[英]Opening cache files in Hadoop 2.2.0
使用job.addCacheFile()
将缓存文件添加到作业后,使用带有context.getCacheFiles()
映射器将其拉下来。 如何打开缓存文件。 我尝试过使用:
BufferedReader reader = new BufferedReader(new FileReader(filename));
(评论如下)
其中filename是URI
的toString()
,但是我得到一个IOException,说该文件不存在。 谁能帮我吗?
import java.io.*;
import java.net.*;
import java.util.*;
import java.util.regex.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.chain.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.mapreduce.lib.reduce.*;
public class UFOLocation2
{
public static class MapClass extends Mapper<LongWritable, Text, Text, LongWritable>
{
private final static LongWritable one = new LongWritable(1);
private static Pattern locationPattern = Pattern.compile("[a-zA-Z]{2}[^a-zA-Z]*$");
private Map<String, String> stateNames;
@Override
public void setup(Context context)
{
try
{
URI[] cacheFiles = context.getCacheFiles();
setupStateMap(cacheFiles[0].toString());
}
catch (IOException ioe)
{
System.err.println("Error reading state file.");
ioe.printStackTrace();
System.exit(1);
}
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException
{
String line = value.toString();
String[] fields = line.split("\t");
String location = fields[2].trim();
if (location.length() >= 2)
{
Matcher matcher = locationPattern.matcher(location);
if (matcher.find())
{
int start = matcher.start();
String state = location.substring(start, start + 2);
context.write(new Text(lookupState(state.toUpperCase())), one);
}
}
}
private void setupStateMap(String filename) throws IOException
{
Map<String, String> states = new HashMap<String, String>();
// the following line causes an IOException
BufferedReader reader = new BufferedReader(new FileReader(filename));
String line = reader.readLine();
while (line != null)
{
String[] split = line.split("\t");
states.put(split[0], split[1]);
line = reader.readLine();
}
stateNames = states;
}
private String lookupState(String state)
{
String fullName = stateNames.get(state);
return fullName == null ? "Other" : fullName;
}
}
public static void main(String[] args) throws Exception
{
Configuration config = new Configuration();
Job job = Job.getInstance(config, "UFO Location 2");
job.setJarByClass(UFOLocation2.class);
job.addCacheFile(new URI("/user/kevin/data/states.txt"));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
Configuration mapconf1 = new Configuration(false);
ChainMapper.addMapper(job, UFORecordValidationMapper.class, LongWritable.class,
Text.class, LongWritable.class, Text.class, mapconf1);
Configuration mapconf2 = new Configuration(false);
ChainMapper.addMapper(job, MapClass.class, LongWritable.class,
Text.class, Text.class, LongWritable.class, mapconf2);
job.setMapperClass(ChainMapper.class);
job.setCombinerClass(LongSumReducer.class);
job.setReducerClass(LongSumReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
这是代码问题还是配置问题? 我正在运行一个据称是伪造的分布式集群
你可以使用这样的东西
Path path = new Path(uri[0].getPath().toString());
if (fileSystem.exists(path)) {
FSDataInputStream dataInputStream = fileSystem.open(path);
byte[] data = new byte[1024];
while (dataInputStream.read(data) > 0) {
//do your stuff here
}
dataInputStream.close();
}
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.