small tornado server that translate a few parts of markdown syntax to mediawiki, not 100% functional but helps a lot

markdown2mediawiki.py

# #!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright (C) <2011>  Gabriel Falcão <[email protected]>
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation
# files (the "Software"), to deal in the Software without
# restriction, including without limitation the rights to use,
# copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following
# conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.

import re

class Markdown2MediaWiki(object):
    """
        >>> cv = Markdown2MediaWiki('# foobar')
        >>> cv.convert()
        u'= foobar =\\n'

        >>> cv = Markdown2MediaWiki('###### iasydlasdaskdakdu @#$%)(*&&')
        >>> cv.convert()
        u'====== iasydlasdaskdakdu @#$%)(*&& ======\\n'

        >>> cv = Markdown2MediaWiki('[name of the link](http://actual.link.com?with=query%20strings)')
        >>> cv.convert()
        u'[http://actual.link.com?with=query%20strings name of the link]'

        >>> cv = Markdown2MediaWiki('something with `code` inline')
        >>> cv.convert()
        u'something with <pre>code</pre> inline'

        >>> cv = Markdown2MediaWiki('     something with `code` inline  ')
        >>> cv.convert()
        u'<pre> something with `code` inline  </pre>'

        >>> cv = Markdown2MediaWiki('*blabla*')
        >>> cv.convert()
        u"''blabla''"

        >>> cv = Markdown2MediaWiki('**blabla**')
        >>> cv.convert()
        u"'''blabla'''"

        >>> cv = Markdown2MediaWiki('*blabla* **foobar**')
        >>> cv.convert()
        u"''blabla'' '''foobar'''"

    """

    def __init__(self, string):
        self.string = string

    def _filter_headings(self, string):
        regex = re.compile(ur'^(?P<char>[#]+)\s*(?P<title>.*)', re.U)
        found = regex.findall(string)
        for char, title in found:
            string = regex.sub(ur'{0} \g<title> {0}'.format('=' * len(char)), string, 1)

        return string

    def _filter_links(self, string):
        regex = re.compile(ur'[[](?P<name>[^]]+)[]][(](?P<link>https?[:][/]{2}[^)]+)[)]', re.U)
        return regex.sub(ur'[\g<link> \g<name>]', string)

    def _filter_inline_code(self, string):
        regex = re.compile(ur'^(?P<start>[^<]|[<][^p]|[<]p[^r]|[<]pr[^e]|[<]pre[^>])(?P<any1>[^`]*)[`](?P<code>[^`]*)[`](?P<any2>[^`]*)$')
        return regex.sub(ur'\g<start>\g<any1><pre>\g<code></pre>\g<any2>', string)

    def _filter_indented_code(self, string):
        regex = re.compile(ur'^\s{4}(?P<code>.*)$')
        return regex.sub(ur'<pre>\g<code></pre>', string)

    def _filter_bold_and_italic(self, string):
        regex = re.compile(ur'(?P<char>[*]{1,2})\s*(?P<title>[^*]*)\s*(?P=char)', re.U)
        found = regex.findall(string)
        for char, title in found:
            string = regex.sub(ur'{0}\g<title>{0}'.format("'" * (len(char)+1)), string, 1)

        return string

    def convert(self):
        lines = self.string.splitlines()
        transformers = [getattr(self, x) for x in sorted(dir(self)) \
                        if x.startswith("_filter")]

        res = []
        for line in lines:
            for transform in transformers:
                line = transform(line)

            res.append(line)

        string = '\n'.join(map(unicode.strip, res))
        return re.sub(r'[=]$', '=\n', string)

if __name__ == "__main__":
    import doctest
    import tornado.ioloop
    import tornado.web

    class MainHandler(tornado.web.RequestHandler):
        def post(self):
            cv = Markdown2MediaWiki(self.get_argument('md', ''))
            self.set_header('Content-Type', 'text/plain')
            self.write(cv.convert())

        def get(self):
            self.write(self.render_index())

        def render_index(self, top=""):
            return ur'''
            <html>
              <head>
                <title>Markdown2MediaWiki</title>
              </head>
              <body>
              {0}
                <form method="POST">
                  <textarea name="md" style="width:640px;height:480px">
# Put

## some

    markdown

*right* **here**
                  </textarea>
                  <input type="submit" value="convert to media wiki" />
                </form>
              </body>
            </html>
            '''.format(top)

    application = tornado.web.Application([
        (r"/", MainHandler),
    ])

    result = doctest.testmod()

    if not result.failed:
        print "all tests passed, running on http://localhost:9099/"
        application.listen(9099)
        tornado.ioloop.IOLoop.instance().start()