def test_remove_script_tags(self):
html = '''
<h1>Title</h1>
<script type="text/javascript">
</script>
'''
res = html_index_content(html)
assert res == "Title"
def test_process_whitespaces(self):
html = '''
<h1>Title</h1>
<br />
<p>This is a paragraph.</p>
'''
res = html_index_content(html)
assert res == "Title This is a paragraph."
def test_process_whitespaces(self):
html = '''
<h1>Title</h1>
<br />
<p>This is a paragraph.</p>
'''
res = html_index_content(html)
assert res == "Title This is a paragraph."
def test_remove_script_tags(self):
html = '''
<h1>Title</h1>
<script type="text/javascript">
</script>
'''
res = html_index_content(html)
assert res == "Title"
def test_unescape(self):
html = '''
<h1>Title</h1>
<script type="text/javascript">
</script>
<footer>
<a href="./" class="button_accent">
Back to blog
</a>
</footer>
<code>
print 1<3
</code>
'''
res = html_index_content(html)
assert res == "Title Back to blog print 1<3"
def test_unescape(self):
html = '''
<h1>Title</h1>
<script type="text/javascript">
</script>
<footer>
<a href="./" class="button_accent">
Back to blog
</a>
</footer>
<code>
print 1<3
</code>
'''
res = html_index_content(html)
assert res == "Title Back to blog print 1<3"
def _doc_file_as_dict(self, path, name, doc_dir):
last_commit = self.repo.get_last_commit("HEAD", path)
if not last_commit:
return
sd = SphinxDocs(project_name=self.project.name)
data = {
'type': 'docs',
'description': '',
'author': last_commit.author.name,
'time': last_commit.time.strftime('%Y-%m-%dT%H:%M:%S'),
'project_id': self.project.id,
'project_name': self.project.name,
'doc_name': name,
'doc_dir': doc_dir,
'url': sd.get_url_from_path(path)
}
blob = self.repo.get_file('HEAD', path)
src = blob.data or ''
if path.endswith('.html'):
data['content'] = html_index_content(src)
else:
data['content'] = src
return data
