上传txt文件判断编码格式，并转UTF-8

前言

提示：这里可以添加本文要记录的大概内容：
例如：随着人工智能的不断发展，机器学习这门技术也越来越重要，很多人都开启了学习机器学习，本文就介绍了机器学习的基础内容。

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、使用步骤

代码如下（示例）：

 /**
     * @Author wdp
     * @Description //TODO 
     * @Date 16:24 2021/3/18
     * @Param [file, inputFileUrl:源文件路径, outputFileUrl：新文件路径]
     * @return void
     **/
    public static void saveAsUTF8(File file,String inputFileUrl, String outputFileUrl) throws IOException {
        String inputFileEncode = getFilecharset(file);
        System.out.println("inputFileEncode===" + inputFileEncode);
        BufferedReader bufferedReader = new BufferedReader(
                new InputStreamReader(new FileInputStream(inputFileUrl), inputFileEncode));
        BufferedWriter bufferedWriter = new BufferedWriter(
                new OutputStreamWriter(new FileOutputStream(outputFileUrl), "UTF-8"));
        String line;

        while ((line = bufferedReader.readLine()) != null) {
            bufferedWriter.write(line + "\r\n");
        }
        bufferedWriter.close();
        bufferedReader.close();

    }







 //判断编码格式方法
    private static  String getFilecharset(File sourceFile) {
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try {
            boolean checked = false;
            BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile));
            bis.mark(0);
            int read = bis.read(first3Bytes, 0, 3);
            if (read == -1) {
                return charset; //文件编码为 ANSI
            } else if (first3Bytes[0] == (byte) 0xFF
                    && first3Bytes[1] == (byte) 0xFE) {
                charset = "UTF-16LE"; //文件编码为 Unicode
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xFE
                    && first3Bytes[1] == (byte) 0xFF) {
                charset = "UTF-16BE"; //文件编码为 Unicode big endian
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xEF
                    && first3Bytes[1] == (byte) 0xBB
                    && first3Bytes[2] == (byte) 0xBF) {
                charset = "UTF-8"; //文件编码为 UTF-8
                checked = true;
            }
            bis.reset();
            if (!checked) {
                int loc = 0;
                while ((read = bis.read()) != -1) {
                    loc++;
                    if (read >= 0xF0)
                        break;
                    if (0x80 <= read && read <= 0xBF) // 单独出现BF以下的，也算是GBK
                        break;
                    if (0xC0 <= read && read <= 0xDF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) // 双字节 (0xC0 - 0xDF)
                            // (0x80
                            // - 0xBF),也可能在GB编码内
                            continue;
                        else
                            break;
                    } else if (0xE0 <= read && read <= 0xEF) {// 也有可能出错，但是几率较小
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            read = bis.read();
                            if (0x80 <= read && read <= 0xBF) {
                                charset = "UTF-8";
                                break;
                            } else
                                break;
                        } else
                            break;
                    }
                }
            }
            bis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }

2.备注

别忘了删除源文件