mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
78 lines
1.9 KiB
Python
78 lines
1.9 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.en import English
|
|
from spacy.tokenizer import Tokenizer
|
|
from spacy.util import compile_prefix_regex, compile_suffix_regex
|
|
from spacy.util import compile_infix_regex
|
|
|
|
|
|
@pytest.fixture
|
|
def custom_en_tokenizer(en_vocab):
|
|
prefix_re = compile_prefix_regex(English.Defaults.prefixes)
|
|
suffix_re = compile_suffix_regex(English.Defaults.suffixes)
|
|
custom_infixes = [
|
|
"\.\.\.+",
|
|
"(?<=[0-9])-(?=[0-9])",
|
|
# '(?<=[0-9]+),(?=[0-9]+)',
|
|
"[0-9]+(,[0-9]+)+",
|
|
"[\[\]!&:,()\*—–\/-]",
|
|
]
|
|
infix_re = compile_infix_regex(custom_infixes)
|
|
return Tokenizer(
|
|
en_vocab,
|
|
English.Defaults.tokenizer_exceptions,
|
|
prefix_re.search,
|
|
suffix_re.search,
|
|
infix_re.finditer,
|
|
token_match=None,
|
|
)
|
|
|
|
|
|
def test_en_customized_tokenizer_handles_infixes(custom_en_tokenizer):
|
|
sentence = "The 8 and 10-county definitions are not used for the greater Southern California Megaregion."
|
|
context = [word.text for word in custom_en_tokenizer(sentence)]
|
|
assert context == [
|
|
"The",
|
|
"8",
|
|
"and",
|
|
"10",
|
|
"-",
|
|
"county",
|
|
"definitions",
|
|
"are",
|
|
"not",
|
|
"used",
|
|
"for",
|
|
"the",
|
|
"greater",
|
|
"Southern",
|
|
"California",
|
|
"Megaregion",
|
|
".",
|
|
]
|
|
# the trailing '-' may cause Assertion Error
|
|
sentence = "The 8- and 10-county definitions are not used for the greater Southern California Megaregion."
|
|
context = [word.text for word in custom_en_tokenizer(sentence)]
|
|
assert context == [
|
|
"The",
|
|
"8",
|
|
"-",
|
|
"and",
|
|
"10",
|
|
"-",
|
|
"county",
|
|
"definitions",
|
|
"are",
|
|
"not",
|
|
"used",
|
|
"for",
|
|
"the",
|
|
"greater",
|
|
"Southern",
|
|
"California",
|
|
"Megaregion",
|
|
".",
|
|
]
|