def make_node(self, cls, element):
node = cls()
having_block_node = cls in HAVING_BLOCK_NODE
if element.text and element.text != "\n":
text = self.unescape_char(element.text)
if HTML_PLACEHOLDER_RE.search(text):
node += nodes.raw(format='html',
text=self.unescape_char(text, rawHtml=True))
elif having_block_node:
node += nodes.paragraph(text=text)
else:
node += nodes.Text(text)
for child in element:
subnode = self.visit(child)
if having_block_node and isinstance(subnode, INLINE_NODES):
all_nodes_is_in_paragraph = True
if len(node) == 0:
node += nodes.paragraph()
node[0] += subnode
else:
all_nodes_is_in_paragraph = False
node += subnode
if child.tail and child.tail != "\n":
tail = self.unescape_char(child.tail)
if HTML_PLACEHOLDER_RE.search(tail):
node += nodes.raw(format='html', text=tail)
elif all_nodes_is_in_paragraph:
node[0] += nodes.Text(tail)
elif having_block_node:
node += nodes.paragraph(text=tail)
else:
node += nodes.Text(tail)
return node
def make_node(self, cls, element):
node = cls()
having_block_node = cls in HAVING_BLOCK_NODE
if element.text and element.text != "\n":
text = self.unescape_char(element.text)
if HTML_PLACEHOLDER_RE.search(text):
node += nodes.raw(format='html', text=self.unescape_char(text, rawHtml=True))
elif having_block_node:
node += nodes.paragraph(text=text)
else:
node += nodes.Text(text)
for child in element:
subnode = self.visit(child)
if having_block_node and isinstance(subnode, INLINE_NODES):
all_nodes_is_in_paragraph = True
if len(node) == 0:
node += nodes.paragraph()
node[0] += subnode
else:
all_nodes_is_in_paragraph = False
node += subnode
if child.tail and child.tail != "\n":
tail = self.unescape_char(child.tail)
if HTML_PLACEHOLDER_RE.search(tail):
node += nodes.raw(format='html', text=tail)
elif all_nodes_is_in_paragraph:
node[0] += nodes.Text(tail)
elif having_block_node:
node += nodes.paragraph(text=tail)
else:
node += nodes.Text(tail)
return node
def make_node(self, cls, element):
node = cls()
having_block_node = cls in HAVING_BLOCK_NODE
if element.text and element.text != "\n":
text = self.unescape_char(element.text)
if HTML_PLACEHOLDER_RE.search(text):
html_text = self.unescape_char(text, rawHtml=True)
if html_text.startswith("<!--math"):
g = re.match(r"<!--math(.*?)-->", html_text, re.DOTALL)
if g:
node += nodes.math(text=g.group(1).strip(),
latex=g.group(1).strip())
else:
node += nodes.raw(format='html', text=html_text)
elif having_block_node:
node += nodes.paragraph(text=text)
else:
node += nodes.Text(text)
for child in element:
subnode = self.visit(child)
if having_block_node and isinstance(subnode, INLINE_NODES):
all_nodes_is_in_paragraph = True
if len(node) == 0:
node += nodes.paragraph()
node[0] += subnode
else:
all_nodes_is_in_paragraph = False
node += subnode
if child.tail and child.tail != "\n":
tail = self.unescape_char(child.tail)
if HTML_PLACEHOLDER_RE.search(tail):
node += nodes.raw(format='html', text=tail)
elif all_nodes_is_in_paragraph:
node[0] += nodes.Text(tail)
elif having_block_node:
node += nodes.paragraph(text=tail)
else:
node += nodes.Text(tail)
return node
def stashedHTML2text(text, md):
""" Extract raw HTML, reduce to plain text and swap with placeholder. """
def _html_sub(m):
""" Substitute raw html with plain text. """
try:
raw, safe = md.htmlStash.rawHtmlBlocks[int(m.group(1))]
except (IndexError, TypeError):
return m.group(0)
if md.safeMode and not safe:
return ''
# Strip out tags and entities - leaveing text
return re.sub(r'(<[^>]+>)|(&[\#a-zA-Z0-9]+;)', '', raw)
return HTML_PLACEHOLDER_RE.sub(_html_sub, text)
def stashedHTML2text(text, md):
""" Extract raw HTML, reduce to plain text and swap with placeholder. """
def _html_sub(m):
""" Substitute raw html with plain text. """
try:
raw, safe = md.htmlStash.rawHtmlBlocks[int(m.group(1))]
except (IndexError, TypeError):
return m.group(0)
if md.safeMode and not safe:
return ''
# Strip out tags and entities - leaveing text
return re.sub(r'(<[^>]+>)|(&[\#a-zA-Z0-9]+;)', '', raw)
return HTML_PLACEHOLDER_RE.sub(_html_sub, text)
def unescape_char(self, text, rawHtml=False):
def unescape(matched):
return chr(int(matched.group(1)))
def expand_rawhtml(matched):
html_id = int(matched.group(1))
html, safe = self.markdown.htmlStash.rawHtmlBlocks[html_id]
if rawHtml or re.match(r'(&[\#a-zA-Z0-9]*;)', html):
return html # unescape HTML entities only
else:
return matched.group(0)
text = re.sub('\x02(\d\d)\x03', unescape, text)
text = HTML_PLACEHOLDER_RE.sub(expand_rawhtml, text)
return text
def stashedHTML2text(text, md, strip_entities=True):
""" Extract raw HTML from stash, reduce to plain text and swap with placeholder. """
def _html_sub(m):
""" Substitute raw html with plain text. """
try:
raw = md.htmlStash.rawHtmlBlocks[int(m.group(1))]
except (IndexError, TypeError): # pragma: no cover
return m.group(0)
# Strip out tags and/or entities - leaving text
res = re.sub(r'(<[^>]+>)', '', raw)
if strip_entities:
res = re.sub(r'(&[\#a-zA-Z0-9]+;)', '', res)
return res
return HTML_PLACEHOLDER_RE.sub(_html_sub, text)
def unescape_char(self, text, rawHtml=False):
def unescape(matched):
return chr(int(matched.group(1)))
def expand_rawhtml(matched):
html_id = int(matched.group(1))
html, safe = self.markdown.htmlStash.rawHtmlBlocks[html_id]
if rawHtml or re.match(r'(&[\#a-zA-Z0-9]*;)', html):
return html # unescape HTML entities only
else:
return matched.group(0)
text = re.sub('\x02(\d\d)\x03', unescape, text)
text = HTML_PLACEHOLDER_RE.sub(expand_rawhtml, text)
return text
