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

Fix the re in enable_parallel.

Browse Source
This commit is contained in:
Dingyuan Wang 2014-06-14 15:22:13 +08:00
parent 5574304a9e
commit 81f77d7a08
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
jieba/__init__.py
View File

@ -327,7 +327,7 @@ def enable_parallel(processnum=None):
pool = Pool(processnum) pool = Pool(processnum)
def pcut(sentence,cut_all=False): def pcut(sentence,cut_all=False):
parts = re.compile(b'([\r\n]+)').split(sentence) parts = re.compile('([\r\n]+)').split(sentence)
if cut_all: if cut_all:
result = pool.map(__lcut_all,parts) result = pool.map(__lcut_all,parts)
else: else:
@ -337,7 +337,7 @@ def enable_parallel(processnum=None):
yield w yield w
def pcut_for_search(sentence): def pcut_for_search(sentence):
parts = re.compile(b'([\r\n]+)').split(sentence) parts = re.compile('([\r\n]+)').split(sentence)
result = pool.map(__lcut_for_search,parts) result = pool.map(__lcut_for_search,parts)
for r in result: for r in result:
for w in r: for w in r:
@ -371,7 +371,7 @@ def get_abs_path_dict():
def tokenize(unicode_sentence,mode="default"): def tokenize(unicode_sentence,mode="default"):
#mode ("default" or "search") #mode ("default" or "search")
if not isinstance(unicode_sentence, str): if not isinstance(unicode_sentence, str):
raise Exception("jieba: the input parameter should unicode.") raise Exception("jieba: the input parameter should be str.")
start = 0 start = 0
if mode=='default': if mode=='default':
for w in cut(unicode_sentence): for w in cut(unicode_sentence):