# Query processing
tIndexFile = open('topics.xml', 'r')
soup = BeautifulSoup(tIndexFile.read(), 'html.parser')
queries = soup.findAll('query')
fnewstoplis = []
for query in queries:
lisq = str(query.get_text()).split()
#print(len(lisq))
newstoplis = []
for i in range(len(lisq)):
if lisq[i] not in dictStopword:
portword = PorterStemmer().stem(lisq[i])
portword = portword.replace('\'', '')
newstoplis.append(portword)
fnewstoplis.append(newstoplis)
topIds = []
topics = soup.findAll('topic')
topIds = [topics[i].get('number') for i in range(len(topics))]
querydict = {topIds[i]: fnewstoplis[i] for i in range(len(topIds))}
# Real relevent
realRelfile = open('relevance judgements.qrel', 'r')
realRel = realRelfile.readlines()
