JAVA读取HDFS的文件数据出现乱码的解决方案

<dependency>
	<groupId>net.sourceforge.jchardet</groupId>
	<artifactId>jchardet</artifactId>
	<version>1.0</version>
</dependency>

public class DetectorUtils {
	private DetectorUtils() {
	}
 
	static class ChineseCharsetDetectionObserver implements
			nsICharsetDetectionObserver {
		private boolean found = false;
		private String result;
 
		public void Notify(String charset) {
			found = true;
			result = charset;
		}
 
		public ChineseCharsetDetectionObserver(boolean found, String result) {
			super();
			this.found = found;
			this.result = result;
		}
 
		public boolean isFound() {
			return found;
		}
 
		public String getResult() {
			return result;
		}
 
	}
 
	public static String[] detectChineseCharset(InputStream in)
			throws Exception {
		String[] prob=null;
		BufferedInputStream imp = null;
		try {
			boolean found = false;
			String result = Charsets.UTF_8.toString();
			int lang = nsPSMDetector.CHINESE;
			nsDetector det = new nsDetector(lang);
			ChineseCharsetDetectionObserver detectionObserver = new ChineseCharsetDetectionObserver(
					found, result);
			det.Init(detectionObserver);
			imp = new BufferedInputStream(in);
			byte[] buf = new byte[1024];
			int len;
			boolean isAscii = true;
			while ((len = imp.read(buf, 0, buf.length)) != -1) {
				if (isAscii)
					isAscii = det.isAscii(buf, len);
				if (!isAscii) {
					if (det.DoIt(buf, len, false))
						break;
				}
			}
 
			det.DataEnd();
			boolean isFound = detectionObserver.isFound();
			if (isAscii) {
				isFound = true;
				prob = new String[] { "ASCII" };
			} else if (isFound) {
				prob = new String[] { detectionObserver.getResult() };
			} else {
				prob = det.getProbableCharsets();
			}
			return prob;
		} finally {
			IOUtils.closeQuietly(imp);
			IOUtils.closeQuietly(in);
		}
	}
}

		String file = "C:/3737001.xml";
		String[] probableSet = DetectorUtils.detectChineseCharset(new FileInputStream(file));
		for (String charset : probableSet) {
			System.out.println(charset);
		}

<dependency>
	<groupId>net.sourceforge.jchardet</groupId>
	<artifactId>jchardet</artifactId>
	<version>1.0</version>
</dependency>

 // 获取文件的部分数据做预览
 public List<String> getFileDataWithLimitLines(String filePath, Integer limit) {
  FSDataInputStream fileStream = openFile(filePath);
  return readFileWithLimit(fileStream, limit);
 }

 // 获取文件的数据流
 private FSDataInputStream openFile(String filePath) {
  FSDataInputStream fileStream = null;
  try {
   fileStream = fs.open(new Path(getHdfsPath(filePath)));
  } catch (IOException e) {
   logger.error("fail to open file:{}", filePath, e);
  }
  return fileStream;
 }
 
 // 读取最多limit行文件数据
 private List<String> readFileWithLimit(FSDataInputStream fileStream, Integer limit) {
  byte[] bytes = readByteStream(fileStream);
  String data = decodeByteStream(bytes);
  if (data == null) {
   return null;
  }

  List<String> rows = Arrays.asList(data.split("\\r\\n"));
  return rows.stream().filter(StringUtils::isNotEmpty)
    .limit(limit)
    .collect(Collectors.toList());
 }

 // 从文件数据流中读取字节流
 private byte[] readByteStream(FSDataInputStream fileStream) {
  byte[] bytes = new byte[1024*30];
  int len;
  ByteArrayOutputStream stream = new ByteArrayOutputStream();
  try {
   while ((len = fileStream.read(bytes)) != -1) {
    stream.write(bytes, 0, len);
   }
  } catch (IOException e) {
   logger.error("read file bytes stream failed.", e);
   return null;
  }
  return stream.toByteArray();
 }

 // 解码字节流
 private String decodeByteStream(byte[] bytes) {
  if (bytes == null) {
   return null;
  }

  String encoding = guessEncoding(bytes);
  String data = null;
  try {
   data = new String(bytes, encoding);
  } catch (Exception e) {
   logger.error("decode byte stream failed.", e);
  }
  return data;
 }

 // 根据Google的工具判别编码
 private String guessEncoding(byte[] bytes) {
  UniversalDetector detector = new UniversalDetector(null);
  detector.handleData(bytes, 0, bytes.length);
  detector.dataEnd();
  String encoding = detector.getDetectedCharset();
  detector.reset();

  if (StringUtils.isEmpty(encoding)) {
   encoding = "UTF-8";
  }
  return encoding;
 }