Hive基础（45）：Hive 函数(2) 自定义函数/自定义 UDF 函数/自定义 UDTF 函数

package com.atguigu.hive;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import 
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectIn
spectorFactory;
/**
* 自定义 UDF 函数，需要继承 GenericUDF 类
* 需求: 计算指定字符串的长度
*/
public class MyStringLength extends GenericUDF {
 /**
 *
 * @param arguments 输入参数类型的鉴别器对象
 * @return 返回值类型的鉴别器对象
 * @throws UDFArgumentException
 */
 @Override
 public ObjectInspector initialize(ObjectInspector[] arguments) throws 
UDFArgumentException {
 // 判断输入参数的个数
 if(arguments.length !=1){
 throw new UDFArgumentLengthException("Input Args Length 
Error!!!");
 }
 // 判断输入参数的类型
 
if(!arguments[0].getCategory().equals(ObjectInspector.Category.PRIMITIVE)
){
 throw new UDFArgumentTypeException(0,"Input Args Type 
Error!!!");
 }
 //函数本身返回值为 int，需要返回 int 类型的鉴别器对象
 return PrimitiveObjectInspectorFactory.javaIntObjectInspector;
 }
 /**
 * 函数的逻辑处理
 * @param arguments 输入的参数
 * @return 返回值
 * @throws HiveException
 */
 @Override
 public Object evaluate(DeferredObject[] arguments) throws 
HiveException {
 if(arguments[0].get() == null){
 return 0;
 }
 return arguments[0].get().toString().length();
 }
 @Override
 public String getDisplayString(String[] children) {
 return "";
 } }

package com.atguigu.udtf;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import 
org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import 
org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import 
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectIn
spectorFactory;
import java.util.ArrayList;
import java.util.List;
public class MyUDTF extends GenericUDTF {
 private ArrayList<String> outList = new ArrayList<>();
 @Override
 public StructObjectInspector initialize(StructObjectInspector argOIs) 
throws UDFArgumentException {
 //1.定义输出数据的列名和类型
 List<String> fieldNames = new ArrayList<>();
 List<ObjectInspector> fieldOIs = new ArrayList<>();
 //2.添加输出数据的列名和类型
 fieldNames.add("lineToWord");
 
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
 return 
ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, 
fieldOIs);
 }
 @Override
 public void process(Object[] args) throws HiveException {
 
 //1.获取原始数据
 String arg = args[0].toString();
 //2.获取数据传入的第二个参数，此处为分隔符
 String splitKey = args[1].toString();
 //3.将原始数据按照传入的分隔符进行切分
 String[] fields = arg.split(splitKey);
 //4.遍历切分后的结果，并写出
 for (String field : fields) {
 //集合为复用的，首先清空集合
 outList.clear();
 //将每一个单词添加至集合
 outList.add(field);
 //将集合内容写出
 forward(outList);
 }
 }
 @Override
 public void close() throws HiveException {
 } 
}