Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Upd contractions test

This commit is contained in:
Matthew Honnibal 2014-12-21 20:41:13 +11:00
parent 0d9972f4b0
commit 199025609f
1 changed files with 23 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
tests/test_contractions.py
View File

@ -1,32 +1,37 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import pytest
from spacy.en import EN from spacy.en import English
@pytest.fixture
def EN():
return English(pos_tag=False)
def test_possess(): def test_possess(EN):
tokens = EN.tokenize("Mike's") tokens = EN("Mike's")
assert EN.lexicon.strings[tokens[0].sic] == "Mike" assert EN.vocab.strings[tokens[0].sic] == "Mike"
assert EN.lexicon.strings[tokens[1].sic] == "'s" assert EN.vocab.strings[tokens[1].sic] == "'s"
assert len(tokens) == 2 assert len(tokens) == 2
def test_apostrophe(): def test_apostrophe(EN):
tokens = EN.tokenize("schools'") tokens = EN("schools'")
assert len(tokens) == 2 assert len(tokens) == 2
assert tokens[1].string == "'" assert tokens[1].string == "'"
assert tokens[0].string == "schools" assert tokens[0].string == "schools"
def test_LL(): def test_LL(EN):
tokens = EN.tokenize("we'll") tokens = EN("we'll")
assert len(tokens) == 2 assert len(tokens) == 2
assert tokens[1].string == "'ll" assert tokens[1].string == "'ll"
assert tokens[1].lemma == "will" assert tokens[1].lemma == "will"
assert tokens[0].string == "we" assert tokens[0].string == "we"
def test_aint(): def test_aint(EN):
tokens = EN.tokenize("ain't") tokens = EN("ain't")
assert len(tokens) == 2 assert len(tokens) == 2
assert tokens[0].string == "ai" assert tokens[0].string == "ai"
assert tokens[0].lemma == "be" assert tokens[0].lemma == "be"
@ -34,19 +39,19 @@ def test_aint():
assert tokens[1].lemma == "not" assert tokens[1].lemma == "not"
def test_capitalized(): def test_capitalized(EN):
tokens = EN.tokenize("can't") tokens = EN("can't")
assert len(tokens) == 2 assert len(tokens) == 2
tokens = EN.tokenize("Can't") tokens = EN("Can't")
assert len(tokens) == 2 assert len(tokens) == 2
tokens = EN.tokenize("Ain't") tokens = EN("Ain't")
assert len(tokens) == 2 assert len(tokens) == 2
assert tokens[0].string == "Ai" assert tokens[0].string == "Ai"
assert tokens[0].lemma == "be" assert tokens[0].lemma == "be"
def test_punct(): def test_punct(EN):
tokens = EN.tokenize("We've") tokens = EN("We've")
assert len(tokens) == 2 assert len(tokens) == 2
tokens = EN.tokenize("``We've") tokens = EN("``We've")
assert len(tokens) == 3 assert len(tokens) == 3