spaCy/tests/test_tokenizer.py

122 lines
2.9 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2014-12-21 09:38:27 +00:00
import pytest
2014-12-21 09:38:27 +00:00
from spacy.en import English
2014-12-21 09:38:27 +00:00
@pytest.fixture
def EN():
2014-12-30 10:34:09 +00:00
return English()
2014-12-21 09:38:27 +00:00
def test_single_word(EN):
tokens = EN(u'hello')
assert tokens[0].string == 'hello'
2014-12-21 09:38:27 +00:00
def test_two_words(EN):
tokens = EN('hello possums')
assert len(tokens) == 2
assert tokens[0].string != tokens[1].string
2014-12-21 09:38:27 +00:00
def test_punct(EN):
tokens = EN('hello, possums.')
assert len(tokens) == 4
assert tokens[0].string == 'hello'
assert tokens[1].string == ','
assert tokens[2].string == 'possums'
assert tokens[1].string != 'hello'
2014-12-21 09:38:27 +00:00
def test_digits(EN):
tokens = EN('The year: 1984.')
assert len(tokens) == 5
assert tokens[0].sic == EN.vocab['The'].sic
assert tokens[3].sic == EN.vocab['1984'].sic
2014-12-21 09:38:27 +00:00
def test_contraction(EN):
tokens = EN("don't giggle")
assert len(tokens) == 3
assert tokens[1].sic == EN.vocab["n't"].sic
2014-12-21 09:38:27 +00:00
tokens = EN("i said don't!")
assert len(tokens) == 5
assert tokens[4].sic == EN.vocab['!'].sic
2014-12-21 09:38:27 +00:00
def test_contraction_punct(EN):
tokens = EN("(can't")
assert len(tokens) == 3
2014-12-21 09:38:27 +00:00
tokens = EN("`ain't")
assert len(tokens) == 3
2014-12-21 09:38:27 +00:00
tokens = EN('''"isn't''')
assert len(tokens) == 3
2014-12-21 09:38:27 +00:00
tokens = EN("can't!")
assert len(tokens) == 3
2014-12-21 09:38:27 +00:00
def test_sample(EN):
text = """Tributes pour in for late British Labour Party leader
Tributes poured in from around the world Thursday
to the late Labour Party leader John Smith, who died earlier from a massive
heart attack aged 55.
In Washington, the US State Department issued a statement regretting "the
untimely death" of the rapier-tongued Scottish barrister and parliamentarian.
"Mr. Smith, throughout his distinguished"""
2014-12-21 09:38:27 +00:00
tokens = EN(text)
assert len(tokens) > 5
2014-12-21 09:38:27 +00:00
def test_cnts1(EN):
text = u"""The U.S. Army likes Shock and Awe."""
2014-12-21 09:38:27 +00:00
tokens = EN(text)
assert len(tokens) == 8
2014-12-21 09:38:27 +00:00
def test_cnts2(EN):
text = u"""U.N. regulations are not a part of their concern."""
2014-12-21 09:38:27 +00:00
tokens = EN(text)
assert len(tokens) == 10
2014-12-21 09:38:27 +00:00
def test_cnts3(EN):
text = u"“Isn't it?”"
2014-12-21 09:38:27 +00:00
tokens = EN(text)
words = [t.string for t in tokens]
assert len(words) == 6
2014-12-21 09:38:27 +00:00
def test_cnts4(EN):
text = u"""Yes! "I'd rather have a walk", Ms. Comble sighed. """
2014-12-21 09:38:27 +00:00
tokens = EN(text)
words = [t.string for t in tokens]
assert len(words) == 15
2014-12-21 09:38:27 +00:00
def test_cnts5(EN):
text = """'Me too!', Mr. P. Delaware cried. """
2014-12-21 09:38:27 +00:00
tokens = EN(text)
assert len(tokens) == 11
2014-12-21 09:38:27 +00:00
def test_cnts6(EN):
text = u'They ran about 10km.'
2014-12-21 09:38:27 +00:00
tokens = EN(text)
words = [t.string for t in tokens]
assert len(words) == 6
2015-01-22 11:25:18 +00:00
def test_bracket_period(EN):
text = u'(And a 6a.m. run through Washington Park).'
tokens = EN(text)
assert tokens[len(tokens) - 1].string == u'.'
#def test_cnts7():
# text = 'But then the 6,000-year ice age came...'
# tokens = EN.tokenize(text)
# assert len(tokens) == 10