# Importing libraries
from numpy import genfromtxt, savetxt
from time import time
from datetime import datetime
from models import models
from models.database import engine, SessionLocal
# import sustApp.models.models as models
# from sustApp.models.database import engine, SessionLocal

import os, re
from pytz import timezone
import pandas as pd
import glob
#import csv

# def Load_Data(file_name):
#     with open(source_csv, encoding='utf-8-sig') as f:
#         for line in f:
#             fields = line.strip().split(';')
#             print(fields)

def Load_Data(file_name):
    df = pd.read_csv(file_name, delimiter=';', encoding='utf-8-sig', dtype=str, header=None)
    print(df.head())
    return df.values.tolist()

# def Load_Data(file_name):
#     #data = genfromtxt(file_name, delimiter=';', skip_header=1, converters={0: lambda s: str(s)})
#     #str2date = lambda x: datetime.strptime(x, '%d-%m-%y')
#     data = genfromtxt(file_name, delimiter=';', dtype=None, skip_header=0, encoding='utf-8-sig')

#     return data.tolist()

# def Load_Data(file_name):
#     data = []
#     with open(file_name, encoding='utf-8-sig') as f:
#         reader = csv.reader(f, delimiter=';')
#         for row in reader:
#             data.append(row)
#     return data

def extract_values(text):
    # Regular expressions to match the required fields
    regex_patterns = {
        'Auftraggeber': r'Auftraggeber: (.*?) (Verwendungszweck|Zahlungsreferenz|IBAN|BIC)',
        'Verwendungszweck': r'Verwendungszweck: (.*?) (Zahlungsreferenz|IBAN|BIC)',
        'Zahlungsreferenz': r'Zahlungsreferenz: (.*?) (Verwendungszweck|IBAN|BIC)',
        'IBAN': r'IBAN Auftraggeber: (.*?) ',
        'BIC': r'BIC Auftraggeber: (.*?)$'
    }
    
    # Initialize an empty list to store extracted information
    extracted_info = []
    
    # Initialize an empty dictionary to store information from this row
    row_info = {}
    
    # Extract information using regular expressions
    for key, pattern in regex_patterns.items():
        match = re.search(pattern, text)
        if match:
            row_info[key] = match.group(1)
        else:
            row_info[key] = None
    
    # Append the extracted information from this row to the list
    extracted_info.append(row_info)
    
    return extracted_info

if __name__ == "__main__":
    t = time()

    db = SessionLocal()
    models.Base.metadata.create_all(bind=engine)

    try:
        home_directory = os.path.expanduser('~')
        source_path = os.path.join(home_directory, "OneDrive", "Dokumente", "SUST", "import_csv", "*.csv")
        for source_csv in glob.glob(source_path):
            if '_out.csv' not in source_csv:
                #source_csv = os.path.join(home_directory, "OneDrive", "Dokumente", "SUST", "import_csv", "UmsatzListe_AT493443700000113407_20250529_091945_mod.csv")
                target_csv = source_csv.replace(".csv", "_out.csv")
                data = Load_Data(source_csv) 

                tz = timezone('UTC')  # Replace with your desired timezone
                outData = []
                for i in data:
                    if ('Auftraggeber' in i[1]):
                        # extract key-value pairs Auftraggeber, Verwendungszweck, Zahlungsreferenz, IBAN
                        new_list = extract_values(i[1])

                        if len(new_list) > 0:
                            outData.append([i[0], new_list[0].get('Auftraggeber'), new_list[0].get('Zahlungsreferenz'), new_list[0].get('Verwendungszweck'), new_list[0].get('IBAN'), i[2], i[3].replace(',','.'), i[4], i[5]])
                
                # Replace None with empty string before saving
                outData = [['' if x is None else x for x in row] for row in outData]
                savetxt(target_csv, outData, delimiter=";", encoding='utf-8', header='valuta_date;client;reference;intended;IBAN;entry_date;amount;currency;timestamp', fmt='%s')
                bak_dir = os.path.join(os.path.dirname(source_csv), "bak")
                os.makedirs(bak_dir, exist_ok=True)
                os.rename(source_csv, os.path.join(bak_dir, os.path.basename(source_csv)))

    except Exception as e:
        print (e)
    finally:
        print("Time elapsed: " + str(time() - t) + " s.") #0.091s