hadoop入门五步走

# 1st  在本地新建一个文件
[root@node21 admin]# cat wc.txt 
a,1 b,1 b,5
a,3 c,3 d,15 e,11
a,2 d,2
# 2st 在hadoop上创建一个目录，用于存放该文件
[root@node21 admin] hadoop fs -mkdir -p  /user/input
可以看到hadoop的fs命令下，有很多和linux命令相似的地方,无聊可以help看哈
root@node21 admin]# hadoop fs --help
--help: Unknown command
Usage: hadoop fs [generic options]
    [-appendToFile <localsrc> ... <dst>]
    [-cat [-ignoreCrc] <src> ...]
    [-checksum <src> ...]
    [-chgrp [-R] GROUP PATH...]
    [-chmod [-R] <MODE[,MODE]... | OCTALMODE> PATH...]
    [-chown [-R] [OWNER][:[GROUP]] PATH...]
    [-copyFromLocal [-f] [-p] [-l] [-d] [-t <thread count>] <localsrc> ... <dst>]
    [-copyToLocal [-f] [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
    [-count [-q] [-h] [-v] [-t [<storage type>]] [-u] [-x] [-e] <path> ...]
    [-cp [-f] [-p | -p[topax]] [-d] <src> ... <dst>]
    [-createSnapshot <snapshotDir> [<snapshotName>]]
.................省略一堆堆
# 3st 上传到该目录
[root@node21 admin]hadoop fs -put ~/wc.txt  /user/input
# 4st 查看是否已经存在该文件
[root@node21 admin]# hadoop fs -ls /user/input
-rw-r--r--   2 admin supergroup         38 2019-03-30 08:41 /user/input/wc.txt
#5st  ok接下来下载到本地并查看
[root@node21 admin]# hadoop fs -get /user/input/wc.txt /home/
admin/  hadoop/ xzg/    
[root@node21 admin]# hadoop fs -get /user/input/wc.txt /home/
[root@node21 admin]# ls /home/
wc.txt  
### 就酱。 

[admin@node21 ~]$ hadoop fs -cat /user/input/word.txt
i love you

[admin@node21 ~]$ hadoop fs -cat /user/output/part-r-00000
i   1
love    1
you 1

windows本地运行mr程序时(不提交到yarn,运行在jvm靠线程执行)，hadoop.dll防止报nativeio异常、winutils.exe没有的话报空指针异常。

public class Chapter3 {

    public static void main(String[] args) {
        try {
            String filename = "hdfs://10.11.91.225:9000/user/input/data.txt";
            Configuration conf = new Configuration();
            conf.set("fs.defaultFS", "hdfs://10.11.91.225:9000");
//            conf.set("mapreduce.jobtracker.address", "10.11.91.255:9000");
            // 这个解决hdfs问题
            conf.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
            // 这个解决本地file问题
            conf.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
            FileSystem fs = FileSystem.get(conf);
            if(fs.exists(new Path(filename)))
            {
                System.out.println("文件存在");
//                fs.
            }else{
                System.out.println("文件不存在");
            }
        } catch (Exception e)
        {
            e.printStackTrace();
        }
    }
}

[admin@node21 ~]$ hadoop fs -cat /user/input/wc.txt
a,1 b,1 b,5
a,3 c,3 d,15 e,11
a,2 d,2

a   6
b   6
c   3
d   17
e   11

// //这个Mapper类是一个泛型类型，它有四个形参类型，分别指定map函数的输入键、输入值、输出键、输出值的类型
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    //该方法循环调用，从文件的split中读取每行调用一次，把该行所在的下标为key，该行的内容为value
    protected void map(LongWritable key, Text value,
                       Context context)
            throws IOException, InterruptedException {
        String[] words = StringUtils.split(value.toString(), ' ');
        for(String w :words){
            //a,1 a,2 重新组装a:1 a:2
            String[] kevs = w.split(",");
            context.write(new Text(kevs[0]), new IntWritable(Integer.valueOf(kevs[1])));
        }
    }
}

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    //每组调用一次，这一组数据特点：key相同，value可能有多个。
    protected void reduce(Text arg0, Iterable<IntWritable> arg1,
                          Context arg2)
            throws IOException, InterruptedException {
        //增加所有的值
        int sum =0;
        for(IntWritable i: arg1){
            sum=sum+i.get();
        }
        arg2.write(arg0, new IntWritable(sum));
    }
}

public class RunJob {

    public static void main(String[] args) {
        Configuration config =new Configuration();
//        config.set("fs.defaultFS", "hdfs://HadoopMaster:9000");
        config.set("fs.defaultFS", "hdfs://10.11.91.225:9000");
        //node22为hadoopyarn-site.xml中的配置
        config.set("yarn.resourcemanager.hostname", "node22");
        //设置执行的用户，需要是服务端的hadoop用户，否则无权限执行，报错.AccessControlException: Permission denied
        System.setProperty("HADOOP_USER_NAME", "admin");
//    config.set("mapred.jar", "C:\\Users\\Administrator\\Desktop\\wc.jar");//先打包好wc.jar
        try {
            FileSystem fs =FileSystem.get(config);
            Job job = Job.getInstance(config);
            job.setJarByClass(RunJob.class);
            job.setJobName("wc");
            job.setMapperClass(WordCountMapper.class);
            job.setReducerClass(WordCountReducer.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
            FileInputFormat.addInputPath(job, new Path("/user/input/wc.txt"));//新建好输入路径，且数据源
            Path outpath =new Path("/user/output/wc");
            if(fs.exists(outpath)){
                fs.delete(outpath, true);
            }
            FileOutputFormat.setOutputPath(job, outpath);
            boolean f= job.waitForCompletion(true);
            if(f){
                System.out.println("job任务执行成功");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

\hadoop-common-project\hadoop-common\src\main\java\org\apache\hadoop\io\nativeio\NativeIO.java

[admin@node21 ~]$ hadoop fs -cat /user/output/wc/part-r-00000
a   6
b   6
c   3
d   17
e   11