#! /usr/bin/env python3

import requests
import re
from lxml import html
from datetime import datetime, timedelta
import argparse
import sys

#### functions #################################
## working with script arguments
def create_arg_parser():
    parser = argparse.ArgumentParser()
    parser.add_argument('--days', nargs=1, type=int)
    parser.add_argument('--cookies', nargs=1, required=True, type=str)
    parser.add_argument('--metricks', nargs=1, required=True, type=str)
    return parser

# download html page
def html_fetch(url, cookies):
    r = requests.get(url, cookies=cookies)
    # if cookies session is expired abort the script
    if re.findall(r'.*\.auth0\.com/login', r.url):
        sys.exit("expired/wrong cookies")
    parsed_body = html.fromstring(r.text)
    return parsed_body

# find required columns and grab their values
def html_parse(list_data):
    elements_data = {}
    result = []
    html_page = list_data
    table_columns = html_page.xpath("//td/@class")
    table_columns = list(dict.fromkeys(table_columns))
    table_columns = [x for x in table_columns if re.findall(r'col-.*', x)]
    if len(table_columns) > 0:
        for i in table_columns:
            L = html_page.xpath(f"//td[@class='{i}']/text()")
            elements_data[i] = [x.split() for x in L]           # remove spaces in list
        rows_count = len(elements_data[table_columns[0]])
        for i in range(rows_count):
            tmp = {}
            for j in elements_data:
                tmp[j] = elements_data[j][i]
            result.append(tmp)
        return result
    else:
        return ""
################################################

#### variables #################################


root_url = "https://admin.delphiplatform.io"
prefixes = {
    'etl_uow': 'etl_unit_of_work'
}
filters = {
    'cs': {
        'on-hold': 'flt1_4=ON_HOLD',
        'failed': 'flt0_4=FAILED',
        'report_date': 'flt1_7'
    },
    'etl_uow': {
        'completeness_status': 'flt0_3=FAILED',
        'report_date': 'flt1_9'
    }
}
# UoWs or the elements that we can ignore in result data
excluded_elements = {
    "content_status": {
        "unit_of_work_code": ("appreciationengine",)
    }
}

################################################

#######################################################################################################################
################################################### MAIN ##############################################################
#######################################################################################################################


def main():
    def get_result(url, cookies):
        data = html_fetch(url, cookies)
        return html_parse(data)

    def print_message(data):
        message = '\n-----------------\n'.join(map(str, data))
        print(message)

    cookies = {}
    days = 0
    argList = create_arg_parser().parse_args()
    cookies['session'] = argList.cookies[0]

    if argList.days:
        days = argList.days[0]
    start_date = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d")

    if argList.metricks[0] == 'cs_on-hold':
        if days > 0:
            url = f"{root_url}/?{filters['cs']['on-hold']}&{filters['cs']['report_date']}={start_date}"
        else:
            url = f"{root_url}/?{filters['cs']['on-hold']}"
        result_data = get_result(url, cookies)
        print_message(result_data)

    if argList.metricks[0] == 'cs_failed':
        if days > 0:
            url = f"{root_url}/?{filters['cs']['failed']}&{filters['cs']['report_date']}={start_date}"
        else:
            url = f"{root_url}/?{filters['cs']['failed']}"
        result_data = get_result(url, cookies)
        # remove ignored UoWs from result
        # result_data = [x for x in result_data if x['col-unit_of_work.unit_of_work_code'][0].split('-')[0] not in excluded_elements['content_status']['unit_of_work_code']]
        print_message(result_data)


    if argList.metricks[0] == 'etl_uow_failed':
        if days > 0:
            url = f"{root_url}/{prefixes['etl_uow']}?{filters['etl_uow']['completeness_status']}&{filters['etl_uow']['report_date']}={start_date}"
        else:
            url = f"{root_url}/{prefixes['etl_uow']}?{filters['etl_uow']['completeness_status']}"
        result_data = get_result(url, cookies)
        print_message(result_data)


############## RUN ###########################
if __name__ == '__main__':
    main()