spaCy/spacy/tests/vocab/test_shape.py
2015-10-26 00:07:31 +11:00

34 lines
474 B
Python

from __future__ import unicode_literals
import pytest
from spacy.orth import word_shape as ws
def test_capitalized():
assert ws('Nasa') == 'Xxxx'
def test_truncate():
assert ws('capitalized') == 'xxxx'
def test_digits():
assert ws('999999999') == 'dddd'
def test_mix():
assert ws('C3P0') == 'XdXd'
def test_punct():
assert ws(',') == ','
def test_space():
assert ws('\n') == '\n'
def test_punct_seq():
assert ws('``,-') == '``,-'