You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
jieba/test/test_file.py

22 lines
383 B
Python

import time
import sys
sys.path.append("../")
import jieba
jieba.initialize()
url = sys.argv[1]
content = open(url,"rb").read()
t1 = time.time()
words = "/ ".join(jieba.cut(content))
t2 = time.time()
tm_cost = t2-t1
log_f = open("1.log","wb")
log_f.write(words.encode('utf-8'))
log_f.close()
10 years ago
print('cost ' + str(tm_cost))
print('speed %s bytes/second' % (len(content)/tm_cost))