Java 运行MapReduce代码时出现FileReadyExistsException
这个程序应该完成MapReduce的工作。第一个作业的输出必须作为第二个作业的输入 当我运行它时,会出现两个错误:Java 运行MapReduce代码时出现FileReadyExistsException,java,hadoop,mapreduce,Java,Hadoop,Mapreduce,这个程序应该完成MapReduce的工作。第一个作业的输出必须作为第二个作业的输入 当我运行它时,会出现两个错误: 线程“main”org.apache.hadoop.mapred.FileReadyExistsException中的异常 映射部件100%运行,但减速器未运行 这是我的密码: import java.io.IOException; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.a
import java.io.IOException;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.conf.Configuration;
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.Reducer;
import org.apache.hadoop.io.LongWritable;
public class MaxPubYear {
public static class FrequencyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
Text word = new Text();
String delim = ";";
Integer year = 0;
String tokens[] = value.toString().split(delim);
if (tokens.length >= 4) {
year = TryParseInt(tokens[3].replace("\"", "").trim());
if (year > 0) {
word = new Text(year.toString());
context.write(word, new IntWritable(1));
}
}
}
}
public static class FrequencyReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
context.write(key, new IntWritable(sum));
}
}
public static class MaxPubYearMapper extends
Mapper<LongWritable, Text, IntWritable, Text> {
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String delim = "\t";
Text valtosend = new Text();
String tokens[] = value.toString().split(delim);
if (tokens.length == 2) {
valtosend.set(tokens[0] + ";" + tokens[1]);
context.write(new IntWritable(1), valtosend);
}
}
}
public static class MaxPubYearReducer extends
Reducer<IntWritable, Text, Text, IntWritable> {
public void reduce(IntWritable key, Iterable<Text> values,
Context context) throws IOException, InterruptedException {
int maxiValue = Integer.MIN_VALUE;
String maxiYear = "";
for (Text value : values) {
String token[] = value.toString().split(";");
if (token.length == 2
&& TryParseInt(token[1]).intValue() > maxiValue) {
maxiValue = TryParseInt(token[1]);
maxiYear = token[0];
}
}
context.write(new Text(maxiYear), new IntWritable(maxiValue));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "Frequency");
job.setJarByClass(MaxPubYear.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(FrequencyMapper.class);
job.setCombinerClass(FrequencyReducer.class);
job.setReducerClass(FrequencyReducer.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1] + "_temp"));
int exitCode = job.waitForCompletion(true) ? 0 : 1;
if (exitCode == 0) {
Job SecondJob = new Job(conf, "Maximum Publication year");
SecondJob.setJarByClass(MaxPubYear.class);
SecondJob.setOutputKeyClass(Text.class);
SecondJob.setOutputValueClass(IntWritable.class);
SecondJob.setMapOutputKeyClass(IntWritable.class);
SecondJob.setMapOutputValueClass(Text.class);
SecondJob.setMapperClass(MaxPubYearMapper.class);
SecondJob.setReducerClass(MaxPubYearReducer.class);
FileInputFormat.addInputPath(SecondJob, new Path(args[1] + "_temp"));
FileOutputFormat.setOutputPath(SecondJob, new Path(args[1]));
System.exit(SecondJob.waitForCompletion(true) ? 0 : 1);
}
}
public static Integer TryParseInt(String trim) {
// TODO Auto-generated method stub
return(0);
}
}
import java.io.IOException;
导入org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
导入org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
导入org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
导入org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
导入org.apache.hadoop.mapreduce.Mapper;
导入org.apache.hadoop.conf.Configuration;
导入org.apache.hadoop.fs.Path;
导入org.apache.hadoop.io.IntWritable;
导入org.apache.hadoop.io.Text;
导入org.apache.hadoop.mapreduce.Job;
导入org.apache.hadoop.mapreduce.Reducer;
导入org.apache.hadoop.io.LongWritable;
公共课{
公共静态类FrequencyMapper扩展映射器{
公共void映射(LongWritable键、文本值、上下文上下文)引发IOException、InterruptedException{
Text word=新文本();
字符串delim=“;”;
整数年=0;
字符串标记[]=value.toString().split(delim);
如果(tokens.length>=4){
year=TryParseInt(标记[3]。替换(“\”,“”)。trim();
如果(年份>0){
word=新文本(year.toString());
context.write(word,新的intwriteable(1));
}
}
}
}
公共静态类FrequencyReducer扩展
减速器{
public void reduce(文本键、Iterable值、,
上下文)抛出IOException、InterruptedException{
整数和=0;
for(可写入值:值){
sum+=value.get();
}
write(key,newintwriteable(sum));
}
}
公共静态类MaxPubYearMapper扩展
制图员{
公共void映射(可长写键、文本值、上下文)
抛出IOException、InterruptedException{
字符串delim=“\t”;
Text valtosend=新文本();
字符串标记[]=value.toString().split(delim);
if(tokens.length==2){
valtosend.set(令牌[0]+“;”+令牌[1]);
write(新的intwriteable(1),valtosend);
}
}
}
公共静态类MaxPubYearReducer扩展
减速器{
public void reduce(可写键、可写值、,
上下文)抛出IOException、InterruptedException{
int maxiValue=Integer.MIN_值;
字符串maxiYear=“”;
用于(文本值:值){
字符串标记[]=value.toString().split(;);
如果(token.length==2
&&TryParseInt(令牌[1]).intValue()>maxiValue){
maxiValue=TryParseInt(令牌[1]);
maxiYear=token[0];
}
}
write(新文本(maxiYear),新intwriteable(maxiValue));
}
}
公共静态void main(字符串[]args)引发异常{
Configuration conf=新配置();
作业=新作业(配置,“频率”);
job.setJarByClass(MaxPubYear.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(FrequencyMapper.class);
job.setCombinerClass(FrequencyReducer.class);
job.setReducerClass(FrequencyReducer.class);
setOutputFormatClass(TextOutputFormat.class);
setInputFormatClass(TextInputFormat.class);
addInputPath(作业,新路径(args[0]);
setOutputPath(作业,新路径(args[1]+“_temp”);
int exitCode=job.waitForCompletion(true)?0:1;
if(exitCode==0){
Job SecondJob=新作业(conf,“最长出版年”);
SecondJob.setJarByClass(MaxPubYear.class);
SecondJob.setOutputKeyClass(Text.class);
SecondJob.setOutputValueClass(IntWritable.class);
setMapOutputKeyClass(IntWritable.class);
SecondJob.setMapOutputValueClass(Text.class);
setMapperClass(MaxPubYearMapper.class);
SecondJob.setReducerClass(MaxPubYearReducer.class);
addInputPath(第二个作业,新路径(args[1]+“_temp”);
setOutputPath(第二个作业,新路径(args[1]);
系统退出(第二个作业等待完成(真)?0:1;
}
}
公共静态整数TryParseInt(字符串修剪){
//TODO自动生成的方法存根
返回(0);
}
}
线程“main”中出现异常
org.apache.hadoop.mapred.filealreadyexistException
Map reduce作业不会覆盖现有目录中的内容。MR作业的输出路径必须是不存在的目录路径。MR作业将在指定路径创建一个目录,其中包含文件
在代码中:
setOutputPath(作业,新路径(args[1]+“_temp”)
确保运行MR作业时此路径不存在
线程“main”中出现异常
org.apache.hadoop.mapred.filealreadyexistException
Map reduce作业不会覆盖现有目录中的内容。MR作业的输出路径必须是不存在的目录路径。MR作业将在指定路径创建一个目录,其中包含文件
在代码中:
setOutputPath(作业,新路径(args[1]+“_temp”)
确保运行MR作业时此路径不存在
线程“main”中出现异常
org.apache.hadoop.mapred.filealreadyexistseceptio