def _prettifyETree(self, elem):
i = '\n'
if util.isBlockLevel(elem.tag) and elem.tag not in ('code', 'pre'):
if (not elem.text or not elem.text.strip()) and len(elem) and util.isBlockLevel(elem[0].tag):
elem.text = i
for e in elem:
if util.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):
i = '\n'
if util.isBlockLevel(elem.tag) and elem.tag not in ('code', 'pre'):
if (not elem.text or
not elem.text.strip()) and len(elem) and util.isBlockLevel(
elem[0].tag):
elem.text = i
for e in elem:
if util.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 util.isBlockLevel(elem.tag) and elem.tag not in ('code', 'pre'):
if (not elem.text or
not elem.text.strip()) and len(elem) and util.isBlockLevel(
elem[0].tag):
elem.text = i
for e in elem:
if util.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 isblocklevel(self, html):
m = re.match('^\\<\\/?([^ >]+)', html)
if m:
if m.group(1)[0] in ('!', '?', '@', '%'):
return True
return util.isBlockLevel(m.group(1))
return False
def isblocklevel(self, html):
m = re.match('^\\<\\/?([^ >]+)', html)
if m:
if m.group(1)[0] in ('!', '?', '@', '%'):
return True
return util.isBlockLevel(m.group(1))
return False
def run(self, doc):
for elem in doc.getiterator():
#import pdb; pdb.set_trace()
if isBlockLevel(elem.tag):
# Block level: check for attrs on last line of text
RE = self.BLOCK_RE
if isheader(elem):
# header: check for attrs at end of line
RE = self.HEADER_RE
if len(elem) and elem[-1].tail:
# has children. Get from tail of last child
m = RE.search(elem[-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[-1].tail = elem[-1].tail[:m.start()]
if isheader(elem):
# clean up trailing #s
elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
elif elem.text:
# no children. Get from text.
m = RE.search(elem.text)
if m:
self.assign_attrs(elem, m.group(1))
elem.text = elem.text[:m.start()]
if isheader(elem):
# clean up trailing #s
elem.text = elem.text.rstrip('#').rstrip()
else:
# inline: check for attrs at start of tail
if elem.tail:
m = self.INLINE_RE.match(elem.tail)
if m:
self.assign_attrs(elem, m.group(1))
elem.tail = elem.tail[m.end():]
def run(self, doc):
for elem in doc.getiterator():
if isBlockLevel(elem.tag):
# Block level: check for attrs on last line of text
RE = self.BLOCK_RE
if isheader(elem):
# header: check for attrs at end of line
RE = self.HEADER_RE
if len(elem) and elem[-1].tail:
# has children. Get from tail of last child
m = RE.search(elem[-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[-1].tail = elem[-1].tail[:m.start()]
if isheader(elem):
# clean up trailing #s
elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
elif elem.text:
# no children. Get from text.
m = RE.search(elem.text)
if m:
self.assign_attrs(elem, m.group(1))
elem.text = elem.text[:m.start()]
if isheader(elem):
# clean up trailing #s
elem.text = elem.text.rstrip('#').rstrip()
else:
# inline: check for attrs at start of tail
if elem.tail:
m = self.INLINE_RE.match(elem.tail)
if m:
self.assign_attrs(elem, m.group(1))
elem.tail = elem.tail[m.end():]
def run(self, doc):
for elem in doc.getiterator():
if isBlockLevel(elem.tag):
RE = self.BLOCK_RE
if isheader(elem):
RE = self.HEADER_RE
if len(elem) and elem[-1].tail:
m = RE.search(elem[-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[-1].tail = elem[-1].tail[:m.start()]
if isheader(elem):
elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
elif elem.text:
m = RE.search(elem.text)
if m:
self.assign_attrs(elem, m.group(1))
elem.text = elem.text[:m.start()]
if isheader(elem):
elem.text = elem.text.rstrip('#').rstrip()
elif elem.tail:
m = self.INLINE_RE.match(elem.tail)
if m:
self.assign_attrs(elem, m.group(1))
elem.tail = elem.tail[m.end():]
def _parseID(self, element):
''' recursively parse all {#idname}s at eol into ids '''
if isBlockLevel(element.tag) and element.tag not in ['code', 'pre']:
#print element
if element.text and element.text.strip():
m = ID_RE.search(element.text)
if m:
if m.group('type') == '#':
element.set('id',m.group('id'))
else:
element.set('class',m.group('id'))
element.text = element.text[:m.start()]
# TODO: should this be restricted to <h1>..<h4> only?
if element.tag in SECTIONLINK_PERMITTED_TAGS:
child = etree.Element("a")
for k,v in {
'class': 'elementid-sectionlink',
'href': '#'+m.group('id'),
'title': 'Link to this section',
}.iteritems():
child.set(k, v)
# child.text = r" ¶" # U+00B6 PILCROW SIGN
child.text = "¶"
# Actually append the child, and a space before it too.
#element.append(child)
#if len(element):
# element.text += " "
#else:
# element[-1].tail += " "
for e in element:
self._parseID(e)
return element
def _parseID(self, element):
''' recursively parse all {#idname}s at eol into ids '''
if isBlockLevel(element.tag) and element.tag not in ['code', 'pre']:
#print element
if element.text and element.text.strip():
m = ID_RE.search(element.text)
if m:
if m.group('type') == '#':
element.set('id', m.group('id'))
else:
element.set('class', m.group('id'))
element.text = element.text[:m.start()]
# TODO: should this be restricted to <h1>..<h4> only?
if element.tag in SECTIONLINK_PERMITTED_TAGS:
child = etree.Element("a")
for k, v in {
'class': 'elementid-sectionlink',
'href': '#' + m.group('id'),
'title': 'Link to this section',
}.iteritems():
child.set(k, v)
# child.text = r" ¶" # U+00B6 PILCROW SIGN
child.text = "¶"
# Actually append the child, and a space before it too.
#element.append(child)
#if len(element):
# element.text += " "
#else:
# element[-1].tail += " "
for e in element:
self._parseID(e)
return element
def run(self, root):
blocks = root.getiterator('pre')
for block in blocks:
if isBlockLevel(block.tag):
cls = block.get('class')
if cls:
block.set('class', '%s %s' % (cls, PRE_CLASS))
else:
block.set('class', PRE_CLASS)
return root
def run(self, root):
if isBlockLevel(root.tag) and root.tag not in ['code', 'pre']:
child = etree.Element("style")
for k, v in {
'type': 'text/css',
}.iteritems():
child.set(k, v)
# Note upstream doc bug: it's not called markdown.AtomicString().
child.text = markdown.util.AtomicString(SECTIONLINK_CSS)
root.insert(0, child)
child.tail = root.text
root.text = None
def run(self, root):
'''
Find and remove all id specs references from the text,
and add them as the id attribute of the element.
ROOT is div#section_content.
'''
if isBlockLevel(root.tag) and root.tag not in ['code', 'pre']:
self._parseID(root)
child = etree.Element("style")
for k,v in {
'type': 'text/css',
}.iteritems():
child.set(k, v)
# Note upstream doc bug: it's not called markdown.AtomicString().
child.text = markdown.util.AtomicString(SECTIONLINK_CSS)
#root.insert(0, child)
# child.tail = root.text; root.text = None;
return root
def run(self, root):
'''
Find and remove all id specs references from the text,
and add them as the id attribute of the element.
ROOT is div#section_content.
'''
if isBlockLevel(root.tag) and root.tag not in ['code', 'pre']:
self._parseID(root)
child = etree.Element("style")
for k, v in {
'type': 'text/css',
}.iteritems():
child.set(k, v)
# Note upstream doc bug: it's not called markdown.AtomicString().
child.text = markdown.util.AtomicString(SECTIONLINK_CSS)
#root.insert(0, child)
# child.tail = root.text; root.text = None;
return root
def _parseID(self, element):
''' recursively parse all {#idname}s at eol into ids '''
if isBlockLevel(element.tag) and element.tag not in ['code', 'pre']:
#print element
while element.text and element.text.strip():
m = ID_RE.search(element.text)
if m:
if m.group('type') == '#':
element.set('id',m.group('id'))
element.text = element.text[:m.start()]
# TODO: should this be restricted to <h1>..<h4> only?
if element.tag not in HEADER_TAGS:
child = etree.Element("a")
for k,v in {
'class': 'elementid-permalink',
'href': '#'+m.group('id'),
'title': 'Permanent link',
}.iteritems():
child.set(k, v)
# child.text = r" ¶" # U+00B6 PILCROW SIGN
child.text = "¶"
# Actually append the child, and a space before it too.
element.append(child)
# if len(element):
# element.text += " "
# else:
# element[-1].tail += " "
if element.tag not in self.seen_block_tag:
self.css += '%s:hover > .elementid-permalink, ' % element.tag
self.seen_block_tag[element.tag] = True
else:
element.set('class',m.group('id'))
element.text = element.text[:m.start()]
else:
break
for e in element:
self._parseID(e)
return element
def run(self, root):
'''
Find and remove all id specs references from the text,
and add them as the id attribute of the element.
ROOT is div#section_content.
'''
if isBlockLevel(root.tag) and root.tag not in ['code', 'pre']:
self._parseID(root)
child = etree.Element("style")
for k,v in {
'type': 'text/css',
}.iteritems():
child.set(k, v)
# Note upstream doc bug: it's not called markdown.AtomicString().
self.css += 'dt:hover > .elementid-permalink { visibility: visible }'
child.text = markdown.util.AtomicString(self.css)
root.insert(0, child)
self.css = CSS
self.seen_block_tag = {}
# child.tail = root.text; root.text = None;
return root
def run(self, doc):
for elem in doc.getiterator():
if isBlockLevel(elem.tag):
# Block level: check for attrs on last line of text
RE = self.BLOCK_RE
if isheader(elem) or elem.tag == 'dt':
# header or def-term: check for attrs at end of line
RE = self.HEADER_RE
if len(elem) and elem.tag == 'li':
# special case list items. children may include a ul or ol.
pos = None
# find the ul or ol position
for i, child in enumerate(elem):
if child.tag in ['ul', 'ol']:
pos = i
break
if pos is None and elem[-1].tail:
# use tail of last child. no ul or ol.
m = RE.search(elem[-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[-1].tail = elem[-1].tail[:m.start()]
elif pos is not None and pos > 0 and elem[pos-1].tail:
# use tail of last child before ul or ol
m = RE.search(elem[pos-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[pos-1].tail = elem[pos-1].tail[:m.start()]
elif elem.text:
# use text. ul is first child.
m = RE.search(elem.text)
if m:
self.assign_attrs(elem, m.group(1))
elem.text = elem.text[:m.start()]
elif len(elem) and elem[-1].tail:
# has children. Get from tail of last child
m = RE.search(elem[-1].tail)
if m:
self.assign_attrs(elem, m.group(1))
elem[-1].tail = elem[-1].tail[:m.start()]
if isheader(elem):
# clean up trailing #s
elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
elif elem.text:
# no children. Get from text.
m = RE.search(elem.text)
if not m and elem.tag == 'td':
m = re.search(self.BASE_RE, elem.text)
if m:
print elem.text, self.BASE_RE, m
if m:
self.assign_attrs(elem, m.group(1))
elem.text = elem.text[:m.start()]
if isheader(elem):
# clean up trailing #s
elem.text = elem.text.rstrip('#').rstrip()
else:
# inline: check for attrs at start of tail
if elem.tail:
m = self.INLINE_RE.match(elem.tail)
if m:
self.assign_attrs(elem, m.group(1))
elem.tail = elem.tail[m.end():]
def run(self, lines):
text = '\n'.join(lines)
new_blocks = []
text = text.split('\n\n')
items = []
left_tag = ''
right_tag = ''
in_tag = False
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('<') and len(block.strip()) > 1:
if block[1] == '!':
left_tag, left_index, attrs = '--', 2, {}
else:
left_tag, left_index, attrs = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(left_tag, left_index, block)
if data_index < len(block) and (util.isBlockLevel(left_tag) or left_tag == '--'):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (util.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('\\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 util.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, 0, block)
if self._equal_tags(left_tag, right_tag):
if data_index < len(block):
items[-1] = block[:data_index]
text.insert(0, block[data_index:])
in_tag = False
if self.markdown_in_raw and 'markdown' in attrs.keys():
start = re.sub('\\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('\\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)
if end.strip():
new_blocks.append(self.markdown.htmlStash.store(end))
else:
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
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('<') and len(block.strip()) > 1:
if block[1] == '!':
left_tag, left_index, attrs = '--', 2, {}
else:
left_tag, left_index, attrs = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(
left_tag, left_index, block)
if data_index < len(block) and (util.isBlockLevel(left_tag)
or left_tag == '--'):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (util.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(
'\\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 util.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, 0, block)
if self._equal_tags(left_tag, right_tag):
if data_index < len(block):
items[-1] = block[:data_index]
text.insert(0, block[data_index:])
in_tag = False
if self.markdown_in_raw and 'markdown' in attrs.keys():
start = re.sub('\\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('\\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)
if end.strip():
new_blocks.append(self.markdown.htmlStash.store(end))
else:
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')
