#!/usr/bin/python
# -*- coding: utf-8 -*-

import sys
import getopt
from datetime import datetime

import pandas as pd

if __name__ == "__main__":

    # Задаём определения входных параметров
    unixOptions = "r:sdt:edt:"
    gnuOptions = ["regions=", "start_dt=", "end_dt="]

    fullCmdArguments = sys.argv
    argumentList = fullCmdArguments[1:]
    try:
        arguments, values = getopt.getopt(argumentList, unixOptions, gnuOptions)
    except getopt.error as err:
        print (str(err))
        sys.exit(2)

    # Обрабатываем входные параметры
    regions = 'Germany,France,Russia'.split(',')
    start_dt = '1998-01-01 00:00:00'
    end_dt = '1999-12-31 23:59:59'
    for currentArgument, currentValue in arguments:
        if currentArgument in ("-r", "--regions"):
            regions = currentValue.split(',')
        elif currentArgument in ("-sdt", "--start_dt"):
            start_dt = datetime.strptime(currentValue, '%Y-%m-%d %H-%M-%S')
        elif currentArgument in ("-edt", "--end_dt"):
            end_dt = datetime.strptime(currentValue, '%Y-%m-%d %H-%M-%S')

    urbanization = pd.read_csv('/datasets/urbanization.csv')[['Entity', 'Year', 'Urban']]

    # Приводим колонки urbanization к нужным типам
    urbanization['Year'] = pd.to_datetime(urbanization['Year'], format = '%Y-%m-%d')

    # Фильтруем и определяем максимальный уровень урбанизации
    urbanization = urbanization.query('Entity.isin(@regions) and Year >= @start_dt and Year <= @end_dt')

    print(urbanization.sort_values(by = ['Entity', 'Year']))