在Web中集成Kettle-CSDN博客

原创文章，转载请注明出处：http://qq85609655.iteye.com/blog/1306555

今天，想将kettle整合到web工程中。这个想法一出现，就马上查找资料，可惜资料太少，没有现成的。

后面查看源码。。。终于整合到web工程中，方法如下:

编写一个Servlet，工程启动时成功，顺利完成集成。

<?xml version="1.0" encoding="UTF-8"?>
<web-app xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://java.sun.com/xml/ns/javaee" xmlns:web="http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd" xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd" id="WebApp_ID" version="2.5">
	<display-name>kettleapi4_2</display-name>
	<servlet>
		<servlet-name>KettleStartServlet</servlet-name>
		<servlet-class>zhangxin.kettle.servlet.KettleStartServlet</servlet-class>
		<load-on-startup>0</load-on-startup>
		<init-param>
			<param-name>dir</param-name>
			<param-value>/test</param-value>
		</init-param>
		<init-param>
			<param-name>jobname</param-name>
			<param-value>测试作业</param-value>
		</init-param>
	</servlet>
	<welcome-file-list>
		<welcome-file>index.html</welcome-file>
		<welcome-file>index.htm</welcome-file>
		<welcome-file>index.jsp</welcome-file>
		<welcome-file>default.html</welcome-file>
		<welcome-file>default.htm</welcome-file>
		<welcome-file>default.jsp</welcome-file>
	</welcome-file-list>
</web-app>

Servlet代码如下:

package zhangxin.kettle.servlet;

import java.io.File;
import java.util.List;

import javax.servlet.ServletConfig;
import javax.servlet.ServletConfig;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;

import org.pentaho.di.core.KettleEnvironment;
import org.pentaho.di.core.Result;
import org.pentaho.di.core.exception.KettleException;
import org.pentaho.di.core.plugins.PluginRegistry;
import org.pentaho.di.core.plugins.RepositoryPluginType;
import org.pentaho.di.job.Job;
import org.pentaho.di.job.JobMeta;
import org.pentaho.di.repository.ObjectId;
import org.pentaho.di.repository.RepositoriesMeta;
import org.pentaho.di.repository.Repository;
import org.pentaho.di.repository.RepositoryDirectoryInterface;
import org.pentaho.di.repository.RepositoryElementMetaInterface;
import org.pentaho.di.repository.RepositoryMeta;
import org.pentaho.di.repository.StringObjectId;
import org.pentaho.di.trans.Trans;
import org.pentaho.di.trans.TransMeta;

public class KettleStartServlet extends HttpServlet {

	/**
	 * 
	 */
	private static final long serialVersionUID = 4122742794095256794L;

	public void init() throws ServletException {
		try {
			// 设置Kettle的初始化配置信息路径
			initKettleEnvironment();

			ServletConfig config=getServletConfig();
			//通过 ServletConfig对象获取配置参数:dirverString
			String dir = config.getInitParameter("dir");
			String jobname = config.getInitParameter("jobname");
			executeJob(dir, jobname);
		} catch (KettleException e) {
			e.printStackTrace();
		}
	}

	/**
	 * 设置Kettle的初始化配置信息路径
	 * @throws KettleException
	 */
	private void initKettleEnvironment() throws KettleException {
		// 获得执行类的当前路径
		String user_dir = System.getProperty("user.dir");
		String kettleHome = this.getServletContext().getRealPath(File.separator + "WEB-INF");
		// Kettle初始化需要修改相应的配置路径
		System.setProperty("user.dir", kettleHome);
		System.setProperty("KETTLE_HOME", kettleHome);
		// 运行环境初始化（设置主目录、注册必须的插件等）
		KettleEnvironment.init();
		// Kettle初始化完毕，还原执行类的当前路径
		System.setProperty("user.dir", user_dir);
	}

	/**
	 * Kettle执行Job
	 * @throws KettleException
	 */
	public void executeJob(String dir, String jobname) throws KettleException {
		
		RepositoriesMeta repositoriesMeta = new RepositoriesMeta();
		// 从文件读取登陆过的资源库信息
		repositoriesMeta.readData();
		// 选择登陆过的资源库
		RepositoryMeta repositoryMeta = repositoriesMeta.findRepository("4_2");
		// 获得资源库实例
		Repository repository = PluginRegistry.getInstance().loadClass(RepositoryPluginType.class, repositoryMeta, Repository.class);
		repository.init(repositoryMeta);
		// 连接资源库
		repository.connect("admin", "admin");

		RepositoryDirectoryInterface tree = repository.loadRepositoryDirectoryTree();
		RepositoryDirectoryInterface fooBar = tree.findDirectory(dir);
		JobMeta jobMeta = repository.loadJob(jobname, fooBar, null, null);
		// 执行指定作业
		Job job = new Job(repository, jobMeta);
		job.start();
		job.waitUntilFinished();
		Result result = job.getResult();
		result.getRows();
		if (job.getErrors() > 0) {
			throw new RuntimeException("There were errors during transformation execution.");
		}
		repository.disconnect();
	}
}

这样就集成好了。。。

下面是工程的结构

KETTLE结构

工程中的包和资源如下

libraries=
../lib
../libext
../libext/commons
../libext/elasticsearch
../libext/feeds
../libext/google
../libext/hive
../libext/hl7
../libext/JDBC
../libext/jersey
../libext/jfree
../libext/mondrian
../libext/pentaho
../libext/poi
../libext/reporting
../libext/rules
../libext/salesforce
../libext/spring
../libext/web
../libext/webservices
../libswt

classpath=
../
../ui
../ui/images
../libext/mondrian/config
../libext/pentaho/pigConf