问Hive : Hive不向UDF发送适当的参数。

EN

CREATE TABLE `dum`(`val` map<string,array<string>>);
insert into dum select map('A',array('1','2','3'),'B',array('4','5','6'));

select * from dum;
{"A":["1","2","3"],"B":["4","5","6"]}

select modudf(val) from dum;
["1","2","3","4","5","6"]

package some.package;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.hive.ql.udf.UDFType;
import java.util.ArrayList;

import java.util.List;
import java.util.Map;

@UDFType(deterministic = true)
public class CustomUDF extends UDF {

public List<String> evaluate(Map<String, String[]> inMap) {

            ArrayList<String> res = new ArrayList<String>();
                for(Map.Entry<String, String[]> ent : inMap.entrySet()){
                    for(String item : ent.getValue())
                        res.add(item);
            }
        return res;
   }
}

add jar /path/to/my/jar;
CREATE TEMPORARY FUNCTION modudf AS 'some.package.CustomUDF';
select modudf(val) from dum;

FAILED: SemanticException [Error 10014]: Line 1:7 Wrong arguments 'val': No matching method for class some.package.CustomUDF with (map<string,array<string>>). Possible choices: _FUNC_(map<struct<>,struct<>>)

public List<CharSequence> evaluate(Map<CharSequence, List<CharSequence>> inMap) {

        modLogger.info(inMap);
            ArrayList<CharSequence> res = new ArrayList<CharSequence>();
                for(Map.Entry<CharSequence, List<CharSequence>> ent : inMap.entrySet()){
                    for(CharSequence item : ent.getValue())
                        res.add(item);
            }
        return res;
   }
}

hive> add jar /path/to/my/jar;
Added [/path/to/my/jar] to class path
Added resources: [/path/to/my/jar]
hive> CREATE TEMPORARY FUNCTION modudf AS 'some.package.CustomUDF';
hive> desc dum;
OK
val                     map<string,array<string>>
Time taken: 0.094 seconds, Fetched: 1 row(s)
hive> select val from dum;
Query ID = root_20200629170147_80b5248f-4519-4dae-a070-3c5185f742ea
Total jobs = 1
Launching Job 1 out of 1
Status: Running (Executing on YARN cluster with App id application_1593449512239_0001)

----------------------------------------------------------------------------------------------
        VERTICES      MODE        STATUS  TOTAL  COMPLETED  RUNNING  PENDING  FAILED  KILLED
----------------------------------------------------------------------------------------------
Map 1 .......... container     SUCCEEDED      1          1        0        0       0       0
----------------------------------------------------------------------------------------------
VERTICES: 01/01  [==========================>>] 100%  ELAPSED TIME: 6.12 s
----------------------------------------------------------------------------------------------
OK
{"A":["1","2","3"],"B":["4","5","6"]}
Time taken: 10.631 seconds, Fetched: 1 row(s)
hive> select modudf(val) from dum;
FAILED: SemanticException [Error 10014]: Line 1:7 Wrong arguments 'val': No matching method for class com.walmart.labs.search.sib.gcp.ModularTransformUDF with (map<string,array<string>>). Possible choices: _FUNC_(map<struct<>,array<struct<>>>)