彻底解决android读取txt乱码终极方案

解决android读取txt乱码

一，工具类FileUtil

/**
* 获取文件内容
*
* @param filePath
* @return
*/
public static String getFileOutputString(String filePath, String charset) {
try {
File file = new File(filePath);
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(new FileInputStream(file), charset), 8192);
StringBuilder sb = new StringBuilder();
String line = null;
while ((line = bufferedReader.readLine()) != null) {
sb.append("\n").append(line);
}
bufferedReader.close();
return sb.toString();
} catch (IOException e) {
e.printStackTrace();
}
return null;
}

/**
 * 获取文件编码
 * @param filePath
 * @return
 */
public static String getCharset(String filePath) {
    BufferedInputStream bis = null;
    String charset = "GBK";
    byte[] first3Bytes = new byte[3];
    try {
        boolean checked = false;
        bis = new BufferedInputStream(new FileInputStream(filePath));
        bis.mark(0);
        int read = bis.read(first3Bytes, 0, 3);
        if (read == -1)
            return charset;
        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;
        }
        bis.mark(0);
        if (!checked) {
            while ((read = bis.read()) != -1) {
                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;
                }
            }
        }
    } catch (Exception e) {
        e.printStackTrace();
    } finally {
        if (bis != null) {
            try {
                bis.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

    return charset;
}

二，使用方法

String charset = FileUtil.getCharset(file.getAbsolutePath());
            String content = FileUtil.getFileOutputString(file.getAbsolutePath(),charset);