Update to 0.0.2

.gitignore

@@ -2,4 +2,5 @@ build
 *.spec
 venv
 .DS_Store
-.idea/
+.idea/
+charset_mnbvc.egg-info

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Alan Shi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -6,12 +6,12 @@
 2. 尝试使用5种编码对字符进行decode ```utf_8```,```utf_16```,```gb18030```,```gb2312```,```big5```
 3. 将每一组decode的结果对中文字符串和常用中文字进行正则匹配,有匹配结果的表明符合编码要求
 
+#### 模块安装
+```
+pip install charset-mnbvc
+```
 
-#### 使用说明
-* chinese_charset_detect.py -i <inputDirectory> inputDirectory为需要检测的目录
-* dist目录包含macos下的可执行文件,windows环境下暂未打包,希望有朋友帮忙编译一下
 
-#### 模块调用方法
 ##### 根据文件夹获取所有文件编码
 ```
 from charset_mnbvc import api
@@ -36,15 +36,13 @@ print(f"文件名: {file_path}, 编码: {coding_name}")
 ```
 
 
-#### 使用可执行文件范例:
+#### 完整使用范例:
 ```
-./dist/chinese_charset_detect -i tests
-or
 python chinese_charset_detect.py -i tests
 ```
 
-```
 #### 测试结果:
+```
 文件名: tests/.DS_Store, 编码: unknow
 文件名: tests/fixtures/test4.txt, 编码: gb18030
 文件名: tests/fixtures/1045.txt, 编码: gb18030
@@ -56,4 +54,47 @@ python chinese_charset_detect.py -i tests
 总文件数: 8
 总耗时长: 0.5920612812042236
 
+```
+
+chinese_charset_detect.py
+```
+import time
+import sys
+import getopt
+from charset_mnbvc import api
+
+
+def main(argv):
+    ifolder_path = ""
+    try:
+        opts, args = getopt.getopt(argv, "hi:o:", ["ifolder_path="])
+    except getopt.GetoptError:
+        print('test.py -i <inputDirectory>')
+        sys.exit(2)
+    for opt, arg in opts:
+        if opt == '-h':
+            print('chinese_charset_detect.py -i <inputDirectory> inputDirectory为需要检测的目录')
+            sys.exit()
+        elif opt in ("-i", "--ifolder_path"):
+         ifolder_path = arg
+
+    start = time.time()
+    file_count, results = api.from_dir(
+        folder_path=ifolder_path,
+    )
+    for result in results:
+        print(f"文件名: {result[0]}, 编码: {result[1]}")
+    print(f"总文件数: {file_count}")
+
+
+    end = time.time()
+    print(f"总耗时长: {end - start}")
+
+
+if __name__ == "__main__":
+    try:
+        main(sys.argv[1:])
+    except Exception as e:
+        print('chinese_charset_detect.py -i <inputDirectory> inputDirectory为需要检测的目录')
+        sys.exit(2)
 ```

setup.py

@@ -0,0 +1,28 @@
+from setuptools import setup, find_packages
+import pathlib
+
+here = pathlib.Path(__file__).parent.resolve()
+
+long_description = (here / "README.md").read_text(encoding="utf-8")
+
+
+setup(
+    name="charset_mnbvc",
+    version="0.0.2",
+    description="本项目旨在对大量文本文件进行快速编码检测以辅助mnbvc语料集项目的数据清洗工作",
+    url="https://github.com/alanshi/charset_mnbvc",
+    author="Alan Shi",
+    author_email="[email protected]",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    classifiers=[
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3"
+    ],
+    packages=['charset_mnbvc'],
+    python_requires=">=3.7",
+    project_urls={  # Optional
+        "Bug Reports": "https://github.com/alanshi/charset_mnbvc/issues",
+        "Source": "https://github.com/alanshi/charset_mnbvc/",
+    },
+)