try:

    from datetime import timedelta, datetime
    from airflow import DAG
    
    from airflow.operators.python_operator import PythonOperator
    from airflow.operators.http_operator import SimpleHttpOperator
    from datetime import datetime
    from pandas.io.json import json_normalize
    from airflow.operators.postgres_operator import PostgresOperator

    import pandas as pd
    import json
    import requests
    import numpy as np

    import psycopg2
    from sqlalchemy import create_engine

except Exception as e:
    print("Error {} ".format(e))

dRoW_api_end_url = "https://drow.cloud"

def getDrowToken(**context):
    response = requests.post(
    url=f"{dRoW_api_end_url}/api/auth/authenticate",
    data={
        "username": "icwp2@drow.cloud",
        "password": "dGVzdDAxQHRlc3QuY29t"
    }).json()
    context["ti"].xcom_push(key="token", value=response['token'])


def getMongoDB(**context):
    token = context.get("ti").xcom_pull(key="token")
    response = requests.get(
        url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/657fb9a2fde5354c3626cc11?export_type=0",
        headers={
            "x-access-token": f"Bearer {token}",
            "ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
        }
    )
    RISC_Data = json.loads(response.text)
    Mapping= {
        "A01 Date" : "a01_date",
    }

    host                  = 'drowdatewarehouse.crlwwhgepgi7.ap-east-1.rds.amazonaws.com'  
    # User name of the database server
    dbUserName            = 'dRowAdmin'  
    # Password for the database user
    dbUserPassword        = 'drowsuper'  
    # Name of the database 
    database              = 'drowDateWareHouse'
    # Character set
    charSet               = "utf8mb4"  
    port                  = "5432"

    conn_string = ('postgres://' +
                           dbUserName + ':' + 
                           dbUserPassword +
                           '@' + host + ':' + port +
                           '/' + database)
    
    db = create_engine(conn_string)
    conn = db.connect()
    with conn as conn:
        df3=pd.read_sql("SELECT * FROM public.site_diary_activities_general_count_dc202312;",
            conn,
            parse_dates=["a01_date"])
        df = pd.DataFrame()
        _df = pd.DataFrame()
        for x in RISC_Data:
            df_nested_list = json_normalize(x['data'])
            df2 = df_nested_list.reindex(columns=Mapping.keys())
            if x['data']['A01 Date']is not None:
                date = datetime.strptime(x['data']['A01 Date'], '%Y-%m-%dT%H:%M:%S.%f%z')
            if x['data']['A01 Date'] is None:
                date = datetime.strptime('2022-09-22T00:00:00.000Z', '%Y-%m-%dT%H:%M:%S.%f%z')

            no_of_site_activities = df3.query('a01_date == @date')
            if(len(no_of_site_activities['Count'])!= 0):
                df2['no_of_site_activities'] = no_of_site_activities['Count'].iloc[0]
            else:
                df2['no_of_site_activities'] = 0

            if (date < datetime.strptime('2022-10-01T00:00:00.000Z', '%Y-%m-%dT%H:%M:%S.%f%z')):
                df2['complete_or_incomplete'] = 'complete'
            else :
                if x['Status'] == 'Z : SD Completed':
                    df2['complete_or_incomplete'] = 'complete'
                else:
                    df2['complete_or_incomplete'] = 'incomplete'

            if len(x['ApproveLogSummary']) > 0:
                pmd_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="D : Sign CRE/SRE"]
                contractor_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="C1 : Check(Contactor Engineer)"]
                supervisor_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="B : SIOW Sign (Building Team)"]

            if len(pmd_sign_date) > 0 and ('to' in pmd_sign_date[len(pmd_sign_date)-1]):
                pmd_receive_time = pmd_sign_date[len(pmd_sign_date)-1]['from']
                pmd_sign_time = pmd_sign_date[len(pmd_sign_date)-1]['to']
                df2['pmd_sign_time'] = pmd_sign_date[len(pmd_sign_date)-1]['to']
                df2['Overdue_PMD']= (pmd_sign_time != '' and pmd_receive_time != '' and (datetime.strptime(pmd_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') -  datetime.strptime(pmd_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
                df2['pmd_sign_time'] = datetime.strptime(pmd_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') + pd.Timedelta(8, unit='h')
            else: 
                df2['pmd_sign_time'] = None
                df2['Overdue_PMD'] = None

            if len(contractor_sign_date) > 0 and ('to' in contractor_sign_date[len(contractor_sign_date)-1]):
                cr_receive_time = contractor_sign_date[len(contractor_sign_date)-1]['from']
                cr_sign_time = contractor_sign_date[len(contractor_sign_date)-1]['to']
                df2['cr_sign_time'] = contractor_sign_date[len(contractor_sign_date)-1]['to']
                df2['Overdue_CR']= (cr_sign_time != '' and cr_receive_time != '' and (datetime.strptime(cr_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') -  datetime.strptime(cr_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
                df2['cr_sign_time'] = datetime.strptime(cr_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') + pd.Timedelta(8, unit='h')
            else: 
                df2['cr_sign_time'] = None
                df2['Overdue_CR'] = None

            if len(supervisor_sign_date) > 0 and ('to' in supervisor_sign_date[len(supervisor_sign_date)-1]):
                sup_receive_time = supervisor_sign_date[len(supervisor_sign_date)-1]['from']
                sup_sign_time = supervisor_sign_date[len(supervisor_sign_date)-1]['to']
                df2['sup_sign_time'] = supervisor_sign_date[len(supervisor_sign_date)-1]['to']
                df2['Overdue_SUP']= (sup_sign_time != '' and sup_receive_time != '' and (datetime.strptime(sup_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') -  datetime.strptime(sup_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
                df2['sup_sign_time'] = datetime.strptime(sup_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') + pd.Timedelta(8, unit='h')
            else: 
                df2['sup_sign_time'] = None
                df2['Overdue_SUP'] = None
            
            df6 = df_nested_list[Mapping.keys()]
            df4 = pd.DataFrame()
            if "A04 Contractor's Site Staff" in x['data'] and len(x['data']["A04 Contractor's Site Staff"]) > 0:
                _df3 = df6.copy()
                for c in x['data']["A04 Contractor's Site Staff"]:
                    labourName = str(c["A04.1 Contractor's Site Staff"])
                    labourNum = 0
                    if ("A04.3 Contractor's Site Staff No" in c) and not c["A04.3 Contractor's Site Staff No"] is None:
                        labourNum = c["A04.3 Contractor's Site Staff No"]
                    else:
                        labourNum = 0
                    _df3['contractor_management_post_name'] = labourName
                    _df3['contractor_management_number'] = labourNum
                    df4 = df4.append(_df3)
            
            df2.rename(columns=Mapping, inplace=True)
            df4.rename(columns=Mapping, inplace=True)
            df2.columns = df2.columns.str.replace(' ', '_').str.replace('.', '_').str.replace('(', '_').str.replace(')', '').str.replace('%', 'percent').str.replace('/', '_').str.replace('__', '_')
            df4.columns = df4.columns.str.replace(' ', '_').str.replace('.', '_').str.replace('(', '_').str.replace(')', '').str.replace('%', 'percent').str.replace('/', '_').str.replace('__', '_')

            df = df.append(df2)
            _df = _df.append(df4) 

        df['a01_date']=df['a01_date'].apply(pd.to_datetime)
        _df['a01_date']=_df['a01_date'].apply(pd.to_datetime)

        df.to_sql('site_diary_general_dc202312', con=conn, if_exists='replace', index= False)
        _df.to_sql('site_diary_general_contractor_management_dc202312', con=conn, if_exists='replace', index= False)

# */2 * * * * Execute every two minute 
with DAG(
        dag_id="dc202312_icwp_site_diary_general",
        schedule_interval="20 15 * * *",
        default_args={
            "owner": "airflow",
            "retries": 1,
            "retry_delay": timedelta(minutes=5),
            "start_date": datetime(2023, 1, 17)
        },
        catchup=False) as f:
    
    getMongoDB = PythonOperator(
        task_id="getMongoDB",
        python_callable=getMongoDB,
        op_kwargs={"name": "Dylan"},
        provide_context=True,
    )

    getDrowToken = PythonOperator(
        task_id="getDrowToken",
        python_callable=getDrowToken,
        provide_context=True,
        # op_kwargs={"name": "Dylan"}
    )

getDrowToken >> getMongoDB