java 自动识别语言编码

导入pom.xml依赖
<dependency>
    <groupId>com.ibm.icu</groupId>
    <artifactId>icu4j</artifactId>
    <version>64.2</version>
</dependency>

public class TestIcu {
    /**
     * 获取编码
     * @throws IOException
     * @throws Exception
     */
    public static String getEncode(byte[] data){
        CharsetDetector detector = new CharsetDetector();
        detector.setText(data);
        CharsetMatch match = detector.detect();
        String encoding = match.getName();
        //System.out.println("The Content in " + match.getName());
        CharsetMatch[] matches = detector.detectAll();
        //System.out.println("All possibilities");
        for (CharsetMatch m : matches) {
            //System.out.println("CharsetName:" + m.getName() + " Confidence:" + m.getConfidence());
        }
        return encoding;
    }
    public static String getEncode(InputStream data) throws IOException {
        CharsetDetector detector = new CharsetDetector();
        detector.setText(data);
        CharsetMatch match = detector.detect();
        String encoding = match.getName();
        System.out.println("The Content in " + match.getName());
        CharsetMatch[] matches = detector.detectAll();
        System.out.println("All possibilities");
        for (CharsetMatch m : matches) {
            System.out.println("CharsetName:" + m.getName() + " Confidence:"
                    + m.getConfidence());
        }
        return encoding;
    }


    public static void main(String[] args) {
        System.out.println(TestIcu.getEncode("111asdfasdfad fqwef asdfw".getBytes()));
    }

    

}