Github user chrismattmann commented on a diff in the pull request:
https://github.com/apache/nutch/pull/38#discussion_r33432889
--- Diff:
src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java
---
@@ -0,0 +1,204 @@
+/**
+ * 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.parsefilter.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.hadoop.util.StringUtils;
+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 parsefilter.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 parsefilter.naivebayes.wordlist. CAUTION: Set the
parser.timeout to
+ * -1 or a bigger value than 30, when using this classifier.
+ */
+public class NaiveBayesParseFilter implements HtmlParseFilter {
+
+ private static final Logger LOG = LoggerFactory
+ .getLogger(NaiveBayesParseFilter.class);
+
+ public static final String TRAINFILE_MODELFILTER =
"parsefilter.naivebayes.trainfile";
+ public static final String DICTFILE_MODELFILTER =
"parsefilter.naivebayes.wordlist";
+
+ private Configuration conf;
+ private String inputFilePath;
+ private String dictionaryFile;
+ private ArrayList<String> wordlist = new ArrayList<String>();
+
+ public boolean filterParse(String text) {
+
+ try {
+ return classify(text);
+ } catch (IOException e) {
+ // TODO Auto-generated catch block
--- End diff --
I asked for this to be removed.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
