[
https://issues.apache.org/jira/browse/NUTCH-2038?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14599655#comment-14599655
]
ASF GitHub Bot commented on NUTCH-2038:
---------------------------------------
Github user chrismattmann commented on a diff in the pull request:
https://github.com/apache/nutch/pull/35#discussion_r33165500
--- Diff:
src/plugin/htmlparsefilter-naivebayes/src/java/org/apache/nutch/htmlparsefilter/naivebayes/NaiveBayesHTMLParseFilter.java
---
@@ -0,0 +1,214 @@
+/**
+ * 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.htmlparsefilter.naivebayes;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import org.w3c.dom.DocumentFragment;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.nutch.parse.HTMLMetaTags;
+import org.apache.nutch.parse.HtmlParseFilter;
+import org.apache.nutch.parse.Outlink;
+import org.apache.nutch.parse.Parse;
+import org.apache.nutch.parse.ParseData;
+import org.apache.nutch.parse.ParseResult;
+import org.apache.nutch.parse.ParseStatus;
+import org.apache.nutch.parse.ParseText;
+import org.apache.nutch.protocol.Content;
+
+import java.io.Reader;
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.util.ArrayList;
+
+/**
+ * Html Parse filter that classifies the outlinks from the parseresult as
+ * relevant or irrelevant based on the parseText's relevancy (using a
training
+ * file where you can give positive and negative example texts see the
+ * description of htmlparsefilter.naivebayes.trainfile) and if found
irrelevent
+ * it gives the link a second chance if it contains any of the words from
the
+ * list given in htmlparsefilter.naivebayes.wordlist. CAUTION: Set the
+ * parser.timeout to -1 or a bigger value than 30, when using this
classifier.
+ */
+public class NaiveBayesHTMLParseFilter implements HtmlParseFilter {
+
+ private static final Logger LOG = LoggerFactory
+ .getLogger(NaiveBayesHTMLParseFilter.class);
+
+ public static final String TRAINFILE_MODELFILTER =
"htmlparsefilter.naivebayes.trainfile";
+ public static final String DICTFILE_MODELFILTER =
"htmlparsefilter.naivebayes.wordlist";
+
+ private Configuration conf;
+ private String inputFilePath;
+ private String dictionaryFile;
+ private ArrayList<String> wordlist = new ArrayList<String>();
+
+ public NaiveBayesHTMLParseFilter() {
+
+ }
+
+ public boolean filterParse(String text) {
+
+ try {
+ return classify(text);
+ } catch (IOException e) {
+ // TODO Auto-generated catch block
--- End diff --
remove
> Naive Bayes classifier based url filter
> ---------------------------------------
>
> Key: NUTCH-2038
> URL: https://issues.apache.org/jira/browse/NUTCH-2038
> Project: Nutch
> Issue Type: New Feature
> Components: fetcher, injector, parser
> Reporter: Asitang Mishra
> Assignee: Chris A. Mattmann
> Labels: memex, nutch
> Fix For: 1.11
>
>
> A url filter that will filter out the urls (after the parsing stage, will
> keep only those urls that contain some "hot words" provided again in a list.)
> from that pages that are classified irrelevant by the classifier.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
