mirror of
https://github.com/fxsjy/jieba.git
synced 2025-07-10 00:01:33 +08:00
merge chage from chao78787
This commit is contained in:
commit
9ea14a8a54
@ -144,7 +144,7 @@ Output:
|
||||
* 实验结果:在4核3.4GHz Linux机器上,对金庸全集进行精确分词,获得了1MB/s的速度,是单进程版的3.3倍。
|
||||
|
||||
|
||||
功能 5) : Tokenize:返回词语在原文的起始位置
|
||||
功能 6) : Tokenize:返回词语在原文的起始位置
|
||||
============================================
|
||||
* 注意,输入参数只接受unicode
|
||||
* 默认模式
|
||||
@ -181,7 +181,7 @@ word 有限公司 start: 6 end:10
|
||||
```
|
||||
|
||||
|
||||
功能 6) : ChineseAnalyzer for Whoosh搜索引擎
|
||||
功能 7) : ChineseAnalyzer for Whoosh搜索引擎
|
||||
============================================
|
||||
* 引用: `from jieba.analyse import ChineseAnalyzer `
|
||||
* 用法示例:https://github.com/fxsjy/jieba/blob/master/test/test_whoosh.py
|
||||
|
@ -264,9 +264,16 @@ def load_userdict(f):
|
||||
if line_no==1:
|
||||
word = word.replace(u'\ufeff',u"") #remove bom flag if it exists
|
||||
if len(tup)==3:
|
||||
user_word_tag_tab[word]=tup[2].strip()
|
||||
add_word(word, freq, tup[2])
|
||||
else:
|
||||
add_word(word, freq)
|
||||
|
||||
def add_word(word, freq, tag=None):
|
||||
global FREQ, trie, total, user_word_tag_tab
|
||||
freq = float(freq)
|
||||
FREQ[word] = log(freq / total)
|
||||
if tag is not None:
|
||||
user_word_tag_tab[word] = tag.strip()
|
||||
p = trie
|
||||
for c in word:
|
||||
if not c in p:
|
||||
|
Loading…
x
Reference in New Issue
Block a user