Refer to:http://blog.csdn.net/wf1982/article/details/7623708
1.介绍
UDTF(User-Defined Table-Generating Functions) 用来解决 输入一行输出多行(On-to-many maping) 的需求。同时,也可以解决一列拆分成多列的问题(Hive支持复杂的数据格式,包括List)。
2.编写需要的UDTF
1) 继承org.apache.hadoop.hive.ql.udf.generic.GenericUDTF。
2) 实现initialize, process, close三个方法
3) UDTF首先会调用initialize方法,此方法返回UDTF的返回行的信息(返回个数,类型)。
初始化完成后,会调用process方法,对传入的参数进行处理,可以通过forword()方法把结果返回。
最后close()方法调用,对需要清理的方法进行清理。
这是一个用来切分 key:value;key:value 这种字符串,返回结果为key, value两个字段。
import java.util.ArrayList;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
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.PrimitiveObjectInspectorFactory;
public class ExplodeMap extends GenericUDTF{
@Override
public void close() throws HiveException {
// TODO Auto-generated method stub
}
@Override
public StructObjectInspector initialize(ObjectInspector[] args)
throws UDFArgumentException {
if (args.length != 1) {
throw new UDFArgumentLengthException("ExplodeMap takes only one argument");
}
if (args[0].getCategory() != ObjectInspector.Category.PRIMITIVE) {
throw new UDFArgumentException("ExplodeMap takes string as a parameter");
}
ArrayList<String> fieldNames = new ArrayList<String>();
ArrayList<ObjectInspector> fieldOIs = new ArrayList<ObjectInspector>();
fieldNames.add("col1");
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
fieldNames.add("col2");
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames,fieldOIs);
}
@Override
public void process(Object[] args) throws HiveException {
String input = args[0].toString();
String[] test = input.split(";");
for(int i=0; i<test.length; i++) {
try {
String[] result = test[i].split(":");
forward(result);
} catch (Exception e) {
continue;
}
}
}
}
3. 使用方法
UDTF有两种使用方法,一种直接放到select后面,一种和lateral view一起使用。
1) 直接select中使用:select explode_map(properties) as (col1,col2) from src;
不可以添加其他字段使用:select a, explode_map(properties) as (col1,col2) from src
不可以嵌套调用:select explode_map(explode_map(properties)) from src
不可以和group by/cluster by/distribute by/sort by一起使用:select explode_map(properties) as (col1,col2) from src group by col1, col2
2) 和lateral view一起使用:
select src.id, mytable.col1, mytable.col2 from src lateral view explode_map(properties) mytable as col1, col2;
此方法更为方便日常使用。执行过程相当于单独执行了两次抽取,然后union到一个表里。
4. 参考文档
http://wiki.apache.org/hadoop/Hive/LanguageManual/UDF
http://wiki.apache.org/hadoop/Hive/DeveloperGuide/UDTF
http://www.slideshare.net/pauly1/userdefined-table-generating-functions
Appendix:
一个用于将字符串拆分成多个字段的:
import java.util.ArrayList;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
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.PrimitiveObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantIntObjectInspector;
/**
* GenericUDTFRD: this
*
*/
@Description(name = "tr_rd", value = "_FUNC_(x)")
public class GenericUDTFRD extends GenericUDTF {
private static Log LOG = LogFactory.getLog(GenericUDTFRD.class.getName());
@Override
public void close() throws HiveException {
}
@Override
public StructObjectInspector initialize(ObjectInspector[] args)
throws UDFArgumentException {
LOG.debug("========================initialize");
LOG.debug("args.length" + args.length);
if (args.length != 2) {
throw new UDFArgumentLengthException(
"ExplodeMap takes only two argument");
}
WritableConstantIntObjectInspector x = (WritableConstantIntObjectInspector) args[1];
int numCols = x.getWritableConstantValue().get();
LOG.debug("numCols:" + numCols);
// construct output object inspector
ArrayList<String> fieldNames = new ArrayList<String>(numCols);
ArrayList<ObjectInspector> fieldOIs = new ArrayList<ObjectInspector>(
numCols);
for (int i = 0; i < numCols; ++i) {
fieldNames.add("c" + i);
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
}
return ObjectInspectorFactory.getStandardStructObjectInspector(
fieldNames, fieldOIs);
}
@Override
public void process(Object[] o) throws HiveException {
LOG.debug("========================process");
String input = o[0].toString();
//字段分隔符
String[] test = input.split("\t");
LOG.debug("input:" + input);
LOG.debug("test:" + test);
for(int i=0;i<test.length;i++){
if("".equals(test[i])||null==test[i]){
test[i]="\\N";
}
}
forward(test);
}
@Override
public String toString() {
return "tr_rd";
}
}
用法是:
--将一个字段,拆分成3个。
select tr_rd(tt.col1,3) as (c1,c2,c3)
from table tt