3.1.8 NLineInputFormat使用案例
1.需求
- 对每个单词进行个数统计,要求根据每个输入文件的行数来规定输出多少个切片。此案例要求每三行放入一个切片中。
(1)输入数据
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang banzhang ni hao
xihuan hadoop banzhang
(2)期望输出数据
Number of splits:4
2.需求分析
- 使用本地的Hadoop3.1.2进行测试输入的数据,得到输出的数据
3.代码实现
(1)编写Mapper类
/**
* @Author zhangyong
* @Date 2020/3/6 9:17
* @Version 1.0
*/
public class NLineMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
private Text k = new Text ();
private LongWritable v = new LongWritable (1);
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取一行
String line = value.toString ();
// 2 切割
String[] splited = line.split (" ");
// 3 循环写出
for (int i = 0; i < splited.length; i++) {
k.set (splited[i]);
context.write (k, v);
}
}
}
(2)编写Reducer类
/**
* @Author zhangyong
* @Date 2020/3/6 9:18
* @Version 1.0
*/
public class NLineReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
LongWritable v = new LongWritable ();
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum = 0L;
// 1 汇总
for (LongWritable value : values) {
sum += value.get ();
}
v.set (sum);
// 2 输出
context.write (key, v);
}
}
(3)编写Driver类
/**
* @Author zhangyong
* @Date 2020/3/6 9:18
* @Version 1.0
*/
public class NLineDriver {
public static void main(String[] args) throws IOException, URISyntaxException, ClassNotFoundException, InterruptedException {
// 数据输入路径和输出路径
args = new String[2];
args[0] = "src/main/resources/nlinei/";
args[1] = "src/main/resources/nlineo";
Configuration cfg = new Configuration();
cfg.set("mapreduce.framework.name", "local");
cfg.set("fs.defaultFS", "file:///");
final FileSystem filesystem = FileSystem.get(cfg);
if (filesystem.exists(new Path(args[1]))) {
filesystem.delete(new Path(args[1]), true);
}
Job job = Job.getInstance (cfg);
// 7设置每个切片InputSplit中划分三条记录
NLineInputFormat.setNumLinesPerSplit (job, 3);
// 8使用NLineInputFormat处理记录数
job.setInputFormatClass (NLineInputFormat.class);
// 2设置jar包位置,关联mapper和reducer
job.setJarByClass (NLineDriver.class);
job.setMapperClass (NLineMapper.class);
job.setReducerClass (NLineReducer.class);
// 3设置map输出kv类型
job.setMapOutputKeyClass (Text.class);
job.setMapOutputValueClass (LongWritable.class);
// 4设置最终输出kv类型
job.setOutputKeyClass (Text.class);
job.setOutputValueClass (LongWritable.class);
// 5设置输入输出数据路径
FileInputFormat.setInputPaths (job, new Path (args[0]));
FileOutputFormat.setOutputPath (job, new Path (args[1]));
// 6提交job
job.waitForCompletion (true);
}
}