#!/usr/bin/env python3
"""Round-trip verifier for the .torso and .engine decompilers.

Regenerates both files for every chassis and compares key order and values
against the authored source. `$(SYMBOL)` and its numeric expansion are treated
as equal, since the record stores only the resolved float.

    python3 verify_smallmodel.py [--show KIND CHASSIS]
"""
import argparse, collections, glob, os, re, sys

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import smallmodel

REC = "/home/rich/Repositories/FS_Ours_extracted/core/mechs"
SRC = "/home/rich/Repositories/firestorm/Gameleap/mw4/Content/Mechs"
NUM = re.compile(r'^-?(?:\d+\.?\d*|\.\d+)$')


def resolve(value, symbols):
    """$(NAME) -> its numeric value, so symbol and literal compare equal."""
    m = re.fullmatch(r'\$\((\w+)\)', value.strip())
    if m:
        return symbols.get(m.group(1).lower(), value.strip().lower())
    return value.strip().lower()


def canon(value, symbols):
    v = resolve(value, symbols)
    return f"{float(v):.5g}" if NUM.match(str(v)) else str(v)


def symbol_values(path):
    """-> {symbolNameLower: numericString}"""
    out = {}
    if os.path.exists(path):
        txt = re.sub(r'//[^\n]*', '', open(path, encoding="latin-1", errors="replace").read())
        for name, val in re.findall(r'^\s*!(\w+)\s*=\s*([-\d.]+)\s*$', txt, re.M):
            out[name.lower()] = val
    return out


def source_kv(path):
    txt = re.sub(r'//[^\n]*', '', open(path, "rb").read().decode("latin-1"))
    return [(m.group(1), m.group(2).strip())
            for m in re.finditer(r'^([A-Za-z]\w*)=([^\r\n]*)', txt, re.M)]


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--show", nargs=2, metavar=("KIND", "CHASSIS"))
    args = ap.parse_args()

    t = collections.Counter()
    bad = collections.Counter()
    examples = []
    order_bad = []

    for kind, spec in sorted(smallmodel.SPECS.items()):
        symbols = symbol_values(spec["defines"])
        for d in sorted(glob.glob(REC + "/*")):
            ch = os.path.basename(d)
            src = [p for p in glob.glob(f"{SRC}/*/*.{kind}")
                   if os.path.basename(p).lower() == f"{ch.lower()}.{kind}"]
            if not src or smallmodel.record(d, kind) is None:
                continue
            t[f"{kind} files"] += 1
            want = source_kv(src[0])
            got = smallmodel.decompile(d, kind)

            if args.show and args.show[0] == kind and args.show[1].lower() == ch.lower():
                sys.stdout.write(smallmodel.emit(kind, got))
                return

            if [k.lower() for k, _ in want] != [k.lower() for k, _ in got]:
                order_bad.append((kind, ch, [k for k, _ in want], [k for k, _ in got]))
                continue
            for (wk, wv), (_gk, gv) in zip(want, got):
                t["keys"] += 1
                if canon(wv, symbols) == canon(gv, symbols):
                    t["ok"] += 1
                else:
                    bad[f"{kind}.{wk}"] += 1
                    if len(examples) < 12:
                        examples.append((kind, ch, wk, wv, gv))

    for kind in sorted(smallmodel.SPECS):
        print(f"{kind:8s} files : {t[kind + ' files']}")
    print(f"keys compared  : {t['keys']}   exact: {t['ok']}   wrong: {t['keys'] - t['ok']}")
    if order_bad:
        print(f"\nkey order mismatches: {len(order_bad)}")
        for kind, ch, w, g in order_bad[:3]:
            print(f"   {kind} {ch}\n      want {w}\n      got  {g}")
    if bad:
        print("\nvalue mismatches:")
        for k, n in bad.most_common(15):
            print(f"   {k:34s} x{n}")
        print("\nexamples (kind, chassis, key, source, decoded):")
        for e in examples:
            print(f"   {e[0]:7s} {e[1]:14s} {e[2]:22s} want={e[3]!r:22s} got={e[4]!r}")


if __name__ == "__main__":
    main()