Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Upd tests

This commit is contained in:
Matthew Honnibal 2015-09-12 04:23:35 +02:00
parent c808cd50d9
commit 6d38c3cff0
1 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
tests/spans/test_times.py
View File

@ -2,20 +2,21 @@ from __future__ import unicode_literals
import pytest
@pytest.mark.models
def test_am_pm(en_nlp):
numbers = ['1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12']
variants = ['a.m.', 'am', 'p.m.', 'pm']
spaces = ['', ' ']
for num in numbers:
for var in variants:
for space in spaces:
string = u"The meeting was at %s%s%s wasn't it?" % (num, space, var)
tokens = en_nlp(string, merge_mwes=True)
assert tokens[4].orth_ == '%s%s%s' % (num, space, var)
ents = list(tokens.ents)
assert len(ents) == 1, ents
assert ents[0].label_ == 'TIME', string
if ents[0].start == 4 and ents[0].end == 5:
assert ents[0].orth_ == '%s%s%s' % (num, space, var)
# This approach is deprecated for now
#
#@pytest.mark.models
#def test_am_pm(en_nlp):
# numbers = ['1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12']
# variants = ['a.m.', 'am', 'p.m.', 'pm']
# spaces = ['', ' ']
# for num in numbers:
# for var in variants:
# for space in spaces:
# string = u"The meeting was at %s%s%s wasn't it?" % (num, space, var)
# tokens = en_nlp(string, merge_mwes=True)
# assert tokens[4].orth_ == '%s%s%s' % (num, space, var)
# ents = list(tokens.ents)
# assert len(ents) == 1, ents
# assert ents[0].label_ == 'TIME', string
# if ents[0].start == 4 and ents[0].end == 5:
# assert ents[0].orth_ == '%s%s%s' % (num, space, var)