import os
import re
def remove_chinese_code_and_comments_in_folder(folder_path):
for root, dirs, files in os.walk(folder_path):
for file_name in files:
if file_name.endswith((".java", ".js", ".py")):
file_path = os.path.join(root, file_name)
with open(file_path, "r", encoding="utf-8") as file:
code = file.read()
cleaned_code = remove_chinese_code_and_comments(code)
with open(file_path, "w", encoding="utf-8") as file:
file.write(cleaned_code)
def remove_chinese_code_and_comments(code):
lines = code.split('\n')
result = []
in_comment_block = False
for line in lines:
# 去除包含中文字符的注释行
if "//" in line or "#" in line or "/*" in line:
if "//" in line:
line_parts = line.split('//', 1)
elif "#" in line:
line_parts = line.split('#', 1)
else:
line_parts = re.split('/\*', line, 1)
comment = line_parts[-1].strip()
if re.search('[\u4e00-\u9fff]', comment):
line = line_parts[0]
# 去除包含中文字符的代码行
if re.search('[\u4e00-\u9fff]', line):
line = ""
if '"""' in line or "'''" in line or "*/" in line:
in_comment_block = not in_comment_block
result.append(line)
return '\n'.join(result)
# 指定要处理的文件夹路径
folder_path = "文件夹路径文件夹路径"
remove_chinese_code_and_comments_in_folder(folder_path)
