explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-11 17:56:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix check for '@' in like_url (see #1715)

Browse Source
This commit is contained in:
ines 2017-12-16 13:48:43 +01:00
parent 21482b391b
commit 22dc744b48
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/lang/lex_attrs.py
View File

@ -74,8 +74,6 @@ def like_email(text):
def like_url(text): def like_url(text):
if '@' in text: # prevent matches on e-mail addresses
return False
# We're looking for things that function in text like URLs. So, valid URL # 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. # or not, anything they say http:// is going to be good.
if text.startswith('http://') or text.startswith('https://'): if text.startswith('http://') or text.startswith('https://'):
@ -84,6 +82,10 @@ def like_url(text):
return True return True
if text[0] == '.' or text[-1] == '.': if text[0] == '.' or text[-1] == '.':
return False return False
if '@' in text:
# prevent matches on e-mail addresses – check after splitting the text
# to still allow URLs containing an '@' character (see #1715)
return False
for i in range(len(text)): for i in range(len(text)):
if text[i] == '.': if text[i] == '.':
break break