Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Soup hyphen in comment #251

Merged
merged 4 commits into from Jul 29, 2017
Merged

Soup hyphen in comment #251

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6d226ca
Soupparser: Fix bug with double hyphen (--) in comment element
mozbugbox Jul 28, 2017
d2be1b2
Soupparser: Fix "No parser was explicitly specified" warning
mozbugbox Jul 28, 2017
03ec585
soupparser: Use html.HtmlComment() to create commend
mozbugbox Jul 29, 2017
f8a21e1
soupparse: add test case for double-hyphen
mozbugbox Jul 29, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/lxml/html/soupparser.py
View file
Open in desktop
Expand Up @@ -74,7 +74,7 @@ def _parse(source, beautifulsoup, makeelement, **bsargs):
bsargs['convertEntities'] = 'html'
if hasattr(beautifulsoup, "DEFAULT_BUILDER_FEATURES"): # bs4
if 'features' not in bsargs:
bsargs['features'] = ['html.parser'] # use Python html parser
bsargs['features'] = 'html.parser' # use Python html parser
tree = beautifulsoup(source, **bsargs)
root = _convert_tree(tree, makeelement)
# from ET: wrap the document in a html root element, if necessary
Expand Down Expand Up @@ -255,7 +255,7 @@ def convert_tag(bs_node, parent):

@converter(Comment)
def convert_comment(bs_node, parent):
res = etree.Comment(bs_node)
res = html.HtmlComment(bs_node)
if parent is not None:
parent.append(res)
return res
Expand Down
11 changes: 11 additions & 0 deletions src/lxml/html/tests/test_elementsoup.py
View file
Open in desktop
Expand Up @@ -45,6 +45,17 @@ def test_wrap_html(self):
tree = self.soupparser.fromstring(html)
self.assertEqual(tostring(tree), res)

def test_comment_hyphen(self):
# These are really invalid XML as per specification
# https://www.w3.org/TR/REC-xml/#sec-comments
html = b'<html><!-- comment -- with double-hyphen --></html>'
tree = self.soupparser.fromstring(html)
self.assertEqual(tostring(tree), html)

html = b'<html><!-- comment ends with hyphen ---></html>'
tree = self.soupparser.fromstring(html)
self.assertEqual(tostring(tree), html)

def test_comment_pi(self):
html = '''<!-- comment -->
<?test asdf?>
Expand Down