//! How many sub-waves does each resupply voice bank hold?
//!
//! The corpus records `VOICE_D_452` as the binding the game rejected in-game
//! ("wrong recording"), and separately notes that `VOICE_D_453`/`454` decode to
//! 0.14 s / 0.43 s — "far too short for the spoken line". Both observations are
//! explained if these banks are multi-sub-wave and the extractor plays only the
//! first. This prints the shape so that stops being a guess.
use sylpheed_formats::{slb, PakArchive};

fn main() {
    let disc = std::env::var("SYLPHEED_DISC").expect("set SYLPHEED_DISC");
    let snd = PakArchive::open(format!("{disc}/dat/sound.pak")).expect("sound.pak");
    println!(
        "{:<14} {:>7} {:>6} {:>6} {:>7}  sub-wave data sizes",
        "bank", "bytes", "RIFFs", "waves", "cover"
    );
    for n in 450..=454 {
        for dir in ["etc", "Voice", "Movie"] {
            let path = format!("eng\\{dir}\\VOICE_D_{n}.slb");
            let Some(entry) = snd.find_by_name(&path) else { continue };
            let bytes = snd.read(entry).expect("read");
            let riffs = slb::to_xma_riffs(&bytes);
            let sizes: Vec<usize> = riffs.iter().map(|r| r.len()).collect();
            // How many RIFF magics does the bank actually contain, versus how
            // many sub-waves the walker recovered? A gap means the walk stops
            // early, and the missing bytes are the missing audio.
            let magics = bytes.windows(4).filter(|w| *w == b"RIFF").count();
            let covered: usize = sizes.iter().sum();
            // What are the UNCOVERED bytes? If the tail past the last data
            // chunk is all zero it is padding and the short duration is real;
            // if it is high-entropy it is audio the parse is throwing away.
            let last = bytes
                .windows(4)
                .rposition(|w| w == b"data")
                .map(|i| {
                    let sz = u32::from_le_bytes(bytes[i + 4..i + 8].try_into().unwrap()) as usize;
                    (i + 8 + sz).min(bytes.len())
                })
                .unwrap_or(0);
            // Where does the RIFF structure START? If it begins far into the
            // file, the uncovered bytes are a leading region the parse skips,
            // not a missed sub-wave.
            let first_riff = bytes.windows(4).position(|w| w == b"RIFF").unwrap_or(0);
            let datas = bytes.windows(4).filter(|w| *w == b"data").count();
            // Is the leading region padding, or content? Padding is nearly all
            // zero and uses few distinct byte values.
            let head = &bytes[..first_riff];
            let head_zero = head.iter().filter(|b| **b == 0).count();
            let head_distinct = {
                let mut seen = [false; 256];
                for b in head {
                    seen[*b as usize] = true;
                }
                seen.iter().filter(|s| **s).count()
            };
            let tail = &bytes[last..];
            let zeros = tail.iter().filter(|b| **b == 0).count();
            // Dump the first bytes of the leading region so its structure is
            // visible rather than guessed at.
            let hex: String = head
                .iter()
                .take(48)
                .map(|b| format!("{b:02x}"))
                .collect::<Vec<_>>()
                .join(" ");
            println!("  head[0..48] {hex}");
            println!(
                "{:<14} {:>7} {:>6} {:>6} {:>6.1}%  1st RIFF @{:>6}  data chunks {}  head {:>5.1}% zero/{:>3} distinct  tail {:>5} B ({:>5.1}% zero)  {:?}",
                format!("VOICE_D_{n}"),
                bytes.len(),
                magics,
                riffs.len(),
                100.0 * covered as f64 / bytes.len() as f64,
                first_riff,
                datas,
                if head.is_empty() { 0.0 } else { 100.0 * head_zero as f64 / head.len() as f64 },
                head_distinct,
                tail.len(),
                if tail.is_empty() { 0.0 } else { 100.0 * zeros as f64 / tail.len() as f64 },
                sizes
            );
            break;
        }
    }
}