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 #71 from chao787/feature_richard

Browse Source 
Separate cal and IO process.
This commit is contained in:
Sun Junyi 2013-07-03 01:57:34 -07:00
commit 632a086035
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
jieba/__init__.py
View File

@ -264,9 +264,15 @@ def load_userdict(f):
if line_no==1: if line_no==1:
word = word.replace(u'\ufeff',u"") #remove bom flag if it exists word = word.replace(u'\ufeff',u"") #remove bom flag if it exists
if len(tup)==3: if len(tup)==3:
user_word_tag_tab[word]=tup[2].strip() add_word(word, freq, tup[2])
add_word(word, freq)
def add_word(word, freq, tag=None):
global FREQ, trie, total, user_word_tag_tab
freq = float(freq) freq = float(freq)
FREQ[word] = log(freq / total) FREQ[word] = log(freq / total)
if tag is not None:
user_word_tag_tab[word] = tag.strip()
p = trie p = trie
for c in word: for c in word:
if not c in p: if not c in p: