yacy_search_server/source/de/anomic/kelondro/text/AbstractIndex.java
orbiter c8624903c6 full redesign of index access data model:
terms (words) are not any more retrieved by their word hash string, but by a byte[] containing the word hash.
this has strong advantages when RWIs are sorted in the ReferenceContainer Cache and compared with the sun.java TreeMap method, which needed getBytes() and new String() transformations before.
Many thousands of such conversions are now omitted every second, which increases the indexing speed by a factor of two.

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5812 6c8d7289-2bf4-0310-a012-ef5d649a1542
2009-04-16 15:29:00 +00:00

89 lines
3.9 KiB
Java

// AbstractIndex.java
// -----------------------------
// (C) 2009 by Michael Peter Christen; mc@yacy.net, Frankfurt a. M., Germany
// first published 15.3.2009 on http://yacy.net
//
// This is a part of YaCy, a peer-to-peer based web search engine
//
// $LastChangedDate: 2006-04-02 22:40:07 +0200 (So, 02 Apr 2006) $
// $LastChangedRevision: 1986 $
// $LastChangedBy: orbiter $
//
// LICENSE
//
// 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 de.anomic.kelondro.text;
import java.io.IOException;
import java.util.Iterator;
import java.util.Set;
import java.util.TreeSet;
import de.anomic.kelondro.order.Order;
public abstract class AbstractIndex <ReferenceType extends Reference> implements Index<ReferenceType> {
final protected ReferenceFactory<ReferenceType> factory;
public AbstractIndex(final ReferenceFactory<ReferenceType> factory) {
this.factory = factory;
}
public int remove(final TreeSet<byte[]> termHashes, final String urlHash) throws IOException {
// remove the same url hashes for multiple words
// this is mainly used when correcting a index after a search
final Iterator<byte[]> i = termHashes.iterator();
int c = 0;
while (i.hasNext()) {
if (remove(i.next(), urlHash)) c++;
}
return c;
}
public void remove(final TreeSet<byte[]> termHashes, final Set<String> urlHashes) throws IOException {
// remove the same url hashes for multiple words
// this is mainly used when correcting a index after a search
final Iterator<byte[]> i = termHashes.iterator();
while (i.hasNext()) {
remove(i.next(), urlHashes);
}
}
public synchronized TreeSet<ReferenceContainer<ReferenceType>> references(final byte[] startHash, final boolean rot, int count) throws IOException {
// creates a set of indexContainers
// this does not use the cache
final Order<ReferenceContainer<ReferenceType>> containerOrder = new ReferenceContainerOrder<ReferenceType>(factory, this.ordering().clone());
ReferenceContainer<ReferenceType> emptyContainer = ReferenceContainer.emptyContainer(factory, startHash, 0);
containerOrder.rotate(emptyContainer);
final TreeSet<ReferenceContainer<ReferenceType>> containers = new TreeSet<ReferenceContainer<ReferenceType>>(containerOrder);
final Iterator<ReferenceContainer<ReferenceType>> i = references(startHash, rot);
//if (ram) count = Math.min(size(), count);
ReferenceContainer<ReferenceType> container;
// this loop does not terminate using the i.hasNex() predicate when rot == true
// because then the underlying iterator is a rotating iterator without termination
// in this case a termination must be ensured with a counter
// It must also be ensured that the counter is in/decreased every loop
while ((count > 0) && (i.hasNext())) {
container = i.next();
if ((container != null) && (container.size() > 0)) {
containers.add(container);
}
count--; // decrease counter even if the container was null or empty to ensure termination
}
return containers; // this may return less containers as demanded
}
}