hive创建java函数_spark通过java的api创建hive的UDF用户自定义函数

public class UDF {

public static void main(String[] args) {

SparkConf conf = new SparkConf().setMaster(“local”).setAppName(“udf”);

JavaSparkContext sc = new JavaSparkContext(conf);

SQLContext sqlContext = new SQLContext(sc);

JavaRDD parallelize = sc.parallelize(Arrays.asList(“zhangsan”,“lisi”,“wangwu”));

//将rdd转为rowrdd

JavaRDD rowRDD = parallelize.map(new Function() {

/**

*

*/

private static final long serialVersionUID = 1L;

@Override

public Row call(String s) throws Exception {

return RowFactory.create(s);

}

});

/**

* 动态创建Schema方式加载DF

/

List fields = new ArrayList();

fields.add(DataTypes.createStructField(“name”, DataTypes.StringType,true));

StructType schema = DataTypes.createStructType(fields);

DataFrame df = sqlContext.createDataFrame(rowRDD,schema);

df.registerTempTable(“user”);

/*

* 根据UDF函数参数的个数来决定是实现哪一个UDF UDF1，UDF2。。。。UDF1xxx

*/

sqlContext.udf().register(“StrLen”, new UDF1() {

private static final long serialVersionUID = 1L;

@Override

public Integer call(String t1) throws Exception {

return t1.length();

}

}, DataTypes.IntegerType);

sqlContext.sql(“select name ,StrLen(name) as length from user”).show();

// sqlContext.udf().register(“StrLen”,new UDF2() {

// private static final long serialVersionUID = 1L;

//

// @Override

// public Integer call(String t1, Integer t2) throws Exception {

// return t1.length()+t2;

// }

// } ,DataTypes.IntegerType );

// sqlContext.sql(“select name ,StrLen(name,10) as length from user”).show();

sc.stop();

}

}