#!/usr/bin/env python3
"""Builds app/assets/security/common-passwords.txt from SecLists (MIT).

Usage:
  build-common-passwords.py <xato-1000000.txt> <german-top-100000.txt> <out.txt>

Inputs (SecLists commit 68bcd12457978649d41ae4f56e3b5d2db2b72560,
Passwords/Common-Credentials/):
  xato-net-10-million-passwords-1000000.txt
  Language-Specific/German_common-password-list-top-100000.txt

Rules: lowercase, trimmed, at least 10 code points (shorter ones are caught by
the length rule), printable, unique. First GERMAN_COUNT entries of the German
list (frequency order), then XATO_COUNT entries of the xato list.
"""
import sys

GERMAN_COUNT = 4000
XATO_COUNT = 6000
MIN_LENGTH = 10


def take(path, limit, seen):
    out = []
    with open(path, encoding="utf-8", errors="ignore") as handle:
        for line in handle:
            entry = line.strip().lower()
            if (
                len(entry) >= MIN_LENGTH
                and entry.isprintable()
                and not entry.startswith("#")
                and entry not in seen
            ):
                seen.add(entry)
                out.append(entry)
                if len(out) >= limit:
                    break
    return out


def main():
    xato, german, target = sys.argv[1:4]
    seen = set()
    entries = take(german, GERMAN_COUNT, seen) + take(xato, XATO_COUNT, seen)
    with open(target, "w", encoding="utf-8", newline="\n") as handle:
        handle.write("\n".join(entries) + "\n")
    print(len(entries))


if __name__ == "__main__":
    main()