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

def one_edit(a, b):
    if abs(len(a) - len(b)) > 1:
        return False
    if len(a) == len(b):
        return sum(x != y for x, y in zip(a, b)) == 1
    short, long = sorted((a, b), key=len)
    i = j = edits = 0
    while i < len(short) and j < len(long):
        if short[i] == long[j]:
            i += 1
        else:
            edits += 1
            if edits > 1:
                return False
        j += 1
    return True

parser = argparse.ArgumentParser(description="Screen domain labels for brand variants")
parser.add_argument("file")
parser.add_argument("--brand", required=True)
args = parser.parse_args()
brand = args.brand.strip().lower()
if not brand:
    parser.error("brand must not be empty")
writer = csv.writer(sys.stdout)
writer.writerow(["domain", "reason"])
for domain in domains(args.file):
    labels = domain.split(".")[:-1]
    if any(brand in label for label in labels):
        writer.writerow([domain, "brand mention"])
    elif any(one_edit(brand, label) for label in labels):
        writer.writerow([domain, "one-edit label"])