third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-24 00:00:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

prevent moving across different filesystems at tempfile.mkstemp

Browse Source
This commit is contained in:
Dingyuan Wang 2015-06-26 22:12:39 +08:00
parent be46ddef9a
commit 66fe17517d
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
jieba/__init__.py
View File

@ -15,7 +15,10 @@ from hashlib import md5
from ._compat import * from ._compat import *
from . import finalseg from . import finalseg
from shutil import move as _replace_file if os.name == 'nt':
from shutil import move as _replace_file
else:
_replace_file = os.rename
_get_module_path = lambda path: os.path.normpath(os.path.join(os.getcwd(), _get_module_path = lambda path: os.path.normpath(os.path.join(os.getcwd(),
os.path.dirname(__file__), path)) os.path.dirname(__file__), path))
@ -107,11 +110,14 @@ class Tokenizer(object):
# default dictionary # default dictionary
elif abs_path == DEFAULT_DICT: elif abs_path == DEFAULT_DICT:
cache_file = "jieba.cache" cache_file = "jieba.cache"
else: # custom dictionary # custom dictionary
else:
cache_file = "jieba.u%s.cache" % md5( cache_file = "jieba.u%s.cache" % md5(
abs_path.encode('utf-8', 'replace')).hexdigest() abs_path.encode('utf-8', 'replace')).hexdigest()
cache_file = os.path.join( cache_file = os.path.join(
self.tmp_dir or tempfile.gettempdir(), cache_file) self.tmp_dir or tempfile.gettempdir(), cache_file)
# prevent absolute path in self.cache_file
tmpdir = os.path.dirname(cache_file)
load_from_cache_fail = True load_from_cache_fail = True
if os.path.isfile(cache_file) and os.path.getmtime(cache_file) > os.path.getmtime(abs_path): if os.path.isfile(cache_file) and os.path.getmtime(cache_file) > os.path.getmtime(abs_path):
@ -132,7 +138,8 @@ class Tokenizer(object):
default_logger.debug( default_logger.debug(
"Dumping model to file cache %s" % cache_file) "Dumping model to file cache %s" % cache_file)
try: try:
fd, fpath = tempfile.mkstemp() # prevent moving across different filesystems
fd, fpath = tempfile.mkstemp(dir=tmpdir)
with os.fdopen(fd, 'wb') as temp_cache_file: with os.fdopen(fd, 'wb') as temp_cache_file:
marshal.dump( marshal.dump(
(self.FREQ, self.total), temp_cache_file) (self.FREQ, self.total), temp_cache_file)