def test_tokenize_method(self):
tokenizer = nltk.tokenize.TabTokenizer()
blob = tb.TextBlob("This is\ttext.")
# If called without arguments, should default to WordTokenizer
assert_equal(blob.tokenize(), tb.WordList(["This", "is", "text", "."]))
# Pass in the TabTokenizer
assert_equal(blob.tokenize(tokenizer), tb.WordList(["This is", "text."]))
def test_slicing(self):
wl = tb.WordList(self.words)
first = wl[0]
assert_true(isinstance(first, tb.Word))
assert_equal(first, 'Beautiful')
dogs = wl[0:2]
assert_true(isinstance(dogs, tb.WordList))
assert_equal(dogs, tb.WordList(['Beautiful', 'is']))
def test_ngrams(self):
blob = tb.TextBlob("I am eating a pizza.")
three_grams = blob.ngrams()
assert_equal(three_grams, [
tb.WordList(('I', 'am', 'eating')),
tb.WordList(('am', 'eating', 'a')),
tb.WordList(('eating', 'a', 'pizza'))
])
four_grams = blob.ngrams(n=4)
assert_equal(four_grams, [
tb.WordList(('I', 'am', 'eating', 'a')),
tb.WordList(('am', 'eating', 'a', 'pizza'))
])
def test_join(self):
l = ['explicit', 'is', 'better']
wl = tb.WordList(l)
assert_equal(
tb.TextBlob(' ').join(l), tb.TextBlob('explicit is better'))
assert_equal(
tb.TextBlob(' ').join(wl), tb.TextBlob('explicit is better'))
def test_repr(self):
wl = tb.WordList(['Beautiful', 'is', 'better'])
if PY2:
assert_equal(repr(wl),
"WordList([u'Beautiful', u'is', u'better'])")
else:
assert_equal(repr(wl), "WordList(['Beautiful', 'is', 'better'])")
def test_overrides(self):
b = tb.Blobber(tokenizer=SentenceTokenizer(),
np_extractor=ConllExtractor())
blob = b("How now? Brown cow?")
assert_true(isinstance(blob.tokenizer, SentenceTokenizer))
assert_equal(blob.tokens, tb.WordList(["How now?", "Brown cow?"]))
blob2 = b("Another blob")
# blobs have the same tokenizer
assert_true(blob.tokenizer is blob2.tokenizer)
# but aren't the same object
assert_not_equal(blob, blob2)
def test_words(self):
blob = tb.TextBlob('Beautiful is better than ugly. '
'Explicit is better than implicit.')
assert_true(isinstance(blob.words, tb.WordList))
assert_equal(blob.words, tb.WordList([
'Beautiful',
'is',
'better',
'than',
'ugly',
'Explicit',
'is',
'better',
'than',
'implicit',
]))
short = tb.TextBlob("Just a bundle of words")
assert_equal(short.words, tb.WordList([
'Just', 'a', 'bundle', 'of', 'words'
]))
def test_count(self):
wl = tb.WordList(['monty', 'python', 'Python', 'Monty'])
assert_equal(wl.count('monty'), 2)
assert_equal(wl.count('monty', case_sensitive=True), 1)
assert_equal(wl.count('mon'), 0)
def test_strip_and_words(self):
blob = tb.TextBlob('Beautiful is better! ')
assert_equal(blob.strip().words,
tb.WordList(['Beautiful', 'is', 'better']))
def test_upper(self):
wl = tb.WordList(self.words)
assert_equal(wl.upper(), tb.WordList([w.upper() for w in self.words]))
def test_lower(self):
wl = tb.WordList(['Zen', 'oF', 'PYTHON'])
assert_equal(wl.lower(), tb.WordList(['zen', 'of', 'python']))
def test_can_use_an_different_tokenizer(self):
tokenizer = nltk.tokenize.TabTokenizer()
blob = tb.TextBlob("This is\ttext.", tokenizer=tokenizer)
assert_equal(blob.tokens, tb.WordList(["This is", "text."]))
def test_lemmatize(self):
wl = tb.WordList(["cat", "dogs", "oxen"])
assert_equal(wl.lemmatize(), tb.WordList(['cat', 'dog', 'ox']))
def test_tokens_property(self):
assert_true(self.blob.tokens,
tb.WordList(WordTokenizer().tokenize(self.text)))
def test_pluralize(self):
wl = tb.WordList(['dog', 'cat', 'buffalo'])
assert_equal(wl.pluralize(), tb.WordList(['dogs', 'cats',
'buffaloes']))
def test_extend(self):
wl = tb.WordList(["cats", "dogs"])
wl.extend(["buffalo", 4])
assert_true(isinstance(wl[2], tb.Word))
assert_true(isinstance(wl[3], int))
def test_convert_to_list(self):
wl = tb.WordList(self.words)
assert_equal(list(wl), self.words)
def test_len(self):
wl = tb.WordList(['Beautiful', 'is', 'better'])
assert_equal(len(wl), 3)
def test_upper_and_words(self):
blob = tb.TextBlob('beautiful is better')
assert_equal(blob.upper().words,
tb.WordList(['BEAUTIFUL', 'IS', 'BETTER']))
def test_split(self):
blob = tb.TextBlob('Beautiful is better')
assert_equal(blob.split(), tb.WordList(['Beautiful', 'is', 'better']))
def test_append(self):
wl = tb.WordList(['dog'])
wl.append("cat")
assert_true(isinstance(wl[1], tb.Word))
wl.append(('a', 'tuple'))
assert_true(isinstance(wl[2], tuple))
def test_singularize(self):
wl = tb.WordList(['dogs', 'cats', 'buffaloes', 'men', 'mice'])
assert_equal(wl.singularize(),
tb.WordList(['dog', 'cat', 'buffalo', 'man', 'mouse']))
