yacy_search_server/htroot/yacy/crawlReceipt.java
theli a2fa75e688 *) Asynchronous queuing of crawl job URLs (stackCrawl)
various checks like the blacklist check or the robots.txt disallow check are now
   done by a separate thread to unburden the indexer thread(s)
   TODO: maybe we have to introduce a threadpool here if it turn out that this single
         thread is a bottleneck because of the time consuming robots.txt downloads

*) improved index transfer
   The index selection and transmission is done in parallel now to improve index 
   transfer performance.
   TODO: maybe we could speed up performance by unsing multiple transmission threads in 
         parallel instead of only a single one.

*) gzip encoded post requests
   it is now configureable if a gzip encoded post request should be send on
   intex transfer/distribution

*) storage Peer (very experimentell and not optimized yet)
   Now it's possible to send the result of the yacy indexer thread to a remote peer 
   istead of storing the indexed words locally. 
   This could be done by setting the property "storagePeerHash" in the yacy config file
   - Please note that if the index transfer fails, the index ist stored locally.
   - TODO: currently this index transfer is done by the indexer thread. 
     To seedup the indexer
     a) this transmission should be done in parallel and
     b) multiple chunks should be bundled and transfered together


*) general performance improvements  
   - better memory cleanup after http request processing has finished
   - replacing some string concatenations with stringBuffers
   - replacing BufferedInputStreams with serverByteBuffer
   - replacing vectors with arraylists wherever possible
   - replacing hashtables with hashmaps wherever possible
   This was done because function calls to verctor or hashtable functions
   take 3 time longer than calls to functions of arraylists or hashmaps.
   TODO: we should take a look on the class serverObject which is inherited from hashmap
         Do we realy need a synchronization for this class?
   TODO: replace arraylists with linkedLists if random access to the list elements is not needed

*) Robots Parser supports if-modified-since downloads now
   If the downloaded robots.txt file is older than 7 days the robots parser tries to
   download the robots.txt with the if-modified-since header to avoid unnecessary downloads
   if the file was not changed. Additionally the ETag header is used to detect changes.

*) Crawler: better handling of unsupported mimeTypes + FileExtension

*) Bugfix: plasmaWordIndexEntity was not closed correctly in 
   - query.java
   - plasmaswitchboard.java

*) function minimizeUrlDB added to yacy.java 
   this function tests the current urlHashDB for unused urls
   ATTENTION: please don't use this function at the moment because
              it causes the wordIndexDB to flush all words into the
              word directory!

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@853 6c8d7289-2bf4-0310-a012-ef5d649a1542
2005-10-05 10:45:33 +00:00

141 lines
6.6 KiB
Java

// crawlReceipt.java
// -----------------------
// part of the AnomicHTTPD caching proxy
// (C) by Michael Peter Christen; mc@anomic.de
// first published on http://www.anomic.de
// Frankfurt, Germany, 2004
// last change: 02.05.2004
//
// 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
//
// Using this software in any meaning (reading, learning, copying, compiling,
// running) means that you agree that the Author(s) is (are) not responsible
// for cost, loss of data or any harm that may be caused directly or indirectly
// by usage of this softare or this documentation. The usage of this software
// is on your own risk. The installation and usage (starting/running) of this
// software may allow other people or application to access your computer and
// any attached devices and is highly dependent on the configuration of the
// software which must be done by the user of the software; the author(s) is
// (are) also not responsible for proper configuration and usage of the
// software, even if provoked by documentation provided together with
// the software.
//
// Any changes to this file according to the GPL as documented in the file
// gpl.txt aside this file in the shipment you received can be done to the
// lines that follows this copyright notice here, but changes must not be
// done inside the copyright notive above. A re-distribution must contain
// the intact and unchanged copyright notice.
// Contributions and changes to the program code must be marked as such.
// You must compile this file with
// javac -classpath .:../classes crawlOrder.java
import de.anomic.http.httpHeader;
import de.anomic.plasma.plasmaCrawlNURL;
import de.anomic.plasma.plasmaCrawlLURL;
import de.anomic.plasma.plasmaSwitchboard;
import de.anomic.plasma.plasmaURL;
import de.anomic.server.serverObjects;
import de.anomic.server.serverSwitch;
import de.anomic.tools.bitfield;
import de.anomic.tools.crypt;
import de.anomic.yacy.yacyCore;
public final class crawlReceipt {
/*
* this is used to respond on a remote crawling request
*/
public static serverObjects respond(httpHeader header, serverObjects post, serverSwitch env) {
// return variable that accumulates replacements
plasmaSwitchboard switchboard = (plasmaSwitchboard) env;
serverObjects prop = new serverObjects();
if ((post == null) || (env == null)) return prop;
int proxyPrefetchDepth = Integer.parseInt(env.getConfig("proxyPrefetchDepth", "0"));
int crawlingDepth = Integer.parseInt(env.getConfig("crawlingDepth", "0"));
// request values
String iam = (String) post.get("iam", ""); // seed hash of requester
String youare = (String) post.get("youare", ""); // seed hash of the target peer, needed for network stability
String process = (String) post.get("process", ""); // process type
String key = (String) post.get("key", ""); // transmission key
String urlhash = (String) post.get("urlhash", ""); // the url hash that has been crawled
String result = (String) post.get("result", ""); // the result; either "ok" or "fail"
String reason = (String) post.get("reason", ""); // the reason for that result
String words = (String) post.get("wordh", ""); // priority word hashes
String propStr = crypt.simpleDecode((String) post.get("lurlEntry", ""), key);
/*
the result can have one of the following values:
negative cases, no retry
unavailable - the resource is not available (a broken link); not found or interrupted
exception - an exception occurred
robot - a robot-file has denied to crawl that resource
negative cases, retry possible
rejected - the peer has rejected to load the resource
dequeue - peer too busy - rejected to crawl
positive cases with crawling
fill - the resource was loaded and processed
update - the resource was already in database but re-loaded and processed
positive cases without crawling
known - the resource is already in database, believed to be fresh and not reloaded
stale - the resource was reloaded but not processed because source had no changes
*/
if ((yacyCore.seedDB.mySeed == null) || (!(yacyCore.seedDB.mySeed.hash.equals(youare)))) {
// no yacy connection / unknown peers
prop.put("delay", "3600");
} else if (propStr == null) {
// error with url / wrong key
prop.put("delay", "3600");
} else if (result.equals("fill")) {
// put new data into database
switchboard.urlPool.loadedURL.addEntry(switchboard.urlPool.loadedURL.newEntry(propStr, true), youare, iam, 1);
switchboard.urlPool.noticeURL.remove(urlhash);
// write log
plasmaCrawlLURL.Entry entry = switchboard.urlPool.loadedURL.getEntry(urlhash);
if (entry == null) {
switchboard.getLog().logSevere("RECEIVED wrong RECEIPT for hash " + urlhash + " from peer " + iam);
} else {
switchboard.getLog().logInfo("RECEIVED RECEIPT for URL " + entry.url().toString());
}
// ready for more
prop.put("delay", "10");
} else {
plasmaCrawlNURL.Entry en = switchboard.urlPool.noticeURL.getEntry(urlhash);
if (en != null) {
switchboard.urlPool.errorURL.newEntry(en.url(), en.referrerHash(), en.initiator(), iam, en.name(), result + ":" + reason, new bitfield(plasmaURL.urlFlagLength), false);
switchboard.urlPool.noticeURL.remove(urlhash);
}
prop.put("delay", "100"); // what shall we do with that???
}
// return rewrite properties
return prop;
}
}