explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove semi-redundant URLs and punctuation for faster testing

Browse Source
This commit is contained in:
Ines Montani 2017-01-10 15:54:25 +01:00
parent 3a3cb2c90c
commit e10d4ca964
1 changed files with 7 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/tests/tokenizer/test_urls.py
View File

@ -5,20 +5,17 @@ import pytest
URLS = [
u"http://www.nytimes.com/2016/04/20/us/politics/new-york-primary-preview.html?hp&action=click&pgtype=Homepage&clickSource=story-heading&module=a-lede-package-region&region=top-news&WT.nav=top-news&_r=0",
u"www.google.com?q=google",
u"google.com",
u"www.red-stars.com",
pytest.mark.xfail(u"red-stars.com"),
u"http://foo.com/blah_(wikipedia)#cite-1",
u"http://www.example.com/wpstyle/?bar=baz&inga=42&quux",
u"mailto:foo.bar@baz.com",
u"mailto:foo-bar@baz-co.com"
"http://www.nytimes.com/2016/04/20/us/politics/new-york-primary-preview.html?hp&action=click&pgtype=Homepage&clickSource=story-heading&module=a-lede-package-region&region=top-news&WT.nav=top-news&_r=0",
"www.google.com?q=google",
"www.red-stars.com",
"http://foo.com/blah_(wikipedia)#cite-1",
"mailto:foo.bar@baz.com",
"mailto:foo-bar@baz-co.com"
]
# Punctuation we want to check is split away before the URL
PREFIXES = [
"(", '"', "...", ">"
"(", '"', ">"
]
# Punctuation we want to check is split away after the URL