今天有同事来问一个我写过的UDF的问题，想起之前貌似写过一篇这样的文章，草稿箱里找了下，确实有，躺了一年半了，发出来，也许对某些同学有帮助~
hive> show functions; OK ! != ...... Time taken: 0.275 seconds hive> desc function substr; OK substr(str, pos[, len]) - returns the substring of str that starts at pos and is of length len orsubstr(bin, pos[, len]) - returns the slice of byte array that starts at pos and is of length len Time taken: 0.095 seconds
编写Hive UDF有两种方式：
1. extends UDF ， 重写evaluate方法
2. extends GenericUDF，重写initialize、getDisplayString、evaluate方法
package test.udf;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;
public class ToLowerCase extends UDF {
public Text evaluate(final Text s) {
if (s == null) { return null; }
return new Text(s.toString().toLowerCase());
}
}功能：计算array中去重后元素个数
UDFArrayUniqElementNumber .java
package test.udf;
import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
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.ListObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector.Category;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.apache.hadoop.io.IntWritable;
/**
* UDF:
* Get nubmer of objects with duplicate elements eliminated
* @author xiaomin.zhou
*/
@Description(name = "array_uniq_element_number", value = "_FUNC_(array) - Returns nubmer of objects with duplicate elements eliminated.", extended = "Example:\n"
+ " > SELECT _FUNC_(array(1, 2, 2, 3, 3)) FROM src LIMIT 1;\n" + " 3")
public class UDFArrayUniqElementNumber extends GenericUDF {
private static final int ARRAY_IDX = 0;
private static final int ARG_COUNT = 1; // Number of arguments to this UDF
private static final String FUNC_NAME = "ARRAY_UNIQ_ELEMENT_NUMBER"; // External Name
private ListObjectInspector arrayOI;
private ObjectInspector arrayElementOI;
private final IntWritable result = new IntWritable(-1);
public ObjectInspector initialize(ObjectInspector[] arguments)
throws UDFArgumentException {
// Check if two arguments were passed
if (arguments.length != ARG_COUNT) {
throw new UDFArgumentException("The function " + FUNC_NAME
+ " accepts " + ARG_COUNT + " arguments.");
}
// Check if ARRAY_IDX argument is of category LIST
if (!arguments[ARRAY_IDX].getCategory().equals(Category.LIST)) {
throw new UDFArgumentTypeException(ARRAY_IDX, "\""
+ org.apache.hadoop.hive.serde.Constants.LIST_TYPE_NAME
+ "\" " + "expected at function ARRAY_CONTAINS, but "
+ "\"" + arguments[ARRAY_IDX].getTypeName() + "\" "
+ "is found");
}
arrayOI = (ListObjectInspector) arguments[ARRAY_IDX];
arrayElementOI = arrayOI.getListElementObjectInspector();
return PrimitiveObjectInspectorFactory.writableIntObjectInspector;
}
public IntWritable evaluate(DeferredObject[] arguments)
throws HiveException {
result.set(0);
Object array = arguments[ARRAY_IDX].get();
int arrayLength = arrayOI.getListLength(array);
if (arrayLength <= 1) {
result.set(arrayLength);
return result;
}
//element compare; Algorithm complexity: O(N^2)
int num = 1;
int i, j;
for(i = 1; i < arrayLength; i++)
{
Object listElement = arrayOI.getListElement(array, i);
for(j = i - 1; j >= 0; j--)
{
if (listElement != null) {
Object tmp = arrayOI.getListElement(array, j);
if (ObjectInspectorUtils.compare(tmp, arrayElementOI, listElement,
arrayElementOI) == 0) {
break;
}
}
}
if(-1 == j)
{
num++;
}
}
result.set(num);
return result;
}
public String getDisplayString(String[] children) {
assert (children.length == ARG_COUNT);
return "array_uniq_element_number(" + children[ARRAY_IDX]+ ")";
}
}hive> select * from test; OK Hello wORLD ZXM ljz Time taken: 13.76 seconds hive> add jar /home/work/udf.jar; Added /home/work/udf.jar to class path Added resource: /home/work/udf.jar hive> create temporary function mytest as ‘test.udf.ToLowerCase‘; OK Time taken: 0.103 seconds hive> show functions; ...... mytest ...... hive> select mytest(test.name) from test; ...... OK hello world zxm ljz Time taken: 38.218 seconds这种方式在会话结束后，函数自动销毁，因此每次打开新的会话，都需要重新add jar并且create temporary function
$ cat hive_init add jar /home/work/udf.jar; create temporary function mytest as ‘test.udf.ToLowerCase‘; $ hive -i hive_init Logging initialized using configuration in file:/home/work/hive/hive-0.8.1/conf/hive-log4j.properties Hive history file=/tmp/work/hive_job_log_work_201209200147_1951517527.txt hive> show functions; ...... mytest ...... hive> select mytest(test.name) from test; ...... OK hello world zxm ljz方法2和方法1本质上是相同的，区别在于方法2在会话初始化时自动完成
和前两者相比，第三种方式直接将用户的自定义函数作为注册为内置函数，未来使用起来非常简单，但这种方式也非常危险，一旦出错，将是灾难性的，因此，建议如果不是特别通用，并且固化下来的函数，还是使用前两种方式比较靠谱。
Reference：
原文：http://blog.csdn.net/yfkiss/article/details/7885262