:::python
#!/usr/bin/env python
from __future__ import print_function

import sys
import json
import re

def parse_subtokens(tokens):
    """ Parses subtokens and returns a dictionary. If invalid, None is returned.

    We expect all user agents to start with "HBR MOBILE", after which we can encounter
    OS, device, app, authentication, browser, and app version strings. Everything except
    version is matched using exact string comparisons. Version uses a regex.
    """
    res = {'OS': 'N/A', 'DEVICE': 'N/A', 'APP': 'N/A', 'AUTH': 'N/A', 'VERSION': 'N/A', 'BROWSER': 'N/A'}

    token_mapping = {'ANDROID': 'OS', 'IOS': 'OS',
                     'PHONE': 'DEVICE', 'TABLET': 'DEVICE',
                     'MYBLOCK': 'APP', 'TAXES': 'APP',
                     'TOUCHID': 'AUTH', 'FACEID': 'AUTH',
                     'Mozilla': 'BROWSER'}

    if tokens[0] != 'HRB':
        return None

    if tokens[1] != 'MOBILE':
        return None

    for token in tokens[2:]:
        if token in token_mapping:
            res[token_mapping[token]] = token
        elif re.match('v?[0-9]+\.[0-9]+\.[0-9]+', token):
            res['VERSION'] = token
        else:
            print('WARNING: Unknown token: %s from %s' % (token, str(tokens)), file=sys.stderr)

    # Cleanups:
    #     1) Some versions of the Android app prefix 'v' onto version

    if res['VERSION'][0] == 'v':
        res['VERSION'] = res['VERSION'][1:]

    assert len(res) == 6
    return res

def is_hrb(year, filter, line):
    """ Validate that a line should be parsed and added to the buckets.

    Specifically, entry should contain the right year, be a HRB user-agent,
    and contain the filter keyword if one was provided.
    """
    if line[:4] != year:
        return False
    if line[11:14] != 'HRB':
        return False
    if not filter is None and not filter in line:
        return False
    return True

if __name__ == '__main__':

    if len(sys.argv) < 3:
        print('Usage: %s <tax-year> [filter] <filepath>' % sys.argv[0])
        sys.exit(0)

    if len(sys.argv) == 3:
        filter = None
    else:
        filter = sys.argv[2]

    with open(sys.argv[-1], 'r') as ifile:
        data = [line.strip() for line in ifile if is_hrb(sys.argv[1], filter, line)]

    buckets = {
        'OS': {
            'IOS':     0,
            'ANDROID': 0,
        },
        'DEVICE': {
            'PHONE':   0,
            'TABLET':  0,
        },
        'APP': {
            'MYBLOCK': 0,
            'TAXES':   0,
        },
        'AUTH': {
            'TOUCHID': 0,
            'FACEID':  0,
            'N/A':     0,
        },
        'VERSION': {},
        'BROWSER': {},
    }

    for line in data:
        tokens = line.split(',')
        if len(tokens) != 3:
            print('WARNING: Cannot tokenize: %s' % line, file=sys.stderr)
            continue

        subtokens = parse_subtokens(tokens[1].split('-'))
        if subtokens is None:
            print('WARNING: Cannot subtokenize: %s' % tokens[1].split('-'), file=sys.stderr)
            continue

        try:
            count = int(tokens[-1])
        except ValueError:
            print('WARNING: Could not parse count from: %s' % line, file=sys.stderr)
            continue

        buckets['OS'][subtokens['OS']]         += count
        buckets['DEVICE'][subtokens['DEVICE']] += count
        buckets['APP'][subtokens['APP']]       += count
        buckets['AUTH'][subtokens['AUTH']]     += count

        if subtokens['VERSION'] in buckets['VERSION']:
            buckets['VERSION'][subtokens['VERSION']] += count
        else:
            buckets['VERSION'][subtokens['VERSION']] = count

        if subtokens['BROWSER'] in buckets['BROWSER']:
            buckets['BROWSER'][subtokens['BROWSER']] += count
        else:
            buckets['BROWSER'][subtokens['BROWSER']] = count

    print(json.dumps(buckets, indent=4))