The name says...

urlify.py

#!/usr/bin/env python

import cgi
import re

import elml


def _urlify_re_proc(match):
    #TODO: Truncate the display text for long URLs. e.g.:
    # http://example.com/post/this-url-is-too-long-so-it-needs-to-be-trucated-nicely
    # into
    # example.com/post/this-...-nicely
    # see the codes I've written for another app or see the Google search
    urll = match.group(2)
    urlt = urll
    if not ':' in urll:
        if not '/' in urll:
            urll += '/'
        # Naked web URL
        urll = 'http://' + urll
        urlt = urlt.replace('www.', '', 1)
    else:
        # Remove the protocol
        urlt = re.sub(r'[^:]*:', '', urll)
        urlt = urlt.lstrip('/')
        if urlt.endswith('/') and urlt.count('/') == 1:
            urlt = urlt[:-1]
    if urll.startswith('http'):
        urlt = urlt.replace('www.', '', 1)
    return match.group(1) + '<a class="autourl" href="%s">%s</a>' % (urll, urlt)

# Shamelessly stolen from
# http://daringfireball.net/2010/07/improved_regex_for_matching_urls
_urlify_re = re.compile(ur"""(?xi)
    ([^"]*?)
    \b
    (                           # Capture 1: entire matched URL
      (?:
        [a-z][\w-]+:                # URL protocol and colon
        (?:
          /{1,3}                        # 1-3 slashes
          |                             #   or
          [a-z0-9%]                     # Single letter or digit or '%'
                                        # (Trying not to match e.g. "URI::Escape")
        )
        |                           #   or
        www\d{0,3}[.]               # "www.", "www1.", "www2." ... "www999."
        |                           #   or
        [a-z0-9.\-]+[.][a-z]{2,4}/  # looks like domain name followed by a slash
      )
      (?:                           # One or more:
        [^\s()<>]+                      # Run of non-space, non-()<>
        |                               #   or
        \(([^\s()<>]+|(\([^\s()<>]+\)))*\)  # balanced parens, up to 2 levels
      )+
      (?:                           # End with:
        \(([^\s()<>]+|(\([^\s()<>]+\)))*\)  # balanced parens, up to 2 levels
        |                                   #   or
        [^\s`!()\[\]{};:'".,<>?\u00AB\u00BB\u201C\u201D\u2018\u2019] # not a space or one of these punct chars
      )
    )
    """)


def urlify(text):
    #TODO: naked email address
    #TODO: use Google's Safe Browsing API to check for malicious sites
    return _urlify_re.sub(_urlify_re_proc, text)

_user_re = re.compile(r"""\B@([0-9a-zA-Z_]+)""")

#TODO: custom params
def convert(text):
    outp = urlify(outp)
    outp = _user_re.sub(r'@<a href="/user/\1">\1</a>', outp)
    return outp