rafaelcaricio/moviewyrm
1
0
Fork 0
forked from mirrors/bookwyrm
Code Issues 4 Pull requests Projects Releases Wiki Activity

fix link formatting issue, for real this time

Browse source
This commit is contained in:
reesporte 2021-08-30 14:23:04 -05:00
parent c6d08050e2
commit 4f321e5f33
2 changed files with 24 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
bookwyrm/tests/views/test_status.py
View file

@ -307,14 +307,14 @@ class StatusViews(TestCase):
self.assertEqual(
views.status.format_links(url), '<a href="%s">tech.lgbt/@bookwyrm</a>' % url
)
url = "users.speakeasy.net/~lion/nb/book.pdf"
url = "https://users.speakeasy.net/~lion/nb/book.pdf"
self.assertEqual(
views.status.format_links(url),
'<a href="%s">users.speakeasy.net/~lion/nb/book.pdf</a>' % url,
)
url = "pkm.one/#/page/The%20Book%20which%20launched%20a%201000%20Note%20taking%20apps"
url = "https://pkm.one/#/page/The%20Book%20which%20launched%20a%201000%20Note%20taking%20apps"
self.assertEqual(
views.status.format_links(url), '<a href="%s">%s</a>' % (url, url)
views.status.format_links(url), '<a href="%s">%s</a>' % (url, url[8:])
)
def test_to_markdown(self, *_):

37
bookwyrm/views/status.py
View file

@ -153,32 +153,37 @@ def find_mentions(content):
def format_links(content):
"""detect and format links"""
validator = URLValidator()
formatted_content = ""
for potential_link in content.split():
try:
# raises an error on anything that's not a valid
URLValidator(potential_link)
except (ValidationError, UnicodeError):
formatted_content += potential_link + " "
continue
split_content = content.split()
for index, potential_link in enumerate(split_content):
wrapped = _wrapped(potential_link)
if wrapped:
wrapper_close = potential_link[-1]
formatted_content += potential_link[0]
potential_link = potential_link[1:-1]
# so we can use everything but the scheme in the presentation of the link
url = urlparse(potential_link)
link = url.netloc + url.path + url.params
if url.query != "":
link += "?" + url.query
if url.fragment != "":
link += "#" + url.fragment
try:
# raises an error on anything that's not a valid link
validator(potential_link)
formatted_content += '<a href="%s">%s</a>' % (potential_link, link)
# use everything but the scheme in the presentation of the link
url = urlparse(potential_link)
link = url.netloc + url.path + url.params
if url.query != "":
link += "?" + url.query
if url.fragment != "":
link += "#" + url.fragment
formatted_content += '<a href="%s">%s</a>' % (potential_link, link)
except (ValidationError, UnicodeError):
formatted_content += potential_link
if wrapped:
formatted_content += wrapper_close
if index < len(split_content) - 1:
formatted_content += " "
return formatted_content
@ -194,8 +199,8 @@ def _wrapped(text):
def to_markdown(content):
"""catch links and convert to markdown"""
content = markdown(content)
content = format_links(content)
content = markdown(content)
# sanitize resulting html
sanitizer = InputHtmlParser()
sanitizer.feed(content)