def setUp(self):
self.maxDiff = None
options.cfg = argparse.Namespace()
options.cfg.number_of_tokens = 0
options.cfg.limit_matches = False
options.cfg.regexp = False
options.cfg.query_case_sensitive = False
options.get_configuration_type = lambda: SQL_MYSQL
self.Session = MockOptions()
self.Session.Resource = self.resource
self.Session.Lexicon = None
self.Session.Corpus = None
COCAToken.set_pos_check_function(self.pos_check_function)
def test_token_conditions_lemmatized_deep_2(self):
S = "#/a*/"
token = COCAToken(S, self.Session)
d = self.resource.get_token_conditions(0, token)
self.assertEqual(
self.simple(d["word"][0]),
self.simple("""
COQ_LEMMA_1.Lemma IN
(SELECT DISTINCT Lemma
FROM Lexicon AS COQ_WORD_1
INNER JOIN Lemmas AS COQ_LEMMA_1
ON COQ_LEMMA_1.LemmaId = COQ_WORD_1.LemmaId
WHERE (COQ_WORD_1.Transcript LIKE 'a%'))"""))
def test_token_conditions_lemmatized_flat_1(self):
self.Session.Resource = self.flat_resource
S = "#abc"
token = COCAToken(S, self.Session)
d = self.flat_resource.get_token_conditions(0, token)
self.assertEqual(
self.simple(d["word"][0]),
self.simple("""
COQ_WORD_1.Lemma IN
(SELECT DISTINCT Lemma
FROM Lexicon AS COQ_WORD_1
WHERE (COQ_WORD_1.Word = 'abc'))"""))
self.Session.Resource = self.resource
def test_token_condition_empty_4(self):
token = COCAToken("a*.[*]")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d,
{"word": ["COQ_WORD_1.Word LIKE 'a%'"]})
def test_token_condition_empty_3(self):
token = COCAToken("*.[n*]")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d,
{"word": ["COQ_WORD_1.POS LIKE 'n%'"]})
def test_token_condition_empty_2(self):
token = COCAToken("*.[*]")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d, {})
def test_get_token_conditions_quote_char_2(self):
token = COCAToken("'ll|ll")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d,
{"word": ["COQ_WORD_1.Word IN ('''ll', 'll')"]})
def test_get_token_conditions_5(self):
token = COCAToken("*'ll")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d,
{"word": ["COQ_WORD_1.Word LIKE '%''ll'"]})
def test_get_token_conditions_3(self):
token = COCAToken("[a*|b*]")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d, {"lemma": ["COQ_LEMMA_1.Lemma LIKE 'a%' OR COQ_LEMMA_1.Lemma LIKE 'b%'"]})
def test_get_token_conditions_2(self):
token = COCAToken("a*|b*.[n*]")
d = self.resource.get_token_conditions(0, token)
self.assertDictEqual(d, {"word": ["COQ_WORD_1.Word LIKE 'a%' OR COQ_WORD_1.Word LIKE 'b%'",
"COQ_WORD_1.POS LIKE 'n%'"]})