def generate_snippet(file_name):
relevant_list = open('cacm.rel', 'r')
query_relevant = {}
for line in relevant_list.readlines():
words = line.split()
if query_relevant.has_key(words[0]):
doc_no = words[2][5:]
doc_no = str(doc_no)
doc = 'CACM-' + (4 - len(doc_no)) * '0' + doc_no
query_relevant[words[0]].append(doc)
else:
query_relevant[words[0]] = []
doc_no = words[2][5:]
doc = 'CACM-' + (4 - len(doc_no)) * '0' + doc_no
query_relevant[words[0]].append(doc)
#Get query_dict from the file cacm.query.txt
f = open('cacm.query.txt', 'r')
soup = BeautifulSoup(f.read(), 'html.parser')
f.close()
rawquery_dict = {}
for i in range(64):
query_no = (soup.find('docno')).text.encode('utf-8')
(soup.find('docno')).decompose()
query = (soup.find('doc')).text.encode('utf-8')
(soup.find('doc')).decompose()
query_no = query_no.strip(" ")
rawquery_dict[query_no] = query
r = Retriever("", "")
query_dict = {}
for query_no, raw_query in rawquery_dict.viewitems():
query_dict[query_no] = r.process_query(raw_query, True)
print "Enter the query no"
no = raw_input()
no = str(no)
query = query_dict[no]
print query
s = SnippetGen(file_name)
query_results = s.get_queryresults(name='bms25')
results = query_results[no]
# pdb.set_trace()
s.get_snippet(query, results)
#Get query_dict from the file cacm.query.txt
f = open('cacm.query.txt','r')
soup = BeautifulSoup(f.read(), 'html.parser')
f.close()
rawquery_dict = {}
for i in range(64):
query_no = (soup.find('docno')).text.encode('utf-8')
(soup.find('docno')).decompose()
query = (soup.find('doc')).text.encode('utf-8')
(soup.find('doc')).decompose
query_no = query_no.strip(" ")
rawquery_dict[query_no] = query
r = Retriever("", "")
query_dict = {}
for query_no, raw_query in rawquery_dict.viewitems():
query_dict[query_no] = r.process_query(raw_query, True)
print "Enter the query no"
no = raw_input()
no = str(no)
query = query_dict[no]
print query
s = SnippetGen()
query_results = s.get_queryresults(name = 'bms25')
results = query_results[no]
# pdb.set_trace()
s.get_snippet(query,results)
