mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-11-04 18:07:26 +03:00 
			
		
		
		
	
		
			
				
	
	
		
			53 lines
		
	
	
		
			1.9 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			53 lines
		
	
	
		
			1.9 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
# coding: utf-8
 | 
						|
from __future__ import unicode_literals
 | 
						|
 | 
						|
from ...attrs import intify_attrs, ORTH, NORM, LEMMA, IS_ALPHA
 | 
						|
from ...lang.lex_attrs import is_punct, is_ascii, like_url, word_shape
 | 
						|
 | 
						|
import pytest
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text', ["dog"])
 | 
						|
def test_attrs_key(text):
 | 
						|
    assert intify_attrs({"ORTH": text}) == {ORTH: text}
 | 
						|
    assert intify_attrs({"NORM": text}) == {NORM: text}
 | 
						|
    assert intify_attrs({"lemma": text}, strings_map={text: 10}) == {LEMMA: 10}
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text', ["dog"])
 | 
						|
def test_attrs_idempotence(text):
 | 
						|
    int_attrs = intify_attrs({"lemma": text, 'is_alpha': True}, strings_map={text: 10})
 | 
						|
    assert intify_attrs(int_attrs) == {LEMMA: 10, IS_ALPHA: True}
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text', ["dog"])
 | 
						|
def test_attrs_do_deprecated(text):
 | 
						|
    int_attrs = intify_attrs({"F": text, 'is_alpha': True}, strings_map={text: 10},
 | 
						|
                              _do_deprecated=True)
 | 
						|
    assert int_attrs == {ORTH: 10, IS_ALPHA: True}
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text,match', [(',', True), (' ', False), ('a', False)])
 | 
						|
def test_lex_attrs_is_punct(text, match):
 | 
						|
    assert is_punct(text) == match
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text,match', [(',', True), ('£', False), ('♥', False)])
 | 
						|
def test_lex_attrs_is_ascii(text, match):
 | 
						|
    assert is_ascii(text) == match
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text,match', [
 | 
						|
    ('www.google.com', True), ('google.com', True), ('sydney.com', True),
 | 
						|
    ('2girls1cup.org', True), ('http://stupid', True), ('www.hi', True),
 | 
						|
    ('dog', False), ('1.2', False), ('1.a', False), ('hello.There', False)])
 | 
						|
def test_lex_attrs_like_url(text, match):
 | 
						|
    assert like_url(text) == match
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize('text,shape', [
 | 
						|
    ('Nasa', 'Xxxx'), ('capitalized', 'xxxx'), ('999999999', 'dddd'),
 | 
						|
    ('C3P0', 'XdXd'), (',', ','), ('\n', '\n'), ('``,-', '``,-')])
 | 
						|
def test_lex_attrs_word_shape(text, shape):
 | 
						|
    assert word_shape(text) == shape
 |