#!/usr/bin/python
from xml.dom import minidom
from xml.sax import parseString, SAXParseException
from xml.sax.handler import ContentHandler
import cgi, os, re, sys, traceback, urllib

if os.environ['REQUEST_METHOD']=="GET":
  print "Status: 403 Forbidden"

print "Content-type: text/html\r\n\r\n"

def text(element, tag):
  nodes = element.getElementsByTagName(tag)
  if not nodes: return ""
  return "".join([child.data for child in nodes[0].childNodes])

class rdf(ContentHandler):
    """ xml -> dictionary of {dc:identifier => trackback:ping|rdf:about}

    Parse a given html page, and retrieve the rdf:about information associated
    with a given href.
    """

    ids = {}
    def startElement(self, name, attrs):
        if name == 'rdf:Description':
            attrs=dict(attrs)
            if attrs.has_key('dc:identifier'):
                if attrs.has_key('trackback:ping'):
                    self.ids[attrs['dc:identifier']] = attrs['trackback:ping']
                elif attrs.has_key('about'):
                    self.ids[attrs['dc:identifier']] = attrs['about']
                elif attrs.has_key('rdf:about'):
                    self.ids[attrs['dc:identifier']] = attrs['rdf:about']

tb_re=re.compile('(<rdf:RDF .*?</rdf:RDF>)')
def backref(href):
    """ href -> trackback

    Parse a given html page, and retrieve the rdf:about for that url.
    """

    base = href.split("#")[0]
    file = urllib.urlopen(base)
    data = file.read().replace('\n',' ')
    file.close()

    trackback = None

    for x in tb_re.findall(data):
        try:
            parseString(x, rdf())
        except SAXParseException:
            pass

    if rdf.ids.has_key(href): trackback = rdf.ids[href]

    return trackback

fail = None
title = "Server Failure"
url = cgi.FieldStorage().getvalue("url")
tb = None

try:
  tb = backref(url.replace("&amp;","&"))
  if not tb:
    fail = "Trackback RDF not found"

  if not fail:
    tb = backref(cgi.FieldStorage().getvalue("url"))
    if tb.find('?')>=0:
      tb = tb + "&__mode=rss"
    else:
      tb = tb + "?__mode=rss"

    stream=urllib.urlopen(tb)
    rss=minidom.parse(stream)
    stream.close()

    channel = rss.getElementsByTagName('channel')[0]
    title = text(channel, "title")
    link = text(channel, "link")
except:
  fail = ''.join(apply(traceback.format_exception, sys.exc_info()))

head=open("blosxom/head.html").read()
head=re.sub("\$blog_title", "Backtrack: " + title, head)
print head

try:
  if not fail:
    print '<div class="blogbody">'
    print '<h3>%s</h3>' % title
    print text(channel, "description").encode('latin-1')
    print '<div class="posted"><a href="%s">[more]</a></div>' % link
    print '</div>'

    print '<h2>Backtracks</h2>'

    for item in rss.getElementsByTagName('item'):
      link = text(item, "link")
      back = re.sub("#", "%23", link)
      print '<div class="comment">'
      print '<h3>%s</h3>' % text(item, "title").encode('latin-1')
      print text(item, "description").encode('latin-1')
      print '<div class="posted">'
      print '<a href="%s">[more]</a>' % link
      print '<a href="http://www.intertwingly.net/backtrack.cgi?url=%s">[back]</a>' % back
      print '</div>'
      print '</div>'
except:
  fail=''.join(apply(traceback.format_exception, sys.exc_info()))

if fail:
  print '<h2>Exception Traceback</h2>'
  if url: print '<code>url=</code> <a href="%s">%s</a><br />' % (url, url)
  if tb: print '<code>tb=</code> <a href="%s">%s</a><br />' % (tb, tb)
  print '<xmp>'
  print fail
  print '</xmp>'

foot=open("blosxom/foot.html").read()
list=re.split('#include "(\S+)"', foot)
print list.pop(0)

while list:
  print open("blosxom/"+list.pop(0)).read()
  print list.pop(0)