pom.xml文件配置
1 <!-- 声明公有的属性 --> 2 <properties> 3 <maven.compiler.source>1.8</maven.compiler.source> 4 <maven.compiler.target>1.8</maven.compiler.target> 5 <encoding>UTF-8</encoding> 6 <scala.version>2.11.8</scala.version> 7 <spark.version>2.2.0</spark.version> 8 <hadoop.version>2.7.1</hadoop.version> 9 <scala.compat.version>2.11</scala.compat.version> 10 </properties> 11 <!-- 声明并引入公有的依赖 --> 12 <dependencies> 13 <dependency> 14 <groupId>org.scala-lang</groupId> 15 <artifactId>scala-library</artifactId> 16 <version>${scala.version}</version> 17 </dependency> 18 <dependency> 19 <groupId>org.apache.spark</groupId> 20 <artifactId>spark-core_2.11</artifactId> 21 <version>${spark.version}</version> 22 </dependency> 23 <dependency> 24 <groupId>org.apache.hadoop</groupId> 25 <artifactId>hadoop-client</artifactId> 26 <version>${hadoop.version}</version> 27 </dependency> 28 </dependencies> 29 30 <!-- 配置构建信息 --> 31 <build> 32 <!-- 资源文件夹 --> 33 <sourceDirectory>src/main/scala</sourceDirectory> 34 <!-- 声明并引入构建的插件 --> 35 <plugins> 36 <!-- 用于编译Scala代码到class --> 37 <plugin> 38 <groupId>net.alchim31.maven</groupId> 39 <artifactId>scala-maven-plugin</artifactId> 40 <version>3.2.2</version> 41 <executions> 42 <execution> 43 <goals> 44 <goal>compile</goal> 45 <goal>testCompile</goal> 46 </goals> 47 <configuration> 48 <args> 49 <arg>-dependencyfile</arg> 50 <arg>${project.build.directory}/.scala_dependencies</arg> 51 </args> 52 </configuration> 53 </execution> 54 </executions> 55 </plugin> 56 <plugin> 57 <!-- 程序打包 --> 58 <groupId>org.apache.maven.plugins</groupId> 59 <artifactId>maven-shade-plugin</artifactId> 60 <version>2.4.3</version> 61 <executions> 62 <execution> 63 <phase>package</phase> 64 <goals> 65 <goal>shade</goal> 66 </goals> 67 <configuration> 68 <!-- 过滤掉以下文件，不打包 ：解决包重复引用导致的打包错误--> 69 <filters> 70 <filter><artifact>*:*</artifact> 71 <excludes> 72 <exclude>META-INF/*.SF</exclude> 73 <exclude>META-INF/*.DSA</exclude> 74 <exclude>META-INF/*.RSA</exclude> 75 </excludes> 76 </filter> 77 </filters> 78 <transformers> 79 <!-- 打成可执行的jar包 的主方法入口--> 80 <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer"> 81 <mainClass></mainClass> 82 </transformer> 83 </transformers> 84 </configuration> 85 </execution> 86 </executions> 87 </plugin> 88 </plugins> 89 </build>
第一个WordCount
1 package SparkCore_01 2 3 import org.apache.spark.rdd.RDD 4 import org.apache.spark.{SparkConf, SparkContext} 5 6 /** 7 * 第一个Spark程序 8 */ 9 object SparkWordCount { 10 //Spark程序都需要使用main 11 def main(args: Array[String]): Unit = { 12 //0.构建系统环境变量,为了SparkContext加在环境变量所使用 13 /* 14 三个核心方法 15 set(key,value) --> 主要应对的是 环境变量设置 key 环境变量名 value 是具体值 16 setAppName(name) --> 设置程序运行的名称 17 setMaster(执行方式),如果需要运行本地环境,那么就需要配置SetMaster这个值 18 "local" --> 代表本地模式,相当于启用一个线程来模拟Spark运行 19 "local[数值]" --> 代表本地模式, 根据数值来决定启用多少个线程来模拟spark运行 20 ps:数值不能大于当前cpu 核心数 21 "local[*]" --> 代表本地模式 * 相当于是系统空闲多少线程就用多少线程来执行spark程序 22 */ 23 val conf =new SparkConf().setAppName("SparkWordCount").setMaster("local") 24 //1.先构建SparkContext对象,需要对SparkContext对象进行环境配置即将conf对象传入到SparkContext中 25 val sc = new SparkContext(conf) 26 27 //Spark对数据的处理 28 //1.读取文件内容,参数是文件路径(多用于读取txt或log文件) 29 val lines: RDD[String] = sc.textFile("dir/SparkCore_01/File.txt") 30 //2.对文件中数据进行切分处理 31 val words: RDD[String] = lines.flatMap(_.split(" ")) 32 //3.对单词进行统计之前,需要对单词的个数进行计数 33 val tuples: RDD[(String, Int)] = words.map((_,1)) 34 //Spark中提供了一个根据key计算value的算子(这个算子是你使用最广泛一个算子),相同key为一组计算一次value的值 35 val sumed: RDD[(String, Int)] = tuples.reduceByKey(_+_) 36 37 //println(sumed.collect().toList) 38 39 sc.stop()//关闭Sparkcontext 40 41 42 //提交集群版本(修改位置): 43 //sc.textFile(args(0)) //获取外部输入读取数据路径 44 //将数据文件存储到集群(也可以存储在本地)没有返回值 45 // sumed.saveAsTextFile(args(1)) // 获取外部输入的存储路径 ,不要打印语句 46 } 47 }
程序打包提交集群
将jar包上传到对应节点,然后在Spark安装目录下bin目录下执行以下操作
./spark-submit \
> --class SparkCore_01.SparkWordCount\
> --master spark://hadoop01:7077 \
> --executor-memory 512m \
> --total-executor-cores 2 \
> /root/Spark_1905-1.0-SNAPSHOT.jar hdfs://hadoop01:8020/word.txt hdfs://hadoop01:8020/out2
ps: jar包所在路径 hdfs集群读取文件 写入到hdfs集群中
去掉打印日志
log4j.properties
1 # contributor license agreements. See the NOTICE file distributed with 2 # this work for additional information regarding copyright ownership. 3 # The ASF licenses this file to You under the Apache License, Version 2.0 4 # (the "License"); you may not use this file except in compliance with 5 # the License. You may obtain a copy of the License at 6 # 7 # http://www.apache.org/licenses/LICENSE-2.0 8 # 9 # Unless required by applicable law or agreed to in writing, software 10 # distributed under the License is distributed on an "AS IS" BASIS, 11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 # See the License for the specific language governing permissions and 13 # limitations under the License. 14 # 15 # Set everything to be logged to the console 16 # 修改此处更改显示信息级别 17 log4j.rootCategory=ERROR, console 18 log4j.appender.console=org.apache.log4j.ConsoleAppender 19 log4j.appender.console.target=System.err 20 log4j.appender.console.layout=org.apache.log4j.PatternLayout 21 log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
