Storm整合 HDFS/HBase

一、整合HDFS

新增hdfs的pom包

<?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>com</groupId>
    <artifactId>storm</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <storm.version>1.2.2</storm.version>
    </properties>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-core</artifactId>
            <version>1.2.2</version>
        </dependency>
        <!--Storm 整合 HDFS 依赖-->
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-hdfs</artifactId>
            <version>${storm.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0-cdh5.15.2</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-cdh5.15.2</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.15.2</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
    </dependencies>

    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
</project>

修改前面讲解的wordCount的示例

package example;

import org.apache.storm.Config;
import org.apache.storm.LocalCluster;
import org.apache.storm.StormSubmitter;
import org.apache.storm.generated.AlreadyAliveException;
import org.apache.storm.generated.AuthorizationException;
import org.apache.storm.generated.InvalidTopologyException;
import org.apache.storm.hdfs.bolt.HdfsBolt;
import org.apache.storm.hdfs.bolt.format.DefaultFileNameFormat;
import org.apache.storm.hdfs.bolt.format.DelimitedRecordFormat;
import org.apache.storm.hdfs.bolt.format.FileNameFormat;
import org.apache.storm.hdfs.bolt.format.RecordFormat;
import org.apache.storm.hdfs.bolt.rotation.FileRotationPolicy;
import org.apache.storm.hdfs.bolt.rotation.FileSizeRotationPolicy;
import org.apache.storm.hdfs.bolt.sync.CountSyncPolicy;
import org.apache.storm.hdfs.bolt.sync.SyncPolicy;
import org.apache.storm.topology.TopologyBuilder;

public class DataToHdfsApp {
    private static final String DATA_SOURCE_SPOUT = "dataSourceSpout";
    private static final String HDFS_BOLT = "hdfsBolt";
    public static void main(String[] args) {
        System.setProperty("HADOOP_USER_NAME","root" );
        //定义输出字段的分隔符
        RecordFormat recordFormat=new DelimitedRecordFormat()
                .withFieldDelimiter( "|" );
        //设置同步策略每200个Tuples从缓存刷新到Hdfs
        SyncPolicy syncPolicy=new CountSyncPolicy(200  );
        //文件策略:设置每个文件的上限为20M 超过限定则新建文件继续写入
        FileRotationPolicy rotationPolicy=new FileSizeRotationPolicy( 20.0f, FileSizeRotationPolicy.Units.MB );
        //定义存储路径
        FileNameFormat fileNameFormat=new DefaultFileNameFormat().withPath( "/storm/HdfsFile" );
        //定义HdfsBolt
        HdfsBolt hdfsBolt=new HdfsBolt()
                .withFsUrl( "hdfs://node01:8020" )
                .withFileNameFormat( fileNameFormat )
                .withRecordFormat( recordFormat )
                .withRotationPolicy( rotationPolicy )
                .withSyncPolicy( syncPolicy );
        //构建Topology
        TopologyBuilder topologyBuilder=new TopologyBuilder();
        topologyBuilder.setSpout( DATA_SOURCE_SPOUT,new StormWordCount());
        //保存至hdfs
        topologyBuilder.setBolt( HDFS_BOLT,hdfsBolt,1 ).shuffleGrouping( DATA_SOURCE_SPOUT );
        //判断是否外部传参
        if(args.length>0){
            try {
                StormSubmitter.submitTopology("ClusterDataToHdfsApp", new Config(), topologyBuilder.createTopology());
            } catch (AlreadyAliveException | InvalidTopologyException | AuthorizationException e) {
                e.printStackTrace();
            }
        }else{
            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology("LocalDataToHdfsApp",
                    new Config(), topologyBuilder.createTopology());
        }


    }
}

HDFS存储

二、整合HBase

引入相关依赖

 <!--Storm 整合 HBase 依赖-->
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-hbase</artifactId>
            <version>1.2.2</version>
        </dependency>

编写示例

/**
 * 产生词频样本的数据源
 */
public class DataSourceSpout extends BaseRichSpout {

    private List<String> list = Arrays.asList("Spark", "Hadoop", "HBase", "Storm", "Flink", "Hive");

    private SpoutOutputCollector spoutOutputCollector;

    @Override
    public void open(Map map, TopologyContext topologyContext, SpoutOutputCollector spoutOutputCollector) {
        this.spoutOutputCollector = spoutOutputCollector;
    }

    @Override
    public void nextTuple() {
        // 模拟产生数据
        String lineData = productData();
        spoutOutputCollector.emit(new Values(lineData));
        Utils.sleep(1000);
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
        outputFieldsDeclarer.declare(new Fields("line"));
    }


    /**
     * 模拟数据
     */
    private String productData() {
        Collections.shuffle(list);
        Random random = new Random();
        int endIndex = random.nextInt(list.size()) % (list.size()) + 1;
        return StringUtils.join(list.toArray(), "\t", 0, endIndex);
    }

}

//对数据进行处理 分割之类的操作
/**
 * 将每行数据按照指定分隔符进行拆分
 */
public class SplitBolt extends BaseRichBolt {

    private OutputCollector collector;

    @Override
    public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) {
        this.collector = collector;
    }

    @Override
    public void execute(Tuple input) {
        String line = input.getStringByField("line");
        String[] words = line.split("\t");
        for (String word : words) {
            collector.emit(tuple(word, 1));
        }
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("word", "count"));
    }
}
//对单词数据统计
public class CountBolt extends BaseRichBolt {

    private Map<String, Integer> counts = new HashMap<>();

    private OutputCollector collector;


    @Override
    public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) {
            this.collector=collector;
    }

    @Override
    public void execute(Tuple input) {
        String word = input.getStringByField("word");
        Integer count = counts.get(word);
        if (count == null) {
            count = 0;
        }
        count++;
        counts.put(word, count);
        // 输出
        collector.emit(new Values(word, String.valueOf(count)));

    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("word", "count"));
    }
}
//编写main方法
/**
 * 进行词频统计 并将统计结果存储到 HBase 中
 */
public class WordCountToHBaseApp {

    private static final String DATA_SOURCE_SPOUT = "dataSourceSpout";
    private static final String SPLIT_BOLT = "splitBolt";
    private static final String COUNT_BOLT = "countBolt";
    private static final String HBASE_BOLT = "hbaseBolt";

    public static void main(String[] args) {

        // storm 的配置
        Config config = new Config();

        // HBase 的配置
        Map<String, Object> hbConf = new HashMap<>();
        hbConf.put("hbase.rootdir", "hdfs://hadoop001:8020/hbase");
        hbConf.put("hbase.zookeeper.quorum", "hadoop001:2181");

        // 将 HBase 的配置传入 Storm 的配置中
        config.put("hbase.conf", hbConf);

        // 定义流数据与 HBase 中数据的映射
        SimpleHBaseMapper mapper = new SimpleHBaseMapper()
                .withRowKeyField("word")
                .withColumnFields(new Fields("word","count"))
                .withColumnFamily("info");

        /*
         * 给 HBaseBolt 传入表名、数据映射关系、和 HBase 的配置信息
         * 表需要预先创建: create 'WordCount','info'
         */
        HBaseBolt hbase = new HBaseBolt("WordCount", mapper)
                .withConfigKey("hbase.conf");

        // 构建 Topology
        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout(DATA_SOURCE_SPOUT, new DataSourceSpout(),1);
        // split
        builder.setBolt(SPLIT_BOLT, new SplitBolt(), 1).shuffleGrouping(DATA_SOURCE_SPOUT);
        // count
        builder.setBolt(COUNT_BOLT, new CountBolt(),1).shuffleGrouping(SPLIT_BOLT);
        // save to HBase
        builder.setBolt(HBASE_BOLT, hbase, 1).shuffleGrouping(COUNT_BOLT);


        // 如果外部传参 cluster 则代表线上环境启动,否则代表本地启动
        if (args.length > 0 && args[0].equals("cluster")) {
            try {
                StormSubmitter.submitTopology("ClusterWordCountToRedisApp", config, builder.createTopology());
            } catch (AlreadyAliveException | InvalidTopologyException | AuthorizationException e) {
                e.printStackTrace();
            }
        } else {
            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology("LocalWordCountToRedisApp",
                    config, builder.createTopology());
        }
    }
}

流程
DATA_SOURCE_SPOUT产生数据===>然后Split对数据进行分割 根据\t分割
COUNT_BOLT对数据进行统计统计完成之后把数据丢到HBase数据库