#! /usr/bin/env python
# -*- coding: UTF-8 -*-
""" Test that the crawler can crawl

$Id: test.py 1350 2009-04-25 10:02:44Z goodwin $
"""

#      Copyright 2008-2010 eGovMon
#      This program is distributed under the terms of the GNU General
#      Public License.
#
#  This file is part of the eGovernment Monitoring
#  (eGovMon)
#
#  eGovMon 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.
#
#  eGovMon 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 eGovMon; if not, write to the Free Software
#  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
#  MA 02110-1301 USA

__author__ = "$Author$"
__version__ = "$Revision$"
__updated__ = "$LastChangedDate: 2009-04-25 10:02:44 +0000 (Sat, 25 Apr 2009) $"


import unittest
import os
import time
import random

import psycopg2

import sc
import RDFreader

sc = sc.SystemConfiguration()


class TestSequenceFunctions(unittest.TestCase):

    def testnormalsequence(self):
        #Setup towards URL repositoriy
        con = psycopg2.connect(host=sc.egovmondbhost,user=sc.egovmondbusername,database=sc.egovmondbdatabase,password=sc.egovmondbpassword) 
        cur = con.cursor()
        site,title,source,coverage,category,testrunid = 'www.egovmon.no','eGovernment Monitoring','maintainer@egovmon.no','','','1'
        db = dbname="rdf_"+str(testrunid)+"_"+str(time.time()).replace('.','_')+"_"+str(random.randint(1,100000))

        cur.execute("insert into egovmondb.testrun (testrunid,started,responsible,urllistid) select %(testrunid)s,timestamp 'now',%(source)s,1 where not exists (select True from egovmondb.testrun where testrunid = %(testrunid)s);",locals())
        
        con.commit()
        
        cur.execute('insert into egovmondb.WebSite (site,title) select %(site)s,%(title)s where not exists (select True from egovmondb.WebSite where site=%(site)s);',locals())

        cur.execute('update egovmondb.WebSite set smallsite=True where site=%(site)s;',locals())

        cur.execute('delete from egovmondb.SiteWAMResults where siteid in (select siteid from website where site=%(site)s) and testrunid=%(testrunid)s;',locals())

        con.commit()

        cur.execute('insert into egovmondb.SiteWAMResults (siteid,testrunid) select (select siteid from website where site=%(site)s),%(testrunid)s;',locals())

        cur.execute('delete from WebPage where siteid in (select siteid from website where site=%(site)s) and testrunid=%(testrunid)s;',locals()) 
        con.commit()
        
        #Checking that the eGovMonDB is empty.
        cur.execute('select count(*) from WebPage where siteid in (select siteid from website where site=%(site)s) and testrunid=%(testrunid)s;',locals())
        self.assert_(cur.fetchall()[0][0]==0)

        #Install the crawler
        curdir = os.path.abspath(os.path.curdir)
        if sc.homedir.rstrip('/').endswith('trunk'):
            sc.homedir = sc.homedir[:-5]
        os.chdir(os.path.join(sc.homedir,'trunk','Crawler'))
        os.system('python setup.py install')

        #Restarting Memcached
        os.system('/etc/init.d/memcached restart')        

        #Running the crawler
        os.system('crawlerwrapper onlycrawl %(site)s %(testrunid)s'%locals())

        #Checking that there is pages in the URL repository
        cur.execute('select count(*) from WebPage where siteid in (select siteid from website where site=%(site)s) and testrunid=%(testrunid)s;',locals())
        self.assert_(cur.fetchall()[0][0]>0)      

      
if __name__ == '__main__':
    unittest.main()