java识别文件或字符串的编码格式

1, 用juniversalchardet：

http://code.google.com/p/juniversalchardet/

官方示例：

import org.mozilla.universalchardet.UniversalDetector;

public class TestDetector

{

  public static void main(String[] args)

  {

    byte[] buf = new byte[4096];

    java.io.FileInputStream fis = new java.io.FileInputStream("test.txt");

    // (1)

    UniversalDetector detector = new UniversalDetector(null);

    // (2)

    int nread;

    while ((nread = fis.read(buf)) > 0 && !detector.isDone()) {

      detector.handleData(buf, 0, nread);

    }

    // (3)

    detector.dataEnd();

    // (4)

    String encoding = detector.getDetectedCharset();

    if (encoding != null) {

      System.out.println("Detected encoding = " + encoding);

    } else {

      System.out.println("No encoding detected.");

    }

    // (5)

    detector.reset();

  }

}

他人示例代码:

public static String guessEncoding(byte[] bytes) {

    String DEFAULT_ENCODING = "UTF-8";

    org.mozilla.universalchardet.UniversalDetector detector =

        new org.mozilla.universalchardet.UniversalDetector(null);

    detector.handleData(bytes, 0, bytes.length);

    detector.dataEnd();

    String encoding = detector.getDetectedCharset();

    detector.reset();

    if (encoding == null) {

        encoding = DEFAULT_ENCODING;

    }

    return encoding;

}