#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
In this problem set you work with cities infobox data, audit it, come up with a cleaning idea and then clean it up.
In the first exercise we want you to audit the datatypes that can be found in some particular fields in the dataset.
The possible types of values can be:
- 'NoneType' if the value is a string "NULL" or an empty string ""
- 'list', if the value starts with "{"
- 'int', if the value can be cast to int
- 'float', if the value can be cast to float, but is not an int
- 'str', for all other values

The audit_file function should return a dictionary containing fieldnames and the datatypes that can be found in the field.
All the data initially is a string, so you have to do some checks on the values first.

"""
import codecs
import csv
import json
import pprint

CITIES = 'cities.csv'

FIELDS = ["name", "timeZone_label", "utcOffset", "homepage", "governmentType_label", "isPartOf_label", "areaCode", "populationTotal",
          "elevation", "maximumElevation", "minimumElevation", "populationDensity", "wgs84_pos#lat", "wgs84_pos#long",
          "areaLand", "areaMetro", "areaUrban"]

#type(1.1) instead of 'float"
#type(1) instead of 'int'
#type([]) instead of list 'list'
#type(None) instead of 'NoneType"

def is_int(s):
    try:
        int(s)
        return True
    except ValueError:
        return False

def is_float(s):
    try:
        float(s)
        return True
    except ValueError:
        return False

def audit_file(filename, fields):
    with open(filename,'rb') as f:
        fieldtypes={}
        index_fields={}
        for field in f:
            all_fields = field.split('","')
            all_fields[0]=all_fields[0].strip('"')
            if (all_fields[0]=='URI') and (all_fields[1]=='rdf-schema#label'):
                for each_field in fields:
                    print each_field
                    index_fields[each_field]=all_fields.index(each_field)
                    fieldtypes[each_field]=[]
            else:
                for each_field in fields:
                    print each_field
                    cities_index=index_fields[each_field]
                    if (all_fields[cities_index]=='NULL') or (all_fields[cities_index]==''):
                        if type(None) not in fieldtypes[each_field]:
                            fieldtypes[each_field].append(type(None))
                    elif all_fields[cities_index].startswith('{'):
                        if type([]) not in fieldtypes[each_field]:
                            fieldtypes[each_field].append(type([]))
                    elif is_int(all_fields[cities_index]):
                        if type(1) not in fieldtypes[each_field]:
                            fieldtypes[each_field].append(type(1))
                    elif is_float(all_fields[cities_index]):
                        if type(1.1) not in fieldtypes[each_field]:
                            fieldtypes[each_field].append(type(1.1))


    # YOUR CODE HERE


    return fieldtypes


def test():
    fieldtypes = audit_file(CITIES, FIELDS)

    pprint.pprint(fieldtypes)

    assert fieldtypes["areaLand"] == set([type(None),type([]),type(1.1)])
    assert fieldtypes['areaMetro'] == set([type(1.1), type(None)])

if __name__ == "__main__":
    test()