[ https://issues.apache.org/jira/browse/NUTCH-2039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14585839#comment-14585839 ]
ASF GitHub Bot commented on NUTCH-2039: --------------------------------------- Github user chrismattmann commented on a diff in the pull request: https://github.com/apache/nutch/pull/30#discussion_r32413617 --- Diff: src/plugin/scoring-similarity/src/java/org/apache/nutch/scoring/similarity/SimilarityScoringFilter.java --- @@ -0,0 +1,150 @@ +/** + * 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; + +import java.io.File; +import java.io.IOException; +import java.util.Collection; +import java.util.List; +import java.util.Map.Entry; + +import org.apache.commons.io.FileUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.io.Text; +import org.apache.nutch.crawl.CrawlDatum; +import org.apache.nutch.crawl.Inlinks; +import org.apache.nutch.indexer.NutchDocument; +import org.apache.nutch.metadata.Nutch; +import org.apache.nutch.parse.Parse; +import org.apache.nutch.parse.ParseData; +import org.apache.nutch.protocol.Content; +import org.apache.nutch.scoring.ScoringFilter; +import org.apache.nutch.scoring.ScoringFilterException; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class SimilarityScoringFilter implements ScoringFilter { + + private Configuration conf; + private String goldStandardDocPath; + private final static Logger LOG = LoggerFactory + .getLogger(SimilarityScoringFilter.class); + + @Override + public Configuration getConf() { + return conf; + } + + @Override + public void setConf(Configuration conf) { + this.conf = conf; + goldStandardDocPath = conf.get("similarity.model.path"); + LOG.info("Getting the goldstanrd path {}",goldStandardDocPath); + } + + @Override + public void injectedScore(Text url, CrawlDatum datum) + throws ScoringFilterException { --- End diff -- I think in these cases, you should simply call Tika on the URL. > Relevance based scoring filter > ------------------------------ > > Key: NUTCH-2039 > URL: https://issues.apache.org/jira/browse/NUTCH-2039 > Project: Nutch > Issue Type: New Feature > Reporter: Sujen Shah > Labels: memex, nutch > Fix For: 1.11 > > > A ScoringFilter plugin that uses a similarity measure to calculate the > similarity between a given page(gold standard) and the currently parsed page. > The score obtained from this similarity is then distributed to its outlinks. > This filter aims to focus the crawler to crawl/explore relevant pages. -- This message was sent by Atlassian JIRA (v6.3.4#6332)