def _search_pharse_func_tester(pharse, doc_id):
terms = []
t_st = Token_Preprocessing_Engine()
for token in pharse.split():
terms.append(t_st.process_token(token))
result = search_pharse(terms, doc_id)
send_stdout(result)
def process_query(query):
# initialize stemmer (Lemmatizer)
if STEMMER:
st = Token_Preprocessing_Engine()
# process query
terms = []
for token in query.split():
# Stemming and Lowercasing
if STEMMER:
t = st.process_token(token)
else:
t = token.lower()
terms.append(t)
return terms
def main():
# read arguments
args = parse_arguments()
if args.score not in ['y', 'n']:
send_stdout('Error! arg "scores" should be either y or n')
sys.exit()
# open index file
try:
path = join(args.path, INDEX_FILE)
f = open(path)
except FileNotFoundError as e:
send_stdout('Error! Index file "{}" does not exits.'.format(path))
sys.exit()
# initialize query stemmer (Lemmatizer)
if STEMMER:
st = Token_Preprocessing_Engine()
query = [st.process_token(t) for t in args.terms]
else:
query = [t.lower() for t in args.terms]
# read index
try:
read_index(f)
except:
send_stdout('Error! Invalided index file format.')
sys.exit()
# compute vector space scores
score = cosine_score(query)
k_score = sorted(score.items(), key=lambda x: x[1], reverse=True)
for i in range(min(args.k, len(k_score))):
d, s = k_score[i]
if args.score == 'y':
send_stdout('{id} \t {score}'.format(id=d, score=s))
else:
send_stdout('{id}'.format(id=d))
f.close()