def test_tag_pattern_defaults(self):
_tagger = PatternTagger()
tags = _tagger.tag(self.text)
logging.debug("tags: {0}".format(tags))
words = ["Das", "ist", "ein", "schönes", "Auto"]
for i, word_tag in enumerate(tags):
assert_equal(word_tag[0], words[i])
def test_tag_nltk_tok(self):
_tagger = PatternTagger(tokenizer=NLTKPunktTokenizer())
tags = _tagger.tag(self.text)
logging.debug("tags: {0}".format(tags))
words = ["Das", "ist", "ein", "schönes", "Auto"]
for i, word_tag in enumerate(tags):
assert_equal(word_tag[0], words[i])
def test_tag_blob_pattern_tok_include_punc(self):
blob = TextBlob(self.text, tokenizer=PatternTokenizer(),
pos_tagger=PatternTagger(include_punc=True))
tags = blob.tags
logging.debug("tags: {0}".format(tags))
words = ["Das", "ist", "ein", "schönes", "Auto", "."]
for i, word_tag in enumerate(tags):
assert_equal(word_tag[0], words[i])
def test_tag_blob_nltk_tok_include_punc_stts(self):
blob = TextBlob(
self.text,
tokenizer=NLTKPunktTokenizer(),
pos_tagger=PatternTagger(
include_punc=True,
tagset='stts'))
tags = blob.tags
logging.debug("tags: {0}".format(tags))
words = ["Das", "ist", "ein", "schönes", "Auto", "."]
stts_tags = ["PDS", "VVFIN", "ARTIND", "ADJA", "NN", "S"]
for i, word_tag in enumerate(tags):
assert_equal(word_tag[0], words[i])
assert_equal(word_tag[1], stts_tags[i])
assert_equal(tags[-1][0], ".")