#! /usr/bin/env python

# twitter-links.py
# Copyright (C) 2008, Christopher L. Conway (cconway@cs.nyu.edu)

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

from sys import stdin, stdout
from lxml import etree
from re import sub
from optparse import OptionParser

doc = etree.parse(stdin)

def addlinks(path,namespaces=None):
    for node in doc.xpath(path,namespaces=namespaces):
        # Turn URLs into HREFs
        node.text = sub("((https?|s?ftp|ssh)\:\/\/[^\"\s\<\>]*[^.,;'\">\:\s\<\>\)\]\!])",
                        "<a href=\"\\1\">\\1</a>",
                        node.text)
        # Turn @ refs into links to the user page
        node.text = sub("\B@([_a-z0-9]+)",
                        "@<a href=\"http://twitter.com/\\1\">\\1</a>",
                        node.text)

def stripuser(path,namespaces=None):
    for node in doc.xpath(path,namespaces=namespaces):
        node.text = sub("^[A-Za-z0-9_]+:\s*","",node.text)

parser = OptionParser(usage = "%prog [options] SITE")
parser.add_option("-s", "--strip-username", 
                  action="store_true", 
                  dest="strip_username",
                  default=False,
                  help="Strip the username from item title and description")
(opts,args) = parser.parse_args()

# For RSS feeds
addlinks("//rss/channel/item/description")
# For Atom feeds
addlinks( "//n:feed/n:entry/n:content", 
          {'n': 'http://www.w3.org/2005/Atom'} )

if opts.strip_username:
     # RSS title/description
     stripuser( "//rss/channel/item/title" )
     stripuser( "//rss/channel/item/description" )
     # Atom title/description
     stripuser( "//n:feed/n:entry/n:title", 
                namespaces = {'n': 'http://www.w3.org/2005/Atom'} )
     stripuser( "//n:feed/n:entry/n:content", 
                namespaces = {'n': 'http://www.w3.org/2005/Atom'} )

doc.write(stdout)