文件编码转换

import os
import chardet
import codecs

def write_file(file_path, content, encoding="utf-8"):
    with codecs.open(file_path, "w", encoding) as f:
        f.write(content)

def convert_to_utf8(src_path):
    with open(src_path, "rb") as f:
        raw_data = f.read()
        detected = chardet.detect(raw_data)
        original_encoding = detected["encoding"]

    if original_encoding is None:
        print(f"[SKIP] {src_path}: encoding not detected")
        return

    if original_encoding.lower() != "utf-8":
        try:
            with codecs.open(src_path, "r", original_encoding) as f:
                content = f.read()
            write_file(src_path, content, encoding="utf-8")
            print(f"[OK] {src_path}: {original_encoding} → utf-8")
        except Exception as e:
            print(f"[ERROR] {src_path}: failed to convert ({original_encoding}) - {e}")
    else:
        print(f"[SKIP] {src_path}: already utf-8")

def process_directory(root_dir):
    for parent, dirnames, filenames in os.walk(root_dir):
        for filename in filenames:
            if filename.endswith((".java", ".jsp")):
                full_path = os.path.join(parent, filename)
                convert_to_utf8(full_path)

if __name__ == "__main__":
    src_path = "C:/Users/File"
    process_directory(src_path)