def setUp(self):
# make sure to create a new Parser for each test
self.prs = Parser(wordlist=[],
addons=dict(),
stems=dict(),
uniques=dict(),
inflects=dict(),
wordkeys=set())
def setUpClass(cls):
cls.par = Parser()
def setUpClass(cls):
cls.par = Parser()
cls.full_par = Parser(frequency="X")
class MinimalDictionaryParseTest(unittest.TestCase):
def setUp(self):
# make sure to create a new Parser for each test
self.prs = Parser(wordlist=[],
addons=dict(),
stems=dict(),
uniques=dict(),
inflects=dict(),
wordkeys=set())
def test_empty(self):
result = self.prs.parse("word")
self.assertEqual(result.forms, [])
def test_minimal_functional(self):
self.prs.data.wordkeys.add("")
self.prs.data.inflects["0"] = {'': [{'ending': ''}]}
result = self.prs.parse("word")
self.assertEqual(result.forms, [])
def test_minimal_with_result(self):
word: DictEntry = {
'orth': 'word',
'pos': 'NUM',
'n': ['a'],
'form': ['CARD'],
'wid': 0,
'parts': ['word'],
'senses': []
}
self.prs.data.wordkeys.add("word")
self.prs.data.empty = {
'NUM': [{
'ending': '',
'pos': 'NUM',
'n': ['a'],
'form': ['X', 'X', 'X', 'CARD'],
'iid': 0,
'stem': 0
}]
}
self.prs.data.stems["word"] = [word]
self.prs.data.wordlist.append(word)
result = self.prs.parse("word")
self.assertEqual(len(result.forms), 1)
self.assertEqual(len(result.forms[0].analyses), 1)
self.assertEqual(result.forms[0].analyses[0].lexeme.category, ['a'])
self.assertEqual(result.forms[0].analyses[0].lexeme.wordType,
WordType.NUM)
self.assertEqual(len(result.forms[0].analyses[0].inflections), 1)
self.assertEqual(result.forms[0].analyses[0].inflections[0].category,
['a'])
self.assertEqual(result.forms[0].analyses[0].inflections[0].wordType,
WordType.NUM)
def test_minimal_empty_unique(self):
self.prs.data.uniques['word'] = []
result = self.prs.parse("word")
self.assertEqual(result.forms, [])
def test_minimal_unique_with_result(self):
word: Unique = {
'orth': 'word',
'pos': 'PREP',
'n': [],
'form': 'a cdef',
'senses': []
}
self.prs.data.uniques['word'] = [word]
result = self.prs.parse("word")
self.assertEqual(len(result.forms), 1)
self.assertEqual(len(result.forms[0].analyses), 1)
self.assertEqual(result.forms[0].analyses[0].lexeme.category, [])
self.assertEqual(result.forms[0].analyses[0].lexeme.wordType,
WordType.PREP)
def test_minimal_unique_with_addon(self):
word = {'orth': 'wor', 'pos': 'PREP', 'form': 'abc', 'senses': []}
self.prs.data.uniques['wor'] = [word]
self.prs.data.addons['tackons'] = [{
'orth': 'd',
'pos': '',
'senses': []
}]
result = self.prs.parse("word")
self.assertEqual(len(result.forms), 1)
self.assertEqual(result.forms[0].enclitic.text, 'd')
self.assertEqual(result.forms[0].text, 'wor')
self.assertEqual(len(result.forms[0].analyses), 1)
self.assertEqual(result.forms[0].analyses[0].lexeme.category, [])
self.assertEqual(result.forms[0].analyses[0].lexeme.wordType,
WordType.PREP)
def test_subsetting_interference(self):
subsetParser = Parser()
fullParser = Parser(frequency="X")
self.assertNotEqual(len(subsetParser.data.stems), len(fullParser.data.stems))