def visit_reference(self, node):
refuri = node.get('refuri', '')
if refuri.startswith('<<') and refuri.endswith('>>'): # moin macro
macro_name = refuri[2:-2].split('(')[0]
if macro_name == "TableOfContents":
arguments = refuri[2:-2].split('(')[1][:-1].split(',')
node = moin_page.table_of_content()
self.open_moin_page_node(node)
if arguments and arguments[0]:
node.set(moin_page.outline_level, arguments[0])
return
if macro_name == "Include":
# include macros are expanded by include.py similar to transclusions
# rst include handles only wiki pages and does not support additional arguments like moinwiki
arguments = refuri[2:-2].split('(')[1][:-1].split(',')
link = Iri(scheme='wiki.local', path=arguments)
node = xinclude.include(
attrib={
xinclude.href: link,
moin_page.alt: refuri,
moin_page.content_type: 'x-moin/macro;name=' +
macro_name,
})
self.open_moin_page_node(node)
return
try:
arguments = refuri[2:-2].split('(')[1][:-1]
except IndexError:
arguments = '' # <<DateTime>>
self.open_moin_page_node(
moin_page.inline_part(
attrib={
moin_page.content_type:
"x-moin/macro;name={0}".format(macro_name)
}))
if arguments:
self.open_moin_page_node(moin_page.arguments())
self.open_moin_page_node(arguments)
self.close_moin_page_node()
self.close_moin_page_node()
return
if not allowed_uri_scheme(refuri):
self.visit_error(node)
return
if refuri == '':
# build a link to a heading or an explicitly defined anchor
refuri = Iri(scheme='wiki.local',
fragment=node.attributes['name'].replace(' ', '_'))
self.open_moin_page_node(moin_page.a(attrib={xlink.href: refuri}))
def _TableOfContents_repl(self, args, text, context_block):
if not context_block:
return text
attrib = {}
if args:
try:
level = int(args[0])
assert 0 < level < 7
except (ValueError, AssertionError):
pass
else:
attrib[moin_page.outline_level] = str(level)
return moin_page.table_of_content(attrib=attrib)
def postproc_text(markdown, text):
"""
Removes HTML or XML character references and entities from a text string.
:param text: The HTML (or XML) source text.
:returns: The plain text, as a Unicode string, if necessary.
"""
# http://effbot.org/zone/re-sub.htm#unescape-html
if text is None:
return None
if text == '[TOC]':
return moin_page.table_of_content(attrib={})
for pp in markdown.postprocessors:
text = pp.run(text)
if text.startswith('<pre>') or text.startswith(
'<div class="codehilite"><pre>'):
# TODO: with markdown 3.0.0 indented code is somehow escaped twice - see issue #707
text = text.replace('&lt;',
'<').replace('&gt;', '>').replace(
'&amp;', '&')
return text
def fixup(m):
text = m.group(0)
if text[:2] == "&#":
# character reference
try:
if text[:3] == "&#x":
return chr(int(text[3:-1], 16))
else:
return chr(int(text[2:-1]))
except ValueError:
pass
else:
# named entity
try:
text = chr(name2codepoint[text[1:-1]])
except KeyError:
pass
return text # leave as is
return re.sub(r"&#?\w+;", fixup, text)