This script has a very specific set of skills

make-it-fit.py

"""
Title: make-it-fit.py
Description: Transforms a very specific csv into a very specific json format
Owner: Elijah C. Voigt <elijah.caine@coreos.com>
Usage: ``python make-it-fit.py > my-output-file.json``
CSV Format: ``Timestamp(optional),Name (First and Last),Start date at CoreOS,End date at CoreOS(optional),Github handle,Primary Coreos email,Other emails used for commits(optional)``
CSV Example Line: ``1/10/2016 12:00:00,Foo Bazington,1/10/2016,1/10/2017,bazington84,foo.bazington@coreos.com,foobazington@someschool.edu,foobazington@yahoo.net``
"""
import json
import datetime
from sys import argv


INPUT_FILE = ''

def blacklist():
    return []

def organizations():
    return {}

def identity(line, index):
    """
    ['Timestamp', 'Name (First and Last)', 'Start date at CoreOS',
     'Github handle', 'Primary Coreos email', 'Other emails used for commits']
    """
    global INPUT_FILE
    line_arr = line.split(',')
    emails = [x.strip().strip('"') for x in line_arr[4:]]
    for email in emails:
        if ' ' in email:
            emails.remove(email)
            emails += email.split(' ')
        if '@' not in email:
            emails.remove(email)

    return {'enrollments': [
                {
                  'end': None,
                  'organization': 'CoreOS', # TODO: extract this from email?
                  'start': datetime.datetime.strptime(line_arr[2], '%m/%d/%Y').isoformat().replace('T',' ') if line_arr[2] else None,
                  'uuid': str(index)
                }
               ],
               'identities': [
                { 
                  'email': email, 
                  'id': str(index),
                  'name': line_arr[1],
                  'soruce': INPUT_FILE,
                  'username': line_arr[3],
                  'uuid': str(index)+str(i)
                } for i, email in enumerate(emails, 0) ],
               'profile': None,
               'uuid': str(index)
              }
    

def uidentities():
    """
    returns:
    {
      #: {
        enrollments: []
        identities: [
          {
            "email": null,
            "id": "0",
            "name": null,
            "source": "example_csv",
            "username": "ncopernico",
            "uuid": "0"
          },
        ],
        "profile": null,
        "uuid": "0"
      } 
    """
    global INPUT_FILE
    with open(INPUT_FILE,'r') as f:
        f.readline().strip().split(',')
        return {int(index): identity(line, index) for index, line in enumerate(f, 0)}


if __name__ == '__main__':
    try:
        INPUT_FILE= argv[1]

        obj = { 'blacklist': blacklist(),
                'organizations': organizations(),
                'soruce': INPUT_FILE,
                'time': datetime.datetime.now().isoformat().replace('T',' '),
                'uidentities': uidentities()
        }

        print(json.dumps(obj,
                         sort_keys=True,
                         indent=2,
                         separators=(',', ': ')))
    except IndexError:
        print("Usage:\n\tpython make-it-fit.py input_file.csv > output_file.json")
    except IOError:
        print("Couldn't find `{}`.\nDid you spell it right?".format(INPUT_FILE))