mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Remove semi-redundant URLs and punctuation for faster testing
This commit is contained in:
parent
3a3cb2c90c
commit
e10d4ca964
|
@ -5,20 +5,17 @@ import pytest
|
||||||
|
|
||||||
|
|
||||||
URLS = [
|
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®ion=top-news&WT.nav=top-news&_r=0",
|
"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®ion=top-news&WT.nav=top-news&_r=0",
|
||||||
u"www.google.com?q=google",
|
"www.google.com?q=google",
|
||||||
u"google.com",
|
"www.red-stars.com",
|
||||||
u"www.red-stars.com",
|
"http://foo.com/blah_(wikipedia)#cite-1",
|
||||||
pytest.mark.xfail(u"red-stars.com"),
|
"mailto:foo.bar@baz.com",
|
||||||
u"http://foo.com/blah_(wikipedia)#cite-1",
|
"mailto:foo-bar@baz-co.com"
|
||||||
u"http://www.example.com/wpstyle/?bar=baz&inga=42&quux",
|
|
||||||
u"mailto:foo.bar@baz.com",
|
|
||||||
u"mailto:foo-bar@baz-co.com"
|
|
||||||
]
|
]
|
||||||
|
|
||||||
# Punctuation we want to check is split away before the URL
|
# Punctuation we want to check is split away before the URL
|
||||||
PREFIXES = [
|
PREFIXES = [
|
||||||
"(", '"', "...", ">"
|
"(", '"', ">"
|
||||||
]
|
]
|
||||||
|
|
||||||
# Punctuation we want to check is split away after the URL
|
# Punctuation we want to check is split away after the URL
|
||||||
|
|
Loading…
Reference in New Issue
Block a user