Java RecordFormat类代码示例

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
/**
 * Create bolt which will persist ticks to HDFS.
 */
private static HdfsBolt createHdfsBolt() {

  // Use "|" instead of "," for field delimiter:
  RecordFormat format = new DelimitedRecordFormat()
    .withFieldDelimiter("|");
  // sync the filesystem after every 1k tuples:
  SyncPolicy syncPolicy = new CountSyncPolicy(100);

  // Rotate files when they reach 5MB:
  FileRotationPolicy rotationPolicy = 
    new FileSizeRotationPolicy(5.0f, Units.MB);

  // Write records to <user>/stock-ticks/ directory in HDFS:
  FileNameFormat fileNameFormat = new DefaultFileNameFormat()
    .withPath("stock-ticks/");

  HdfsBolt hdfsBolt = new HdfsBolt()
    .withFsUrl("hdfs://localhost:8020")
    .withFileNameFormat(fileNameFormat)
    .withRecordFormat(format)
    .withRotationPolicy(rotationPolicy)
    .withSyncPolicy(syncPolicy);

  return hdfsBolt;
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
private static HdfsBolt createHdfsBolt() {
    // use "|" instead of "," for field delimiter
    RecordFormat format = new DelimitedRecordFormat()
            .withFieldDelimiter("|");

    // sync the filesystem after every 1k tuples
    SyncPolicy syncPolicy = new CountSyncPolicy(1000);

    // rotate files when they reach 5MB
    FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(5.0f, FileSizeRotationPolicy.Units.MB);

    FileNameFormat fileNameFormat = new DefaultFileNameFormat()
            .withPath(Properties.getString("sa.storm.hdfs_output_file"));

    return new HdfsBolt()
            .withFsUrl(Properties.getString("sa.storm.hdfs_url"))
            .withFileNameFormat(fileNameFormat)
            .withRecordFormat(format)
            .withRotationPolicy(rotationPolicy)
            .withSyncPolicy(syncPolicy);
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public HdfsBolt getHdfsBolt() {

        LOG.info("HDFSBOLT: Configuring the HdfsBolt");

        // Define the RecordFormat, SyncPolicy, and FileNameFormat
        RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(fieldDelimiter);
        SyncPolicy syncPolicy = new CountSyncPolicy(syncCount);
        FileNameFormat fileNameFormat = new DefaultFileNameFormat().withPath(outputLocation);

        // Configure the Bolt
        return new HdfsBolt()
                .withFsUrl(hdfsDefaultFs)
                .withFileNameFormat(fileNameFormat)
                .withRecordFormat(format)
                .withRotationPolicy(fileRotationPolicy)
                .withSyncPolicy(syncPolicy);

    }
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public static HdfsBolt getHdfsBolt(String fsUrl, String srcDir, String rotationDir) {
    // sync the filesystem after every tuple
    SyncPolicy syncPolicy = new CountSyncPolicy(1);

    FileNameFormat fileNameFormat = new DefaultFileNameFormat()
            .withPath(srcDir)
            .withExtension(".txt");

    RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(",");
    FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(1f, FileSizeRotationPolicy.Units.KB);

    HdfsBolt bolt = new HdfsBolt()
            .withFsUrl(fsUrl)
            .withFileNameFormat(fileNameFormat)
            .withRecordFormat(format)
            .withSyncPolicy(syncPolicy)
            .withRotationPolicy(rotationPolicy)
            .addRotationAction(new MoveFileAction().toDestination(rotationDir));

    return bolt;
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public static void configureHdfsBolt(TopologyBuilder builder, 
                                     String delimiter, 
                                     String outputPath, 
                                     String hdfsUri,
                                     String hdfsBoltName, 
                                     String spoutName,
                                     int parallelismHint,
                                     FileRotationPolicy rotationPolicy,
                                     int syncCount) {
    
    LOG.info("HDFSBOLT: Configuring the HdfsBolt");
    
    // Define the RecordFormat, SyncPolicy, and FileNameFormat
    RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(delimiter);
    SyncPolicy syncPolicy = new CountSyncPolicy(syncCount);
    FileNameFormat fileNameFormat = new DefaultFileNameFormat().withPath(outputPath);
    
    // Configure the Bolt
    HdfsBolt bolt = new HdfsBolt()
            .withFsUrl(hdfsUri)
            .withFileNameFormat(fileNameFormat)
            .withRecordFormat(format)
            .withRotationPolicy(rotationPolicy)
            .withSyncPolicy(syncPolicy);
    
    // Set the Bolt
    builder.setBolt(hdfsBoltName, bolt, parallelismHint).shuffleGrouping(spoutName);

}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public static void configureHdfsBolt(TopologyBuilder builder, String delimiter, String outputPath, String hdfsUri) {
    RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(delimiter);
    SyncPolicy syncPolicy = new CountSyncPolicy(1000);
    //FileRotationPolicy rotationPolicy = new TimedRotationPolicy(300, TimedRotationPolicy.TimeUnit.SECONDS);
    FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(1, FileSizeRotationPolicy.Units.KB);
    FileNameFormat fileNameFormat = new DefaultFileNameFormat().withPath(outputPath);
    HdfsBolt bolt = new HdfsBolt()
            .withFsUrl(hdfsUri)
            .withFileNameFormat(fileNameFormat)
            .withRecordFormat(format)
            .withRotationPolicy(rotationPolicy)
            .withSyncPolicy(syncPolicy);
    builder.setBolt("hdfsbolt", bolt, 1).shuffleGrouping("kafkaspout");

}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public static void main(String[] args) {
    try{
        String zkhost = "wxb-1:2181,wxb-2:2181,wxb-3:2181";
        String topic = "order";
        String groupId = "id";
        int spoutNum = 3;
        int boltNum = 1;
        ZkHosts zkHosts = new ZkHosts(zkhost);//kafaka所在的zookeeper
        SpoutConfig spoutConfig = new SpoutConfig(zkHosts, topic, "/order", groupId);  // create /order /id
        spoutConfig.scheme = new SchemeAsMultiScheme(new StringScheme());
        KafkaSpout kafkaSpout = new KafkaSpout(spoutConfig);

        // HDFS bolt
        // use "|" instead of "," for field delimiter
        RecordFormat format = new DelimitedRecordFormat()
                .withFieldDelimiter("|");

        // sync the filesystem after every 1k tuples
        SyncPolicy syncPolicy = new CountSyncPolicy(1000);

        // rotate files when they reach 5MB
        FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(5.0f, FileSizeRotationPolicy.Units.MB);
        // FileRotationPolicy rotationPolicy = new TimedRotationPolicy(1.0f, TimedRotationPolicy.TimeUnit.MINUTES);

        FileNameFormat fileNameFormat = new DefaultFileNameFormat()
                .withPath("/tmp/").withPrefix("order_").withExtension(".log");

        HdfsBolt hdfsBolt = new HdfsBolt()
                .withFsUrl("hdfs://wxb-1:8020")
                .withFileNameFormat(fileNameFormat)
                .withRecordFormat(format)
                .withRotationPolicy(rotationPolicy)
                .withSyncPolicy(syncPolicy);

        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout("spout", kafkaSpout, spoutNum);
        builder.setBolt("check", new CheckOrderBolt(), boltNum).shuffleGrouping("spout");
        builder.setBolt("counter", new CounterBolt(),boltNum).shuffleGrouping("check");
        builder.setBolt("hdfs", hdfsBolt,boltNum).shuffleGrouping("counter");

        Config config = new Config();
        config.setDebug(true);

        if(args!=null && args.length > 0) {
            config.setNumWorkers(2);
            StormSubmitter.submitTopology(args[0], config, builder.createTopology());
        } else {
            config.setMaxTaskParallelism(2);

            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology("Wordcount-Topology", config, builder.createTopology());

            Thread.sleep(500000);

            cluster.shutdown();
        }
    }catch (Exception e) {
        e.printStackTrace();
    }
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public void configureHDFSBolt(TopologyBuilder builder) {
  // Use pipe as record boundary

  String rootPath = topologyConfig.getProperty("hdfs.path");
  String prefix = topologyConfig.getProperty("hdfs.file.prefix");
  String fsUrl = topologyConfig.getProperty("hdfs.url");
  String sourceMetastoreUrl = topologyConfig.getProperty("hive.metastore.url");
  String hiveStagingTableName = topologyConfig.getProperty("hive.staging.table.name");
  String databaseName = topologyConfig.getProperty("hive.database.name");
  Float rotationTimeInMinutes = Float.valueOf(topologyConfig.getProperty("hdfs.file.rotation.time.minutes"));

  RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(",");

  //Synchronize data buffer with the filesystem every 1000 tuples
  SyncPolicy syncPolicy = new CountSyncPolicy(1000);

  // Rotate data files when they reach five MB
  //FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(5.0f, Units.MB);

  //Rotate every X minutes
  FileTimeRotationPolicy rotationPolicy = new FileTimeRotationPolicy(rotationTimeInMinutes, FileTimeRotationPolicy
      .Units.MINUTES);

  //Hive Partition Action
  HiveTablePartitionAction hivePartitionAction = new HiveTablePartitionAction(sourceMetastoreUrl,
      hiveStagingTableName, databaseName, fsUrl);

  //MoveFileAction moveFileAction = new MoveFileAction().toDestination(rootPath + "/working");


  FileNameFormat fileNameFormat = new DefaultFileNameFormat()
      .withPath(rootPath + "/staging")
      .withPrefix(prefix);

  // Instantiate the HdfsBolt
  HdfsBolt hdfsBolt = new HdfsBolt()
      .withFsUrl(fsUrl)
      .withFileNameFormat(fileNameFormat)
      .withRecordFormat(format)
      .withRotationPolicy(rotationPolicy)
      .withSyncPolicy(syncPolicy)
      .addRotationAction(hivePartitionAction);

  int hdfsBoltCount = Integer.valueOf(topologyConfig.getProperty("hdfsbolt.thread.count"));
  builder.setBolt("hdfs_bolt", hdfsBolt, hdfsBoltCount).shuffleGrouping("kafkaSpout");
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
private boolean initializeHDFSBolt(String topology_name, String name) {
	try {

		String messageUpstreamComponent = messageComponents
				.get(messageComponents.size() - 1);

		System.out.println("[OpenSOC] ------" + name
				+ " is initializing from " + messageUpstreamComponent);

		RecordFormat format = new DelimitedRecordFormat()
				.withFieldDelimiter(
						config.getString("bolt.hdfs.field.delimiter")
								.toString()).withFields(
						new Fields("message"));

		// sync the file system after every x number of tuples
		SyncPolicy syncPolicy = new CountSyncPolicy(Integer.valueOf(config
				.getString("bolt.hdfs.batch.size").toString()));

		// rotate files when they reach certain size
		FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(
				Float.valueOf(config.getString(
						"bolt.hdfs.file.rotation.size.in.mb").toString()),
				Units.MB);

		FileNameFormat fileNameFormat = new DefaultFileNameFormat()
				.withPath(config.getString("bolt.hdfs.wip.file.path")
						.toString());

		// Post rotate action
		MoveFileAction moveFileAction = (new MoveFileAction())
				.toDestination(config.getString(
						"bolt.hdfs.finished.file.path").toString());

		HdfsBolt hdfsBolt = new HdfsBolt()
				.withFsUrl(
						config.getString("bolt.hdfs.file.system.url")
								.toString())
				.withFileNameFormat(fileNameFormat)
				.withRecordFormat(format)
				.withRotationPolicy(rotationPolicy)
				.withSyncPolicy(syncPolicy)
				.addRotationAction(moveFileAction);
		if (config.getString("bolt.hdfs.compression.codec.class") != null) {
			hdfsBolt.withCompressionCodec(config.getString(
					"bolt.hdfs.compression.codec.class").toString());
		}

		builder.setBolt(name, hdfsBolt,
				config.getInt("bolt.hdfs.parallelism.hint"))
				.shuffleGrouping(messageUpstreamComponent, "message")
				.setNumTasks(config.getInt("bolt.hdfs.num.tasks"));

	} catch (Exception e) {
		e.printStackTrace();
		System.exit(0);
	}

	return true;
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public void configureHDFSBolt(TopologyBuilder builder) {
	// Use pipe as record boundary
	
	String rootPath = topologyConfig.getProperty("hdfs.path");
	String prefix = topologyConfig.getProperty("hdfs.file.prefix");
	String fsUrl = topologyConfig.getProperty("hdfs.url");
	String sourceMetastoreUrl = topologyConfig.getProperty("hive.metastore.url");
	String hiveStagingTableName = topologyConfig.getProperty("hive.staging.table.name");
	String databaseName = topologyConfig.getProperty("hive.database.name");
	Float rotationTimeInMinutes = Float.valueOf(topologyConfig.getProperty("hdfs.file.rotation.time.minutes"));
	
	RecordFormat format = new DelimitedRecordFormat().withFieldDelimiter(",");

	//Synchronize data buffer with the filesystem every 1000 tuples
	SyncPolicy syncPolicy = new CountSyncPolicy(1000);

	// Rotate data files when they reach five MB
	//FileRotationPolicy rotationPolicy = new FileSizeRotationPolicy(5.0f, Units.MB);
	
	//Rotate every X minutes
	FileTimeRotationPolicy rotationPolicy = new FileTimeRotationPolicy(rotationTimeInMinutes, FileTimeRotationPolicy.Units.MINUTES);
	
	//Hive Partition Action
	HiveTablePartitionAction hivePartitionAction = new HiveTablePartitionAction(sourceMetastoreUrl, hiveStagingTableName, databaseName, fsUrl);
	
	//MoveFileAction moveFileAction = new MoveFileAction().toDestination(rootPath + "/working");


	
	FileNameFormat fileNameFormat = new DefaultFileNameFormat()
			.withPath(rootPath + "/staging")
			.withPrefix(prefix);

	// Instantiate the HdfsBolt
	HdfsBolt hdfsBolt = new HdfsBolt()
			 .withFsUrl(fsUrl)
	         .withFileNameFormat(fileNameFormat)
	         .withRecordFormat(format)
	         .withRotationPolicy(rotationPolicy)
	         .withSyncPolicy(syncPolicy)
	         .addRotationAction(hivePartitionAction);
	
	int hdfsBoltCount = Integer.valueOf(topologyConfig.getProperty("hdfsbolt.thread.count"));
	builder.setBolt("hdfs_bolt", hdfsBolt, hdfsBoltCount).shuffleGrouping("kafkaSpout");
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public HdfsBolt withRecordFormat(RecordFormat format){
    this.format = format;
    return this;
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
    Config config = new Config();
    config.setNumWorkers(1);

    SentenceSpout spout = new SentenceSpout();

    // sync the filesystem after every 1k tuples
    SyncPolicy syncPolicy = new CountSyncPolicy(1000);

    // rotate files when they reach 5MB
    FileRotationPolicy rotationPolicy = new TimedRotationPolicy(1.0f, TimedRotationPolicy.TimeUnit.MINUTES);

    FileNameFormat fileNameFormat = new DefaultFileNameFormat()
            .withPath("/foo/")
            .withExtension(".txt");



    // use "|" instead of "," for field delimiter
    RecordFormat format = new DelimitedRecordFormat()
            .withFieldDelimiter("|");

    Yaml yaml = new Yaml();
    InputStream in = new FileInputStream(args[1]);
    Map<String, Object> yamlConf = (Map<String, Object>) yaml.load(in);
    in.close();
    config.put("hdfs.config", yamlConf);

    HdfsBolt bolt = new HdfsBolt()
            .withConfigKey("hdfs.config")
            .withFsUrl(args[0])
            .withFileNameFormat(fileNameFormat)
            .withRecordFormat(format)
            .withRotationPolicy(rotationPolicy)
            .withSyncPolicy(syncPolicy)
            .addRotationAction(new MoveFileAction().toDestination("/dest2/"));

    TopologyBuilder builder = new TopologyBuilder();

    builder.setSpout(SENTENCE_SPOUT_ID, spout, 1);
    // SentenceSpout --> MyBolt
    builder.setBolt(BOLT_ID, bolt, 4)
            .shuffleGrouping(SENTENCE_SPOUT_ID);

    if (args.length == 2) {
        LocalCluster cluster = new LocalCluster();

        cluster.submitTopology(TOPOLOGY_NAME, config, builder.createTopology());
        waitForSeconds(120);
        cluster.killTopology(TOPOLOGY_NAME);
        cluster.shutdown();
        System.exit(0);
    } else if (args.length == 3) {
        StormSubmitter.submitTopology(args[0], config, builder.createTopology());
    } else{
        System.out.println("Usage: HdfsFileTopology [topology name] <yaml config file>");
    }
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public GzippedRecordFormat(RecordFormat format) {
    baseFormat = format;
}
 

import org.apache.storm.hdfs.bolt.format.RecordFormat; //导入依赖的package包/类
public GzipHdfsBolt withRecordFormat(RecordFormat format) {
    this.format = new GzippedRecordFormat(format);
    return this;
}