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

read() and then split -- faster; from __future__ import with

Browse Source
This commit is contained in:
fxsjy 2013-04-24 22:14:10 +08:00
parent 966532b462
commit 65b78b2b4d
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
jieba/__init__.py
View File

@ -1,3 +1,4 @@
from __future__ import with_statement
import re
import math
import os,sys
@ -19,10 +20,10 @@ def gen_trie(f_name):
ltotal = 0.0
with open(f_name, 'rb') as f:
lineno = 1
for line in f.readlines():
for line in f.read().rstrip().decode('utf-8').split('\n'):
lineno += 1
try:
word,freq,_ = line.decode('utf-8').split(' ')
word,freq,_ = line.split(' ')
freq = float(freq)
lfreq[word] = freq
ltotal+=freq