// Read the manifest + `eng\sounds.tbl` out of `tables.pak`.
fn load_manifest_and_sounds(root: &Path) -> (Vec<u8>, Vec<u8>) {
    let pak = PakArchive::open(root.join("dat/tables.pak")).unwrap();
    let manifest = pak
        .entries()
        .iter()
        .find_map(|e| pak.read(e).ok().filter(|b| movie_manifest::is_manifest(b)))
        .expect("movie manifest present in tables.pak");
    let sounds = pak
        .read_by_name("eng\\sounds.tbl")
        .expect("sounds.tbl present")
        .unwrap();
    (manifest, sounds)
}

#[test]
fn binds_and_resolves_movie_voice() {
    let Some(root) = disc_root() else {
        eprintln!("SKIP: set SYLPHEED_DISC");
        return;
    };
    let (manifest, sounds) = load_manifest_and_sounds(&root);
    let entries = movie_manifest::parse(&manifest);
    // 104 cutscene SLOTS binding 101 distinct movies — three resupply movies are
    // bound by two slots each. Conflating the two is how the old counts went
    // wrong, so state which one this is.
    assert!(
        entries.len() > 90,
        "expected 101 distinct movies (104 slots), got {}",
        entries.len()
    );

    // Standard story movie → VOICE_<movie> in <lang>\Movie\.
    assert_eq!(
        movie_manifest::voice_token(&manifest, "S13A").as_deref(),
        Some("VOICE_S13A")
    );
    assert_eq!(
        movie_manifest::resolve_voice_entry(&manifest, &sounds, "S13A", VoiceLang::English)
            .as_deref(),
        Some("eng\\Movie\\VOICE_S13A.slb")
    );

    // A resupply movie bound to an in-mission radio clip → VOICE_D_* in \etc\.
    // (This is what a `VOICE_<movie>` guess would miss entirely.)
    assert_eq!(
        movie_manifest::voice_token(&manifest, "hokyu_LS_s02A").as_deref(),
        Some("VOICE_D_450")
    );
    assert_eq!(
        movie_manifest::resolve_voice_entry(
            &manifest,
            &sounds,
            "hokyu_LS_s02A",
            VoiceLang::English
        )
        .as_deref(),
        Some("eng\\etc\\VOICE_D_450.slb")
    );

    // ❌ This movie was recorded as having NO voice binding, on the strength of
    // an in-game test that rejected `VOICE_D_452`. Both halves of that were
    // wrong. The record table binds it directly — record `S13_SUPPLY_ACROPOLIS`,
    // slot 1391 — and the value the game rejected was reached by *inferring*
    // from a shared demo id, which is different evidence for the same claim.
    // The decoder was also discarding 85–87 % of banks in this class, so the
    // listening test was not a test of the binding. See
    // docs/re/voice-bank-leading-region.md.
    //
    // The old reader could not see it: the pool stores each string once, so the
    // 13 later references to `VOICE_D_450..454` contribute no token at all.
    let e = entries
        .iter()
        .find(|e| e.movie == "hokyu_DS_s13A")
        .expect("hokyu_DS_s13A present in manifest");
    assert_eq!(e.voice_token.as_deref(), Some("VOICE_D_452"));
    assert_eq!(
        movie_manifest::resolve_voice_entry(
            &manifest,
            &sounds,
            "hokyu_DS_s13A",
            VoiceLang::English
        )
        .as_deref(),
        Some("eng\\etc\\VOICE_D_452.slb")
    );

    // Every resolved voice entry must actually exist in sound.pak.
    let snd = std::fs::read(root.join("dat/sound.pak")).unwrap();
    let keys: std::collections::HashSet<u32> = PakArchive::parse_toc(&snd)
        .unwrap()
        .iter()
        .map(|e| e.name_hash)
        .collect();
    let mut resolved = 0;
    let mut missing = Vec::new();
    for e in &entries {
        if let Some(full) =
            movie_manifest::resolve_voice_entry(&manifest, &sounds, &e.movie, VoiceLang::English)
        {
            resolved += 1;
            if !keys.contains(&sylpheed_formats::hash::name_hash(&full)) {
                missing.push(full);
            }
        }
    }
    assert!(resolved > 80, "expected 80+ voiced movies, got {resolved}");
    assert!(
        missing.is_empty(),
        "resolved but absent in sound.pak: {missing:?}"
    );
}

/// The manifest's shape, pinned. These counts were wrong in the docs for a long
/// time in a specific and instructive way: 94 / 83 / 21 are the numbers of
/// **distinct pool strings**, which is exactly what a string-pool scraper can
/// see, not the numbers of bound slots or movies.
#[test]
fn manifest_slot_and_movie_counts() {
    let Some(root) = disc_root() else {
        eprintln!("SKIP: set SYLPHEED_DISC");
        return;
    };
    let (manifest, _sounds) = load_manifest_and_sounds(&root);
    let entries = movie_manifest::parse(&manifest);

    use std::collections::{HashMap, HashSet};
    let movies: HashSet<&str> = entries.iter().map(|e| e.movie.as_str()).collect();
    assert_eq!(entries.len(), 104, "cutscene slots");
    assert_eq!(movies.len(), 101, "distinct movies");

    let bound = |f: fn(&movie_manifest::MovieEntry) -> Option<&String>| {
        let slots = entries.iter().filter(|e| f(e).is_some()).count();
        let movies: HashSet<&str> = entries
            .iter()
            .filter(|e| f(e).is_some())
            .map(|e| e.movie.as_str())
            .collect();
        let distinct: HashSet<&str> = entries
            .iter()
            .filter_map(|e| f(e))
            .map(String::as_str)
            .collect();
        (slots, movies.len(), distinct.len())
    };
    // (slots, movies, distinct strings) — the third is what the docs used to report.
    assert_eq!(bound(|e| e.voice_token.as_ref()), (99, 96, 83));
    assert_eq!(bound(|e| e.subtitle.as_ref()), (99, 96, 94));
    assert_eq!(bound(|e| e.telop.as_ref()), (22, 22, 21));

    // Three resupply movies are bound by two slots each — which is why "slots"
    // and "movies" are not interchangeable.
    let mut per_movie: HashMap<&str, Vec<&str>> = HashMap::new();
    for e in &entries {
        per_movie.entry(&e.movie).or_default().push(&e.slot);
    }
    let mut shared: Vec<&str> = per_movie
        .iter()
        .filter(|(_, slots)| slots.len() > 1)
        .map(|(m, _)| *m)
        .collect();
    shared.sort_unstable();
    assert_eq!(shared, ["hokyu_DS_s07A", "hokyu_DS_s07H", "hokyu_LS_s02A"]);

    // Every id names a real record, so nothing dangles.
    assert!(entries
        .iter()
        .all(|e| !e.slot.is_empty() && !e.movie.is_empty()));
}

/// Everything the Cutscenes browser shows, asserted against the disc.
///
/// The window's value is that it answers "which cutscenes exist, which mission
/// is each one in, and can I read it without playing it" — so the test checks
/// exactly those three, including the **negative**: five manifest-bound movies
/// have no `.wmv`, and nine more have no English transcript. A browser that
/// quietly omitted them would look complete and be wrong, so the counts are
/// pinned here rather than left to the eye.
#[test]
fn cutscene_catalog_binds_movies_and_transcripts() {
    let Some(root) = disc_root() else {
        eprintln!("SKIP: set SYLPHEED_DISC");
        return;
    };
    use sylpheed_formats::movie_subtitle as ms;
    let (manifest, _) = load_manifest_and_sounds(&root);
    let rows = movie_manifest::parse(&manifest);
    assert_eq!(rows.len(), 104, "manifest slots");

    let movies: std::collections::BTreeSet<&str> = rows.iter().map(|r| r.movie.as_str()).collect();
    assert_eq!(movies.len(), 101, "distinct movies");
    assert_eq!(rows.iter().filter(|r| r.subtitle.is_some()).count(), 99);
    assert_eq!(rows.iter().filter(|r| r.voice_token.is_some()).count(), 99);
    assert_eq!(rows.iter().filter(|r| r.telop.is_some()).count(), 22);

    // Bound-but-absent: the four boot logos and one encoder test clip are named
    // by the manifest and are not on the disc. The browser marks these in red
    // rather than offering a Play button that would fail.
    let on_disc: std::collections::BTreeSet<String> = std::fs::read_dir(root.join("dat/movie"))
        .unwrap()
        .filter_map(|e| {
            let p = e.ok()?.path();
            (p.extension()?.to_str()? == "wmv")
                .then(|| p.file_stem()?.to_str().map(|s| s.to_ascii_lowercase()))?
        })
        .collect();
    let mut absent: Vec<&str> = movies
        .iter()
        .copied()
        .filter(|m| !on_disc.contains(&m.to_ascii_lowercase()))
        .collect();
    absent.sort_unstable();
    assert_eq!(
        absent,
        [
            "SYLPH_HD720p_8M-CBR_2ch",
            "logo1",
            "logo2",
            "logo3",
            "logo4"
        ],
        "manifest-bound movies with no .wmv on the disc"
    );

    // Transcripts, which is what makes a cutscene readable without playback.
    let lang_pak = PakArchive::open(root.join("dat/movie/eng.pak")).unwrap();
    let text_pak = PakArchive::open(root.join("dat/GP_MAIN_GAME_E.pak")).unwrap();
    let resolved = movies
        .iter()
        .filter(|m| !ms::load(m, &lang_pak, &text_pak).is_empty())
        .count();
    assert_eq!(resolved, 92, "movies with an English transcript");
}