import csv
import re
import math
from collections import Counter

csv_file = 'vacancies_big.csv'


def get_suffix_by_rubles(count):
    if count % 10 == 0 or 5 <= count % 10 <= 9 or 10 <= count % 100 <= 19:
        return 'рублей'
    elif 2 <= count % 10 <= 4:
        return 'рубля'
    else:
        return 'рубль'


def get_suffix_by_count(count):
    if count % 10 == 0 or 5 <= count % 10 <= 9 or 10 <= count % 100 <= 19:
        return 'раз'
    elif 2 <= count % 10 <= 4:
        return 'раза'
    else:
        return 'раз'


def get_list_by_salaries(current_list: list, is_high_salary: bool):
    items_counter = 0
    list_sorted_by_average_salary = sorted(
        current_list,
        key=lambda salary: math.floor((float(salary[6]) + float(salary[7])) / 2),
        reverse=is_high_salary)

    for vacancy in list_sorted_by_average_salary:
        if vacancy[9] != 'RUR':
            continue
        if items_counter == 10:
            break

        items_counter += 1
        average_salary = math.floor((float(vacancy[6]) + float(vacancy[7])) / 2)

        print(f'\t{items_counter}) {vacancy[0]} в компании \"{vacancy[5]}\" - '
              f'{average_salary} {get_suffix_by_rubles(average_salary)} (г. {vacancy[10]})')


def get_top_mentioned_skills(current_list: list):
    items_counter = 0
    all_skills = list()

    for vacancy in current_list:
        skills = vacancy[2].split(', ')
        for skill in skills:
            all_skills.append(skill)

    statistic = dict(Counter(all_skills).most_common())

    for key, count in statistic.items():
        if items_counter != 10:
            items_counter += 1
            print(f'\t{items_counter}) {key} - '
                  f'упоминается {count} {get_suffix_by_count(count)}')
        else:
            break


def get_cities_by_salaries(current_list: list):
    items_counter = 0
    all_cities = set()
    list_sorted_by_average_salary = sorted(
        current_list,
        key=lambda salary: math.floor((float(salary[6]) + float(salary[7])) / 2),
        reverse=True)

    for vacancy in list_sorted_by_average_salary:
        if all_cities.__contains__(vacancy[10]):
            continue
        else:
            all_cities.add(vacancy[10])
            if vacancy[9] != 'RUR':
                continue
            if items_counter == 10:
                break

        items_counter += 1
        average_salary = math.floor((float(vacancy[6]) + float(vacancy[7])) / 2)

        print(f'\t{items_counter}) {vacancy[10]} - средняя зарплата '
              f'{average_salary} {get_suffix_by_rubles(average_salary)} '
              f'(1 вакансия)')


def get_cities_count(current_list: list) -> int:
    all_cities = set()
    for vacancy in current_list:
        all_cities.add(vacancy[10])
    return len(all_cities)


def get_skills_count(current_list: list) -> int:
    all_skills = set()
    for vacancy in current_list:
        skills = vacancy[2].split(', ')
        for skill in skills:
            all_skills.add(skill)
    return len(all_skills)


vacancies_list = list()


with open(csv_file, 'r', encoding='utf-8') as f:
    reader = csv.reader(f)
    title = next(reader)
    data, title[0] = [], 'name'
    html_tags = re.compile(r'<[^>]+>')
    for line in reader:
        if len(line) < len(title):
            continue
        is_correct_string = True
        for index, value in enumerate(line):
            normal_string = re.sub(html_tags, '', value)\
                .replace('\n', ', ')\
                .replace('\r\n', ', ')
            normal_string = ' '.join(normal_string.split())
            line[index] = normal_string
            if len(normal_string) == 0:
                is_correct_string = False
                break
        if is_correct_string:
            vacancies_list.append(line)


print('Самые высокие зарплаты:')
get_list_by_salaries(vacancies_list, True)
print()
print('Самые низкие зарплаты:')
get_list_by_salaries(vacancies_list, False)
print()
print(f'Из {get_skills_count(vacancies_list)} скиллов, самыми популярными являются:')
get_top_mentioned_skills(vacancies_list)
print()
print(f'Из {get_cities_count(vacancies_list)} городов, самые высокие средние ЗП:')
get_cities_by_salaries(vacancies_list)