package mapreduce; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class WordCount { public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException { Job job = Job.getInstance(); job.setJobName("WordCount"); job.setJarByClass(WordCount.class); job.setMapperClass(doMapper.class); job.setReducerClass(doReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); Path in = new Path("hdfs://localhost:9000/a/buyer_favorite1"); Path out = new Path("hdfs://localhost:9000/a/out"); FileInputFormat.addInputPath(job,in); FileOutputFormat.setOutputPath(job,out); System.exit(job.waitForCompletion(true)?0:1); } public static class doMapper extends Mapper<Object,Text,Text,IntWritable>{ public static final IntWritable one = new IntWritable(1); public static Text word = new Text(); @Override protected void map(Object key, Text value, Context context) throws IOException,InterruptedException { StringTokenizer tokenizer = new StringTokenizer(value.toString()," "); word.set(tokenizer.nextToken()); context.write(word,one); } } public static class doReducer extends Reducer<Text,IntWritable,Text,IntWritable>{ private IntWritable result = new IntWritable(); @Override protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{ int sum = 0; for (IntWritable value : values){ sum += value.get(); } result.set(sum); context.write(key,result); } } }
题目：
在/home/hadoop/data/mapreduce1/a下面创建buyer_mapreduce1.txt文件并向其中添加一部分数据，通过命令
cd /usr/local/hadoop
切换至/usr/local/hadoop文件夹下将刚才创建的文本文件通过命令
./bin/hdfs dfs -put /home/hadoop/data/mapreduce1/a/buyer_mapreduce1.txt a
上传至hadoop文件夹下的a文件夹下并对其进行后续操作；
运行截图：
经验总结：在linux的文本文件中相邻行数据之间如果存在空行就会报错，去除空行则错误消失；