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/61e27b64b3e8d9753110ee97?export_type=0",
    headers={
    "x-access-token": f"Bearer {token}",
    }
    )
    # print('got_data')
    # print(response)
    Data = json.loads(response.text)
    Mapping= {
            "Original Doc No.": "Original_Doc_No",
            "NEC Doc Type": "NEC_Doc_Type",
            "NEC Event No.": "NEC_Event_No",
            "Doc Ver.": "Doc_Ver",
            "Doc Date": "Doc_Date",
            "Subject": "Subject",
            "From": "From",
            "To": "To",
            "CE Amount": "CE_PMI_Amount",
            "CE Increase / Decrease": "CE_Increase_Decrease",
            "Quotation Status": "Quotation_Status",
            "NEC Clause": "NEC_Clause",
            "Receive Date": "Receive_Date"
    }
    # print('start transform')
    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"

    # #cursor Type
    # cusrsorType            = pymysql.cursors.DictCursor



    #create_engine('mysql+mysqldb://root:password@localhost:3306/mydbname', echo = False)
    conn_string = ('postgres://' +
                           dbUserName + ':' + 
                           dbUserPassword +
                           '@' + host + ':' + port +
                           '/' + database)

    # df = context.get("ti").xcom_pull(key="InsertData")
    # print(df)
    # conn_string = 'postgres://user:password@host/data1'
    
    db = create_engine(conn_string)
    conn = db.connect()
    # print('db connected')
    df = pd.DataFrame()
    i=0
    with conn as conn:
        for x in Data:
            try:
                if len(x['data'].keys()) == 0:
                    continue
                df_nested_list = json_normalize(x['data'])
                # print('process 1')
                # print(x['data'].keys())
                df2 = df_nested_list.reindex(columns=Mapping.keys())
                df2['record_status'] = x['Status']
                df2['NEC Doc Title']=x['data']['NEC Doc Type']+x['data']['NEC Event No.']
                df2['Doc Org Ver']= x['data']['Doc Ver.']
                if x['data']['Receive Date']=='' or x['data']['Receive Date']==None:
                    # print('Doc Title:', df2['NEC Doc Title'])
                    # print('Data:', x['data'])
                    df2['withReceiveDate'] = False
                else:
                    df2['withReceiveDate'] = True
                if x['data']['Receive Date']=='' or x['data']['Receive Date']==None:
                    df2['Receive Date']=x['data']['Doc Date']
                
                y=0
                if x['data']['Doc Ver.'] == None:
                    df2['Doc Ver.'] = y
                elif x['data']['Doc Ver.'].startswith('Rev. '):
                    y = x['data']['Doc Ver.'].replace('Rev. ', '')
                    y = int(y)
                else:
                    y = x['data']['Doc Ver.'].replace('-', '').replace('r','')
                    if y!='' and not y.isnumeric():
                        # print('ver',y)
                        y = int(ord(y)) - int(ord('A')) + 1
                        # print(y)
                    elif y =='':
                        y = 0
                    else :
                        y = int(y)
                    df2['Doc Ver.'] = y
                if (not df2['NEC Doc Title'].empty and 'NEC Doc Title' in df.columns):
                    # print (y)
                    # print('NEC Doc Title' in df.columns)
                    check_ver_df = df.loc[(df['NEC Doc Title'] == x['data']['NEC Doc Type']+x['data']['NEC Event No.'])]
                    if check_ver_df.empty:
                        df2['is_latest'] = 'Yes'
                    else :
                        check_ver_df2 = check_ver_df.loc[(check_ver_df['Doc Ver.'] > y)]
                        if not check_ver_df2.empty:
                            df2['is_latest'] = "No"
                        else:
                            df.loc[(df['NEC Doc Title'] == x['data']['NEC Doc Type']+x['data']['NEC Event No.']) & ( df['Doc Ver.']<y), 'is_latest'] = 'No'
                            df2['is_latest'] = 'Yes'
                else:
                    df2['is_latest'] = 'Yes'
                df2['NEC Doc Title With Version']=x['data']['NEC Doc Type']+x['data']['NEC Event No.']+'-'+str(y)
                
                if (x['data'].get('NEC Doc Type') or '').strip().upper() == 'PMN-' and y==0 and (x['Status'] == 'Receipt by Contractor' or x['Status'] == 'Closed'):
                    df2['From_Status'] = '1. CE notified'
                elif (x['data'].get('NEC Doc Type') or '').strip().upper() == 'CSQ-' and y==0:
                    df2['From_Status'] = '2. Quotation Submitted'
                elif (x['data'].get('NEC Doc Type') or '').strip().upper() == 'QA-' and y==0 and (x['Status'] == 'Receipt by Contractor' or x['Status'] == 'Closed'): # Add current status = Receipt by Contractor 
                    df2['From_Status'] = '3. CE implemented'
                else:
                    df2['From_Status'] = None

                if len(x['data']['Change to Time'])>0 and x['data']['NEC Doc Type']!='EW-':
                    df4=pd.DataFrame()
                    for change_to_time_table in x['data']['Change to Time']:
                        df3=df2.copy()
                        i = i+1
                        if 'Key Date' in change_to_time_table:
                            df3['Key Date'] = change_to_time_table['Key Date']
                        if 'Extension in days' in change_to_time_table:
                            df3['Extension in days'] = change_to_time_table['Extension in days']
                        if 'Ori Completion Date' in change_to_time_table:
                            df3['Ori Completion Date'] = change_to_time_table['Ori Completion Date']
                        if 'Revised Completion Date' in change_to_time_table:
                            df3['Revised Completion Date'] = change_to_time_table['Revised Completion Date']
                        if i >0:
                            df2['From_Status'] = None
                        df4 = df4.append(df3)
                    i = 0
                    df2 = df2.iloc[0:0]
                    df2=df2.append(df4)
                    # print('process 2')
                    # print('loading into DB')
                df = df.append(df2)
            except:
                continue
        # df['is_latest'].fillna('No',inplace=True)
        df.rename(columns=Mapping, inplace=True)
        fields_to_adjust = ['Doc_Date', 'Ori Completion Date', 'Revised Completion Date', 'Receive_Date']

        for field in fields_to_adjust:
            if field in df.columns:
                df[field] = df[field].apply(pd.to_datetime)
                df[field] = df[field] - pd.Timedelta(hours=8)
        # df['Doc_Date']=df['Doc_Date'].apply(pd.to_datetime)
        # df['Doc_Date'] = df['Doc_Date'] - pd.Timedelta(hours=8)
        # df['Ori Completion Date']=df['Ori Completion Date'].apply(pd.to_datetime)
        # df['Ori Completion Date'] = df['Ori Completion Date'] - pd.Timedelta(hours=8)
        # df['Revised Completion Date']=df['Revised Completion Date'].apply(pd.to_datetime)
        # df['Revised Completion Date'] = df['Revised Completion Date'] - pd.Timedelta(hours=8)
        df.columns = df.columns.str.replace(' ', '_').str.replace('.', '').str.replace('(', '_').str.replace(')', '').str.replace('%', 'percent').str.replace('/', '_')
        
        # Received_Date need +800
        def handle_quotation_status(row, df):
            if row['Quotation_Status'] == 'Quotation to be submitted':
                # Filter the DataFrame for the same event and specific document type
                same_event_df = df[(df['NEC_Event_No'] == row['NEC_Event_No']) & (df['NEC_Doc_Type'] == 'CSQ-')]

                # Check if the DataFrame is not empty
                if not same_event_df.empty:
                    # Get the latest document
                    latest_pmn = same_event_df.sort_values(by='Receive_Date', ascending=False).iloc[0] 
                    # Calculate the difference in months
                    months_diff = (row['Receive_Date'] - latest_pmn['Receive_Date']).days / 30
                    if months_diff > 24:
                        return 'Quotation to be submitted > 24 months'
                    else:
                        return 'Quotation to be submitted < 24 months'
                else:
                    # No CSQ records found, calculate the difference from today
                    latest_receive_date = row['Receive_Date']
                    today = pd.Timestamp.today().tz_localize(None).normalize()  # Make today timezone-naive
                    latest_receive_date = latest_receive_date.tz_localize(None).normalize()  # Make latest_receive_date timezone-naive
                    months_diff = (today - latest_receive_date).days / 30
                    if months_diff > 24:
                        return 'Quotation to be submitted > 24 months'
                    else:
                        return 'Quotation to be submitted < 24 months'

            elif row['Quotation_Status'] == 'Quotation to be assessed':
                # Filter the DataFrame for the same event and specific document type
                same_event_df = df[(df['NEC_Event_No'] == row['NEC_Event_No']) & (df['NEC_Doc_Type'] == 'QA-')]

                # Check if the DataFrame is not empty
                if not same_event_df.empty:
                    # Get the latest document
                    latest_pmn = same_event_df.sort_values(by='Receive_Date', ascending=False).iloc[0]
                    # Calculate the difference in months
                    months_diff = (row['Receive_Date'] - latest_pmn['Receive_Date']).days / 30
                    if months_diff > 24:
                        return 'Quotation to be assessed > 24 months'
                    else:
                        return 'Quotation to be assessed < 24 months'
                else:
                    latest_receive_date = row['Receive_Date']
                    today = pd.Timestamp.today().tz_localize(None).normalize()  # Make today timezone-naive
                    latest_receive_date = latest_receive_date.tz_localize(None).normalize()  # Make latest_receive_date timezone-naive
                    months_diff = (today - latest_receive_date).days / 30
                    if months_diff > 24:
                        return 'Quotation to be assessed > 24 months'
                    else:
                        return 'Quotation to be assessed < 24 months'
            else:
                return row['Quotation_Status']
        
        df['Quotation_Status'] = df.apply(lambda row: handle_quotation_status(row, df), axis=1)
        df['Receive_Date'] = df['Receive_Date'].apply(pd.to_datetime) + pd.Timedelta(hours=8)

        def handle_ce_status(row, df):
            same_event_df = df[df['NEC_Event_No'] == row['NEC_Event_No']]
            doc_types = same_event_df['NEC_Doc_Type'].unique()
            same_event_df.sort_values(by='Receive_Date', axis=0, ascending=False, inplace=True)
            today = pd.Timestamp.today().tz_localize(None).normalize()

            if 'QA-' in doc_types:
                latest_row = same_event_df[same_event_df['NEC_Doc_Type'] == 'QA-'].iloc[0]
                if row['NEC_Doc_Type'] == 'QA-' and row['Receive_Date'] == latest_row['Receive_Date']:
                    return 'CE implemented'

            elif 'CSQ-' in doc_types:
                latest_row = same_event_df[same_event_df['NEC_Doc_Type'] == 'CSQ-'].iloc[0]
                if row['NEC_Doc_Type'] == 'CSQ-' and row['Receive_Date'] == latest_row['Receive_Date']:
                    latest_receive_date = row['Receive_Date'].tz_localize(None).normalize()
                    months_diff = (today - latest_receive_date).days / 30
                    if months_diff > 24:
                        return 'Quotation to be assessed > 24 months'
                    else:
                        return 'Quotation to be assessed < 24 months'

            elif 'PMIQ-' in doc_types:
                latest_row = same_event_df[same_event_df['NEC_Doc_Type'] == 'PMIQ-'].iloc[0]
                if row['NEC_Doc_Type'] == 'PMIQ-' and row['Receive_Date'] == latest_row['Receive_Date']:
                    # Calculate the difference in months
                    latest_receive_date = row['Receive_Date'].tz_localize(None).normalize()
                    months_diff = (today - latest_receive_date).days / 30
                    if months_diff > 24:
                        return 'Quotation to be submitted > 24 months'
                    else:
                        return 'Quotation to be submitted < 24 months'

            elif 'PMN-' in doc_types:
                latest_row = same_event_df[same_event_df['NEC_Doc_Type'] == 'PMN-'].iloc[0]
                if row['NEC_Doc_Type'] == 'PMN-':
                    return 'CE to be notified'
            
            elif 'PMI-' in doc_types:
                latest_row = same_event_df[same_event_df['NEC_Doc_Type'] == 'PMI-'].iloc[0]
                if row['NEC_Doc_Type'] == 'PMI-':             
                    return 'CE to be notified'
            
            return ''
        
        df['CE_Status'] = df.apply(lambda row: handle_ce_status(row, df), axis=1)
        df['Receive_Date'] = df['Receive_Date'].apply(pd.to_datetime) + pd.Timedelta(hours=8)

        df.to_sql('nec_c04', con=conn, if_exists='replace', index= False)