scala: 操作hdfs,mapreduce

女爷i 2022-05-15 16:38 390阅读 0赞

scala是构建在java之上的脚本化语言，而hadoop的底层也是java代码，所以用java写mapreduce是最合适的，而scala是怎样的呢？

因为scala是推荐不加类型声明的， 如val a=“hello”, 但是在hadoop的mapreduce接口中，都有泛型要求，这就像要一个speak English 的老外 ，叫他去学chiness一样，是不太友好的！

下面是具体探究过程：

# 首先，来看下scala如何与hdfs交互： #

*  文件读，写，上传，下载  
    在idea中导入hadoop依赖

<dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-client</artifactId>
                <version>2.7.3</version>
            </dependency>

写一个object： 含有main方法的class伴生对象

import org.apache.hadoop.conf.Configuration
    import org.apache.hadoop.fs.{FileSystem, Path}
    /**
      * 连接hadoop集群，读取文件
      */
    object ConHdfs {
      // 配置,文件系统
      val conf = new Configuration()
      conf.set("fs.defaultFS", "hdfs://localhost:9000")
      val fs = FileSystem.get(conf)
    
      //读取文件
      def readFile(): Unit = {
        val in = fs.open(new Path("/people.txt"))
        var buf = new Array[Byte](1024)
    
        var len = in.read(buf)
        while (len != -1) {
          print(new String(buf, 0, len))
          len = in.read(buf)
        }
        //关闭资源
        in.close()
      }
    
      //写文件
      def writeFile(): Unit = {
        val out = fs.create(new Path("/a.txt"), true)
        for (x <- 1 to 5) {
          out.writeBytes("hello," + x)
        }
        out.close()
      }
    
      //上传文件//下载文件
      def cpFile(): Unit = {
        fs.copyFromLocalFile(new Path("/home/wang/a.txt"), new Path("/a2.txt"))
        fs.copyToLocalFile(new Path("/a.txt"), new Path("/home/wang/aaa.txt"))
        fs.close()
      }
    
      /**
        * 启动程序
        */
      def main(args: Array[String]): Unit = {
        readFile()
        writeFile()
        cpFile()
      }
    }

# 然后，再看scala如何与mapreduce交互 #

*  准备三要素【mapper, reducer, job】,  
    他们要被hadoop框架调度就必须要实现map,reduce接口，实现job的调度规则，这样才能正确的被接入hadoop的mapreduce程序

import org.apache.hadoop.conf.{Configuration, Configured}
    import org.apache.hadoop.fs.Path
    import org.apache.hadoop.io.{IntWritable, LongWritable, Text}
    import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
    import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat
    import org.apache.hadoop.mapreduce.{Job, Mapper, Reducer}
    import org.apache.hadoop.util.Tool
    /**
      * mapper
      */
    class Map1 extends Mapper[LongWritable, Text, Text, IntWritable] {
      override def map(key: LongWritable,
                       value: Text,
                       context: Mapper[LongWritable, Text, Text, IntWritable]#Context): Unit = {
        val words = value.toString
        val arr = words.split(",")
    
        //遍历所欲单词
        for (x <- arr) {
          context.write(new Text(x), new IntWritable(1))
        }
      }
    }
    /**
      * reducer
      */
    class Red1 extends Reducer[Text, IntWritable, Text, IntWritable] {
      def reduce(key: Text,
                          values: Iterable[IntWritable],
                          context: Reducer[Text, IntWritable, Text, IntWritable]#Context): Unit = {
        //统计个数
        var cnt:Int=0
        for (x :IntWritable<- values){
          cnt +=x.get()
        }
        context.write(key,new IntWritable(cnt))
      }
    }
    /**
      * 启动类
      */
    object MrTest extends Configured with Tool{
      override def run(args: Array[String]): Int = {
        val conf = new Configuration()
        conf.set("fs.defaultFS","hdfs://localhost:9000")
        val job = Job.getInstance(conf)
        job.setJarByClass(this.getClass)
        job.setJobName("wordcnt")
    
        //map,reduce,combiner
        job.setMapperClass(classOf[Map])
        job.setCombinerClass(classOf[Red1])
        job.setReducerClass(classOf[Red1])
        job.setMapOutputKeyClass(classOf[Text])
        job.setOutputValueClass(classOf[IntWritable])
        //输入输出
        FileInputFormat.addInputPath(job,new Path("/people.txt"))
        FileOutputFormat.setOutputPath(job,new Path("/wc"))
        //等待作业完成
        val status:Boolean= job.waitForCompletion(true)
        //返回值： int 【0完成, 1 失败】
        if (status) 0 else 1
      }
      def main(args: Array[String]): Unit = {
        run(Array())
      }
    }