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

Merge pull request #179 from changyy/master

Browse Source 
新增自訂 cache_file 產生的目錄位置，可支援 jieba 運行在 Read-Only File System，如： Embedded Linux、Google App Engine 和 Heroku 等
This commit is contained in:
Sun Junyi 2015-02-28 10:05:52 +08:00
commit 1b4721ebb8
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
jieba/__init__.py
View File

@ -23,6 +23,7 @@ total = 0
user_word_tag_tab = {} user_word_tag_tab = {}
initialized = False initialized = False
pool = None pool = None
tmp_dir = None
_curpath = os.path.normpath( _curpath = os.path.normpath(
os.path.join(os.getcwd(), os.path.dirname(__file__))) os.path.join(os.getcwd(), os.path.dirname(__file__)))
@ -61,7 +62,7 @@ def gen_pfdict(f_name):
def initialize(dictionary=None): def initialize(dictionary=None):
global FREQ, total, initialized, DICTIONARY, DICT_LOCK global FREQ, total, initialized, DICTIONARY, DICT_LOCK, tmp_dir
if not dictionary: if not dictionary:
dictionary = DICTIONARY dictionary = DICTIONARY
with DICT_LOCK: with DICT_LOCK:
@ -73,9 +74,9 @@ def initialize(dictionary=None):
t1 = time.time() t1 = time.time()
# default dictionary # default dictionary
if abs_path == os.path.join(_curpath, "dict.txt"): if abs_path == os.path.join(_curpath, "dict.txt"):
cache_file = os.path.join(tempfile.gettempdir(), "jieba.cache") cache_file = os.path.join(tmp_dir if tmp_dir else tempfile.gettempdir(),"jieba.cache")
else: # custom dictionary else: # custom dictionary
cache_file = os.path.join(tempfile.gettempdir(), "jieba.u%s.cache" % md5( cache_file = os.path.join(tmp_dir if tmp_dir else tempfile.gettempdir(),"jieba.u%s.cache" % md5(
abs_path.encode('utf-8', 'replace')).hexdigest()) abs_path.encode('utf-8', 'replace')).hexdigest())
load_from_cache_fail = True load_from_cache_fail = True