#!/usr/bin/env python
# copyright 2007    Francesco Crippa <fcrippa [at] byte-code (dot) com>
#
# 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 2 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.

import pycurl
import StringIO
import urllib
import re
import sys
import time

def find_world_region(data):
    list = data.split("\n")
    counts = {}
    country = "Not Defined"
    counts[country] = 0
    for x in list:
        if re.search("^=== ", x):
            country = x.replace("===", "").strip().title()
            counts[country] = 0
        elif re.search("^ \* ", x):
            counts[country] = counts[country] + 1
    return counts

def print_stats(counts):
    out = open('ambassadors_country_list.csv', 'w')
    sys.stdout = out 
    print "FedoraAmbassadrs,",
    for date in counts:
        # date = 2008-01
        for country in counts[date]:
            # country = Italy
            # counts[date][country] = 5
            print "%s," % country ,
        break
    print ""
    for date in counts:
        print "%s," % date ,
        for country in counts[date]:
            print "%d," % counts[date][country],
        print ""
    out.close()


def find_page_date(page):
    find_date = re.compile("([0-9]+)[- /.](0[1-9]|1[012])[- /.](0[1-9]|[12][0-9]|3[01])")
    date = find_date.findall(page)
    return date[0]

print "Welcome to Stats generator for Fedora Ambassadors"

if __name__ == "__main__":
    page = pycurl.Curl()
    vars = {"action": "raw"}
    url = "http://fedoraproject.org/wiki/Ambassadors/CountryList"

    print "    * Start configuration"
    page.setopt(pycurl.URL, url)
    page.setopt(pycurl.FOLLOWLOCATION, 1)
    page.setopt(pycurl.USERAGENT, "Mozilla/4.0")
    page.setopt(pycurl.MAXREDIRS, 5)
    page.setopt(pycurl.VERBOSE, 0)


    print "    * Downloading pages"
    counts = {}
    k = 0
    for i in range(1,663):
        #k = k + 1
        #if k == 50:
        #    print "        - I'm waiting some minutes..."
        #    time.sleep(100)
        #    k = 0
        content = StringIO.StringIO()
        page.setopt(pycurl.WRITEFUNCTION, content.write)
        vars = {}
        vars["rev"] = i
        print "        - Revision %d" % vars["rev"],
        page.setopt(pycurl.POSTFIELDS, urllib.urlencode(vars))
        page.perform()
        year, month, day = find_page_date(content.getvalue())
        print "(Modified on %s-%s-%s)" % (year, month, day)
        vars["action"] = "raw"
        page.setopt(pycurl.POSTFIELDS, urllib.urlencode(vars))
        page.perform()
        #print content.getvalue()
        counts[year+"-"+month] = find_world_region(content.getvalue())
    
    print_stats(counts)
    page.close