#!/usr/bin/env python3
"""
mw4index.py - fast TSV manifest of every *.mw4 package under a directory.

    python3 mw4index.py <resource-root>  > manifest.tsv

Columns:  pkgRelPath \t recordId \t entryName \t dataLen \t recLen \t md5(storedBytes)

Directory-only, so a 780 MB resource tree indexes in about a second.

CAUTION: md5 of the *stored* bytes is NOT a reliable equality test. Two builds
that packed identical source can still produce different stored bytes (raw vs
LZW selection, dictionary state). Use it only as a cheap "definitely identical"
signal; confirm real differences with pkgcmp.py, which decodes.
"""
import sys, os
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from mw4db import read_index, walk_packages, md5


def main():
    if len(sys.argv) != 2:
        sys.exit(__doc__)
    root = sys.argv[1]
    for path, rel in walk_packages(root):
        try:
            r = read_index(path)
        except Exception as e:                    # truncated / unreadable package
            print(f"!ERR\t{rel}\t{e}", file=sys.stderr)
            continue
        if r is None:
            print(f"!NOTVBD\t{rel}", file=sys.stderr)
            continue
        _content, recs = r
        for rid, name, dlen, rlen, raw in recs:
            print(f"{rel}\t{rid}\t{name}\t{dlen}\t{rlen}\t{md5(raw)}")


if __name__ == "__main__":
    main()