我想Hadoop的MapReduce的基本方案,其教程上http://java.dzone.com/articles/hadoop-basics-creating
类的完整代码是(该代码存在于净上面URL)
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.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class Dictionary {
public static class WordMapper extends Mapper<Text, Text, Text, Text> {
private Text word = new Text();
public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString(), ",");
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(key, word);
}
}
}
public static class AllTranslationsReducer extends Reducer<Text, Text, Text, Text> {
private Text result = new Text();
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
String translations = "";
for (Text val : values) {
translations += "|" + val.toString();
}
result.set(translations);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
System.out.println("welcome to Java 1");
Configuration conf = new Configuration();
System.out.println("welcome to Java 2");
Job job = new Job(conf, "dictionary");
job.setJarByClass(Dictionary.class);
job.setMapperClass(WordMapper.class);
job.setReducerClass(AllTranslationsReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setInputFormatClass(KeyValueTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path("/tmp/hadoop-cscarioni/dfs/name/file"));
FileOutputFormat.setOutputPath(job, new Path("output"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
但在Eclipse中运行后, 我发现了错误,
welcome to Java 1
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/commons/logging/LogFactory
at org.apache.hadoop.conf.Configuration.<clinit>(Configuration.java:73)
at Dictionary.main(Dictionary.java:43)
Caused by: java.lang.ClassNotFoundException: org.apache.commons.logging.LogFactory
at java.net.URLClassLoader$1.run(Unknown Source)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
at sun.misc.Launcher$AppClassLoader.loadClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
... 2 more