# -*- coding: utf-8  -*-
#    Copyright (C) 2009 Osama Khalid
#    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/>.
#
#    Please report bugs or help imporving this program by connecting to
#    <OsamaK.WFM@gmail.com>
import wikipedia, okbot
import sys, time, webbrowser

class dup:
  def __init__(self):
    self.recordfile = open('./getdup','a')
    self.site = wikipedia.getSite(code='commons', fam='commons')
    self.childkey = {}
    self.mainCatFiles = []
    self.subCats = []

  def getSubCats(self, cmcontinue):
    #http://en.wikipedia.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:User-created_public_domain_images&cmnamespace=6&cmcontinue=Shervin|&cmlimit=50&format=jsonfm
    #print cmcontinue, "def" # FOR TESTING
    predata = {
               'action': 'query',
               'list': 'categorymembers',
               'cmtitle': 'Category:' + self.targetCategory,
               'cmnamespace': '14',
               'cmcontinue': cmcontinue,
               'cmprop': 'title',
               'cmlimit': '500',
               'format': 'json',
                }
    while True:
      catsdata = okbot.getAPI(self.site, predata)
      if catsdata != None: break

    for category in catsdata['query']['categorymembers']:
      self.subCats.append(unicode(category['title']))

    if 'query-continue' in catsdata:
      #print "in",cmcontinue#test
      #print "out",catsdata['query-continue']['categorymembers']['cmcontinue']#test
      return catsdata['query-continue']['categorymembers']['cmcontinue']
    else:
      return None

  def getMainCatFiles(self, cmcontinue):
    predata = {
               'action': 'query',
               'list': 'categorymembers',
               'cmtitle': 'Category:' + self.targetCategory,
               'cmnamespace': '6',
               'cmcontinue': cmcontinue,
               'cmprop': 'title',
               'cmlimit': '500',
               'format': 'json',
                }

    while True:
      filesdata = okbot.getAPI(self.site, predata)
      if filesdata != None: break

    for file in filesdata['query']['categorymembers']:
      #print "Adding " + unicode(file['title']) + "...",
      self.mainCatFiles.append(unicode(file['title']))

    if 'query-continue' in filesdata:
      return filesdata['query-continue']['categorymembers']['cmcontinue']
    else:
      return None

  def getSubCatsFiles(self, subCategory, cmcontinue):
    predata = {
               'action': 'query',
               'list': 'categorymembers',
               'cmtitle': subCategory,
               'cmnamespace': '6',
               'cmcontinue': cmcontinue,
               'cmprop': 'title',
               'cmlimit': '500',
               'format': 'json',
                }

    while True:
      subcatdata = okbot.getAPI(self.site, predata)
      if subcatdata != None: break

    if len(subcatdata['query']['categorymembers']) == 0:
      wikipedia.output(subCategory + " is empty!")
      return None

    if not subCategory in self.childkey:
      self.childkey[subCategory]=[]

    for file in subcatdata['query']['categorymembers']:
      #print file#test
      self.childkey[subCategory].append(unicode(file['title']))

    if 'query-continue' in subcatdata:
      return subcatdata['query-continue']['categorymembers']['cmcontinue']
    else:
      return None

  def findDup(self):
    for cat, list in self.childkey.items():
      for file in [file for file in list if file in self.mainCatFiles]:
        print "<http://commons.wikimedia.org/wiki/"+file.replace(' ','_')+"> in "+ cat +" is also in "+ self.targetCategory
        self.recordfile.write(file.encode('utf-8')+'\n'.encode('utf-8'))
        #webbrowser.open("http://commons.wikimedia.org/wiki/"+file)

  def getTarget(self):
    for argv in [argv[6:] for argv in sys.argv if argv.startswith("--cat:")]:
      self.targetCategory = argv
    else:
      self.targetCategory = raw_input("You want to scan the category... ").strip()

  def run(self):
    self.getTarget()

    self.recordfile.write("Running on " + self.targetCategory + ":\n")

    print "Getting " + self.targetCategory + " subcategories..."
    getSubCatsCM='!|'
    while True:
      getSubCatsCM = self.getSubCats(getSubCatsCM)
      #print "main cat subcats return",getSubCatsCM#test
      if getSubCatsCM == None:
        break

    print "Scanning " + self.targetCategory + " for files..."
    getMainCatFilesCM='!|'
    while True:
      getMainCatFilesCM = self.getMainCatFiles(getMainCatFilesCM) 
      #print "main cat files return", getMainCatFilesCM#test
      if getMainCatFilesCM == None:
        break

    for subCategory in self.subCats:
      print "Scanning " + subCategory + "..."
      getSubCatsFilesCM='!|'
      while True:
        getSubCatsFilesCM = self.getSubCatsFiles(subCategory, getSubCatsFilesCM) 
        #print "subcat files return",getSubCatsFilesCM#test
        if getSubCatsFilesCM == None:
          break
    self.findDup()
    self.recordfile.close()
if __name__ == '__main__':
  try:
    bot = dup()
    bot.run()
  finally:
    wikipedia.stopme()