Skip to main content

check language

import os
import re

def contains_chinese(text):
"""Check if the text contains Chinese characters"""
chinese_pattern = re.compile(r'[\u4e00-\u9fff]')
return chinese_pattern.search(text) is not None

def check_files_for_chinese(directory):
"""Check files in the specified directory and its subdirectories for Chinese characters"""
for root, dirs, files in os.walk(directory):
# Exclude any level of node_modules and .git directories
dirs[:] = [d for d in dirs if d not in {'node_modules', '.git'}]

for file in files:
file_path = os.path.join(root, file)
try:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
if contains_chinese(content):
print(f"File {file_path} contains Chinese characters")
except (UnicodeDecodeError, FileNotFoundError):
# Skip files that cannot be read
continue

if __name__ == "__main__":
# Directory to check
directory_to_check = '.'

check_files_for_chinese(directory_to_check)