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

make cache dumping more robust

Browse Source
This commit is contained in:
Sun Junyi 2013-06-24 13:48:16 +08:00
parent 38b6bcd54e
commit 1a3be67691
1 changed files with 14 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
jieba/__init__.py
View File

@ -81,15 +81,20 @@ def initialize(*args):
FREQ = dict([(k,log(float(v)/total)) for k,v in FREQ.iteritems()]) #normalize
min_freq = min(FREQ.itervalues())
print >> sys.stderr, "dumping model to file cache " + cache_file
tmp_suffix = "."+str(random.random())
with open(cache_file+tmp_suffix,'wb') as temp_cache_file:
marshal.dump((trie,FREQ,total,min_freq),temp_cache_file)
if os.name=='nt':
import shutil
replace_file = shutil.move
else:
replace_file = os.rename
replace_file(cache_file+tmp_suffix,cache_file)
try:
tmp_suffix = "."+str(random.random())
with open(cache_file+tmp_suffix,'wb') as temp_cache_file:
marshal.dump((trie,FREQ,total,min_freq),temp_cache_file)
if os.name=='nt':
import shutil
replace_file = shutil.move
else:
replace_file = os.rename
replace_file(cache_file+tmp_suffix,cache_file)
except:
print >> sys.stderr, "dump cache file failed."
import traceback
print >> sys.stderr, traceback.format_exc()
initialized = True