Wikipedia Example has incorrect input Key -----------------------------------------
Key: MAHOUT-91 URL: https://issues.apache.org/jira/browse/MAHOUT-91 Project: Mahout Issue Type: Bug Components: Classification Reporter: Grant Ingersoll Assignee: Grant Ingersoll Priority: Minor Fix For: 0.1 Running the WikipediaDataSetCreator {code} bin/hadoop jar ~/projects/lucene/mahout/mahout-clean/examples/build/ org.apache.mahout.examples.classifiers.cbayes.WikipediaDatasetCreator -i wikipediadump -o wikipediainput -c ~/projects/lucene/mahout/mahout-clean/examples/src/test/resources/country.txt {code} yielded: 08/10/31 11:15:26 INFO mapred.JobClient: Task Id : attempt_200810301619_0001_m_000000_0, Status : FAILED java.lang.ClassCastException: org.apache.hadoop.io.LongWritable cannot be cast to org.apache.hadoop.io.Text at org.apache.mahout.classifier.bayes.WikipediaDatasetCreatorMapper.map(WikipediaDatasetCreatorMapper.java:41) at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:47) at org.apache.hadoop.mapred.MapTask.run(MapTask.java:227) at org.apache.hadoop.mapred.TaskTracker$Child.main(TaskTracker.java:2207) The fix is: {code} Index: src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java =================================================================== --- src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java (revision 709230) +++ src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java (working copy) @@ -20,6 +20,7 @@ import org.apache.commons.lang.StringEscapeUtils; import org.apache.hadoop.io.DefaultStringifier; import org.apache.hadoop.io.Text; +import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.mapred.JobConf; import org.apache.hadoop.mapred.MapReduceBase; import org.apache.hadoop.mapred.Mapper; @@ -39,11 +40,11 @@ import java.util.Set; public class WikipediaDatasetCreatorMapper extends MapReduceBase implements - Mapper<Text, Text, Text, Text> { + Mapper<LongWritable, Text, Text, Text> { private static Set<String> countries = null; - public void map(Text key, Text value, + public void map(LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter) throws IOException { String document = value.toString(); {code} -- This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.