mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
788288eb9e
The default schema uses only some of them and the resting search index has now the following properties: - webgraph size will have about 40 times as much entries as default index - the complete index size will increase and may be about the double size of current amount As testing showed, not much indexing performance is lost. The default index will be smaller (moved fields out of it); thus searching can be faster. The new index will cause that some old parts in YaCy can be removed, i.e. specialized webgraph data and the noload crawler. The new index will make it possible to: - search within link texts of linked but not indexed documents (about 20 times of document index in size!!) - get a very detailed link graph - enhance ranking using a complete link graph To get the full access to the new index, the API to solr has now two access points: one with attribute core=collection1 for the default search index and core=webgraph to the new webgraph search index. This is also avaiable for p2p operation but client access is not yet implemented.
113 lines
4.0 KiB
Java
113 lines
4.0 KiB
Java
//SitemapImporter.java
|
|
//------------------------
|
|
//part of YaCy
|
|
//(C) by Michael Peter Christen; mc@yacy.net
|
|
//first published on http://www.anomic.de
|
|
//Frankfurt, Germany, 2007
|
|
//
|
|
//this file was contributed by Martin Thelian
|
|
//last major change: $LastChangedDate$ by $LastChangedBy$
|
|
//Revision: $LastChangedRevision$
|
|
//
|
|
//This program is free software; you can redistribute it and/or modify
|
|
//it under the terms of the GNU General Public License as published by
|
|
//the Free Software Foundation; either version 2 of the License, or
|
|
//(at your option) any later version.
|
|
//
|
|
//This program is distributed in the hope that it will be useful,
|
|
//but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
//MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
//GNU General Public License for more details.
|
|
//
|
|
//You should have received a copy of the GNU General Public License
|
|
//along with this program; if not, write to the Free Software
|
|
//Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
|
|
package net.yacy.crawler.retrieval;
|
|
|
|
import java.net.MalformedURLException;
|
|
import java.util.Date;
|
|
|
|
import net.yacy.cora.document.ASCII;
|
|
import net.yacy.crawler.HarvestProcess;
|
|
import net.yacy.crawler.data.CrawlProfile;
|
|
import net.yacy.document.parser.sitemapParser;
|
|
import net.yacy.document.parser.sitemapParser.URLEntry;
|
|
import net.yacy.kelondro.data.meta.DigestURI;
|
|
import net.yacy.kelondro.data.meta.URIMetadataNode;
|
|
import net.yacy.kelondro.logging.Log;
|
|
import net.yacy.search.Switchboard;
|
|
|
|
public class SitemapImporter extends Thread {
|
|
|
|
private CrawlProfile crawlingProfile = null;
|
|
private static final Log logger = new Log("SITEMAP");
|
|
private DigestURI siteMapURL = null;
|
|
private final Switchboard sb;
|
|
|
|
public SitemapImporter(final Switchboard sb, final DigestURI sitemapURL, final CrawlProfile profileEntry) {
|
|
assert sitemapURL != null;
|
|
this.sb = sb;
|
|
this.siteMapURL = sitemapURL;
|
|
assert profileEntry != null;
|
|
this.crawlingProfile = profileEntry;
|
|
}
|
|
|
|
@Override
|
|
public void run() {
|
|
try {
|
|
logger.logInfo("Start parsing sitemap file " + this.siteMapURL);
|
|
sitemapParser.SitemapReader parser = sitemapParser.parse(this.siteMapURL);
|
|
parser.start();
|
|
URLEntry item;
|
|
while ((item = parser.take()) != sitemapParser.POISON_URLEntry) {
|
|
process(item);
|
|
}
|
|
} catch (final Exception e) {
|
|
logger.logWarning("Unable to parse sitemap file " + this.siteMapURL, e);
|
|
}
|
|
}
|
|
|
|
public void process(sitemapParser.URLEntry entry) {
|
|
|
|
// get the url hash
|
|
byte[] nexturlhash = null;
|
|
DigestURI url = null;
|
|
try {
|
|
url = new DigestURI(entry.url());
|
|
nexturlhash = url.hash();
|
|
} catch (final MalformedURLException e1) {
|
|
}
|
|
|
|
// check if the url is known and needs to be recrawled
|
|
Date lastMod = entry.lastmod(null);
|
|
if (lastMod != null) {
|
|
final HarvestProcess dbocc = this.sb.urlExists(ASCII.String(nexturlhash));
|
|
if (dbocc != null && dbocc == HarvestProcess.LOADED) {
|
|
// the url was already loaded. we need to check the date
|
|
final URIMetadataNode oldEntry = this.sb.index.fulltext().getMetadata(nexturlhash);
|
|
if (oldEntry != null) {
|
|
final Date modDate = oldEntry.moddate();
|
|
// check if modDate is null
|
|
if (modDate.after(lastMod)) return;
|
|
}
|
|
}
|
|
}
|
|
|
|
// URL needs to crawled
|
|
this.sb.crawlStacker.enqueueEntry(new Request(
|
|
ASCII.getBytes(this.sb.peers.mySeed().hash),
|
|
url,
|
|
null, // this.siteMapURL.toString(),
|
|
entry.url(),
|
|
entry.lastmod(new Date()),
|
|
this.crawlingProfile.handle(),
|
|
0,
|
|
0,
|
|
0,
|
|
0
|
|
));
|
|
logger.logInfo("New URL '" + entry.url() + "' added for loading.");
|
|
}
|
|
}
|