def _prettifyETree(self, elem):
""" Recursively add linebreaks to ElementTree children. """
i = "\n"
if markdown.isBlockLevel(elem.tag) and elem.tag not in ['code', 'pre']:
if (not elem.text or not elem.text.strip()) \
and len(elem) and markdown.isBlockLevel(elem[0].tag):
elem.text = i
for e in elem:
if markdown.isBlockLevel(e.tag):
self._prettifyETree(e)
if not elem.tail or not elem.tail.strip():
elem.tail = i
if not elem.tail or not elem.tail.strip():
elem.tail = i
def _prettifyETree(self, elem):
""" Recursively add linebreaks to ElementTree children. """
i = "\n"
if markdown.isBlockLevel(elem.tag) and elem.tag not in ['code', 'pre']:
if (not elem.text or not elem.text.strip()) \
and len(elem) and markdown.isBlockLevel(elem[0].tag):
elem.text = i
for e in elem:
if markdown.isBlockLevel(e.tag):
self._prettifyETree(e)
if not elem.tail or not elem.tail.strip():
elem.tail = i
if not elem.tail or not elem.tail.strip():
elem.tail = i
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
if block.startswith("\n"):
block = block[1:]
text = text[1:]
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(left_tag, block)
if data_index < len(block):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (markdown.isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag, data_index = self._get_right_tag(left_tag, block)
# keep checking conditions below and maybe just append
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
else: #if not block[1] == "!":
# if is block level tag and is not complete
if markdown.isBlockLevel(left_tag) or left_tag == "--" \
and not block.rstrip().endswith(">"):
items.append(block.strip())
in_tag = True
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
new_blocks.append(block)
else:
items.append(block.strip())
right_tag, data_index = self._get_right_tag(left_tag, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
new_blocks.append('\n')
new_text = "\n\n".join(new_blocks)
return new_text.split("\n")
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
if block.startswith("\n"):
block = block[1:]
text = text[1:]
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(
left_tag, block)
if data_index < len(block):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (markdown.isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag, data_index = self._get_right_tag(
left_tag, block)
# keep checking conditions below and maybe just append
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
else: #if not block[1] == "!":
# if is block level tag and is not complete
if markdown.isBlockLevel(left_tag) or left_tag == "--" \
and not block.rstrip().endswith(">"):
items.append(block.strip())
in_tag = True
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
new_blocks.append(block)
else:
items.append(block.strip())
right_tag, data_index = self._get_right_tag(left_tag, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
new_blocks.append(self.markdown.htmlStash.store(
'\n\n'.join(items)))
new_blocks.append('\n')
new_text = "\n\n".join(new_blocks)
return new_text.split("\n")
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
text = text[1:]
if not in_tag:
if not block.startswith("<"):
new_blocks.append(block)
continue
left_tag = self._get_left_tag(block)
# data_index 是 right_tag 结束的地方
right_tag, data_index = self._get_right_tag(left_tag, block)
if block[1] == "!":
# 处理 "<!--html注释-->"
left_tag = "--"
right_tag, data_index = self._get_right_tag(left_tag, block)
if data_index < len(block) and \
markdown.isBlockLevel(left_tag):
# 处理这样的 block： "<pre>内容</pre>其他"
# 这样 data_index 的值会小于 block 长度
# 需先将 pre 块后面的放回 text 列表，下次处理
text.insert(0, block[data_index:])
block = block[:data_index]
if not markdown.isBlockLevel(left_tag) and \
block[1] not in ["!", "?", "@", "%"]:
# 既不是合法html块标签，又不是特殊标签
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
# 处理 "<hr/>","<hr>" 这样的行分割符
new_blocks.append(block.strip())
continue
if not block.rstrip().endswith(">") or not\
self._equal_tags(left_tag, right_tag) and\
markdown.isBlockLevel(left_tag) or\
left_tag == "--" :
# block 里的 html 标签对还未结束
items.append(block.strip())
in_tag = True
continue
# 现在 block 里一定是 html 块处理
new_blocks.append(self.markdown.htmlStash.store(block.strip()))
else:
# 进入跨 block 的 html 块标签
right_tag, data_index = self._get_right_tag(left_tag, block)
if data_index < len(block) and \
markdown.isBlockLevel(left_tag):
text.insert(0, block[data_index:])
block = block[:data_index]
items.append(block.strip())
if self._equal_tags(left_tag, right_tag):
# 如果左右标签成对，就准备结束 in_tag 情况
in_tag = False
new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
# 如果 items 里面还有内容，说明有 html 块标签未配对，直接加上
new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
new_blocks.append('\n')
return "\n\n".join(new_blocks).split("\n")
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
text = text[1:]
if not in_tag:
if not block.startswith("<"):
new_blocks.append(block)
continue
left_tag = self._get_left_tag(block)
# data_index 是 right_tag 结束的地方
right_tag, data_index = self._get_right_tag(left_tag, block)
if block[1] == "!":
# 处理 "<!--html注释-->"
left_tag = "--"
right_tag, data_index = self._get_right_tag(
left_tag, block)
if data_index < len(block) and \
markdown.isBlockLevel(left_tag):
# 处理这样的 block： "<pre>内容</pre>其他"
# 这样 data_index 的值会小于 block 长度
# 需先将 pre 块后面的放回 text 列表，下次处理
text.insert(0, block[data_index:])
block = block[:data_index]
if not markdown.isBlockLevel(left_tag) and \
block[1] not in ["!", "?", "@", "%"]:
# 既不是合法html块标签，又不是特殊标签
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
# 处理 "<hr/>","<hr>" 这样的行分割符
new_blocks.append(block.strip())
continue
if not block.rstrip().endswith(">") or not\
self._equal_tags(left_tag, right_tag) and\
markdown.isBlockLevel(left_tag) or\
left_tag == "--" :
# block 里的 html 标签对还未结束
items.append(block.strip())
in_tag = True
continue
# 现在 block 里一定是 html 块处理
new_blocks.append(self.markdown.htmlStash.store(block.strip()))
else:
# 进入跨 block 的 html 块标签
right_tag, data_index = self._get_right_tag(left_tag, block)
if data_index < len(block) and \
markdown.isBlockLevel(left_tag):
text.insert(0, block[data_index:])
block = block[:data_index]
items.append(block.strip())
if self._equal_tags(left_tag, right_tag):
# 如果左右标签成对，就准备结束 in_tag 情况
in_tag = False
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
# 如果 items 里面还有内容，说明有 html 块标签未配对，直接加上
new_blocks.append(self.markdown.htmlStash.store(
'\n\n'.join(items)))
new_blocks.append('\n')
return "\n\n".join(new_blocks).split("\n")
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
if block.startswith("\n"):
block = block[1:]
text = text[1:]
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag, left_index, attrs = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(left_tag,
left_index,
block)
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag, data_index = self._get_right_tag(left_tag,
left_index,
block)
# keep checking conditions below and maybe just append
if data_index < len(block) \
and markdown.isBlockLevel(left_tag):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (markdown.isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
if self.markdown_in_raw and 'markdown' in attrs.keys():
start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?',
'', block[:left_index])
end = block[-len(right_tag)-2:]
block = block[left_index:-len(right_tag)-2]
new_blocks.append(
self.markdown.htmlStash.store(start))
new_blocks.append(block)
new_blocks.append(
self.markdown.htmlStash.store(end))
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
else:
# if is block level tag and is not complete
if markdown.isBlockLevel(left_tag) or left_tag == "--" \
and not block.rstrip().endswith(">"):
items.append(block.strip())
in_tag = True
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
new_blocks.append(block)
else:
items.append(block)
right_tag, data_index = self._get_right_tag(left_tag,
left_index,
block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
if self.markdown_in_raw and 'markdown' in attrs.keys():
start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?',
'', items[0][:left_index])
items[0] = items[0][left_index:]
end = items[-1][-len(right_tag)-2:]
items[-1] = items[-1][:-len(right_tag)-2]
new_blocks.append(
self.markdown.htmlStash.store(start))
new_blocks.extend(items)
new_blocks.append(
self.markdown.htmlStash.store(end))
else:
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
if self.markdown_in_raw and 'markdown' in attrs.keys():
start = re.sub(r'\smarkdown(=[\'"]?[^> ]*[\'"]?)?',
'', items[0][:left_index])
items[0] = items[0][left_index:]
end = items[-1][-len(right_tag)-2:]
items[-1] = items[-1][:-len(right_tag)-2]
new_blocks.append(
self.markdown.htmlStash.store(start))
new_blocks.extend(items)
new_blocks.append(
self.markdown.htmlStash.store(end))
else:
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
#new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
new_blocks.append('\n')
new_text = "\n\n".join(new_blocks)
return new_text.split("\n")
