explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-11 08:42:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Check for email address first

Browse Source
This commit is contained in:
Ines Montani 2017-12-12 10:25:13 +01:00 committed by GitHub
parent afd9fc9d36
commit 6455b574fc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lang/lex_attrs.py
View File

@ -74,6 +74,8 @@ 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://'):
@ -82,8 +84,6 @@ 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
return False
for i in range(len(text)): for i in range(len(text)):
if text[i] == '.': if text[i] == '.':
break break