def render(self, context):
try:
cls = ''
url = self.href
page = context['page']
if self.is_relative_link(url):
if url.startswith('_files/'):
filename = file_url_to_name(url)
url = reverse('pages:file-info', args=[page.pretty_slug,
filename])
try:
file = PageFile.objects.get(slug__exact=page.slug,
name__exact=filename)
cls = ' class="file_%s"' % file.rough_type
except PageFile.DoesNotExist:
cls = ' class="missing_link"'
else:
try:
page = Page.objects.get(slug__exact=slugify(url))
url = reverse('pages:show', args=[page.pretty_slug])
except Page.DoesNotExist:
cls = ' class="missing_link"'
# Convert to proper URL: My%20page -> My_page
url = name_to_url(url_to_name(url))
url = reverse('pages:show', args=[url])
return '<a href="%s"%s>%s</a>' % (url, cls,
self.nodelist.render(context))
except:
return ''
def extract_included_tags(html):
"""
Args:
html: A string containing an HTML5 fragment.
Returns:
A list of the included tag slugs (lowercased).
"""
from tags.models import slugify
parser = html5lib.HTMLParser(
tree=html5lib.treebuilders.getTreeBuilder("lxml"),
namespaceHTMLElements=False)
# Wrap to make the tree lookup easier
tree = parser.parseFragment('<div>%s</div>' % html)[0]
a_s = tree.xpath('//a')
# Grab the link source if it's an included page
l = []
for a in a_s:
if _is_included_tag(a):
try:
item = slugify(url_to_name(a.attrib.get('href'))[TAGS_PATH_LEN:].lower())
except UnicodeDecodeError:
continue
l.append(item)
return l
def __init__(self, parser, token, *args, **kwargs):
super(IncludePageNode, self).__init__(*args, **kwargs)
bits = token.split_contents()
if len(bits) < 2:
raise template.TemplateSyntaxError, ('%r tag requires at least one'
' argument' % token.contents.split()[0])
page_name = bits[1]
if is_quoted(page_name):
page_name = unescape_string_literal(page_name)
self.page_name = url_to_name(page_name)
self.args = bits[2:]
def extract_included_pagenames(html):
"""
Args:
html: A string containing an HTML5 fragment.
Returns:
A list of the included page names.
"""
parser = html5lib.HTMLParser(
tree=html5lib.treebuilders.getTreeBuilder("lxml"),
namespaceHTMLElements=False)
# Wrap to make the tree lookup easier
tree = parser.parseFragment('<div>%s</div>' % html)[0]
a_s = tree.xpath('//a')
# Grab the link source if it's an included page
l = []
for a in a_s:
if _is_included_page(a):
l.append(url_to_name(a.attrib.get('href')))
return l
def extract_internal_links(html):
"""
Args:
html: A string containing an HTML5 fragment.
Returns:
A dictionary of the linked-to page names and the number of times that
link has been made in this HTML. E.g.
{'Downtown Park': 3, 'Rollercoaster': 1}
"""
parser = html5lib.HTMLParser(
tree=html5lib.treebuilders.getTreeBuilder("lxml"),
namespaceHTMLElements=False)
# Wrap to make the tree lookup easier
tree = parser.parseFragment('<div>%s</div>' % html)[0]
a_s = tree.xpath('//a')
# Grab the links if they're not anchors or external.
d = {}
for a in a_s:
if 'href' not in a.attrib:
continue
href = a.attrib['href']
if (not _is_absolute(href) and not _is_anchor_link(href) and
not _is_plugin(a) and not _invalid(href)):
try:
if not slugify(href) in d:
d[slugify(href)] = (url_to_name(href), 1)
else:
name, count = d[slugify(href)]
d[slugify(href)] = (name, count + 1)
except UnicodeDecodeError:
pass
# Format the result correctly.
links = {}
for _, (name, count) in d.iteritems():
links[name] = count
return links
def test_url_to_name(self):
self.assertEqual(url_to_name('Front_Page'), 'Front Page')
self.assertEqual(url_to_name('Ben_%26_Jerry%27s'), "Ben & Jerry's")