import re

re_hgt = re.compile(r"(?P<no>\d+)(?P<type>cm|in)")
re_hcl = re.compile(r"#[\da-f]{6}")
re_pid = re.compile(r"^\d{9}$")

def parse(data):
	rec = {}
	for line in data.split("\n"):
		if not line:
			yield rec
			rec = {}
			continue

		pairs = line.split(" ")
		for pair in pairs:
			k, v = pair.split(":", 1)
			rec[k] = v


def load(filename):
	with open(filename, "r", encoding="utf-8") as f:
		s = f.read()
	return parse(s)


def is_valid_1(rec):
	required_fields = set(("byr", "iyr", "eyr", "hgt", "hcl", "ecl", "pid"))
	fields = set(rec.keys())
	return not (required_fields - fields)


def is_valid_2(rec):
	if not is_valid_1(rec):
		return False

	if not 1920 <= int(rec["byr"]) <= 2002:
		return False

	if not 2010 <= int(rec["iyr"]) <= 2020:
		return False

	if not 2020 <= int(rec["eyr"]) <= 2030:
		return False

	m = re_hgt.match(rec["hgt"])
	if not m:
		return False

	if m.group("type") == "cm":
		if not 150 <= int(m.group("no")) <= 193:
			return False
	elif m.group("type") == "in":
		if not 59 <= int(m.group("no")) <= 76:
			return False

	m = re_hcl.match(rec["hcl"])
	if not m:
		return False

	if rec["ecl"] not in ("amb", "blu", "brn", "gry", "grn", "hzl", "oth"):
		return False

	if not re_pid.match(rec["pid"]):
		return False

	return True


if __name__ == "__main__":
	data = load("data.txt")
	n_valid_1 = n_valid_2 = 0
	for x in data:
		if is_valid_1(x):
			n_valid_1 += 1

		if is_valid_2(x):
			n_valid_2 += 1

	print(f"Task 1: There are {n_valid_1} valid passports.")
	print(f"Task 2: There are {n_valid_2} valid passports.")