我试图在java中运行一个简单的mapreduce,但出现以下错误:
不支持的名称:有方案但有相对路径部分
如何更正代码或hadoop使其正常工作?
如果需要提供更多信息,请告诉我。
我将文件夹中的文件复制如下:
hadoop fs -copyFromLocal c:\hwork\recipeitems-latest.json /in
我已在以下位置更改了文件夹/的权限:
hadoop fs -chmod -R 777 /in
我基本上是在提示符下执行这个命令(是的,我现在正在使用windows):
hadoop jar c:\hwork\Recipe.jar Recipe /in /out
java代码:
import java.io.IOException;
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;
import com.google.gson.Gson;
public class Recipe {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
Gson gson = new Gson();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
/* StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
} */
Roo roo=gson.fromJson(value.toString(),Roo.class);
if(roo.cookTime!=null)
{
word.set(roo.cookTime);
}
else
{
word.set("none");
}
context.write(word, one);
}
}
public static class IntSumReducer
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();
/* for ( String string : otherArgs) {
System.out.println(string);
}*/
if (otherArgs.length != 2) {
System.err.println("Usage: recipe <in> <out>");
System.exit(2);
}
@SuppressWarnings("deprecation")
Job job = new Job(conf, "Recipe");
job.setJarByClass(Recipe.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
// FileInputFormat.addInputPath(job, new Path("hdfs://127.0.0.1:9000/in"));
// FileOutputFormat.setOutputPath(job, new Path("hdfs://127.0.0.1:9000/out"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
// job.submit();
}
}
class Id
{
public String oid;
}
class Ts
{
public long date ;
}
class Roo
{
public Id _id ;
public String name ;
public String ingredients ;
public String url ;
public String image ;
public Ts ts ;
public String cookTime;
public String source ;
public String recipeYield ;
public String datePublished;
public String prepTime ;
public String description;
}
1条答案
按热度按时间huus2vyu1#
如何使用roo roo=gson.fromjson(value.tostring(),roo.class)初始化roo的值。
另外,请你给一个输入文件的样本列表,你正在传递的驱动程序代码。