scripts/tsv2universities.py

#!/usr/bin/env python
#
# Copyright 2014 the Melange authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Converts the GSoC Schools spreadsheet to a python dictionary.

Converts the GSoC Schools spreadsheet (in tsv format) to a python
dictionary suitable for inclusion in app/soc/models/universities.py.

The input file is a tab delimited file containing three columns:
country, school, and (optional and unused) url.  The first two lines
are skipped as headers.

Output is written to STDOUT.
"""

import collections
import pprint
import sys


def main(argv):
  if len(argv) != 2:
    print "Usage: %s <schools.tsv>" % argv[0]
    sys.exit(1)

  universities_file = file(argv[1])

   # first two lines are headers
  universities_file.readline()
  universities_file.readline()

  universities = collections.defaultdict(list)
  count = 0

  for line in universities_file:
    country, school, unused_url = line.split("\t", 3)

    if country and school:
      count += 1
      universities[country].append(school)

  pp = pprint.PrettyPrinter()
  # convert the collections.defaultdict back to a dict so pprint can
  # make it prettier.
  pp.pprint(dict(universities))

  print >>sys.stderr, "%d schools extracted." % count

if __name__ == "__main__":
  main(sys.argv)