import argparse
import csv
import gzip
import sys


def domains(path):
    with gzip.open(path, "rt", encoding="utf-8") as source:
        for line in source:
            domain = line.strip().lower().rstrip(".")
            if domain:
                yield domain

parser = argparse.ArgumentParser(description="Shortlist short removed domain names")
parser.add_argument("file")
parser.add_argument("--tld", default="com")
parser.add_argument("--max-length", type=int, default=8)
args = parser.parse_args()
if args.max_length < 1:
    parser.error("max-length must be positive")
suffix = "." + args.tld.lower().lstrip(".")
writer = csv.writer(sys.stdout)
writer.writerow(["domain", "name_length"])
for domain in domains(args.file):
    if domain.endswith(suffix):
        name = domain[:-len(suffix)]
        if name.isascii() and name.isalpha() and len(name) <= args.max_length:
            writer.writerow([domain, len(name)])