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

//! What ARE the chunks a movie-voice region decodes to?
//!
//! The port reports a resolved voice region decoding to **three** chunks — two
//! of equal duration each spanning the whole movie, and a leading one that
//! "matches nothing" — and notes that this is the same 2+1 signature the BGM
//! banks showed before `bank_header_len` attributed the extra to a bank header.
//! Two different asset kinds with one signature is worth checking, because if
//! the same explanation applies then `bank_header_len` is incomplete, and if it
//! does not then the leading chunk is something we are discarding.
//!
//! `slb.rs`'s own doc comment already predicts the answer and disagrees with
//! "drop it": the header signature fires on 28 entries, all music banks, with
//! "zero false positives on the 7 993 mid-bank windows, WHERE THE LEADING
//! REGION IS REAL". A voice region is a mid-bank window by construction —
//! `resolve_movie_voice_region` starts it at the PREDECESSOR cue's trailer.
//!
//!     cargo run -p sylpheed-formats --example voice_region_chunks -- <disc-dir>
use sylpheed_formats::media::{self, DirectorySource, DiscSource};
use sylpheed_formats::slb::{self, VoiceLang};

fn main() {
    let disc = std::env::args()
        .nth(1)
        .unwrap_or_else(|| std::env::var("SYLPHEED_DISC").expect("disc dir"));
    let src = DirectorySource::new(std::path::PathBuf::from(&disc));

    // Disc-wide, not the four movies that motivated the question: every movie
    // the manifest binds a voice to.
    let movies: Vec<String> = {
        use sylpheed_formats::movie_manifest;
        let tpak = src.open_pak("dat/tables.pak").expect("tables.pak");
        let manifest = tpak
            .entries()
            .iter()
            .find_map(|e| tpak.read(e).ok().filter(|b| movie_manifest::is_manifest(b)))
            .expect("movie manifest");
        movie_manifest::parse(&manifest)
            .into_iter()
            .map(|m| m.movie)
            .collect()
    };
    println!("{} movies in the manifest\n", movies.len());
    let mut census: std::collections::BTreeMap<usize, usize> = Default::default();
    let (mut with_header, mut with_leading, mut no_leading) = (0, 0, 0);
    for movie in movies.iter().map(|s| s.as_str()) {
        let Some((start, end)) = media::resolve_movie_voice_region(&src, movie, VoiceLang::English)
        else {
            continue;
        };
        let len = end - start;
        let Ok(bytes) = src.read_segment_range("dat/sound", start, len as usize) else {
            println!("{movie:8}  region {start}..{end} unreadable");
            continue;
        };
        // Where does the first RIFF sit? Everything before it is the leading
        // headerless packet region.
        let first_riff = bytes
            .windows(4)
            .position(|w| w == b"RIFF")
            .map(|p| p as i64)
            .unwrap_or(-1);
        let hdr = slb::bank_header_len(&bytes);
        let riffs = slb::to_xma_riffs(&bytes);
        let kind = if first_riff <= 0 {
            no_leading += 1;
            "no leading region".to_string()
        } else if hdr == Some(first_riff as usize) {
            with_header += 1;
            format!(
                "BANK HEADER ({first_riff} B = {} packets exactly)",
                first_riff / 2048
            )
        } else {
            with_leading += 1;
            *census.entry(first_riff as usize % 2048).or_default() += 1;
            format!(
                "leading STREAM ({first_riff} B = {} packets + {} B)",
                first_riff / 2048,
                first_riff % 2048
            )
        };
        println!(
            "{movie:10} {start:12}..{end:12} {len:9} B  chunks {}  {kind}",
            riffs.len()
        );
        if let Ok(dir) = std::env::var("VOICE_CHUNK_DUMP") {
            for (i, r) in riffs.iter().enumerate() {
                let _ = std::fs::write(format!("{dir}/{movie}-chunk{i}.wav"), r);
            }
        }
    }
    println!(
        "\n{with_header} region(s) open with a BANK HEADER (bank_header_len fires)\n\
{with_leading} open with a leading STREAM\n{no_leading} start at a RIFF"
    );
    println!("leading-stream length mod 2048, i.e. the derived data offset:");
    for (rem, n) in &census {
        println!("  {rem:5} B  x{n}");
    }
}