spark连接mongodb



hadoop和mongodb的连接器

<dependency>
<groupId>org.mongodb.mongo-hadoop</groupId>
<artifactId>mongo-hadoop-core</artifactId>
<version>1.4.2</version>
</dependency>

java连接mongodb连接器
<dependency>
<groupId>org.mongodb </groupId>
<artifactId>mongo-java-driver </artifactId>
<version>2.13.0 </version>
</dependency>
2.使用示例
import com.mongodb.hadoop.MongoOutputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.bson.BSONObject;
import scala.Tuple2;

import java.util.Date;
import java.util.List;

/**
 * Created by Administrator on 2015/12/8.
 */
public class ConnectMongo {

    public static void main(String args[]){
        JavaSparkContext sc =new JavaSparkContext("local","test");
        Configuration config =new Configuration();
        //解释 主机:端口号/数据库名.Collection        config.set("mongo.input.uri","mongodb://127.0.0.1:27017/lang.sanlu");
        config.set("mongo.output.uri", "mongodb://127.0.0.1:27017/lang.output");
        //读取
        JavaPairRDD<Object, BSONObject> mongoRDD = sc.newAPIHadoopRDD(config, com.mongodb.hadoop.MongoInputFormat.class, Object.class, BSONObject.class);
        //BasonObject-> text
        JavaRDD<text> result = mongoRDD.map(
                new Function<Tuple2<Object, BSONObject>, text>() {
                    public text call(Tuple2<Object, BSONObject> v1) throws Exception {
                        String title = (String) v1._2().get("title");
                        Date date =(Date) v1._2().get("date");
                        List<String> paragraph = (List<String>) v1._2().get("paragraph");
                        return new text(title,date,paragraph);
                    }
                }
        );
        //copy lang.sanlu to lang.output
        mongoRDD.saveAsNewAPIHadoopFile("file:///copy",Object.class, Object.class, MongoOutputFormat.class, config);


    }
}


  • 1
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 3
    评论
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值