import re
import json

#this is a test comment

person_list = []

with open("Studienleistung2/Personen.txt") as input:
    for lines in input:
        current_line = lines.split(",")

        titel = re.findall(r"([A-Z][a-z]+\.)", current_line[0])

        name = re.findall(r"([A-Z][a-z]+[^\.]*$)", current_line[0])
        name = re.split("\s", name[0])

        # getting the fragments building the whole name
        first_name = name[0]

        # if there are more than one second names 
        second_name = ""
        counter = 1
        while counter<len(name)-1:
            second_name = second_name + name[counter] + " "
            counter += 1

        # -1 to get the last elem of the list name
        last_name = name[-1]


        address = re.findall(r"(.+)([1-9]+).([\d]{5})(.+)", current_line[1])
        address = address[0]

        street_name = address[0]
        house_number = address[1]
        plz = address[2]
        city = address[3]

        geb_date = re.findall("([0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])", current_line[2])
        tel = re.findall("(\d{12,15})", current_line[3])




        person = {
            "titel": titel[0],
            "Vorname": first_name,
            "Zweitname": second_name,
            "Nachname": last_name,
            "Straße": street_name,
            "Hausnummer": house_number,
            "PLZ": plz,
            "Stadt": city,
            "Geb.Datum": geb_date[0],
            "Tel.": tel[0],
        }
        
        person_list.append(person)



with open("Studienleistung2/Person_Neu.json", "w") as outfile:
    json.dump(person_list, outfile, indent=2, ensure_ascii=False)