[
https://issues.apache.org/jira/browse/NUTCH-2209?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15127637#comment-15127637
]
ASF GitHub Bot commented on NUTCH-2209:
---------------------------------------
Github user chrismattmann commented on a diff in the pull request:
https://github.com/apache/nutch/pull/87#discussion_r51521822
--- Diff:
src/plugin/scoring-similarity/src/java/org/apache/nutch/scoring/similarity/util/LuceneIndexManager.java
---
@@ -0,0 +1,113 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nutch.scoring.similarity.util;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.Reader;
+
+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.Analyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.document.FieldType;
+import org.apache.lucene.index.AtomicReader;
+import org.apache.lucene.index.DirectoryReader;
+import org.apache.lucene.index.Fields;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.index.MultiFields;
+import org.apache.lucene.index.SegmentReader;
+import org.apache.lucene.index.SlowCompositeReaderWrapper;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.NIOFSDirectory;
+import org.apache.lucene.store.RAMDirectory;
+import org.apache.lucene.util.Version;
+import
org.apache.nutch.scoring.similarity.util.LuceneAnalyzerUtil.StemFilterType;
+import org.apache.tika.Tika;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.sun.org.apache.xalan.internal.xsltc.compiler.sym;
+
+/**
+ * This class provides the functionality to read/write Lucene indexes
+ * @author Sujen Shah
--- End diff --
no author tags.
> Improved Tokenization for Similarity Scoring plugin
> ---------------------------------------------------
>
> Key: NUTCH-2209
> URL: https://issues.apache.org/jira/browse/NUTCH-2209
> Project: Nutch
> Issue Type: Improvement
> Components: scoring
> Reporter: Sujen Shah
> Assignee: Sujen Shah
> Labels: memex
> Fix For: 1.13
>
>
> This patch would add Lucene based tokenization to the cosine similarity
> plugin and clean up the code currently present.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
