mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
9a478b6db8
* splitting up latin unicode interval * removing hyphen as infix for French * adding failing test for issue 1235 * test for issue #3002 which now works * partial fix for issue #2070 * keep the hyphen as infix for French (as it was) * restore french expressions with hyphen as infix (as it was) * added succeeding unit test for Issue #2656 * Fix issue #2822 with custom Italian exception * Fix issue #2926 by allowing numbers right before infix / * splitting up latin unicode interval * removing hyphen as infix for French * adding failing test for issue 1235 * test for issue #3002 which now works * partial fix for issue #2070 * keep the hyphen as infix for French (as it was) * restore french expressions with hyphen as infix (as it was) * added succeeding unit test for Issue #2656 * Fix issue #2822 with custom Italian exception * Fix issue #2926 by allowing numbers right before infix / * remove duplicate * remove xfail for Issue #2179 fixed by Matt * adjust documentation and remove reference to regex lib
22 lines
594 B
Python
22 lines
594 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
from spacy.lang.fr import French
|
|
|
|
|
|
def test_issue2926():
|
|
""" Test that the tokenizer correctly splits tokens separated by a slash (/) ending in a digit """
|
|
nlp = French()
|
|
text = "Learn html5/css3/javascript/jquery"
|
|
doc = nlp(text)
|
|
|
|
assert len(doc) == 8
|
|
|
|
assert doc[0].text == "Learn"
|
|
assert doc[1].text == "html5"
|
|
assert doc[2].text == "/"
|
|
assert doc[3].text == "css3"
|
|
assert doc[4].text == "/"
|
|
assert doc[5].text == "javascript"
|
|
assert doc[6].text == "/"
|
|
assert doc[7].text == "jquery"
|