def test_problematic_patterns(self):
self.obj._modifiers = [
Modifiers.CaseConverter(),
Modifiers.RegexpReplacer()
]
self.obj._filters = [
Filters.NumeralFilter(),
Filters.PunctuationFilter()
]
# patterns which had problems in testing of program
problem_strings = ['..']
for ps in problem_strings:
self.assertEqual(None, self.obj.process(ps))
def test_happy_run_filters(self):
test = self.faker.word()
nf = Filters.NumeralFilter()
print(type(nf))
self.assertTrue(isinstance(nf, Filters.IFilter))
self.obj.add_filters(nf)
self.obj.add_filters(Filters.PunctuationFilter())
self.assertTrue(len(self.obj._filters) is 2)
self.assertEqual(True, self.obj._run_filters(test))
with self.assertRaises(ExcludedString):
self.obj._run_filters('5')
with self.assertRaises(ExcludedString):
self.obj._run_filters('.')
def test_happy_process(self):
self.obj._modifiers = [
Modifiers.CaseConverter(),
Modifiers.RegexpReplacer()
]
self.obj._filters = [
Filters.NumeralFilter(),
Filters.PunctuationFilter()
]
# should make lowercase and replace contraction
self.assertEqual('taco', self.obj.process('Taco'))
self.assertEqual("will not", self.obj.process("WON'T"))
# with self.assertRaises(ExcludedString):
self.assertEqual(None, self.obj.process(43))
# with self.assertRaises(ExcludedString):
self.assertEqual(None, self.obj.process('.'))
def setUp(self):
self.object = Filters.UsernameFilter()
def setUp(self):
self.object = Filters.URLFilter()
def test_happy_path_number(self):
self.obj = Filters.PunctuationFilter()
test = 5
self.assertTrue(self.obj.run(test))
def test_happy_path_num_string(self):
self.obj = Filters.PunctuationFilter()
test = '5'
self.assertTrue(self.obj.run(test))
def test_happy_path_punctuation(self):
self.obj = Filters.PunctuationFilter()
for i in list(string.punctuation):
with self.assertRaises(ExcludedString):
self.obj.run(i)
def test_happy_path_num_string(self):
self.obj = Filters.NumeralFilter()
test = '5'
self.assertFalse(self.obj.run(test))
def test_happy_path_is_string(self):
self.obj = Filters.NumeralFilter()
test = 'taco'
self.assertRaises()
self.assertTrue(self.obj.run(test))
def test_add_to_ignorelist_string(self):
self.obj = Filters.IgnoreListFilter()
test = 'taco'
self.obj.add_to_ignorelist(test)
self.assertIsInstance(self.obj._ignore, tuple)
self.assertEqual(self.obj._ignore, tuple([test]))
def test_add_to_ignorelist_list(self):
self.obj = Filters.IgnoreListFilter()
test = ['taco', 'cat', 'fish']
self.obj.add_to_ignorelist(test)
self.assertIsInstance(self.obj._ignore, tuple)
[self.assertIn(w, self.obj._ignore) for w in test]
def setUp(self):
self.object = Filters.StopwordFilter()
self.stopwords = english_stops
def setUp(self):
self.object = Filters.NumeralFilter()
def test_expected_inheritance(self):
obj = Filters.NumeralFilter()
print(type(obj))
# self.assertTrue(inspect.isclass(obj))
# self.assertTrue(issubclass(obj, Filters.IFilter))
self.assertTrue(isinstance(obj, Filters.IFilter))
import unittest
from TextProcessingTools.TextTools.Filtration import Filters
from TextProcessingTools.TextTools.Replacement import Modifiers
from TextProcessingTools.StatisticalTools import Counters as C
filters = [
Filters.UsernameFilter(),
Filters.PunctuationFilter(),
Filters.URLFilter(),
Filters.NumeralFilter()
]
modifiers = [Modifiers.WierdBPrefixConverter(), Modifiers.CaseConverter()]
class SelectedCounterTests(unittest.TestCase):
def setUp(self):
self.obj = C.SelectedWordCounter()
self.obj.add_filters(filters)
self.obj.add_modifiers(modifiers)
def test_process_count(self):
test = "My cat eats food of cat"
self.obj.set_words_to_count(['my', 'cat', 'eats'])
expected = {'my': 1, 'cat': 2, 'eats': 1}
self.obj.process(test)
# check
for k in expected.keys():
self.assertEqual(self.obj.counts[k], expected[k])