Github user chrismattmann commented on a diff in the pull request: https://github.com/apache/nutch/pull/87#discussion_r51521777 --- Diff: src/plugin/scoring-similarity/src/java/org/apache/nutch/scoring/similarity/cosine/Model.java --- @@ -0,0 +1,135 @@ +package org.apache.nutch.scoring.similarity.cosine; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.HashMap; +import java.util.List; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.util.StringUtils; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.nutch.scoring.similarity.util.LuceneAnalyzerUtil.StemFilterType; +import org.apache.nutch.scoring.similarity.util.LuceneTokenizer; +import org.apache.nutch.scoring.similarity.util.LuceneTokenizer.TokenizerType; +import org.apache.tika.Tika; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * This class creates a model used to store Document vector representation of the corpus. + * @author Sujen Shah --- End diff -- no author tags.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---