I ran the below code:
object AirportsInUsaSolution {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("airports").setMaster("local[2]")
val sc = new SparkContext(conf)
val airports = sc.textFile("in/airports.text")
val airportsInUSA = airports.filter(line => line.split(Utils.COMMA_DELIMITER)(3) == "\"United States\"")
val airportsNameAndCityNames = airportsInUSA.map(line => {
val splits = line.split(Utils.COMMA_DELIMITER)
splits(1) + ", " + splits(2)
})
airportsNameAndCityNames.saveAsTextFile("out/airports_in_usa.text")
}
}
And received the below error:
Process finished with exit code 1
My final file that I used it to save my data in code is empty.
How can I solve it?
the program made correct file in right directory but it is empty
Related
i am getting error at this line
val Array(outputDirectory, Utils.IntParam(numTweetsToCollect), Utils.IntParam(intervalSecs), Utils.IntParam(partitionsEachInterval)) =
Utils.parseCommandLineWithTwitterCredentials(args)
recursive value x$7 needs
type
recursive value x$1 needs
type
what does this error meaning, please guide me how to resolve this error.
object Collect {
private var numTweetsCollected = 0L
private var partNum = 0
private var gson = new Gson()
def main(args: Array[String]) {
// Process program arguments and set properties
if (args.length < 3) {
System.err.println("Usage: " + this.getClass.getSimpleName +
"<outputDirectory> <numTweetsToCollect> <intervalInSeconds> <partitionsEachInterval>")
System.exit(1)
}
val Array(outputDirectory, Utils.IntParam(numTweetsToCollect), Utils.IntParam(intervalSecs), Utils.IntParam(partitionsEachInterval)) =
Utils.parseCommandLineWithTwitterCredentials(args)
val outputDir = new File(outputDirectory.toString)
if (outputDir.exists()) {
System.err.println("ERROR - %s already exists: delete or specify another directory".format(
outputDirectory))
System.exit(1)
}
outputDir.mkdirs()
println("Initializing Streaming Spark Context...")
val conf = new SparkConf().setAppName(this.getClass.getSimpleName)
val sc = new SparkContext(conf)
val ssc = new StreamingContext(sc, Seconds(intervalSecs))
val tweetStream = TwitterUtils.createStream(ssc, Utils.getAuth)
.map(gson.toJson(_))
tweetStream.foreachRDD((rdd, time) => {
val count = rdd.count()
if (count > 0) {
val outputRDD = rdd.repartition(partitionsEachInterval)
outputRDD.saveAsTextFile(outputDirectory + "/tweets_" + time.milliseconds.toString)
numTweetsCollected += count
if (numTweetsCollected > numTweetsToCollect) {
System.exit(0)
}
}
})
ssc.start()
ssc.awaitTermination()
}
}
Try removing the Utils.IntParam(.. from your pattern matched values. Extract the values, then parse them separately.
My architecture right now is AWS ELB writes log to S3 and it sends a message to SQS for further processing by Spark Streaming. It's working right now but my problem right now is it's taking a bit of time. I'm new to Spark and Scala so just want to make sure that I'm not doing something stupid.
val conf = new SparkConf()
.setAppName("SparrowOrc")
.set("spark.hadoop.fs.s3a.impl","org.apache.hadoop.fs.s3a.S3AFileSystem")
.set("spark.hadoop.mapreduce.fileoutputcommitter.algorithm.version","2")
.set("spark.speculation","false")
val sc = new SparkContext(conf)
val streamContext = new StreamingContext(sc, Seconds(1))
val sqs = streamContext.receiverStream(new SQSReceiver("queue")
.at(Regions.US_EAST_1)
.withTimeout(5))
// Got 10 messages at a time
val s3Keys = sqs.map(messages => {
val sqsMsg: JsValue = Json.parse(messages)
val s3Key = "s3://" +
Json.stringify(sqsMsg("Records")(0)("s3")("bucket")("name")).replace("\"", "") + "/" +
Json.stringify(sqsMsg("Records")(0)("s3")("object")("key")).replace("\"", "")
s3Key
})
val rawLogs: DStream[String] = s3Keys.transform(keys => {
val fileKeys = keys.collect()
val files = fileKeys.map(f => {
sc.textFile(f)
})
sc.union(files)
})
val jsonRows = rawLogs.mapPartitions(partition => {
// Parsing raw log to json
val txfm = new LogLine2Json
val log = Logger.getLogger("parseLog")
partition.map(line => {
try{
txfm.parseLine(line)
}
catch {
case e: Throwable => {log.info(line); "";}
}
}).filter(line => line != "{}")
})
val sqlSession = SparkSession
.builder()
.getOrCreate()
// Write to S3
jsonRows.foreachRDD(r => {
val parsedFormat = new SimpleDateFormat("yyyy-MM-dd/")
val parsedDate = parsedFormat.format(new java.util.Date())
val outputPath = "bucket" + parsedDate
val jsonDf = sqlSession.read.schema(sparrowSchema.schema).json(r)
jsonDf.write.mode("append").format("orc").option("compression","zlib").save(outputPath)
})
streamContext.start()
streamContext.awaitTermination()
}
Here's the DAG and it seems like everything is merged in union transformation.
Hi I'm new to spark and scala . I'm trying to stream some tweets through spark streaming with the following code:
object TwitterStreaming {
def main(args: Array[String]): Unit = {
if (args.length < 1) {
System.err.println("WrongUsage: PropertiesFile, [<filters>]")
System.exit(-1)
}
StreamingExamples.setStreaningLogLevels()
val myConfigFile = args(0)
val batchInterval_s = 1
val fileConfig = ConfigFactory.parseFile(new File(myConfigFile))
val appConf = ConfigFactory.load(fileConfig)
// Set the system properties so that Twitter4j library used by twitter stream
// can use them to generate OAuth credentials
System.setProperty("twitter4j.oauth.consumerKey", appConf.getString("consumerKey"))
System.setProperty("twitter4j.oauth.consumerSecret", appConf.getString("consumerSecret"))
System.setProperty("twitter4j.oauth.accessToken", appConf.getString("accessToken"))
System.setProperty("twitter4j.oauth.accessTokenSecret", appConf.getString("accessTokenSecret"))
val sparkConf = new SparkConf().setAppName("TwitterStreaming").setMaster(appConf.getString("SPARK_MASTER"))//local[2]
val ssc = new StreamingContext(sparkConf, Seconds(batchInterval_s)) // creating spark streaming context
val stream = TwitterUtils.createStream(ssc, None)
val tweet_data = stream.map(status => TweetData(status.getId, "#" + status.getUser.getScreenName, status.getText.trim()))
tweet_data.foreachRDD(rdd => {
println(s"A sample of tweets I gathered over ${batchInterval_s}s: ${rdd.take(10).mkString(" ")} (total tweets fetched: ${rdd.count()})")
})
}
}
case class TweetData(id: BigInt, author: String, tweetText: String)
My Error:
Exception in thread "main" com.typesafe.config.ConfigException$WrongType:/WorkSpace/InputFiles/application.conf: 5: Cannot concatenate object or list with a non-object-or-list, ConfigString("local") and SimpleConfigList([2]) are not compatible
at com.typesafe.config.impl.ConfigConcatenation.join(ConfigConcatenation.java:116)
can any one check the the code and tell me where I'm doing wrong?
If your config file contains:
SPARK_MASTER=local[2]
Change it to:
SPARK_MASTER="local[2]"
My requirement is to enrich data stream data with profile information from a HBase table. I was looking to use a broadcast variable. Enclosed the whole code here.
The output of HBase data is as follows
In the Driver node HBaseReaderBuilder
(org.apache.spark.SparkContext#3c58b102,hbase_customer_profile,Some(data),WrappedArray(gender, age),None,None,List()))
In the Worker node
HBaseReaderBuilder(null,hbase_customer_profile,Some(data),WrappedArray(gender, age),None,None,List()))
As you can see it has lost the spark context. When i issue the statement val
myRdd = bcdocRdd.map(r => Profile(r._1, r._2, r._3)) i get a NullPointerException
java.lang.NullPointerException
at it.nerdammer.spark.hbase.HBaseReaderBuilderConversions$class.toSimpleHBaseRDD(HBaseReaderBuilder.scala:83)
at it.nerdammer.spark.hbase.package$.toSimpleHBaseRDD(package.scala:5)
at it.nerdammer.spark.hbase.HBaseReaderBuilderConversions$class.toHBaseRDD(HBaseReaderBuilder.scala:67)
at it.nerdammer.spark.hbase.package$.toHBaseRDD(package.scala:5)
at testPartition$$anonfun$main$1$$anonfun$apply$1$$anonfun$apply$2.apply(testPartition.scala:34)
at testPartition$$anonfun$main$1$$anonfun$apply$1$$anonfun$apply$2.apply(testPartition.scala:33)
object testPartition {
def main(args: Array[String]) : Unit = {
val sparkMaster = "spark://x.x.x.x:7077"
val ipaddress = "x.x.x.x:2181" // Zookeeper
val hadoopHome = "/home/hadoop/software/hadoop-2.6.0"
val topicname = "new_events_test_topic"
val mainConf = new SparkConf().setMaster(sparkMaster).setAppName("testingPartition")
val mainSparkContext = new SparkContext(mainConf)
val ssc = new StreamingContext(mainSparkContext, Seconds(30))
val eventsStream = KafkaUtils.createStream(ssc,"x.x.x.x:2181","receive_rest_events",Map(topicname.toString -> 2))
val docRdd = mainSparkContext.hbaseTable[(String, Option[String], Option[String])]("hbase_customer_profile").select("gender","age").inColumnFamily("data")
println ("docRDD from Driver ",docRdd)
val broadcastedprof = mainSparkContext.broadcast(docRdd)
eventsStream.foreachRDD(dstream => {
dstream.foreachPartition(records => {
println("Broadcasted docRDD - in Worker ", broadcastedprof.value)
val bcdocRdd = broadcastedprof.value
records.foreach(record => {
//val myRdd = bcdocRdd.map(r => Profile(r._1, r._2, r._3))
//myRdd.foreach(println)
val Rows = record._2.split("\r\n")
})
})
})
ssc.start()
ssc.awaitTermination()
}
}
I am trying to read records from Kafka message and put into Hbase. Though the scala script is running with out any issue, the inserts are not happening. Please help me.
Input:
rowkey1,1
rowkey2,2
Here is the code which I am using:
object Blaher {
def blah(row: Array[String]) {
val hConf = new HBaseConfiguration()
val hTable = new HTable(hConf, "test")
val thePut = new Put(Bytes.toBytes(row(0)))
thePut.add(Bytes.toBytes("cf"), Bytes.toBytes("a"), Bytes.toBytes(row(1)))
hTable.put(thePut)
}
}
object TheMain extends Serializable{
def run() {
val ssc = new StreamingContext(sc, Seconds(1))
val topicmap = Map("test" -> 1)
val lines = KafkaUtils.createStream(ssc,"127.0.0.1:2181", "test-consumer-group",topicmap).map(_._2)
val words = lines.map(line => line.split(",")).map(line => (line(0),line(1)))
val store = words.foreachRDD(rdd => rdd.foreach(Blaher.blah))
ssc.start()
}
}
TheMain.run()
From the API doc for HTable's flushCommits() method: "Executes all the buffered Put operations". You should call this at the end of your blah() method -- it looks like they're currently being buffered but never executed or executed at some random time.