Idiolectalyzer/tests/test_ngramparser.py

import unittest
import sys
import string
from operator import itemgetter
import re
import collections
import os
sys.path.append("../dataparsers")
import parse_google_ngram

class testNgramParser(unittest.TestCase):
    def test1gramParser(self):
        ngramFile = "mockdata/unlikely1gram.txt"
        generatedFile = "mockdata/frequencyfile.txt"
        startYear = 1980
        minLength = 1
        maxWords = 4
        expectedGeneratedList = ['alcock', 'alberico', 'alkalinizing', "al'cock"]
        word_list = {}
        assert os.path.isfile(ngramFile)
        parse_google_ngram.process_ngram_file(ngramFile, word_list)
        sorted_list = sorted(word_list.iteritems(), key=itemgetter(1), reverse=True)
        generatedList=parse_google_ngram.build_word_list(sorted_list, generatedFile, maxWords, minLength)
        assert os.path.isfile(generatedFile)
        self.assertEqual(generatedList,expectedGeneratedList)
        os.remove(generatedFile)
if __name__ == '__main__':
    unittest.main()