third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-10 00:01:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

in the speed test: initialize first to ignore the time of dict loading

Browse Source
This commit is contained in:
Sun Junyi 2013-04-26 14:51:58 +08:00
parent bc049090a5
commit d3339633d5
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
test/test_file.py
View File

@ -3,6 +3,7 @@ import sys,time
import sys import sys
sys.path.append("../") sys.path.append("../")
import jieba import jieba
jieba.initialize()
url = sys.argv[1] url = sys.argv[1]
content = open(url,"rb").read() content = open(url,"rb").read()
@ -14,7 +15,7 @@ tm_cost = t2-t1
log_f = open("1.log","wb") log_f = open("1.log","wb")
for w in words: for w in words:
print >> log_f, w.encode("gbk"), "/" , print >> log_f, w.encode("utf-8"), "/" ,
print 'cost',tm_cost print 'cost',tm_cost
print 'speed' , len(content)/tm_cost, " bytes/second" print 'speed' , len(content)/tm_cost, " bytes/second"

4
test/test_pos_file.py
View File

@ -2,6 +2,8 @@ import urllib2
import sys,time import sys,time
import sys import sys
sys.path.append("../") sys.path.append("../")
import jieba
jieba.initialize()
import jieba.posseg as pseg import jieba.posseg as pseg
url = sys.argv[1] url = sys.argv[1]
@ -14,7 +16,7 @@ tm_cost = t2-t1
log_f = open("1.log","wb") log_f = open("1.log","wb")
for w in words: for w in words:
print >> log_f, w.encode("gbk"), "/" , print >> log_f, w.encode("utf-8"), "/" ,
print 'speed' , len(content)/tm_cost, " bytes/second" print 'speed' , len(content)/tm_cost, " bytes/second"