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

//! How many voice regions hold three chunks? A COUNT, stated with its population.
//!
//! `voice-region-starts-late.md` published "8 of 10 three-chunk regions start
//! mid-stream". The port agent counts **25** three-chunk regions. Mine was not a
//! count: the audit that produced it was cut short and I read a partial file as a
//! complete one — it ends mid-list with no summary line.
//!
//! This does the cheap half properly. It does not step backwards looking for the
//! clip; it resolves each region once and counts its chunks, and it prints the
//! population, the coverage and the skips **in the same output** so a truncated run
//! cannot be mistaken for a complete one.
//!
//!     cargo run -p sylpheed-formats --example voice_region_chunk_census

use std::collections::BTreeMap;
use sylpheed_formats::media::{self, DirectorySource, DiscSource};
use sylpheed_formats::movie_manifest;
use sylpheed_formats::slb::{self, VoiceLang};

fn main() {
    let disc = std::env::var("SYLPHEED_DISC").expect("SYLPHEED_DISC");
    let src = DirectorySource::new(std::path::PathBuf::from(&disc));
    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("manifest");
    let movies: Vec<String> = movie_manifest::parse(&manifest)
        .into_iter()
        .map(|m| m.movie)
        .collect();
    let total = movies.len();

    let mut hist: BTreeMap<usize, Vec<String>> = BTreeMap::new();
    let (mut resolved, mut unresolved, mut unreadable) = (0, 0, 0);
    for movie in movies {
        let Some((start, end)) =
            media::resolve_movie_voice_region(&src, &movie, VoiceLang::English)
        else {
            unresolved += 1;
            continue;
        };
        let Ok(b) = src.read_segment_range("dat/sound", start, (end - start) as usize) else {
            unreadable += 1;
            continue;
        };
        resolved += 1;
        hist.entry(slb::to_xma_riffs(&b).len())
            .or_default()
            .push(movie);
    }
    println!("POPULATION: {total} movies in the manifest");
    println!("COVERAGE:   {resolved} resolved and read, {unresolved} unresolved, {unreadable} unreadable");
    println!(
        "            {} accounted for\n",
        resolved + unresolved + unreadable
    );
    for (n, ms) in &hist {
        println!(
            "  {n} chunk(s): {:>3} region(s)   {}",
            ms.len(),
            ms.iter().cloned().collect::<Vec<_>>().join(" ")
        );
    }
    println!(
        "\nTHREE-CHUNK REGIONS: {}",
        hist.get(&3).map(|v| v.len()).unwrap_or(0)
    );
    println!("--- END OF CENSUS (if this line is missing, the run did not finish) ---");
}