forked from APCLab/jieba-tw
-
Notifications
You must be signed in to change notification settings - Fork 0
/
setup.py
74 lines (59 loc) · 2.32 KB
/
setup.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
# -*- coding: utf-8 -*-
import os
from setuptools import setup
LONGDOC = """
jieba_tw
=====
“结巴”中文分词:做最好的 Python 中文分词组件
"Jieba" (Chinese for "to stutter") Chinese text segmentation: built to
be the best Python Chinese word segmentation module.
完整文档见 ``README.md``
GitHub: https://github.com/fxsjy/jieba
特点
====
- 支持三种分词模式:
- 精确模式,试图将句子最精确地切开,适合文本分析;
- 全模式,把句子中所有的可以成词的词语都扫描出来,
速度非常快,但是不能解决歧义;
- 搜索引擎模式,在精确模式的基础上,对长词再次切分,提高召回率,适合用于搜索引擎分词。
- 支持繁体分词
- 支持自定义词典
- MIT 授权协议
在线演示: http://jiebademo.ap01.aws.af.cm/
安装说明
========
代码对 Python 2/3 均兼容
- 全自动安装: ``easy_install jieba`` 或者 ``pip install jieba`` / ``pip3 install jieba``
- 半自动安装:先下载 https://pypi.python.org/pypi/jieba/ ,解压后运行
python setup.py install
- 手动安装:将 jieba 目录放置于当前目录或者 site-packages 目录
- 通过 ``import jieba`` 来引用
"""
RELEASE_VERSION = "0.39.2"
setup(name='jieba_tw',
version=RELEASE_VERSION,
description='Traditional Chinese Words Segementation Utilities',
long_description=LONGDOC,
author='Tzing',
author_email='tzingshih@gmail.com',
url='https://github.com/apclab/jieba-tw',
license="MIT",
classifiers=[
'Intended Audience :: Developers',
'License :: OSI Approved :: MIT License',
'Operating System :: OS Independent',
'Natural Language :: Chinese (Traditional)',
'Programming Language :: Python',
'Programming Language :: Python :: 3.9',
'Programming Language :: Python :: 3.10',
'Programming Language :: Python :: 3.11',
'Programming Language :: Python :: 3.12',
'Topic :: Text Processing',
'Topic :: Text Processing :: Indexing',
'Topic :: Text Processing :: Linguistic',
],
keywords='NLP,tokenizing,Chinese word segementation',
packages=['jieba_tw'],
package_dir={'jieba_tw':'jieba_tw'},
package_data={'jieba_tw':['*.*','finalseg/*','analyse/*','posseg/*']}
)