Java SparkConf类代码示例

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) {
		System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils");
		SparkConf conf =new SparkConf().setMaster("local").setAppName("S3 Example");
		JavaSparkContext jsc=new JavaSparkContext(conf);
		//jsc.hadoopConfiguration().set("fs.s3n.awsAccessKeyId", "Your awsAccessKeyId");
		//jsc.hadoopConfiguration().set("fs.s3n.awsSecretAccessKey", "your awsSecretAccessKey");
		
		
		System.out.println(System.getenv("AWS_ACCESS_KEY_ID"));
		JavaRDD<String> textFile = jsc.textFile("s3a://"+"trust"+"/"+"MOCK_DATA.csv");
		
//		textFile.flatMap(x -> Arrays.asList(x.split(",")).iterator()).mapToPair(x -> new Tuple2<String, Integer>((String) x, 1))
//		.reduceByKey((x, y) -> x + y).saveAsTextFile("s3n://"+"trust"+"/"+"out.txt");
		
		textFile.flatMap(x -> Arrays.asList(x.split(",")).iterator()).mapToPair(x -> new Tuple2<String, Integer>((String) x, 1))
		.reduceByKey((x, y) -> x + y).saveAsTextFile("s3a://"+"trust"+"/"+"out.txt");
	}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) {

        SparkConf conf = new SparkConf()
                .setAppName("kafka-sandbox")
                .setMaster("local[*]");
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaStreamingContext ssc = new JavaStreamingContext(sc, new Duration(2000));

        Set<String> topics = Collections.singleton("mytopic");
        Map<String, String> kafkaParams = new HashMap<>();
        kafkaParams.put("metadata.broker.list", "localhost:9092");

        JavaPairInputDStream<String, String> directKafkaStream = KafkaUtils.createDirectStream(ssc,
                String.class, String.class, StringDecoder.class, StringDecoder.class, kafkaParams, topics);

        directKafkaStream.foreachRDD(rdd -> {
            System.out.println("--- New RDD with " + rdd.partitions().size()
                    + " partitions and " + rdd.count() + " records");
            rdd.foreach(record -> System.out.println(record._2));
        });

        ssc.start();
        ssc.awaitTermination();
    }
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) {
    if (args.length != 2) {
        System.err.println("Usage:");
        System.err.println("  SparkWordCount <sourceFile> <targetFile>");
        System.exit(1);
    }

    SparkConf conf = new SparkConf()
            .setAppName("Word Count");
    JavaSparkContext sc = new JavaSparkContext(conf);
    JavaRDD<String> textFile = sc.textFile(args[0]);
    JavaRDD<String> words = textFile.flatMap(LineIterator::new);
    JavaPairRDD<String, Long> pairs =
            words.mapToPair(s -> new Tuple2<>(s, 1L));
    JavaPairRDD<String, Long> counts =
            pairs.reduceByKey((Function2<Long, Long, Long>) (a, b) -> a + b);

    System.out.println("Starting task..");
    long t = System.currentTimeMillis();
    counts.saveAsTextFile(args[1] + "_" + t);
    System.out.println("Time=" + (System.currentTimeMillis() - t));
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws InterruptedException {
  SparkConf sc = new SparkConf().setAppName("POC-Kafka-New");
  
  try(JavaStreamingContext jsc = new JavaStreamingContext(sc, new Duration(2000))) {
    
    JavaPairInputDStream<String, String> stream = KafkaUtils.createDirectStream(
        jsc, String.class, String.class, StringDecoder.class, StringDecoder.class,
        Collections.singletonMap("metadata.broker.list", KAFKA_HOST_PORT),
        Collections.singleton(EXAMPLE_TOPIC));

    JavaDStream<ExampleXML> records = stream.map(t -> t._2()).map(new ParseXML());
    records.foreachRDD(rdd -> System.out.printf("Amount of XMLs: %d\n", rdd.count()));

    jsc.start();
    jsc.awaitTermination();
  }
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws InterruptedException {
  SparkConf sc = new SparkConf().setAppName("POC-Streaming");
  try(JavaStreamingContext jsc = new JavaStreamingContext(sc, new Duration(2000))) {
    //JavaDStream<SampleXML> records = jsc.textFileStream("input/").map(new ParseXML());
    //textFileStream process lines of files, so xml has to be 1 line to work //alternative below

    JavaRDD<String> files = jsc.sparkContext().wholeTextFiles("input/").map(tuple -> tuple._2());
    Queue<JavaRDD<String>> rddQueue = new LinkedList<>();
    rddQueue.add(files);
    JavaDStream<String> records = jsc.queueStream(rddQueue);

    records.foreachRDD(rdd -> System.out.printf("Amount of XMLs: %d\n", rdd.count()));

    jsc.start();
    jsc.awaitTermination();
  }
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws InterruptedException, IOException {
  SparkConf sc = new SparkConf().setAppName("POC-BigQuery");
  
  try(JavaStreamingContext jsc = new JavaStreamingContext(sc, new Duration(60000))) {
    JavaPairInputDStream<String, String> stream = KafkaUtils.createDirectStream(
        jsc, String.class, String.class, StringDecoder.class, StringDecoder.class,
        Collections.singletonMap("metadata.broker.list", KAFKA_HOST_PORT), Collections.singleton(EXAMPLE_TOPIC));

    Configuration conf = new Configuration();
    BigQueryConfiguration.configureBigQueryOutput(conf, BQ_EXAMPLE_TABLE, BQ_EXAMPLE_SCHEMA);
    conf.set("mapreduce.job.outputformat.class", BigQueryOutputFormat.class.getName());

    JavaDStream<ExampleXML> records = stream.map(t -> t._2()).map(new ParseXML());
    records.foreachRDD(rdd -> {
      System.out.printf("Amount of XMLs: %d\n", rdd.count());
      long time = System.currentTimeMillis();
      rdd.mapToPair(new PrepToBQ()).saveAsNewAPIHadoopDataset(conf);
      System.out.printf("Sent to BQ in %fs\n", (System.currentTimeMillis()-time)/1000f);
    });
    
    jsc.start();
    jsc.awaitTermination();
  }
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void wordCountJava8( String filename )
{
    // Define a configuration to use to interact with Spark
    SparkConf conf = new SparkConf().setMaster("local").setAppName("Work Count App");

    // Create a Java version of the Spark Context from the configuration
    JavaSparkContext sc = new JavaSparkContext(conf);

    // Load the input data, which is a text file read from the command line
    JavaRDD<String> input = sc.textFile( filename );

    // Java 8 with lambdas: split the input string into words
   // TODO here a change has happened 
    JavaRDD<String> words = input.flatMap( s -> Arrays.asList( s.split( " " ) ).iterator() );

    // Java 8 with lambdas: transform the collection of words into pairs (word and 1) and then count them
    JavaPairRDD<Object, Object> counts = words.mapToPair( t -> new Tuple2( t, 1 ) ).reduceByKey( (x, y) -> (int)x + (int)y );

    // Save the word count back out to a text file, causing evaluation.
    counts.saveAsTextFile( "output" );
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
@Test
public void test() {
    String hdfsPath = "hdfs://10.196.83.90:9000/stonk/spark/aa/spark-task--aa-b5x59zpv/out3";

    SparkConf conf = new SparkConf().setAppName("111").setMaster("local[3]");
    JavaSparkContext context = new JavaSparkContext(conf);
    JavaRDD<String> rdd = context.textFile(hdfsPath);
    rdd.foreach((str) -> System.out.println(str));
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
/**
 * Initializes a Spark connection. Use it afterwards for execution of Spark
 * SQL queries.
 * 
 * @param appName
 *            the name of the app that will be used with this Spark
 *            connection
 * @param database
 *            name of the database that will be used with this Spark
 *            connection
 */
public Spark(String appName, String database) {

	// TODO check what will happen if there is already in use the same app
	// name
	this.sparkConfiguration = new SparkConf().setAppName(appName);
	this.javaContext = new JavaSparkContext(sparkConfiguration);
	this.hiveContext = new HiveContext(javaContext);
	// TODO check what kind of exception can be thrown here if there is a
	// problem with spark connection

	this.hiveContext.sql(String.format("CREATE DATABASE %s", database));
	// TODO check what kind of exception is thrown if database already

	// use the created database
	this.hiveContext.sql((String.format("USE %s", database)));
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws Exception {

    if (args.length != 1) {
      System.err.println("Usage: JavaSleep <seconds>");
      System.exit(1);
    }

    SparkConf sparkConf = new SparkConf().setAppName("JavaSleep");
    JavaSparkContext ctx = new JavaSparkContext(sparkConf);
    Integer parallel = sparkConf.getInt("spark.default.parallelism", ctx.defaultParallelism());
    Integer seconds = Integer.parseInt(args[0]);

    Integer[] init_val = new Integer[parallel];
    Arrays.fill(init_val, seconds);

    JavaRDD<Integer> workload = ctx.parallelize(Arrays.asList(init_val), parallel).map(new Function<Integer, Integer>() {
      @Override
      public Integer call(Integer s) throws InterruptedException {
	    Thread.sleep(s * 1000);
        return 0;
      }
    });

    List<Integer> output = workload.collect();
    ctx.stop();
  }
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
	Flags.setFromCommandLineArgs(THE_OPTIONS, args);

	// 初始化Spark Conf.
	SparkConf conf = new SparkConf().setAppName("A SECTONG Application: Apache Log Analysis with Spark");
	JavaSparkContext sc = new JavaSparkContext(conf);
	JavaStreamingContext jssc = new JavaStreamingContext(sc, Flags.getInstance().getSlideInterval());
	SQLContext sqlContext = new SQLContext(sc);

	// 初始化参数
	HashSet<String> topicsSet = new HashSet<String>(Arrays.asList(Flags.getInstance().getKafka_topic().split(",")));
	HashMap<String, String> kafkaParams = new HashMap<String, String>();
	kafkaParams.put("metadata.broker.list", Flags.getInstance().getKafka_broker());

	// 从Kafka Stream获取数据
	JavaPairInputDStream<String, String> messages = KafkaUtils.createDirectStream(jssc, String.class, String.class,
			StringDecoder.class, StringDecoder.class, kafkaParams, topicsSet);

	JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() {
		private static final long serialVersionUID = 5266880065425088203L;

		public String call(Tuple2<String, String> tuple2) {
			return tuple2._2();
		}
	});

	JavaDStream<ApacheAccessLog> accessLogsDStream = lines.flatMap(line -> {
		List<ApacheAccessLog> list = new ArrayList<>();
		try {
			// 映射每一行
			list.add(ApacheAccessLog.parseFromLogLine(line));
			return list;
		} catch (RuntimeException e) {
			return list;
		}
	}).cache();

	accessLogsDStream.foreachRDD(rdd -> {

		// rdd to DataFrame
		DataFrame df = sqlContext.createDataFrame(rdd, ApacheAccessLog.class);
		// 写入Parquet文件
		df.write().partitionBy("ipAddress", "method", "responseCode").mode(SaveMode.Append).parquet(Flags.getInstance().getParquetFile());

		return null;
	});

	// 启动Streaming服务器
	jssc.start(); // 启动计算
	jssc.awaitTermination(); // 等待终止
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) 
{
 SparkConf conf = new SparkConf();
 conf.setAppName("Wordcount Background");
 conf.setMaster("local");
  
 
 JavaStreamingContext ssc = new JavaStreamingContext(conf, Durations.seconds(15));
 
 
 JavaDStream<String> lines = ssc.textFileStream("/home/rahul/DATASET");
 JavaDStream<String> words = lines.flatMap(WORDS_EXTRACTOR);
 JavaPairDStream<String, Integer> pairs = words.mapToPair(WORDS_MAPPER);
 JavaPairDStream<String, Integer> counter = pairs.reduceByKey(WORDS_REDUCER);
 
 counter.print();
 
 ssc.start();
 
 ssc.awaitTermination();
 

 /*JavaRDD<String> file = context.textFile("/home/rahul/Desktop/palestine.txt");
 JavaRDD<String> words = file.flatMap(WORDS_EXTRACTOR);
 JavaPairRDD<String, Integer> pairs = words.mapToPair(WORDS_MAPPER);
 JavaPairRDD<String, Integer> counter = pairs.reduceByKey(WORDS_REDUCER);
 counter.saveAsTextFile("/home/rahul/Desktop/wc"); 
 context.close();*/
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws InterruptedException {
    Map<String, Object> kafkaParams = new HashMap<>();
    kafkaParams.put("bootstrap.servers", "localhost:9092");
    kafkaParams.put("key.deserializer", StringDeserializer.class);
    kafkaParams.put("value.deserializer", StringDeserializer.class);
    kafkaParams.put("group.id", "use_a_separate_group_id_for_each_stream");
    kafkaParams.put("auto.offset.reset", "latest");
    kafkaParams.put("enable.auto.commit", false);

    Collection<String> topics = Arrays.asList("data-in");

    SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaSpark");
    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(5));

    final JavaInputDStream<ConsumerRecord<String, String>> stream =
            KafkaUtils.createDirectStream(
                    streamingContext,
                    LocationStrategies.PreferConsistent(),
                    ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams)
            );

    JavaPairDStream<String, Integer>  countOfMessageKeys = stream
            .map((ConsumerRecord<String, String> record) -> record.key())
            .mapToPair((String s) -> new Tuple2<>(s, 1))
            .reduceByKey((Integer i1, Integer i2)-> i1 + i2);

    countOfMessageKeys.print();

    // Start the computation
    streamingContext.start();
    streamingContext.awaitTermination();
}
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws IOException {

        if (args.length < 1) {
            System.err.println("Usage: RepartitionFastq <input path> <output path> <number of partitions>");
            System.exit(1);
        }

        SparkConf conf = new SparkConf().setAppName("RepartitionFastq");
        //conf.set("spark.default.parallelism", String.valueOf(args[2]));
        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaPairRDD<Text, SequencedFragment> fastqRDD = sc.newAPIHadoopFile(args[0], FastqInputFormat.class, Text.class, SequencedFragment.class, sc.hadoopConfiguration());

        JavaPairRDD<Text, SequencedFragment> repartitioned = fastqRDD.repartition(Integer.valueOf(args[2]));

        repartitioned.saveAsNewAPIHadoopFile(args[1], Text.class, SequencedFragment.class, FastqOutputFormat.class, sc.hadoopConfiguration());

        sc.stop();
    }
 

import org.apache.spark.SparkConf; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
    Options options = new Options();
    Option pathOpt = new Option( "in", true, "Path to fastq file in hdfs." );
    Option opOpt = new Option( "out", true, "HDFS path for output files. If not present, the output files are not moved to HDFS." );
    options.addOption(  new Option( "partitions", "Divide or merge to n partitions" ) );
    options.addOption( pathOpt );
    options.addOption( opOpt );

    CommandLineParser parser = new BasicParser();
    CommandLine cmd = null;
    try {
        // parse the command line arguments
        cmd = parser.parse( options, args );

    }
    catch( ParseException exp ) {
        // oops, something went wrong
        System.err.println( "Parsing failed.  Reason: " + exp.getMessage() );
    }

    String out = (cmd.hasOption("out")==true)? cmd.getOptionValue("out"):null;
    String in = (cmd.hasOption("in")==true)? cmd.getOptionValue("in"):null;
    String partitions = (cmd.hasOption("partitions")==true)? cmd.getOptionValue("partitions"):null;

    SparkConf conf = new SparkConf().setAppName("SplitFasta");
    JavaSparkContext sc = new JavaSparkContext(conf);
    sc.hadoopConfiguration().set("textinputformat.record.delimiter", ">");

    JavaRDD<String> rdd = sc.textFile(in);
    JavaRDD<String> crdd = rdd.map(v->">"+v.trim()).repartition(Integer.valueOf(partitions));

    crdd.saveAsTextFile(out);
    sc.stop();
}