hbase-spark组合使用

最新推荐文章于 2025-06-05 07:58:32 发布

小钻风巡山

最新推荐文章于 2025-06-05 07:58:32 发布

阅读量652

点赞数

CC 4.0 BY-SA版权

分类专栏： spark hbase

本文链接：https://blog.youkuaiyun.com/weixin_42660202/article/details/86509195

spark 同时被 2 个专栏收录

13 篇文章

订阅专栏

hbase

4 篇文章

订阅专栏

本文介绍如何使用Apache Spark读取HBase数据，通过配置Spark应用程序、设置HBase连接参数及扫描过滤器，演示了从HBase表中读取特定行键范围的数据，并使用Spark进行数据处理的过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>sparkTest</groupId>
    <artifactId>sparkTest</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.4.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.4.6</version>
        </dependency>
    </dependencies>
</project>

代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.filter.BinaryPrefixComparator;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.protobuf.ProtobufUtil;
import org.apache.hadoop.hbase.protobuf.generated.ClientProtos;
import org.apache.hadoop.hbase.util.Base64;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.hadoop.hbase.mapreduce.TableInputFormat;
import org.apache.hadoop.hbase.client.Result;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.io.IOException;
import java.util.List;

public class SparkTest {
    public static void main(String[] args) {
        SparkConf sparkConf = new SparkConf().setAppName("myTest").setMaster("local[2]");
        JavaSparkContext sc = new JavaSparkContext(sparkConf);
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "mini1:2181,mini2:2181,mini3:2181");
        conf.set(TableInputFormat.INPUT_TABLE, "one");//查询的表
        conf.set(TableInputFormat.SCAN_ROW_START, "001");//起始行键
        conf.set(TableInputFormat.SCAN_ROW_STOP, "103");//结束行键
        Scan scan = new Scan();
        RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.EQUAL, new BinaryPrefixComparator("".getBytes()));//过滤器
        scan.setFilter(rowFilter);
        conf.set(TableInputFormat.SCAN, convertScanToString(scan));
        JavaPairRDD<ImmutableBytesWritable, Result> rdd = sc.newAPIHadoopRDD(conf, TableInputFormat.class, ImmutableBytesWritable.class, Result.class);//获取rdd数据
        //处理数据
        JavaPairRDD<String, Integer> tuple2JavaRDD = rdd.mapToPair(new PairFunction<Tuple2<ImmutableBytesWritable, Result>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<ImmutableBytesWritable, Result> immutableBytesWritableResultTuple2) throws Exception {
                Result result = immutableBytesWritableResultTuple2._2;
                Cell[] cells = result.rawCells();
                for (Cell cell : cells) {//获取行键,列簇,列,时间戳与值
                    String row = Bytes.toString(CellUtil.cloneRow(cell));//行键
                    String value = "value=" + Bytes.toString(CellUtil.cloneValue(cell));//值
                    String family = Bytes.toString(CellUtil.cloneFamily(cell));//列簇
                    String col = Bytes.toString(CellUtil.cloneQualifier(cell));//列名
                    String column = "column=" + family + ":" + col;//列簇与列
                    String timestamp = "timestamp=" + cell.getTimestamp();//时间戳
                    System.out.println(String.format("%s %s %s %s", row, column, timestamp, value));//格式化输出
                }
                return new Tuple2<String, Integer>(new String("test"), 1);//返回数据
            }
        });
        List<Tuple2<String, Integer>> collect = tuple2JavaRDD.collect();//算子计算
        sc.close();
    }

    /**
     * 字符串 过滤器
     *
     * @param scan
     * @return
     */
    public static String convertScanToString(Scan scan) {
        ClientProtos.Scan proto = null;
        try {
            proto = ProtobufUtil.toScan(scan);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return Base64.encodeBytes(proto.toByteArray());
    }
}

运行结果