github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Try unescaped paths in intrasite link discovery

Browse source 
Some content parsers escape link paths in their html output
(i.e. docutils uses HTML escaping and markdown uses URL encoding.
Intrasite link discovery is refactored to also attempt HTML or URL
unescaped versions of the path in order to match more permissively.
This commit is contained in:
Deniz Turgut 2020-10-04 19:29:32 +03:00
commit fd0923d2f2
No known key found for this signature in database
GPG key ID: 87B7168D7AB3ED2F
2 changed files with 106 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

57
pelican/tests/test_contents.py
View file

@ -30,6 +30,9 @@ class TestBase(LoggedTestCase):
'content': TEST_CONTENT,
'context': {
'localsiteurl': '',
'generated_content': {},
'static_content': {},
'static_links': set()
},
'metadata': {
'summary': TEST_SUMMARY,
@ -519,6 +522,60 @@ class TestPage(TestBase):
'<img src="http://static.cool.site/images/poster.jpg"/>'
)
def test_intrasite_link_escape(self):
article = type(
'_DummyArticle', (object,), {'url': 'article-spaces.html'})
asset = type(
'_DummyAsset', (object,), {'url': 'name@example.com'})
args = self.page_kwargs.copy()
args['settings'] = get_settings()
args['source_path'] = 'content'
args['context']['generated_content'] = {'article spaces.rst': article}
args['context']['static_content'] = {'name@example.com': asset}
expected_output = (
'A simple test with a '
'<a href="http://notmyidea.org/article-spaces.html#anchor">link</a> '
'<a href="http://notmyidea.org/name@example.com#anchor">file</a>'
)
# not escaped
args['content'] = (
'A simple test with a '
'<a href="{filename}article spaces.rst#anchor">link</a> '
'<a href="{static}name@example.com#anchor">file</a>'
)
content = Page(**args).get_content('http://notmyidea.org')
self.assertEqual(content, expected_output)
# html escaped
args['content'] = (
'A simple test with a '
'<a href="{filename}article spaces.rst#anchor">link</a> '
'<a href="{static}name&#64;example.com#anchor">file</a>'
)
content = Page(**args).get_content('http://notmyidea.org')
self.assertEqual(content, expected_output)
# url escaped
args['content'] = (
'A simple test with a '
'<a href="{filename}article%20spaces.rst#anchor">link</a> '
'<a href="{static}name%40example.com#anchor">file</a>'
)
content = Page(**args).get_content('http://notmyidea.org')
self.assertEqual(content, expected_output)
# html and url escaped
args['content'] = (
'A simple test with a '
'<a href="{filename}article%20spaces.rst#anchor">link</a> '
'<a href="{static}name&#64;example.com#anchor">file</a>'
)
content = Page(**args).get_content('http://notmyidea.org')
self.assertEqual(content, expected_output)
def test_intrasite_link_markdown_spaces(self):
cls_name = '_DummyArticle'
article = type(cls_name, (object,), {'url': 'article-spaces.html'})