java获取文本文件的编码格式

/**
     * 获取文件的编码格式
     * @param file
     * @return
     */
    public String GetCharset(File file) {
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try {
            boolean checked = false;
            //BufferedInputStream bis = new BufferedInputStream(
            //new FileInputStream(file));
            //bis.mark(0);
            //int read = bis.read(first3Bytes, 0, 3);
            InputStream is = new FileInputStream(file);
            int read = is.read(first3Bytes, 0, 3);

            if (read == -1)
                return charset;
            //Log.i(TAG,"[GetCharset]first3Bytes[0]:"+first3Bytes[0]+", first3Bytes[1]:"+first3Bytes[1]+",first3Bytes[2]:"+first3Bytes[2]);
            if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
                charset = "UTF-16LE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xFE
                    && first3Bytes[1] == (byte) 0xFF) {
                charset = "UTF-16BE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xEF
                    && first3Bytes[1] == (byte) 0xBB
                    && first3Bytes[2] == (byte) 0xBF) {
                charset = "UTF-8";
                checked = true;
            }else if (first3Bytes[0] == (byte) 0xA
                    && first3Bytes[1] == (byte) 0x5B
                    && first3Bytes[2] == (byte) 0x30) {
                charset = "UTF-8";
                checked = true;
            }else if (first3Bytes[0] == (byte) 0xD
                    && first3Bytes[1] == (byte) 0xA
                    && first3Bytes[2] == (byte) 0x5B) {
                charset = "GBK";
                checked = true;
            }else if (first3Bytes[0] == (byte) 0x5B
                    && first3Bytes[1] == (byte) 0x54
                    && first3Bytes[2] == (byte) 0x49) {
                charset = "windows-1251";
                checked = true;
            }
            //bis.reset();
            InputStream istmp = new FileInputStream(file);
            if (!checked) {
                int loc = 0;
                while ((read = istmp.read()) != -1) {
                    loc++;
                    if (read >= 0xF0)
                        break;
                    if (0x80 <= read && read <= 0xBF)
                        break;
                    if (0xC0 <= read && read <= 0xDF) {
                        read = istmp.read();
                        if (0x80 <= read && read <= 0xBF)
                            continue;
                        else
                            break;
                    } else if (0xE0 <= read && read <= 0xEF) {
                        read = istmp.read();
                        if (0x80 <= read && read <= 0xBF) {
                            read = istmp.read();
                            if (0x80 <= read && read <= 0xBF) {
                                charset = "UTF-8";
                                break;
                            } else
                                break;
                        } else
                            break;
                    }
                }
            }
            is.close();
            istmp.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }

  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

peak wang

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值