#!/usr/bin/env python3
"""
pkgcmp.py - authoritative content diff of two versions of the same *.mw4.

    python3 pkgcmp.py <A.mw4> <B.mw4>

Decodes every record on both sides and compares the *decompressed* bytes, so
the result is free of packer noise. This is the only trustworthy equality test;
stored-byte comparison badly over-reports (peaks.mw4: 9 stored-byte diffs, 1
real one).

Throughput is roughly 2 MB/s of package (props.mw4, 114 MB, takes ~50 s).
"""
import sys, os
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from mw4db import read_records, norm, md5


def load(path):
    _content, recs = read_records(path)
    return {norm(name): (dlen, md5(blob), blob) for _rid, name, dlen, _rlen, blob in recs}


def main():
    if len(sys.argv) != 3:
        sys.exit(__doc__)
    a, b = load(sys.argv[1]), load(sys.argv[2])
    aonly = sorted(set(a) - set(b))
    bonly = sorted(set(b) - set(a))
    diff = sorted(k for k in set(a) & set(b) if a[k][1] != b[k][1])
    print(f"# entries: A={len(a)} B={len(b)} "
          f"A_only={len(aonly)} B_only={len(bonly)} decoded-differ={len(diff)}")
    for k in aonly:
        print(f"+A {k}  {a[k][0]}B")
    for k in bonly:
        print(f"-B {k}  {b[k][0]}B")
    for k in diff:
        print(f"~ {k}  A={a[k][0]}B B={b[k][0]}B")


if __name__ == "__main__":
    main()