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

import hashlib
import json
import sqlite3
import tempfile
from pathlib import Path

parser = argparse.ArgumentParser(description="Compare two domain snapshots")
parser.add_argument("before")
parser.add_argument("after")
args = parser.parse_args()

def checksum(path):
    digest = hashlib.sha256()
    with open(path, "rb") as source:
        for chunk in iter(lambda: source.read(1024 * 1024), b""):
            digest.update(chunk)
    return digest.hexdigest()

with tempfile.TemporaryDirectory() as temp:
    connection = sqlite3.connect(str(Path(temp) / "comparison.sqlite"))
    try:
        with connection:
            for table, path in [("before_names", args.before), ("after_names", args.after)]:
                connection.execute(f"CREATE TABLE {table} (domain TEXT PRIMARY KEY)")
                connection.executemany(f"INSERT OR IGNORE INTO {table} VALUES (?)",
                                       ((name,) for name in domains(path)))
        added = connection.execute("SELECT COUNT(*) FROM (SELECT domain FROM after_names "
                                   "EXCEPT SELECT domain FROM before_names)").fetchone()[0]
        removed = connection.execute("SELECT COUNT(*) FROM (SELECT domain FROM before_names "
                                     "EXCEPT SELECT domain FROM after_names)").fetchone()[0]
    finally:
        connection.close()
print(json.dumps({"before_file": args.before, "after_file": args.after,
                  "before_sha256": checksum(args.before), "after_sha256": checksum(args.after),
                  "observed_additions": added, "observed_removals": removed}, indent=2))