#!/usr/bin/python

import os
import re
import sys
import urlparse
import mechanize

from argparse import ArgumentParser
from BeautifulSoup import BeautifulSoup

base_url="http://lists.freedesktop.org/archives/wayland-devel"

def get_latest_month_archive(br, base_url):
	r = br.open(base_url)
	html = r.read()
	soup = BeautifulSoup(html)

	# TODO: Determine the appropriate month to load.  For now, just pick
	# the first month listed.

	row = soup.findAll('tr')[1]
	month = row.findAll('td')[0].text.replace(':', '')
	links = row.findAll('td')[1]
	for link in links.findAll('a'):
		if link.text == "[ Date ]":
			return "%s/%s" %(base_url, link['href'])
	return None


if __name__ == '__main__':
	### Handle program arguments
	parser = ArgumentParser(description='Get release announcement URLs from mailman archives')
	args=parser.parse_args()

	br = mechanize.Browser()
	br.set_handle_redirect(True)
	br.set_handle_referer(True)
	br.set_handle_robots(False)
	br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
	br.addheaders = [
		('User-agent', ('Mozilla/5.0 (X11; U; Linux i686; en-US;'
		' rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox'
		'/3.0.1'))
		]

	month_archive_url = get_latest_month_archive(br, base_url)
	if month_archive_url is None:
		print "Error: Couldn't find month archive url"
		sys.exit(1)

	r = br.open(month_archive_url)
	html = r.read()
	soup = BeautifulSoup(html)
	for item in soup.findAll('li'):
		# Parse the subject
		links = item.findAll('a')
		if len(links) < 1:
			continue
		subject = links[0].text

		if "[ANNOUNCE]" not in subject:
			continue
		package = subject.split(' ')[1]
		version = subject.split(' ')[2]
		date_str = "tbd"

		## Parse the author
		#name = item.findAll('i')
		#if len(name) < 1:
		#    continue
		#author = name[0].text

		url_parts = month_archive_url.split('/')
		url_parts.pop()
		url_parts.append(links[0]['href'])
		post_url = '/'.join(url_parts)

		r = br.open(post_url)
		post_html = r.read()
		post_soup = BeautifulSoup(post_html)
		date_str = post_soup.findAll('i')[0].text

		print "%s %s %s %s" %(package, version, post_url, date_str)