explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 10:46:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Upd tests for tighter interface

Browse Source
This commit is contained in:
Matthew Honnibal 2014-10-30 18:15:30 +11:00
parent ea8f1e7053
commit 63114820cf
3 changed files with 18 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tests/test_lexeme_flags.py
View File

@ -7,18 +7,18 @@ from spacy.lexeme import *
def test_is_alpha(): def test_is_alpha():
the = EN.lexicon.lookup('the') the = EN.lexicon['the']
assert the['flags'] & (1 << IS_ALPHA) assert the['flags'] & (1 << IS_ALPHA)
year = EN.lexicon.lookup('1999') year = EN.lexicon['1999']
assert not year['flags'] & (1 << IS_ALPHA) assert not year['flags'] & (1 << IS_ALPHA)
mixed = EN.lexicon.lookup('hello1') mixed = EN.lexicon['hello1']
assert not mixed['flags'] & (1 << IS_ALPHA) assert not mixed['flags'] & (1 << IS_ALPHA)
def test_is_digit(): def test_is_digit():
the = EN.lexicon.lookup('the') the = EN.lexicon['the']
assert not the['flags'] & (1 << IS_DIGIT) assert not the['flags'] & (1 << IS_DIGIT)
year = EN.lexicon.lookup('1999') year = EN.lexicon['1999']
assert year['flags'] & (1 << IS_DIGIT) assert year['flags'] & (1 << IS_DIGIT)
mixed = EN.lexicon.lookup('hello1') mixed = EN.lexicon['hello1']
assert not mixed['flags'] & (1 << IS_DIGIT) assert not mixed['flags'] & (1 << IS_DIGIT)

8
tests/test_tokenizer.py
View File

@ -27,17 +27,17 @@ def test_punct():
def test_digits(): def test_digits():
tokens = EN.tokenize('The year: 1984.') tokens = EN.tokenize('The year: 1984.')
assert len(tokens) == 5 assert len(tokens) == 5
assert tokens[0].sic == EN.lexicon.lookup('The')['sic'] assert tokens[0].sic == EN.lexicon['The']['sic']
assert tokens[3].sic == EN.lexicon.lookup('1984')['sic'] assert tokens[3].sic == EN.lexicon['1984']['sic']
def test_contraction(): def test_contraction():
tokens = EN.tokenize("don't giggle") tokens = EN.tokenize("don't giggle")
assert len(tokens) == 3 assert len(tokens) == 3
assert tokens[1].sic == EN.lexicon.lookup("not")['sic'] assert tokens[1].sic == EN.lexicon["not"]['sic']
tokens = EN.tokenize("i said don't!") tokens = EN.tokenize("i said don't!")
assert len(tokens) == 5 assert len(tokens) == 5
assert tokens[4].sic == EN.lexicon.lookup('!')['sic'] assert tokens[4].sic == EN.lexicon['!']['sic']
def test_contraction_punct(): def test_contraction_punct():

16
tests/test_vocab.py
View File

@ -4,20 +4,20 @@ from spacy.en import EN
def test_neq(): def test_neq():
addr = EN.lexicon.lookup('Hello') addr = EN.lexicon['Hello']
assert EN.lexicon.lookup('bye')['sic'] != addr['sic'] assert EN.lexicon['bye']['sic'] != addr['sic']
def test_eq(): def test_eq():
addr = EN.lexicon.lookup('Hello') addr = EN.lexicon['Hello']
assert EN.lexicon.lookup('Hello')['sic'] == addr['sic'] assert EN.lexicon['Hello']['sic'] == addr['sic']
def test_case_neq(): def test_case_neq():
addr = EN.lexicon.lookup('Hello') addr = EN.lexicon['Hello']
assert EN.lexicon.lookup('hello')['sic'] != addr['sic'] assert EN.lexicon['hello']['sic'] != addr['sic']
def test_punct_neq(): def test_punct_neq():
addr = EN.lexicon.lookup('Hello') addr = EN.lexicon['Hello']
assert EN.lexicon.lookup('Hello,')['sic'] != addr['sic'] assert EN.lexicon['Hello,']['sic'] != addr['sic']