import re
from datetime import datetime, timedelta
import holidays
import calendar
import json

def timedelta_to_string(td: timedelta) -> str:
    """Convert a timedelta object to a string in the format HH:MM."""

    total_minutes = int(td.total_seconds() / 60)
    hours = abs(total_minutes) // 60
    minutes = abs(total_minutes) % 60
    sign = "-" if td.total_seconds() < 0 else ""

    return f"{sign}{hours:02}:{minutes:02}"

def process_input_txt(text: str) -> list:
    """
    Process text containing work records and return a sorted list of dictionaries
    containing the extracted data.

    Args:
        text (str): Text containing work records.

    Returns:
        list[dict]: List of dictionaries containing the fields 'enter', 'exit', and 'duration'.
    """
    pattern = re.compile(
        r"""
        (?P<name>\S+\s\S+)\s+          # Name
        (?P<start_date>\d{2}\.\d{2}\.\d{4}\s\d{2}:\d{2}:\d{2})\s+  # Start date
        (?P<end_date>\d{2}\.\d{2}\.\d{4}\s\d{2}:\d{2}:\d{2})\s+    # End date
        (?P<duration>\d{2}:\d{2})                                  # Duration
        """,
        re.VERBOSE,
    )

    results = []
    for line in text.splitlines():
        line = line.strip()
        if not line:
            continue
        match = pattern.match(line)
        if match:
            try:
                start_date = datetime.strptime(match.group("start_date"), "%d.%m.%Y %H:%M:%S")
                end_date = datetime.strptime(match.group("end_date"), "%d.%m.%Y %H:%M:%S")
                duration = timedelta(
                    hours=int(match.group("duration")[:2]), minutes=int(match.group("duration")[3:])
                )
                results.append(
                    {
                        "enter": start_date,
                        "exit": end_date,
                        "duration": duration,
                    }
                )
            except ValueError:
                # Ignore invalid dates
                continue

    # Sort results by start date
    results.sort(key=lambda x: x["enter"])
    return results


def generate_monthly_summary(work_records: list, year: int, month: int) -> list:
    # Polska lista dni świątecznych
    pl_holidays = holidays.Poland(years=year)

    # Liczba dni w miesiącu
    _, num_days = calendar.monthrange(year, month)
    summary = []

    # Oblicz godziny pracy na dzień (8h 15min = 8.25h)
    daily_work_hours = timedelta(hours=8, minutes=15)
    holiday_work_hours = timedelta(hours=0, minutes=15)

    # Suma godzin oczekiwanych i rzeczywistych
    total_expected = timedelta(0)
    total_actual = timedelta(0)

    # Tworzenie wpisów dla każdego dnia
    for day in range(1, num_days + 1):
        date = datetime(year, month, day)
        weekday = date.weekday()  # 0 = poniedziałek, ..., 6 = niedziela
        is_holiday = date in pl_holidays
        should_work = weekday < 5 and not is_holiday  # Praca w dni robocze poza świętami

        # Aktualizuj oczekiwany czas pracy
        if should_work:
            total_expected += daily_work_hours

        # Znajdź godziny faktyczne dla tego dnia
        daily_actual = sum(
            (record["duration"]
            for record in work_records
            if record["enter"].date() == date.date()) , timedelta()
        )
        total_actual += daily_actual  # Dodanie timedelta do sumy

        # Dodaj dane do listy podsumowania
        summary.append({
            "day": date.date(),
            "weekday": weekday,
            "is_holiday": is_holiday,
            "total_expected": timedelta_to_string(total_expected),
            "total_actual": timedelta_to_string(total_actual),
            "total_diffrance": timedelta_to_string(total_actual - total_expected),
            "daily_actual": timedelta_to_string(daily_actual),
            "daily_diffrance": timedelta_to_string(daily_actual - (daily_work_hours if should_work else holiday_work_hours if daily_actual >= holiday_work_hours else timedelta(0))),
        })

    return summary

# text3 = """
# Worked hours
	
# Attendance Reason
# 	Marcin Nowak	22.11.2024 07:12:30	22.11.2024 16:05:33	08:53
	
# 	Marcin Nowak	21.11.2024 07:25:38	21.11.2024 16:43:19	09:18
	
# 	Marcin Nowak	20.11.2024 07:31:46	20.11.2024 15:47:36	08:16
	
# 	Marcin Nowak	19.11.2024 07:10:39	19.11.2024 15:54:14	08:44
	
# 	Marcin Nowak	18.11.2024 07:13:11	18.11.2024 16:04:15	08:51
	
# 	Marcin Nowak	15.11.2024 07:06:31	15.11.2024 15:41:49	08:35
	
# 	Marcin Nowak	14.11.2024 06:56:23	14.11.2024 16:11:52	09:15
	
# 	Marcin Nowak	13.11.2024 07:12:25	13.11.2024 17:19:58	10:08
	
# 	Marcin Nowak	12.11.2024 07:40:57	12.11.2024 16:10:42	08:30
	
# 	Marcin Nowak	08.11.2024 07:01:22	08.11.2024 15:48:01	08:47
	
# 	Marcin Nowak	07.11.2024 07:07:53	07.11.2024 16:26:30	09:19
	
# 	Marcin Nowak	06.11.2024 07:11:46	06.11.2024 16:08:43	08:57
	
# 	Marcin Nowak	05.11.2024 07:16:33	05.11.2024 16:10:52	08:54
	
# 	Marcin Nowak	04.11.2024 07:28:10	04.11.2024 15:51:19	08:23
	
# """

# # Przetwórz dane wejściowe
# work_records = process_input_txt(text3)
# date = work_records[-1]["enter"].date()
# monthly_summary = generate_monthly_summary(work_records, date.year, date.month)

# # Przykład wyświetlenia podsumowania
# import pprint
# pprint.pprint(monthly_summary)