def html_to_markmin(html):
"""Replace HTML with Markmin"""
if html is None:
return ''
from gluon.html import markmin_serializer, TAG
return TAG(html).flatten(markmin_serializer).lstrip(' ')
def test_markdown(self):
def markdown(text, tag=None, attributes={}):
r = {None: re.sub('\s+',' ',text), \
'h1':'#'+text+'\\n\\n', \
'p':text+'\\n'}.get(tag,text)
return r
a=TAG('<h1>Header</h1><p>this is a test</p>')
ret = a.flatten(markdown)
self.assertEqual(ret, '#Header\\n\\nthis is a test\\n')
def pdflatex_from_html(html):
if os.system('which pdflatex > /dev/null') == 0:
markmin = TAG(html).element('body').flatten(markmin_serializer)
out, warnings, errors = markmin2pdf(markmin)
if errors:
current.response.headers['Content-Type'] = 'text/html'
raise HTTP(405, HTML(BODY(H1('errors'),
UL(*errors),
H1('warnings'),
UL(*warnings))).xml())
else:
return XML(out)
def html_to_markmin(html):
"""
Replace HTML with Markmin, converting unicode to references first
>>> html_to_markmin('<p class="foo"><b>Bold</b><i>Italics</i><ol><li>Item 1</li><li><a href="http://kvasir.io">Kvasir</a></li></ol><br>')
"**Bold**''Italics''\n- Item 1\n- [[Kvasir http://kvasir.io]]\n\n\n\n"
>>> html_to_markmin(u'<p>asdfsadf</p>')
'asdfsadf\n\n'
>>> html_to_markmin(u'<p>\ufffdq\ufffd</p>')
'\xef\xbf\xbdq\xef\xbf\xbd\n\n'
>>> html_to_markmin('[[ a link http://url.com]]')
'[[a link http://url.com]]'
"""
if html is None:
return ''
from gluon.html import markmin_serializer, TAG
html = html.encode('ascii', 'xmlcharrefreplace') # cleanup unicode
html = TAG(html).flatten(markmin_serializer) # turn to markmin
html = html.replace('[[ ', '[[') # fix bad url
html = html.replace(' ]]', ']]') # fix bad url
return html
def latex_from_html(html):
markmin = TAG(html).element('body').flatten(markmin_serializer)
return XML(markmin2latex(markmin))
