清除py代码注释

# -*- coding: utf-8 -*-
#
# @Author: CPS
# @email: 373704015@qq.com
# @Date: 2022-07-06 22:16:38.320013
# @Last Modified by: CPS
# @Last Modified time: 2022-07-06 22:16:38.320013
# @file_path "W:\CPS\MyProject\test"
# @Filename "remove_comments.py"
# @Description: 功能描述
#
import os, sys, re
from types import coroutine

sys.path.append("..")
from os import path

INLINE_REG = re.compile(r"(.*)(#.*$)")


def main(target_path: str, skip_list: list[str] = []):
    count = 0
    for dir_path, dir_list, file_list in os.walk(target_path):
        for each in file_list:
            if each in skip_list:
                continue

            # *.py文件去掉注释
            if each.endswith(".py"):
                target = os.path.join(dir_path, each)
                if os.path.exists(target):
                    clean_comments(target, True)
                    count += 1

            # 处理*.pyc文件
            if each.endswith(".pyc"):
                target = os.path.join(dir_path, each)
                os.remove(target)

    # 处理__pycache__目录
    clean_pycache(target_path)
    print("已处理文件： ", count)


def clean_pycache(target_path: str) -> int:
    """
    首先清楚所有`.pyc`文件，然后再将`__pycache__`空目录删掉

    - param dir_path :{str} {description}

    @returns `{ int}` {description}

    """

    # 删除 __pycache__ 空目录
    for dir_path, dir_list, file_list in os.walk(target_path):
        for each_dir in dir_list:
            if path.basename(each_dir) == "__pycache__":
                target = os.path.join(dir_path, each_dir)
                try:
                    os.rmdir(target)
                except Exception as e:
                    print(f"删除目录失败{target}", e)


def clean_comments(file_path: str, overwirte=False) -> str:
    """
    @Description {description}

    - param file_path       :{str}  {description}
    - param overwirte=False :{bool} {description}

    @returns `{ str}` {description}

    """
    if overwirte:
        new_file = file_path
    else:
        new_file = os.path.join(
            os.path.dirname(file_path), f"{os.path.basename(file_path)}_str"
        )

    with open(file_path, "r", encoding="utf-8") as f:
        new_str = ""
        skip = False
        has_main = False
        for each_line in f.readlines():
            # 不稳定，需要在最后的 new_str 上遍历
            # 查找行内注释
            # has_inline_comment = INLINE_REG.findall(each_line)
            # if len(has_inline_comment) > 0 and len(has_inline_comment[0]) == 2:
            #     if len(has_inline_comment[0][0].strip()) > 0:
            #         each_line = has_inline_comment[0][0] + "\n"

            trim_str = each_line.strip()
            # 过滤 """ 注释块
            if trim_str.startswith('"""'):
                if skip:
                    skip = False
                    continue
                else:
                    skip = True
            # 过滤 # 注释行
            elif trim_str.startswith("#"):
                continue

            # 过滤 测试函数
            elif trim_str == 'if __name__ == "__main__":':
                has_main = True

            if skip:
                continue

            if has_main:
                continue

            new_str += each_line

    # print(new_str)
    with open(new_file, "w", encoding="utf-8") as f:
        f.write(new_str)


if __name__ == "__main__":
    t = r"D:\CPS\MyProject\Project_Outside\PSD文件解析2\psd-tool-10-18-2\src"
    main(t, ["config.py", "main.py"])