nutch-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF GitHub Bot (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (NUTCH-2139) Basic plugin to index inlinks and outlinks
Date Thu, 15 Oct 2015 18:21:05 GMT

    [ https://issues.apache.org/jira/browse/NUTCH-2139?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14959344#comment-14959344
] 

ASF GitHub Bot commented on NUTCH-2139:
---------------------------------------

Github user sebastian-nagel commented on a diff in the pull request:

    https://github.com/apache/nutch/pull/78#discussion_r42160759
  
    --- Diff: src/plugin/index-links/src/java/org/apache/nutch/indexer/links/LinksIndexingFilter.java
---
    @@ -0,0 +1,168 @@
    +/**
    + * 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.indexer.links;
    +
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.io.Text;
    +import org.apache.nutch.crawl.CrawlDatum;
    +import org.apache.nutch.crawl.Inlink;
    +import org.apache.nutch.crawl.Inlinks;
    +import org.apache.nutch.indexer.IndexingException;
    +import org.apache.nutch.indexer.IndexingFilter;
    +import org.apache.nutch.indexer.NutchDocument;
    +import org.apache.nutch.parse.Outlink;
    +import org.apache.nutch.parse.Parse;
    +import org.slf4j.LoggerFactory;
    +
    +import java.net.MalformedURLException;
    +import java.net.URL;
    +import java.util.HashSet;
    +import java.util.Iterator;
    +import java.util.Set;
    +
    +/**
    + * An {@link org.apache.nutch.indexer.IndexingFilter} that adds
    + * <code>outlinks</code> and <code>inlinks</code> field(s) to
the document.
    + *
    + * In case that you want to ignore the outlinks that point to the same host
    + * as the URL being indexed use the following settings in your configuration
    + * file:
    + *
    + * <property>
    + *   <name>outlinks.host.ignore</name>
    + *   <value>true</value>
    + * </property>
    + *
    + * The same configuration is available for inlinks:
    + *
    + * <property>
    + *   <name>inlinks.host.ignore</name>
    + *   <value>true</value>
    + * </property>
    + *
    + * To store only the host portion of each inlink URL or outlink URL add the
    + * following to your configuration file.
    + *
    + * <property>
    + *   <name>links.hosts.only</name>
    + *   <value>false</value>
    + * </property>
    + *
    + */
    +public class LinksIndexingFilter implements IndexingFilter {
    +
    +  public final static String LINKS_OUTLINKS_HOST = "outlinks.host.ignore";
    +  public final static String LINKS_INLINKS_HOST = "inlinks.host.ignore";
    +  public final static String LINKS_ONLY_HOSTS = "links.hosts.only";
    +
    +  public final static org.slf4j.Logger LOG = LoggerFactory
    +      .getLogger(LinksIndexingFilter.class);
    +
    +  private Configuration conf;
    +  private boolean filterOutlinks;
    +  private boolean filterInlinks;
    +  private boolean indexHost;
    +
    +  @Override
    +  public NutchDocument filter(NutchDocument doc, Parse parse, Text url,
    +      CrawlDatum datum, Inlinks inlinks) throws IndexingException {
    +
    +    // Add the outlinks
    +    Outlink[] outlinks = parse.getData().getOutlinks();
    +
    +    try {
    +      if (outlinks != null) {
    +        Set<String> hosts = new HashSet<String>();
    +
    +        for (Outlink outlink : outlinks) {
    +          String linkUrl = outlink.getToUrl();
    +          String outHost = new URL(linkUrl).getHost();
    +
    +          if (indexHost) {
    +            linkUrl = new URL(outlink.getToUrl()).getHost();
    +
    +            if (hosts.contains(linkUrl))
    +              continue;
    +
    +            hosts.add(linkUrl);
    +          }
    +
    +          addFilteredLink("outlinks", url.toString(), linkUrl, outHost,
    +              filterOutlinks, doc);
    +        }
    +      }
    +    } catch (MalformedURLException e) {
    +      LOG.error("Malformed URL in {}: {}", url, e.getMessage());
    +    }
    +
    +    // Add the inlinks
    +    if (null != inlinks) {
    +      Iterator<Inlink> iterator = inlinks.iterator();
    +      Set<String> inlinkHosts = new HashSet<String>();
    +
    +      try {
    +        while (iterator.hasNext()) {
    --- End diff --
    
    Shouldn't the try-catch be inside the while loop? The first invalid URL would break the
loop and cause remaining inlinks to be skipped from being indexed. Is this intended? Ok, this
should never happen since inlinks are validated URLs pointing to already fetched documents.


> Basic plugin to index inlinks and outlinks
> ------------------------------------------
>
>                 Key: NUTCH-2139
>                 URL: https://issues.apache.org/jira/browse/NUTCH-2139
>             Project: Nutch
>          Issue Type: Improvement
>          Components: indexer, plugin
>            Reporter: Jorge Luis Betancourt Gonzalez
>            Priority: Minor
>              Labels: link, plugin
>             Fix For: 1.11
>
>
> Basic plugin that allows to index the inlinks and outlinks of the web pages, this could
be very useful for analytic purposes, including neat visualizations using d3.js for instance.




--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message