我已经编写了一些简单的map-reduce程序，并且用示例代码中要搜索的硬编码单词编写的程序正在运行，但是我的另一个map-reduce程序正在搜索通过命令行参数输入的单词不起作用，它们非常相似，因此我不确定为什么它不起作用。似乎可以开始，但是很快就会失败。
工作程序：
// This is a program that finds the Twitter Users that
// are sending secret messages, i.e., do their tweets contain
// "secretMESSAGE" inside of them.
//
//
import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class SecretMessage {
public static class SecretMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
String itr = new String (value.toString());
String message = "secretMESSAGE";
String[] arrOfitr = itr.split("\t");
String user;
String tweet;
if (arrOfitr.length ==2) {
user = arrOfitr[0];
tweet = arrOfitr[1];
int j=0;
for (int i=0;i<tweet.length();i++) {
if (j<message.length()) {
if (tweet.charAt(i) == message.charAt(j)) {
j++;
}
}
}
if (j==message.length()) {
word.set(user);
context.write(word, one);
}
}
}
}
public static class SecretReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum=0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: secretmessage <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "Secret Message");
job.setJarByClass(SecretMessage.class);
job.setMapperClass(SecretMapper.class);
job.setCombinerClass(SecretReducer.class);
job.setReducerClass(SecretReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
非工作计划：
// This is a program that finds the Twitter Users that
// are sending secret messages, i.e., do their tweets contain
// a general message inside of them.
import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class GeneralMessage {
public static class GeneralMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private String message;
public void setup(Context context
) throws IOException, InterruptedException {
Configuration conf = context.getConfiguration();
message = conf.get("Message");
}
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
String itr = new String (value.toString());
String[] arrOfitr = itr.split("\t");
String user;
String tweet;
if (arrOfitr.length ==2) {
user = arrOfitr[0];
tweet = arrOfitr[1];
int j=0;
for (int i=0;i<tweet.length();i++) {
if (j<message.length()) {
if (tweet.charAt(i) == message.charAt(j)) {
j++;
}
}
}
if (j==message.length()) {
word.set(user);
context.write(word, one);
}
}
}
}
public static class GeneralReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum=0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 3) {
System.err.println("Usage: generalmessage SEARCHSTRING <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, args[0]);
job.setJarByClass(GeneralMessage.class);
job.setMapperClass(GeneralMapper.class);
job.setCombinerClass(GeneralReducer.class);
job.setReducerClass(GeneralReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[1]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[2]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
尝试运行无法运行的程序时出现错误：
jward@pu1:~/CS4000/Homework7/generalmessage$ yarn jar GeneralMessage.jar GeneralMessage ScaryMess input generaloutput
19/04/25 20:23:00 INFO client.RMProxy: Connecting to ResourceManager at pu1.cs.ohio.edu/132.235.1.15:8032
19/04/25 20:23:01 INFO input.FileInputFormat: Total input paths to process : 2
19/04/25 20:23:01 INFO mapreduce.JobSubmitter: number of splits:35
19/04/25 20:23:01 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1556192514620_0026
19/04/25 20:23:01 INFO impl.YarnClientImpl: Submitted application application_1556192514620_0026
19/04/25 20:23:01 INFO mapreduce.Job: The url to track the job: http://pu1.cs.ohio.edu:8088/proxy/application_1556192514620_0026/
19/04/25 20:23:01 INFO mapreduce.Job: Running job: job_1556192514620_0026
19/04/25 20:23:06 INFO mapreduce.Job: Job job_1556192514620_0026 running in uber mode : false
19/04/25 20:23:06 INFO mapreduce.Job: map 0% reduce 0%
19/04/25 20:23:08 INFO mapreduce.Job: Task Id : attempt_1556192514620_0026_m_000000_0, Status : FAILED
Error: java.lang.NullPointerException
at GeneralMessage$GeneralMapper.map(GeneralMessage.java:54)
at GeneralMessage$GeneralMapper.map(GeneralMessage.java:30)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:146)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:787)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1754)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
19/04/25 20:23:09 INFO mapreduce.Job: map 3% reduce 0%
19/04/25 20:23:09 INFO mapreduce.Job: Task Id : attempt_1556192514620_0026_m_000006_0, Status : FAILED
Error: java.lang.NullPointerException
at GeneralMessage$GeneralMapper.map(GeneralMessage.java:54)
at GeneralMessage$GeneralMapper.map(GeneralMessage.java:30)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:146)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:787)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1754)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
Container killed by the ApplicationMaster.
Container killed on request. Exit code is 143
Container exited with a non-zero exit code 143