SparkStreaming与Kafka整合遇到的问题及解决方案

    SparkConf sparkConf = new SparkConf().setAppName("log-etl").setMaster("local[4]");
    JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(2000));
    int numThreads = Integer.parseInt("4");
    Map<String, Integer> topicMap = new HashMap<String, Integer>();
    topicMap.put("group-45", numThreads);
     //接收的参数分别是JavaStreamingConetxt,zookeeper连接地址,groupId,kafak的topic 
    JavaPairReceiverInputDStream<String, String> messages =
    KafkaUtils.createStream(jssc, "172.16.206.27:2181,172.16.206.28:2181,172.16.206.29:2181", "1", topicMap);

SparkConf sparkConf = new SparkConf().setAppName("log-etl");
JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, Durations.seconds(2));

HashSet<String> topicsSet = new HashSet<String>(Arrays.asList(topics.split(",")));
HashMap<String, String> kafkaParams = new HashMap<String, String>();
kafkaParams.put("metadata.broker.list", brokers);
// Create direct kafka stream with brokers and topics
JavaPairInputDStream<String, String> messages = KafkaUtils.createDirectStream(
    jssc,
    String.class,
    String.class,
    StringDecoder.class,
    StringDecoder.class,
    kafkaParams,
    topicsSet
);

SparkConf sparkConf = new SparkConf().setMaster("local[2]").setAppName("log-etl");
 Set<String> topicSet = new HashSet<String>();
        topicSet.add("group-45");
        kafkaParam.put("metadata.broker.list", "172.16.206.17:9092,172.16.206.31:9092,172.16.206.32:9092");
        kafkaParam.put("group.id", "simple1");

        // transform java Map to scala immutable.map
        scala.collection.mutable.Map<String, String> testMap = JavaConversions.mapAsScalaMap(kafkaParam);
        scala.collection.immutable.Map<String, String> scalaKafkaParam =
                testMap.toMap(new Predef.$less$colon$less<Tuple2<String, String>, Tuple2<String, String>>() {
                    public Tuple2<String, String> apply(Tuple2<String, String> v1) {
                        return v1;
                    }
                });

        // init KafkaCluster
        kafkaCluster = new KafkaCluster(scalaKafkaParam);

        scala.collection.mutable.Set<String> mutableTopics = JavaConversions.asScalaSet(topicSet);
        immutableTopics = mutableTopics.toSet();
        scala.collection.immutable.Set<TopicAndPartition> topicAndPartitionSet2 = kafkaCluster.getPartitions(immutableTopics).right().get();

        // kafka direct stream 初始化时使用的offset数据
        Map<TopicAndPartition, Long> consumerOffsetsLong = new HashMap<TopicAndPartition, Long>();

        // 没有保存offset时（该group首次消费时）, 各个partition offset 默认为0
        if (kafkaCluster.getConsumerOffsets(kafkaParam.get("group.id"), topicAndPartitionSet2).isLeft()) {

            System.out.println(kafkaCluster.getConsumerOffsets(kafkaParam.get("group.id"), topicAndPartitionSet2).left().get());

            Set<TopicAndPartition> topicAndPartitionSet1 = JavaConversions.setAsJavaSet((scala.collection.immutable.Set)topicAndPartitionSet2);

            for (TopicAndPartition topicAndPartition : topicAndPartitionSet1) {
                consumerOffsetsLong.put(topicAndPartition, 0L);
            }

        }
        // offset已存在, 使用保存的offset
        else {

            scala.collection.immutable.Map<TopicAndPartition, Object> consumerOffsetsTemp = kafkaCluster.getConsumerOffsets("simple1", topicAndPartitionSet2).right().get();

            Map<TopicAndPartition, Object> consumerOffsets = JavaConversions.mapAsJavaMap((scala.collection.immutable.Map)consumerOffsetsTemp);

            Set<TopicAndPartition> topicAndPartitionSet1 = JavaConversions.setAsJavaSet((scala.collection.immutable.Set)topicAndPartitionSet2);

            for (TopicAndPartition topicAndPartition : topicAndPartitionSet1) {
                Long offset = (Long)consumerOffsets.get(topicAndPartition);
                consumerOffsetsLong.put(topicAndPartition, offset);
            }

        }

        JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(5000));
        kafkaParamBroadcast = jssc.sparkContext().broadcast(kafkaParam);

        // create direct stream
        JavaInputDStream<String> message = KafkaUtils.createDirectStream(
                jssc,
                String.class,
                String.class,
                StringDecoder.class,
                StringDecoder.class,
                String.class,
                kafkaParam,
                consumerOffsetsLong,
                new Function<MessageAndMetadata<String, String>, String>() {
                    public String call(MessageAndMetadata<String, String> v1) throws Exception {
                        System.out.println("接收到的数据《《==="+v1.message());
                        return v1.message();
                    }
                }
        );

        // 得到rdd各个分区对应的offset, 并保存在offsetRanges中
        final AtomicReference<OffsetRange[]> offsetRanges = new AtomicReference<OffsetRange[]>();

        JavaDStream<String> javaDStream = message.transform(new Function<JavaRDD<String>, JavaRDD<String>>() {
            public JavaRDD<String> call(JavaRDD<String> rdd) throws Exception {
                OffsetRange[] offsets = ((HasOffsetRanges) rdd.rdd()).offsetRanges();
                offsetRanges.set(offsets);
                return rdd;
            }
        });

        // output
        javaDStream.foreachRDD(new Function<JavaRDD<String>, Void>() {

            public Void call(JavaRDD<String> v1) throws Exception {
                if (v1.isEmpty()) return null;

                List<String> list = v1.collect();
                for(String s:list){
                    System.out.println("数据==="+s);
                }

                for (OffsetRange o : offsetRanges.get()) {

                    // 封装topic.partition 与 offset对应关系 java Map
                    TopicAndPartition topicAndPartition = new TopicAndPartition(o.topic(), o.partition());
                    Map<TopicAndPartition, Object> topicAndPartitionObjectMap = new HashMap<TopicAndPartition, Object>();
                    topicAndPartitionObjectMap.put(topicAndPartition, o.untilOffset());

                    // 转换java map to scala immutable.map
                    scala.collection.mutable.Map<TopicAndPartition, Object> testMap =
                            JavaConversions.mapAsScalaMap(topicAndPartitionObjectMap);
                    scala.collection.immutable.Map<TopicAndPartition, Object> scalatopicAndPartitionObjectMap =
                            testMap.toMap(new Predef.$less$colon$less<Tuple2<TopicAndPartition, Object>, Tuple2<TopicAndPartition, Object>>() {
                                public Tuple2<TopicAndPartition, Object> apply(Tuple2<TopicAndPartition, Object> v1) {
                                    return v1;
                                }
                            });

                    // 更新offset到kafkaCluster
                    kafkaCluster.setConsumerOffsets(kafkaParamBroadcast.getValue().get("group.id"), scalatopicAndPartitionObjectMap);
                       System.out.println("原数据====》"+o.topic() + " " + o.partition() + " " + o.fromOffset() + " " + o.untilOffset()
                    );
                }
                return null;
            }
        });

        jssc.start();
        jssc.awaitTermination();
    }