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

* Fix https for url detection

This commit is contained in:
Matthew Honnibal 2015-08-23 02:40:35 +02:00
parent aa12b374c0
commit 3879d28457
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/orth.pyx
View File

@ -69,7 +69,7 @@ TLDs = set("com|org|edu|gov|net|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|mu
cpdef bint like_url(unicode string):
# We're looking for things that function in text like URLs. So, valid URL
# or not, anything they say http:// is going to be good.
if string.startswith('http://'):
if string.startswith('http://') or string.startswith('https://'):
return True
elif string.startswith('www.') and len(string) >= 5:
return True