MongoDB数据导入hbase + 代码

需求：
从mongoDB里面查出来数据，判断是否有该列簇，如果有则导入此条数据+列簇，如果没有，则该条数据不包含该列簇

直接贴出代码：

package Test;

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Set;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.util.Bytes;
import org.bson.Document;

import com.mongodb.MongoClient;
import com.mongodb.MongoCredential;
import com.mongodb.ServerAddress;
import com.mongodb.client.FindIterable;
import com.mongodb.client.MongoCollection;
import com.mongodb.client.MongoCursor;
import com.mongodb.client.MongoDatabase;

public class OperateTable2 {
private static Configuration conf = null;
static {
conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum","master.hadoop");
conf.set("hbase.zookeeper.property.clientPort", "2181");
conf.set("hbase.master", "master.hadoop:60000");
}
public static void addRow(String tableName, String row,
            String columnFamily, String column, String value) throws Exception {
        HTable hTable = new HTable(conf, tableName);
        Put put = new Put(Bytes.toBytes(row));
        // 参数出分别：列族、列、值
        put.add(Bytes.toBytes(columnFamily), Bytes.toBytes(column),
                Bytes.toBytes(value));
        hTable.put(put);

    }
public static void main(String[] args) {
// 声明静态配置
String tableName = "house";
        String columnFamilys = "info";
        int a = 0;
try {
ServerAddress serverAddress = new ServerAddress("42.62.66.9",27017);
List addrs = new ArrayList();
addrs.add(serverAddress);
MongoCredential credential = MongoCredential.createScramSha1Credential("admin",
"admin", "bigmaster654321".toCharArray());
List credentials = new ArrayList();
credentials.add(credential);
//通过认证获取mongoDB的连接
MongoClient mongoClient = new MongoClient(addrs,credentials);
MongoDatabase mongoDatabase = mongoClient.getDatabase("house");
System.out.println("MongoDB Connection-----------------Successfully");
MongoCollection collection = mongoDatabase.getCollection("houses2");
FindIterable findIterable  = collection.find();
MongoCursor mongoCursor = findIterable.iterator();
while(mongoCursor.hasNext()){
a=a+1;
Document document = mongoCursor.next();
   Set set = document.keySet();
Iterator it = set.iterator();
while(it.hasNext()){
 String tags = it.next();
 if(tags.equals("_id")){
 continue;
 }
 OperateTable2.addRow(tableName, document.getString("_id"), columnFamilys, tags, document.getString(tags));
}
System.out.println("Insert Into HBase Success"+"This is the "+a+" data");
}
System.out.println("Compelete All Insert");
} catch (Exception e) {
// TODO: handle exception
System.err.println(e.getClass().getName()+ ":" +e.getMessage());
}
}
}

我这里是用_id为hbase的rowkey，列为info，代码无误，根据需求可以改动，关键在于两个while判断的地方，那里最容易出错,导入mysql也可以用此代码改动取值的地方和jdbc连接进行导入

需要用到的包：mongo-java-driver-3.2.2.jar，hbase常用的包可以全导

代码如上，原创转载注明出处！