examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spark.streaming.examples

import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.StreamingContext._


/**
 * Counts words in new text files created in the given directory
 * Usage: HdfsWordCount <master> <directory>
 *   <master> is the Spark master URL.
 *   <directory> is the directory that Spark Streaming will use to find and read new text files.
 *
 * To run this on your local machine on directory `localdir`, run this example
 *    `$ ./bin/run-example spark.streaming.examples.HdfsWordCount local[2] localdir`
 * Then create a text file in `localdir` and the words in the file will get counted.
 */
object HdfsWordCount {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println("Usage: HdfsWordCount <master> <directory>")
      System.exit(1)
    }

    // Create the context
    val ssc = new StreamingContext(args(0), "HdfsWordCount", Seconds(2),
      System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))

    // Create the FileInputDStream on the directory and use the
    // stream to count words in new files created
    val lines = ssc.textFileStream(args(1))
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
    wordCounts.print()
    ssc.start()
  }
}