1
0
mirror of https://github.com/djohnlewis/stackdump synced 2025-12-16 12:53:28 +00:00

Added markdown parsing for comments so links in comments now appear properly.

Also rewrote part of the HTML rewriting code so it doesn't introduce an additional wrapping element in the output which was added due to a html5lib requirements on input.
This commit is contained in:
Samuel Lai
2012-12-15 21:43:06 +11:00
parent 5ac8492f38
commit 993bee4fc1
33 changed files with 5217 additions and 10 deletions

View File

@@ -0,0 +1,110 @@
#!/usr/bin/env python
"""
Definition List Extension for Python-Markdown
=============================================
Added parsing of Definition Lists to Python-Markdown.
A simple example:
Apple
: Pomaceous fruit of plants of the genus Malus in
the family Rosaceae.
: An american computer company.
Orange
: The fruit of an evergreen tree of the genus Citrus.
Copyright 2008 - [Waylan Limberg](http://achinghead.com)
"""
import re
import markdown
from markdown.util import etree
class DefListProcessor(markdown.blockprocessors.BlockProcessor):
""" Process Definition Lists. """
RE = re.compile(r'(^|\n)[ ]{0,3}:[ ]{1,3}(.*?)(\n|$)')
NO_INDENT_RE = re.compile(r'^[ ]{0,3}[^ :]')
def test(self, parent, block):
return bool(self.RE.search(block))
def run(self, parent, blocks):
block = blocks.pop(0)
m = self.RE.search(block)
terms = [l.strip() for l in block[:m.start()].split('\n') if l.strip()]
block = block[m.end():]
no_indent = self.NO_INDENT_RE.match(block)
if no_indent:
d, theRest = (block, None)
else:
d, theRest = self.detab(block)
if d:
d = '%s\n%s' % (m.group(2), d)
else:
d = m.group(2)
sibling = self.lastChild(parent)
if not terms and sibling.tag == 'p':
# The previous paragraph contains the terms
state = 'looselist'
terms = sibling.text.split('\n')
parent.remove(sibling)
# Aquire new sibling
sibling = self.lastChild(parent)
else:
state = 'list'
if sibling and sibling.tag == 'dl':
# This is another item on an existing list
dl = sibling
if len(dl) and dl[-1].tag == 'dd' and len(dl[-1]):
state = 'looselist'
else:
# This is a new list
dl = etree.SubElement(parent, 'dl')
# Add terms
for term in terms:
dt = etree.SubElement(dl, 'dt')
dt.text = term
# Add definition
self.parser.state.set(state)
dd = etree.SubElement(dl, 'dd')
self.parser.parseBlocks(dd, [d])
self.parser.state.reset()
if theRest:
blocks.insert(0, theRest)
class DefListIndentProcessor(markdown.blockprocessors.ListIndentProcessor):
""" Process indented children of definition list items. """
ITEM_TYPES = ['dd']
LIST_TYPES = ['dl']
def create_item(self, parent, block):
""" Create a new dd and parse the block with it as the parent. """
dd = markdown.etree.SubElement(parent, 'dd')
self.parser.parseBlocks(dd, [block])
class DefListExtension(markdown.Extension):
""" Add definition lists to Markdown. """
def extendMarkdown(self, md, md_globals):
""" Add an instance of DefListProcessor to BlockParser. """
md.parser.blockprocessors.add('defindent',
DefListIndentProcessor(md.parser),
'>indent')
md.parser.blockprocessors.add('deflist',
DefListProcessor(md.parser),
'>ulist')
def makeExtension(configs={}):
return DefListExtension(configs=configs)