spark 学习之 IDEA 配置 spark 并 wordcount 提交集群

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>com.xuebusi</groupId>
    <artifactId>spark</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <!-- 这里对jar包版本做集中管理 -->
        <scala.version>2.10.6</scala.version>
        <spark.version>1.6.2</spark.version>
        <hadoop.version>2.6.4</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <!-- scala语言核心包 -->
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <!-- spark核心包 -->
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <!-- hadoop的客户端,用于访问HDFS -->
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>
    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <!-- 由于我们的程序可能有很多，所以这里可以不用指定main方法所在的类名，我们可以在提交spark程序的时候手动指定要调用那个main方法 -->
                            <!--
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>com.xuebusi.spark.WordCount</mainClass>
                                </transformer>
                            </transformers>
                            -->
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

 1 import org.apache.spark.rdd.RDD
 2 import org.apache.spark.{SparkConf, SparkContext}
 3 
 4 /**
 5   * Created by SYJ on 2017/1/23.
 6   */
 7 object WordCount {
 8   def main(args: Array[String]) {
 9     //创建SparkConf
10     val conf: SparkConf = new SparkConf()
11     //创建SparkContext
12     val sc: SparkContext = new SparkContext(conf)
13     //从文件读取数据
14     val lines: RDD[String] = sc.textFile(args(0))
15     //按空格切分单词
16     val words: RDD[String] = lines.flatMap(_.split(" "))
17     //单词计数,每个单词每出现一次就计数为1
18     val wordAndOne: RDD[(String, Int)] = words.map((_, 1))
19     //聚合,统计每个单词总共出现的次数
20     val result: RDD[(String, Int)] = wordAndOne.reduceByKey(_+_)
21     //排序,根据单词出现的次数排序
22     val fianlResult: RDD[(String, Int)] = result.sortBy(_._2, false)
23     //将统计结果保存到文件
24     fianlResult.saveAsTextFile(args(1))
25     //释放资源
26     sc.stop()
27   }
28 }

/hadoop/sbin/start-dfs.sh

/spark/sbin/start-all.sh

bin/spark-submit --class spark.wordCount --executor-memory 512m --total-executor-cores 2 /home/hadoop/hadoop/spark-2.3.1-bin-hadoop2.7/spark_testJar/ljSparkCount-1.0-SNAPSHOT.jar hdfs://slave104:9000/wc hdfs://slave104:9000/wc/output