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