hive udf unicode解码

Posted 2022-12-17 AI算法攻城狮

直接上代码吧

import org.apache.hadoop.hive.ql.exec.UDF;
import static org.apache.commons.lang.StringUtils.trim;

public class UnicodeDecode extends UDF 
    public String evaluate(String asciicode) 
        if(asciicode==null || asciicode.isEmpty())
            return "";
        

        String[] asciis = asciicode.split ("\\\\\\\\u");
        String nativeValue = asciis[0];
        try
            for ( int i = 1; i < asciis.length; i++ )
                String code = asciis[i];
                nativeValue += (char) Integer.parseInt (code.substring (0, 4), 16);
                if (code.length () > 4)
                    nativeValue += code.substring (4, code.length ());
                
            
        catch (NumberFormatException e)
            return asciicode;
        
        return trim(nativeValue);
    
    public static void main(String[] args) 
        Uni