hive-udf开发实例1

1，pom配置：

<dependency>
    <groupId>org.apache.hive</groupId>
    <artifactId>hive-exec</artifactId>
    <version>1.1.0-cdh5.8.3</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-client</artifactId>
    <version>2.6.0-cdh5.8.3</version>
</dependency>


2,java代码：

package com.ibeifeng.udf;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.hadoop.hive.ql.exec.UDF;
public class GetCmsID extends UDF {
/**
* @param args
*/

public String evaluate(String url){
String cmsid = null;
if (url==null || "".equals(url)) {
return cmsid;
}
Pattern pat = Pattern.compile("topicId=[0-9]+") ;
Matcher matcher = pat.matcher(url);

if (matcher.find()) {
cmsid=matcher.group().split("topicId=")[1];
}

return cmsid;
}

public String evaluate(String pattern,String url){
String cmsid = null;
if (url==null || "".equals(url)) {
return cmsid;
}
Pattern pat = Pattern.compile(pattern+"[0-9]+") ;
Matcher matcher = pat.matcher(url);

if (matcher.find()) {
cmsid=matcher.group().split(pattern)[1];
}

return cmsid;
}

public static void main(String[] args) {
// TODO Auto-generated method stub
String url="http://www.taobao.com/cms/view.do?topicId=18980";
GetCmsID getCmsID = new GetCmsID();

System.out.println(getCmsID.evaluate(url)) ;
System.out.println(getCmsID.evaluate("cmsid=",url)) ;
}


}


3，导出jar包

4，hive中导入jar包

addjar /opt/beifeng/jars/hive_UDF.jar;
createtemporary function getcmsid as 'com.ibeifeng.udf.GetCmsID ';


5，hive sql使用udf

select getcmsid(url) from info_tab;