def _build_block_parser(md, **kwargs):
""" Build the default block parser used by Markdown. """
parser = BlockParser(md)
parser.blockprocessors.register(EmptyBlockProcessor(parser), 'empty', 100)
parser.blockprocessors.register(ListIndentProcessor(parser), 'indent', 90)
parser.blockprocessors.register(CodeBlockProcessor(parser), 'code', 80)
parser.blockprocessors.register(BudouXHashHeaderProcessor(parser),
'hashheader', 70)
parser.blockprocessors.register(SetextHeaderProcessor(parser),
'setextheader', 60)
parser.blockprocessors.register(HRProcessor(parser), 'hr', 50)
parser.blockprocessors.register(OListProcessor(parser), 'olist', 40)
parser.blockprocessors.register(UListProcessor(parser), 'ulist', 30)
parser.blockprocessors.register(BlockQuoteProcessor(parser), 'quote', 20)
parser.blockprocessors.register(ReferenceProcessor(parser), 'reference',
15)
parser.blockprocessors.register(BudouXParagraphProcessor(parser),
'paragraph', 10)
return parser
class CustomHtmlListBuilder(HierarchyBuilderWithQueue):
class Level:
def __init__(self, char, element):
self.char = char
self.element = element
def __init__(self, parser, root):
super(CustomHtmlListBuilder, self).__init__()
self._root = root
self._hrProcessor = HRProcessor(parser)
rootUl = property(lambda self: None if not self._levels else self._levels[0].element)
@staticmethod
def _parseLine(line, level=None):
assert line and not line[0].isspace()
if level is not None:
if line[0] == level.char:
char = level.char
text = line[1:].lstrip()
else:
char = None
text = line
else:
if line[0] in '*-|':
char = line[0]
text = line[1:].lstrip()
else:
char = None
text = line
return (char, text)
def _createUl(self, parent, char):
if char is None or char == '*':
return etree.SubElement(parent, 'ul')
elif char == '-':
return etree.SubElement(parent, 'ol')
elif char == '|':
return etree.SubElement(parent, 'ul', { 'class': 'details' })
else:
raise Exception("Invalid char")
def _createLi(self, parent, text):
# Кастомная обработка: если текст соответствует Markdown-разметке горизонтальной линии,
# вместо использования этого текста добавляем элементу списка класс "separator"
shouldBeSeparator = self._hrProcessor.test(parent, text)
li = etree.SubElement(parent, 'li')
if shouldBeSeparator:
li.set('class', 'separator')
else:
li.text = text
return li
def push(self, line):
char, text = self._parseLine(line, level=None)
parentElement = self._root if not self._levels else \
self._levels[-1].element[-1] # последний LI текущего UL
ul = self._createUl(parentElement, char)
self._createLi(ul, text)
self._levels.append(self.Level(char, ul))
def put(self, line):
level = self._levels[-1]
unused_char, text = self._parseLine(line, level)
self._createLi(level.element, text)
def __init__(self, parser, root): super(CustomHtmlListBuilder, self).__init__() self._root = root self._hrProcessor = HRProcessor(parser)
