//! Which mission should the next unit harvest fly?
//!
//! Unit definitions are instantiated per stage, so coverage grows by visiting
//! missions — but only if the mission fields units we have not read yet. This
//! ranks every stage by how many of its roster units are missing from the
//! harvested CSV.
//!
//! Usage: roster_target <disc-root> <unit-runtime-fields.csv>
use sylpheed_formats::hash::name_hash;
use sylpheed_formats::idxd::IdxdObject;
use sylpheed_formats::pak::PakArchive;
use std::collections::{BTreeMap, BTreeSet};

fn main() {
    let a: Vec<String> = std::env::args().collect();
    let pak = PakArchive::open(format!("{}/dat/GP_MAIN_GAME_E.pak", a[1])).expect("pak");
    let have: BTreeSet<String> = std::fs::read_to_string(&a[2])
        .expect("csv")
        .lines()
        .skip(1)
        .filter_map(|l| l.split(',').next().map(str::to_string))
        .collect();
    // Label each roster by STAGE: the TOC stores a hash of the original path, and
    // the table names are known (`EnumUnit_SNN.tbl`), so hashing the candidates
    // maps entries back to stages. Most rosters carry no `UN_S<NN>_` prop id, which
    // is all `UnitRoster::stage` can infer from.
    let mut by_hash: BTreeMap<u32, String> = BTreeMap::new();
    // The TOC hashes a PATH, and these tables live under a directory — try the
    // known schemes (see hash::TOC_NAME_SCHEMES) rather than the bare name.
    for i in 1..=29 {
        let stage = format!("S{i:02}");
        for pre in ["", "unit\\", "battle\\", "stage\\", "enemy\\"] {
            for suf in [".tbl", ""] {
                by_hash.insert(name_hash(&format!("{pre}EnumUnit_{stage}{suf}")), stage.clone());
            }
        }
    }
    let mut rows: Vec<(usize, String, Vec<String>)> = Vec::new();
    for e in pak.entries() {
        let Some(stage) = by_hash.get(&e.name_hash).cloned() else { continue };
        let Ok(b) = pak.read(e) else { continue };
        let Ok(o) = IdxdObject::parse(&b) else { continue };
        let mut units: Vec<String> = Vec::new();
        for id in o.tokens().iter().filter(|s| s.starts_with("UN_")) {
            let prop = id.contains("Asteroid") || id.contains("cmesh") || id.contains("_Box");
            if !prop && !units.iter().any(|u| u == id) {
                units.push(id.clone());
            }
        }
        let missing: Vec<String> = units.iter().filter(|u| !have.contains(*u)).cloned().collect();
        rows.push((missing.len(), stage, missing));
    }
    rows.sort_by_key(|(n, _, _)| std::cmp::Reverse(*n));
    println!("units already harvested: {}\n", have.len());
    println!("stage   missing  roster units not yet read");
    for (n, stage, missing) in rows.iter().take(12) {
        let s: Vec<&str> = missing.iter().take(6).map(|s| s.as_str()).collect();
        println!("{stage:<8} {n:>5}   {}", s.join(", "));
    }
}