You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yacy_search_server/source/net/yacy/peers/SeedDB.java

1039 lines
44 KiB

// yacySeedDB.java
// -------------------------------------
// (C) by Michael Peter Christen; mc@yacy.net
// first published on http://www.anomic.de
// Frankfurt, Germany, 2004, 2005
//
// $LastChangedDate$
// $LastChangedRevision$
// $LastChangedBy$
//
// 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.peers;
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.PrintWriter;
import java.net.InetAddress;
*) 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
19 years ago
import java.util.ArrayList;
import java.util.Collection;
import java.util.Iterator;
import java.util.Map;
import java.util.TreeMap;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentMap;
import net.yacy.cora.document.encoding.ASCII;
import net.yacy.cora.document.encoding.UTF8;
import net.yacy.cora.document.id.DigestURL;
12 years ago
import net.yacy.cora.federate.yacy.Distribution;
12 years ago
import net.yacy.cora.order.Base64Order;
import net.yacy.cora.protocol.ClientIdentification;
import net.yacy.cora.protocol.Domains;
import net.yacy.cora.protocol.HeaderFramework;
import net.yacy.cora.protocol.RequestHeader;
import net.yacy.cora.protocol.http.HTTPClient;
import net.yacy.cora.util.ConcurrentLog;
import net.yacy.cora.util.SpaceExceededException;
import net.yacy.kelondro.blob.MapDataMining;
import net.yacy.kelondro.data.word.Word;
import net.yacy.kelondro.util.FileUtils;
import net.yacy.kelondro.util.kelondroException;
import net.yacy.peers.operation.yacySeedUploader;
import net.yacy.search.Switchboard;
12 years ago
import net.yacy.server.serverCore;
import net.yacy.server.serverSwitch;
import net.yacy.server.http.AlternativeDomainNames;
import net.yacy.server.http.HTTPDemon;
public final class SeedDB implements AlternativeDomainNames {
// global statics
private static final int dhtActivityMagic = 32;
/**
* <p><code>public static final String <strong>DBFILE_OWN_SEED</strong> = "mySeed.txt"</code></p>
* <p>Name of the file containing the database holding this peer's seed</p>
*/
public static final String DBFILE_OWN_SEED = "mySeed.txt";
public static final String[] sortFields = new String[] {Seed.LCOUNT, Seed.RCOUNT, Seed.ICOUNT, Seed.UPTIME, Seed.VERSION, Seed.LASTSEEN};
public static final String[] longaccFields = new String[] {Seed.LCOUNT, Seed.ICOUNT, Seed.ISPEED};
public static final String[] doubleaccFields = new String[] {Seed.RSPEED};
// class objects
private File seedActiveDBFile, seedPassiveDBFile, seedPotentialDBFile;
private File myOwnSeedFile;
private MapDataMining seedActiveDB, seedPassiveDB, seedPotentialDB;
protected int lastSeedUpload_seedDBSize = 0;
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public long lastSeedUpload_timeStamp = System.currentTimeMillis();
protected String lastSeedUpload_myIP = "";
public PeerActions peerActions;
public NewsPool newsPool;
private int netRedundancy;
public Distribution scheme;
private Seed mySeed; // my own seed
public SeedDB(
replaced old DHT transmission method with new method. Many things have changed! some of them: - after a index selection is made, the index is splitted into its vertical components - from differrent index selctions the splitted components can be accumulated before they are placed into the transmission queue - each splitted chunk gets its own transmission thread - multiple transmission threads are started concurrently - the process can be monitored with the blocking queue servlet To implement that, a new package de.anomic.yacy.dht was created. Some old files have been removed. The new index distribution model using a vertical DHT was implemented. An abstraction of this model is implemented in the new dht package as interface. The freeworld network has now a configuration of two vertial partitions; sixteen partitions are planned and will be configured if the process is bug-free. This modification has three main targets: - enhance the DHT transmission speed - with a vertical DHT, a search will speed up. With two partitions, two times. With sixteen, sixteen times. - the vertical DHT will apply a semi-dht for URLs, and peers will receive a fraction of the overall URLs they received before. with two partitions, the fractions will be halve. With sixteen partitions, a 1/16 of the previous number of URLs. BE CAREFULL, THIS IS A MAJOR CODE CHANGE, POSSIBLY FULL OF BUGS AND HARMFUL THINGS. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5586 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
final File networkRoot,
final String seedActiveDBFileName,
final String seedPassiveDBFileName,
final String seedPotentialDBFileName,
final File myOwnSeedFile,
final int redundancy,
final int partitionExponent,
final boolean useTailCache,
final boolean exceed134217727) {
replaced old DHT transmission method with new method. Many things have changed! some of them: - after a index selection is made, the index is splitted into its vertical components - from differrent index selctions the splitted components can be accumulated before they are placed into the transmission queue - each splitted chunk gets its own transmission thread - multiple transmission threads are started concurrently - the process can be monitored with the blocking queue servlet To implement that, a new package de.anomic.yacy.dht was created. Some old files have been removed. The new index distribution model using a vertical DHT was implemented. An abstraction of this model is implemented in the new dht package as interface. The freeworld network has now a configuration of two vertial partitions; sixteen partitions are planned and will be configured if the process is bug-free. This modification has three main targets: - enhance the DHT transmission speed - with a vertical DHT, a search will speed up. With two partitions, two times. With sixteen, sixteen times. - the vertical DHT will apply a semi-dht for URLs, and peers will receive a fraction of the overall URLs they received before. with two partitions, the fractions will be halve. With sixteen partitions, a 1/16 of the previous number of URLs. BE CAREFULL, THIS IS A MAJOR CODE CHANGE, POSSIBLY FULL OF BUGS AND HARMFUL THINGS. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5586 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
this.seedActiveDBFile = new File(networkRoot, seedActiveDBFileName);
this.seedPassiveDBFile = new File(networkRoot, seedPassiveDBFileName);
this.seedPotentialDBFile = new File(networkRoot, seedPotentialDBFileName);
this.mySeed = null; // my own seed
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
this.myOwnSeedFile = myOwnSeedFile;
this.netRedundancy = redundancy;
this.scheme = new Distribution(partitionExponent);
// set up seed database
this.seedActiveDB = openSeedTable(this.seedActiveDBFile);
this.seedPassiveDB = openSeedTable(this.seedPassiveDBFile);
this.seedPotentialDB = openSeedTable(this.seedPotentialDBFile);
// check if we are in the seedCaches: this can happen if someone else published our seed
removeMySeed();
this.lastSeedUpload_seedDBSize = sizeConnected();
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
// tell the httpdProxy how to find this table as address resolver
HTTPDemon.setAlternativeResolver(this);
replaced old DHT transmission method with new method. Many things have changed! some of them: - after a index selection is made, the index is splitted into its vertical components - from differrent index selctions the splitted components can be accumulated before they are placed into the transmission queue - each splitted chunk gets its own transmission thread - multiple transmission threads are started concurrently - the process can be monitored with the blocking queue servlet To implement that, a new package de.anomic.yacy.dht was created. Some old files have been removed. The new index distribution model using a vertical DHT was implemented. An abstraction of this model is implemented in the new dht package as interface. The freeworld network has now a configuration of two vertial partitions; sixteen partitions are planned and will be configured if the process is bug-free. This modification has three main targets: - enhance the DHT transmission speed - with a vertical DHT, a search will speed up. With two partitions, two times. With sixteen, sixteen times. - the vertical DHT will apply a semi-dht for URLs, and peers will receive a fraction of the overall URLs they received before. with two partitions, the fractions will be halve. With sixteen partitions, a 1/16 of the previous number of URLs. BE CAREFULL, THIS IS A MAJOR CODE CHANGE, POSSIBLY FULL OF BUGS AND HARMFUL THINGS. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5586 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
// create or init news database
this.newsPool = new NewsPool(networkRoot, useTailCache, exceed134217727);
// deploy peer actions
this.peerActions = new PeerActions(this, this.newsPool);
}
public void relocate(
final File newNetworkRoot,
final int redundancy,
final int partitionExponent,
final boolean useTailCache,
final boolean exceed134217727) {
// close old databases
this.seedActiveDB.close();
this.seedPassiveDB.close();
this.seedPotentialDB.close();
this.newsPool.close();
this.peerActions.close();
// open new according to the newNetworkRoot
this.seedActiveDBFile = new File(newNetworkRoot, this.seedActiveDBFile.getName());
this.seedPassiveDBFile = new File(newNetworkRoot, this.seedPassiveDBFile.getName());
this.seedPotentialDBFile = new File(newNetworkRoot, this.seedPotentialDBFile.getName());
// replace my (old) seed with new seed definition from other network
// but keep the seed name
final String peername = myName();
this.mySeed = null; // my own seed
this.myOwnSeedFile = new File(newNetworkRoot, SeedDB.DBFILE_OWN_SEED);
this.netRedundancy = redundancy;
this.scheme = new Distribution(partitionExponent);
// set up seed database
this.seedActiveDB = openSeedTable(this.seedActiveDBFile);
this.seedPassiveDB = openSeedTable(this.seedPassiveDBFile);
this.seedPotentialDB = openSeedTable(this.seedPotentialDBFile);
initMySeed();
this.mySeed.setName(peername);
// check if we are in the seedCaches: this can happen if someone else published our seed
removeMySeed();
this.lastSeedUpload_seedDBSize = sizeConnected();
// tell the httpdProxy how to find this table as address resolver
HTTPDemon.setAlternativeResolver(this);
// create or init news database
this.newsPool = new NewsPool(newNetworkRoot, useTailCache, exceed134217727);
replaced old DHT transmission method with new method. Many things have changed! some of them: - after a index selection is made, the index is splitted into its vertical components - from differrent index selctions the splitted components can be accumulated before they are placed into the transmission queue - each splitted chunk gets its own transmission thread - multiple transmission threads are started concurrently - the process can be monitored with the blocking queue servlet To implement that, a new package de.anomic.yacy.dht was created. Some old files have been removed. The new index distribution model using a vertical DHT was implemented. An abstraction of this model is implemented in the new dht package as interface. The freeworld network has now a configuration of two vertial partitions; sixteen partitions are planned and will be configured if the process is bug-free. This modification has three main targets: - enhance the DHT transmission speed - with a vertical DHT, a search will speed up. With two partitions, two times. With sixteen, sixteen times. - the vertical DHT will apply a semi-dht for URLs, and peers will receive a fraction of the overall URLs they received before. with two partitions, the fractions will be halve. With sixteen partitions, a 1/16 of the previous number of URLs. BE CAREFULL, THIS IS A MAJOR CODE CHANGE, POSSIBLY FULL OF BUGS AND HARMFUL THINGS. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5586 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
// deploy peer actions
this.peerActions = new PeerActions(this, this.newsPool);
}
private synchronized void initMySeed() {
if (this.mySeed != null) return;
// create or init own seed
if (this.myOwnSeedFile.length() > 0) try {
// load existing identity
this.mySeed = Seed.load(this.myOwnSeedFile);
if (this.mySeed == null) throw new IOException("current seed is null");
} catch (final IOException e) {
// create new identity
ConcurrentLog.severe("SEEDDB", "could not load stored mySeed.txt from " + this.myOwnSeedFile.toString() + ": " + e.getMessage() + ". creating new seed.", e);
this.mySeed = Seed.genLocalSeed(this);
try {
this.mySeed.save(this.myOwnSeedFile);
} catch (final IOException ee) {
ConcurrentLog.severe("SEEDDB", "error saving mySeed.txt (1) to " + this.myOwnSeedFile.toString() + ": " + ee.getMessage(), ee);
ConcurrentLog.logException(ee);
System.exit(-1);
}
} else {
// create new identity
ConcurrentLog.info("SEEDDB", "could not find stored mySeed.txt at " + this.myOwnSeedFile.toString() + ": " + ". creating new seed.");
this.mySeed = Seed.genLocalSeed(this);
try {
this.mySeed.save(this.myOwnSeedFile);
} catch (final IOException ee) {
ConcurrentLog.severe("SEEDDB", "error saving mySeed.txt (2) to " + this.myOwnSeedFile.toString() + ": " + ee.getMessage(), ee);
ConcurrentLog.logException(ee);
System.exit(-1);
}
}
this.mySeed.setIP(""); // we delete the old information to see what we have now
this.mySeed.put(Seed.PEERTYPE, Seed.PEERTYPE_VIRGIN); // markup startup condition
}
replaced old DHT transmission method with new method. Many things have changed! some of them: - after a index selection is made, the index is splitted into its vertical components - from differrent index selctions the splitted components can be accumulated before they are placed into the transmission queue - each splitted chunk gets its own transmission thread - multiple transmission threads are started concurrently - the process can be monitored with the blocking queue servlet To implement that, a new package de.anomic.yacy.dht was created. Some old files have been removed. The new index distribution model using a vertical DHT was implemented. An abstraction of this model is implemented in the new dht package as interface. The freeworld network has now a configuration of two vertial partitions; sixteen partitions are planned and will be configured if the process is bug-free. This modification has three main targets: - enhance the DHT transmission speed - with a vertical DHT, a search will speed up. With two partitions, two times. With sixteen, sixteen times. - the vertical DHT will apply a semi-dht for URLs, and peers will receive a fraction of the overall URLs they received before. with two partitions, the fractions will be halve. With sixteen partitions, a 1/16 of the previous number of URLs. BE CAREFULL, THIS IS A MAJOR CODE CHANGE, POSSIBLY FULL OF BUGS AND HARMFUL THINGS. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5586 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
public int redundancy() {
if (this.mySeed.isJunior()) return 1;
return this.netRedundancy;
}
public boolean mySeedIsDefined() {
return this.mySeed != null;
}
public Seed mySeed() {
if (this.mySeed == null) {
if (sizeConnected() == 0) try {Thread.sleep(5000);} catch (final InterruptedException e) {} // wait for init
initMySeed();
// check if my seed has an IP assigned
if (myIP() == null || myIP().isEmpty()) {
this.mySeed.setIP(Domains.myPublicLocalIP().getHostAddress());
}
}
return this.mySeed;
}
public void setMyName(final String name) {
this.mySeed.setName(name);
}
13 years ago
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public String myAlternativeAddress() {
return mySeed().getName() + ".yacy";
}
13 years ago
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public String myIP() {
return mySeed().getIP();
}
13 years ago
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public int myPort() {
return mySeed().getPort();
}
13 years ago
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public String myName() {
return this.mySeed.getName();
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
}
13 years ago
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public String myID() {
return this.mySeed.hash;
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
}
public synchronized void removeMySeed() {
if (this.seedActiveDB.isEmpty() && this.seedPassiveDB.isEmpty() && this.seedPotentialDB.isEmpty()) return; // avoid that the own seed is initialized too early
if (this.mySeed == null) initMySeed();
try {
final byte[] mySeedHash = ASCII.getBytes(this.mySeed.hash);
this.seedActiveDB.delete(mySeedHash);
this.seedPassiveDB.delete(mySeedHash);
this.seedPotentialDB.delete(mySeedHash);
} catch (final IOException e) { ConcurrentLog.warn("yacySeedDB", "could not remove hash ("+ e.getClass() +"): "+ e.getMessage()); }
}
public void saveMySeed() {
try {
mySeed().save(this.myOwnSeedFile);
} catch (final IOException e) { ConcurrentLog.warn("yacySeedDB", "could not save mySeed '"+ this.myOwnSeedFile +"': "+ e.getMessage()); }
}
public boolean noDHTActivity() {
// for small networks, we don't perform DHT transmissions, because it is possible to search over all peers
return sizeConnected() <= dhtActivityMagic;
}
private synchronized static MapDataMining openSeedTable(final File seedDBFile) {
final File parentDir = new File(seedDBFile.getParent());
if (!parentDir.exists()) {
if(!parentDir.mkdirs())
ConcurrentLog.warn("yacySeedDB", "could not create directories for "+ seedDBFile.getParent());
}
try {
return new MapDataMining(seedDBFile, Word.commonHashLength, Base64Order.enhancedCoder, 1024 * 512, 500, sortFields, longaccFields, doubleaccFields);
} catch (final Exception e) {
// try again
FileUtils.deletedelete(seedDBFile);
try {
return new MapDataMining(seedDBFile, Word.commonHashLength, Base64Order.enhancedCoder, 1024 * 512, 500, sortFields, longaccFields, doubleaccFields);
} catch (final IOException e1) {
ConcurrentLog.logException(e1);
System.exit(-1);
return null;
}
}
}
private synchronized MapDataMining resetSeedTable(MapDataMining seedDB, final File seedDBFile) {
// this is an emergency function that should only be used if any problem with the
// seed.db is detected
Network.log.warn("seed-db " + seedDBFile.toString() + " reset (on-the-fly)");
seedDB.close();
FileUtils.deletedelete(seedDBFile);
if (seedDBFile.exists())
ConcurrentLog.warn("yacySeedDB", "could not delete file "+ seedDBFile);
// create new seed database
seedDB = openSeedTable(seedDBFile);
return seedDB;
}
public synchronized void resetActiveTable() { this.seedActiveDB = resetSeedTable(this.seedActiveDB, this.seedActiveDBFile); }
private synchronized void resetPassiveTable() { this.seedPassiveDB = resetSeedTable(this.seedPassiveDB, this.seedPassiveDBFile); }
private synchronized void resetPotentialTable() { this.seedPotentialDB = resetSeedTable(this.seedPotentialDB, this.seedPotentialDBFile); }
public void close() {
if (this.seedActiveDB != null) this.seedActiveDB.close();
if (this.seedPassiveDB != null) this.seedPassiveDB.close();
if (this.seedPotentialDB != null) this.seedPotentialDB.close();
this.newsPool.close();
this.peerActions.close();
}
public Iterator<Seed> seedsSortedConnected(final boolean up, final String field) {
// enumerates seed-type objects: all seeds sequentially ordered by field
return new seedEnum(up, field, this.seedActiveDB);
}
public Iterator<Seed> seedsSortedDisconnected(final boolean up, final String field) {
// enumerates seed-type objects: all seeds sequentially ordered by field
return new seedEnum(up, field, this.seedPassiveDB);
}
public Iterator<Seed> seedsSortedPotential(final boolean up, final String field) {
// enumerates seed-type objects: all seeds sequentially ordered by field
return new seedEnum(up, field, this.seedPotentialDB);
}
public TreeMap<byte[], String> /* peer-b64-hashes/ipport */ clusterHashes(final String clusterdefinition) {
// collects seeds according to cluster definition string, which consists of
// comma-separated .yacy or .yacyh-domains
// the domain may be extended by an alternative address specification of the form
// <ip> or <ip>:<port>. The port must be identical to the port specified in the peer seed,
// therefore it is optional. The address specification is separated by a '='; the complete
// address has therefore the form
// address ::= (<peername>'.yacy'|<peerhexhash>'.yacyh'){'='<ip>{':'<port}}
// clusterdef ::= {address}{','address}*
final String[] addresses = (clusterdefinition.isEmpty()) ? new String[0] : clusterdefinition.split(",");
final TreeMap<byte[], String> clustermap = new TreeMap<byte[], String>(Base64Order.enhancedCoder);
Seed seed;
String hash, yacydom, ipport;
int p;
for (final String addresse : addresses) {
p = addresse.indexOf('=');
if (p >= 0) {
yacydom = addresse.substring(0, p);
ipport = addresse.substring(p + 1);
} else {
yacydom = addresse;
ipport = null;
}
if (yacydom.endsWith(".yacyh")) {
// find a peer with its hexhash
hash = Seed.hexHash2b64Hash(yacydom.substring(0, yacydom.length() - 6));
seed = get(hash);
if (seed == null) {
Network.log.warn("cluster peer '" + yacydom + "' was not found.");
} else {
clustermap.put(ASCII.getBytes(hash), ipport);
}
} else if (yacydom.endsWith(".yacy")) {
// find a peer with its name
seed = lookupByName(yacydom.substring(0, yacydom.length() - 5));
if (seed == null) {
Network.log.warn("cluster peer '" + yacydom + "' was not found.");
} else {
clustermap.put(ASCII.getBytes(seed.hash), ipport);
}
} else {
Network.log.warn("cluster peer '" + addresse + "' has wrong syntax. the name must end with .yacy or .yacyh");
}
}
return clustermap;
}
public Iterator<Seed> seedsConnected(final boolean up, final boolean rot, final byte[] firstHash, final double minVersion) {
// enumerates seed-type objects: all seeds sequentially without order
return new seedEnum(up, rot, (firstHash == null) ? null : firstHash, null, this.seedActiveDB, minVersion);
}
private Iterator<Seed> seedsDisconnected(final boolean up, final boolean rot, final byte[] firstHash, final double minVersion) {
// enumerates seed-type objects: all seeds sequentially without order
return new seedEnum(up, rot, (firstHash == null) ? null : firstHash, null, this.seedPassiveDB, minVersion);
}
public Seed anySeedVersion(final double minVersion) {
// return just any seed that has a specific minimum version number
final Iterator<Seed> e = seedsConnected(true, true, Seed.randomHash(), minVersion);
return e.next();
}
/**
* count the number of peers that had been seed within the time limit
* @param limit the time limit in minutes. 1440 minutes is a day
* @return the number of peers seen in the given time
*/
public int sizeActiveSince(final long limit) {
int c = this.seedActiveDB.size();
Seed seed;
Iterator<Seed> i = seedsSortedDisconnected(false, Seed.LASTSEEN);
while (i.hasNext()) {
seed = i.next();
if (seed != null) {
if (Math.abs((System.currentTimeMillis() - seed.getLastSeenUTC()) / 1000 / 60) > limit) break;
c++;
}
}
i = seedsSortedPotential(false, Seed.LASTSEEN);
while (i.hasNext()) {
seed = i.next();
if (seed != null) {
if (Math.abs((System.currentTimeMillis() - seed.getLastSeenUTC()) / 1000 / 60) > limit) break;
c++;
}
}
return c;
}
public int sizeConnected() {
return this.seedActiveDB.size();
}
public int sizeDisconnected() {
return this.seedPassiveDB.size();
}
public int sizePotential() {
return this.seedPotentialDB.size();
}
public long countActiveURL() { return this.seedActiveDB.getLongAcc(Seed.LCOUNT); }
public long countActiveRWI() { return this.seedActiveDB.getLongAcc(Seed.ICOUNT); }
public long countActivePPM() { return this.seedActiveDB.getLongAcc(Seed.ISPEED); }
public float countActiveQPM() { return this.seedActiveDB.getFloatAcc(Seed.RSPEED); }
public long countPassiveURL() { return this.seedPassiveDB.getLongAcc(Seed.LCOUNT); }
public long countPassiveRWI() { return this.seedPassiveDB.getLongAcc(Seed.ICOUNT); }
public long countPotentialURL() { return this.seedPotentialDB.getLongAcc(Seed.LCOUNT); }
public long countPotentialRWI() { return this.seedPotentialDB.getLongAcc(Seed.ICOUNT); }
public void addConnected(final Seed seed) {
if (seed.isProper(false) != null) return;
//seed.put(yacySeed.LASTSEEN, yacyCore.shortFormatter.format(new Date(yacyCore.universalTime())));
synchronized (this) {
try {
final ConcurrentMap<String, String> seedPropMap = seed.getMap();
this.seedActiveDB.insert(ASCII.getBytes(seed.hash), seedPropMap);
this.seedPassiveDB.delete(ASCII.getBytes(seed.hash));
this.seedPotentialDB.delete(ASCII.getBytes(seed.hash));
} catch (final Exception e) {
Network.log.severe("ERROR add: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
resetActiveTable();
}
}
}
protected void addDisconnected(final Seed seed) {
if (seed.isProper(false) != null) return;
synchronized (this) {
try {
this.seedActiveDB.delete(ASCII.getBytes(seed.hash));
this.seedPotentialDB.delete(ASCII.getBytes(seed.hash));
} catch (final Exception e) { ConcurrentLog.warn("yacySeedDB", "could not remove hash ("+ e.getClass() +"): "+ e.getMessage()); }
//seed.put(yacySeed.LASTSEEN, yacyCore.shortFormatter.format(new Date(yacyCore.universalTime())));
try {
final ConcurrentMap<String, String> seedPropMap = seed.getMap();
this.seedPassiveDB.insert(ASCII.getBytes(seed.hash), seedPropMap);
} catch (final Exception e) {
Network.log.severe("ERROR add: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
resetPassiveTable();
}
}
}
protected void addPotential(final Seed seed) {
if (seed.isProper(false) != null) return;
synchronized (this) {
try {
this.seedActiveDB.delete(ASCII.getBytes(seed.hash));
this.seedPassiveDB.delete(ASCII.getBytes(seed.hash));
} catch (final Exception e) { ConcurrentLog.warn("yacySeedDB", "could not remove hash ("+ e.getClass() +"): "+ e.getMessage()); }
//seed.put(yacySeed.LASTSEEN, yacyCore.shortFormatter.format(new Date(yacyCore.universalTime())));
try {
final ConcurrentMap<String, String> seedPropMap = seed.getMap();
this.seedPotentialDB.insert(ASCII.getBytes(seed.hash), seedPropMap);
} catch (final Exception e) {
Network.log.severe("ERROR add: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
resetPotentialTable();
}
}
}
public synchronized void removeDisconnected(final String peerHash) {
if (peerHash == null) return;
try {
this.seedPassiveDB.delete(ASCII.getBytes(peerHash));
} catch (final IOException e) { ConcurrentLog.warn("yacySeedDB", "could not remove hash ("+ e.getClass() +"): "+ e.getMessage()); }
}
public synchronized void removePotential(final String peerHash) {
if (peerHash == null) return;
try {
this.seedPotentialDB.delete(ASCII.getBytes(peerHash));
} catch (final IOException e) { ConcurrentLog.warn("yacySeedDB", "could not remove hash ("+ e.getClass() +"): "+ e.getMessage()); }
}
public boolean hasConnected(final byte[] hash) {
return this.seedActiveDB.containsKey(hash);
}
public boolean hasDisconnected(final byte[] hash) {
return this.seedPassiveDB.containsKey(hash);
}
public boolean hasPotential(final byte[] hash) {
return this.seedPotentialDB.containsKey(hash);
}
private Seed get(final String hash, final MapDataMining database) {
if (hash == null || hash.isEmpty()) return null;
if ((this.mySeed != null) && (hash.equals(this.mySeed.hash))) return this.mySeed;
final ConcurrentHashMap<String, String> entry = new ConcurrentHashMap<String, String>();
try {
final Map<String, String> map = database.get(ASCII.getBytes(hash));
if (map == null) return null;
entry.putAll(map);
} catch (final IOException e) {
ConcurrentLog.logException(e);
return null;
} catch (final SpaceExceededException e) {
ConcurrentLog.logException(e);
return null;
}
return new Seed(hash, entry);
}
public Seed getConnected(final String hash) {
return get(hash, this.seedActiveDB);
}
public Seed getDisconnected(final String hash) {
return get(hash, this.seedPassiveDB);
}
public Seed getPotential(final String hash) {
return get(hash, this.seedPotentialDB);
}
public Seed get(final String hash) {
Seed seed = getConnected(hash);
if (seed == null) seed = getDisconnected(hash);
if (seed == null) seed = getPotential(hash);
return seed;
}
public void update(final String hash, final Seed seed) {
if (this.mySeed == null) initMySeed();
if (hash.equals(this.mySeed.hash)) {
this.mySeed = seed;
return;
}
final byte[] hashb = ASCII.getBytes(hash);
Seed s = get(hash, this.seedActiveDB);
if (s != null) try { this.seedActiveDB.insert(hashb, seed.getMap()); return;} catch (final Exception e) {ConcurrentLog.logException(e);}
s = get(hash, this.seedPassiveDB);
if (s != null) try { this.seedPassiveDB.insert(hashb, seed.getMap()); return;} catch (final Exception e) {ConcurrentLog.logException(e);}
s = get(hash, this.seedPotentialDB);
if (s != null) try { this.seedPotentialDB.insert(hashb, seed.getMap()); return;} catch (final Exception e) {ConcurrentLog.logException(e);}
}
public Seed lookupByName(String peerName) {
// reads a seed by searching by name
if (peerName.endsWith(".yacy")) peerName = peerName.substring(0, peerName.length() - 5);
// local peer?
if (peerName.equals("localpeer")) {
if (this.mySeed == null) initMySeed();
return this.mySeed;
}
peerName = peerName.toLowerCase();
Seed seed;
// enumerate the cache
String name = Seed.checkPeerName(peerName);
synchronized (this) { try {
Collection<byte[]> idx = this.seedActiveDB.select(Seed.NAME, name);
for (byte[] pk: idx) {
seed = this.getConnected(ASCII.String(pk));
if (seed == null) continue;
//System.out.println("*** found lookupByName in seedActiveDB: " + peerName);
return seed;
}
} catch (final IOException e ) {
}}
synchronized (this) { try {
Collection<byte[]> idx = this.seedPassiveDB.select(Seed.NAME, name);
for (byte[] pk: idx) {
seed = this.getDisconnected(ASCII.String(pk));
if (seed == null) continue;
//System.out.println("*** found lookupByName in seedPassiveDB: " + peerName);
return seed;
}
} catch (final IOException e ) {
}}
// check local seed
if (this.mySeed == null) initMySeed();
name = this.mySeed.getName().toLowerCase();
if (name.equals(peerName)) return this.mySeed;
// nothing found
return null;
}
public Seed lookupByIP(
final InetAddress peerIP,
final int port, /* port may be -1 if not significant */
final boolean lookupConnected,
final boolean lookupDisconnected,
final boolean lookupPotential
) {
if (peerIP == null) return null;
// local peer?
if (Domains.isThisHostIP(peerIP)) {
if (this.mySeed == null) initMySeed();
return this.mySeed;
}
// then try to use the cache
Seed seed = null;
String ipString = peerIP.getHostAddress();
if (lookupConnected) synchronized (this) {
try {
Collection<byte[]> idx = this.seedActiveDB.select(Seed.IP, ipString);
for (byte[] pk: idx) {
seed = this.getConnected(ASCII.String(pk));
if (seed == null) continue;
if ((port >= 0) && (seed.getPort() != port)) continue;
//System.out.println("*** found lookupByIP in connected: " + peerIP.toString() + " -> " + seed.getName());
return seed;
}
} catch (final IOException e ) {
}
}
if (lookupDisconnected) synchronized (this) {
try {
Collection<byte[]> idx = this.seedPassiveDB.select(Seed.IP, ipString);
for (byte[] pk: idx) {
seed = this.getDisconnected(ASCII.String(pk));
if (seed == null) continue;
if ((port >= 0) && (seed.getPort() != port)) continue;
//System.out.println("*** found lookupByIP in disconnected: " + peerIP.toString() + " -> " + seed.getName());
return seed;
}
} catch (final IOException e ) {
}
}
if (lookupPotential) synchronized (this) {
try {
Collection<byte[]> idx = this.seedPotentialDB.select(Seed.IP, ipString);
for (byte[] pk: idx) {
seed = this.getPotential(ASCII.String(pk));
if (seed == null) continue;
if ((port >= 0) && (seed.getPort() != port)) continue;
//System.out.println("*** found lookupByIP in potential: " + peerIP.toString() + " -> " + seed.getName());
return seed;
}
} catch (final IOException e ) {
}
}
// check local seed
if (this.mySeed == null) return null;
String s = this.mySeed.getIP();
if (s == null || !ipString.equals(s)) return null;
int p = this.mySeed.getPort();
if ((port >= 0) && (p != port)) return null;
//System.out.println("*** found lookupByIP as my seed: " + peerIP.toString() + " -> " + this.mySeed.getName());
return this.mySeed;
}
private ArrayList<String> storeSeedList(final File seedFile, final boolean addMySeed) throws IOException {
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
PrintWriter pw = null;
final ArrayList<String> v = new ArrayList<String>(this.seedActiveDB.size() + 1);
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
try {
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
pw = new PrintWriter(new BufferedWriter(new FileWriter(seedFile)));
// store own peer seed
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
String line;
if (this.mySeed == null) initMySeed();
if (addMySeed) {
line = this.mySeed.genSeedStr(null);
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
v.add(line);
pw.print(line + serverCore.CRLF_STRING);
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
}
// store active peer seeds
Seed ys;
Iterator<Seed> se = seedsConnected(true, false, null, (float) 0.0);
while (se.hasNext()) {
ys = se.next();
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
if (ys != null) {
line = ys.genSeedStr(null);
v.add(line);
pw.print(line + serverCore.CRLF_STRING);
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
}
}
// store some of the not-so-old passive peer seeds (limit: 1 day)
se = seedsDisconnected(true, false, null, (float) 0.0);
final long timeout = System.currentTimeMillis() - (1000L * 60L * 60L * 24L);
while (se.hasNext()) {
ys = se.next();
if (ys != null) {
if (ys.getLastSeenUTC() < timeout) continue;
line = ys.genSeedStr(null);
v.add(line);
pw.print(line + serverCore.CRLF_STRING);
}
}
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
pw.flush();
} finally {
if (pw != null) try { pw.close(); } catch (final Exception e) {}
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
}
return v;
}
protected String uploadSeedList(final yacySeedUploader uploader,
removed the indexing queue. This queue was superfluous since the introduction of the blocking queues last year, where documents are parsed, analysed and stored in the index with concurrency. - The indexing queue was a historic data structure that was introduced at the very beginning at the project as a part of the switchboard organisation object structure. Without the indexing queue the switchboard queue becomes also superfluous. It has been removed as well. - Removing the switchboard queue requires that all servlets are called without a opaque generic ('<?>'). That caused that all serlets had to be modified. - Many servlets displayed the indexing queue or the size of that queue. In the past months the indexer was so fast that mostly the indexing queue appeared empty, so there was no use of it any more. Because the queue has been removed, the display in the servlets had also to be removed. - The surrogate work task had been a part of the indexing queue control structure. Without the indexing queue the surrogates needed its own task management. That has been integrated here. - Because the indexing queue had a special queue entry object and properties attached to this object, the propterties had to be moved to the queue entry object which is part of the new indexing queue withing the blocking queue, the Response Object. That object has now also the new properties of the removed indexing queue entry object. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6225 6c8d7289-2bf4-0310-a012-ef5d649a1542
16 years ago
final serverSwitch sb,
final SeedDB seedDB,
final DigestURL seedURL) throws Exception {
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
// upload a seed file, if possible
if (seedURL == null) throw new NullPointerException("UPLOAD - Error: URL not given");
String log = null;
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
File seedFile = null;
try {
// create a seed file which for uploading ...
seedFile = File.createTempFile("seedFile",".txt", seedDB.myOwnSeedFile.getParentFile());
seedFile.deleteOnExit();
if (Network.log.isFine()) Network.log.fine("SaveSeedList: Storing seedlist into tempfile " + seedFile.toString());
final ArrayList<String> uv = storeSeedList(seedFile, true);
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
// uploading the seed file
if (Network.log.isFine()) Network.log.fine("SaveSeedList: Trying to upload seed-file, " + seedFile.length() + " bytes, " + uv.size() + " entries.");
log = uploader.uploadSeedFile(sb, seedFile);
// test download
if (Network.log.isFine()) Network.log.fine("SaveSeedList: Trying to download seed-file '" + seedURL + "'.");
final Iterator<String> check = downloadSeedFile(seedURL);
// Comparing if local copy and uploaded copy are equal
final String errorMsg = checkCache(uv, check);
if (errorMsg == null)
log = log + "UPLOAD CHECK - Success: the result vectors are equal" + serverCore.CRLF_STRING;
else {
throw new Exception("UPLOAD CHECK - Error: the result vector is different. " + errorMsg + serverCore.CRLF_STRING);
}
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
} finally {
if (seedFile != null)
try {
FileUtils.deletedelete(seedFile);
} catch (final Exception e) {
/* ignore this */
}
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
}
Multiple updates regarding the yacy seedUpload facility, optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
20 years ago
return log;
}
private static Iterator<String> downloadSeedFile(final DigestURL seedURL) throws IOException {
// Configure http headers
final RequestHeader reqHeader = new RequestHeader();
reqHeader.put(HeaderFramework.PRAGMA, "no-cache");
reqHeader.put(HeaderFramework.CACHE_CONTROL, "no-cache"); // httpc uses HTTP/1.0 is this necessary?
reqHeader.put(HeaderFramework.USER_AGENT, ClientIdentification.yacyInternetCrawlerAgent.userAgent);
final HTTPClient client = new HTTPClient(ClientIdentification.yacyInternetCrawlerAgent);
client.setHeader(reqHeader.entrySet());
byte[] content = null;
try {
// send request
content = client.GETbytes(seedURL);
} catch (final Exception e) {
throw new IOException("Unable to download seed file '" + seedURL + "'. " + e.getMessage());
}
// check response code
if (client.getHttpResponse().getStatusLine().getStatusCode() != 200) {
throw new IOException("Server returned status: " + client.getHttpResponse().getStatusLine());
}
try {
// uncompress it if it is gzipped
content = FileUtils.uncompressGZipArray(content);
// convert it into an array
return FileUtils.strings(content);
} catch (final Exception e) {
throw new IOException("Unable to uncompress seed file '" + seedURL + "'. " + e.getMessage());
}
}
private static String checkCache(final ArrayList<String> uv, final Iterator<String> check) {
if ((check == null) || (uv == null)) {
if (Network.log.isFine()) Network.log.fine("SaveSeedList: Local and uploades seed-list are different");
return "Entry count is different: uv.size() = " + ((uv == null) ? "null" : Integer.toString(uv.size()));
}
if (Network.log.isFine()) Network.log.fine("SaveSeedList: Comparing local and uploades seed-list entries ...");
int i = 0;
while (check.hasNext() && i < uv.size()) {
if (!((uv.get(i)).equals(check.next()))) return "Element at position " + i + " is different.";
i++;
}
// no difference found
return null;
}
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
/**
* resolve a yacy address
*/
@Override
major step forward to network switching (target is easy switch to intranet or other networks .. and back) This change is inspired by the need to see a network connected to the index it creates in a indexing team. It is not possible to divide the network and the index. Therefore all control files for the network was moved to the network within the INDEX/<network-name> subfolder. The remaining YACYDB is superfluous and can be deleted. The yacyDB and yacyNews data structures are now part of plasmaWordIndex. Therefore all methods, using static access to yacySeedDB had to be rewritten. A special problem had been all the port forwarding methods which had been tightly mixed with seed construction. It was not possible to move the port forwarding functions to the place, meaning and usage of plasmaWordIndex. Therefore the port forwarding had been deleted (I guess nobody used it and it can be simulated by methods outside of YaCy). The mySeed.txt is automatically moved to the current network position. A new effect causes that every network will create a different local seed file, which is ok, since the seed identifies the peer only against the network (it is the purpose of the seed hash to give a peer a location within the DHT). No other functional change has been made. The next steps to enable network switcing are: - shift of crawler tables from PLASMADB into the network (crawls are also network-specific) - possibly shift of plasmaWordIndex code into yacy package (index management is network-specific) - servlet to switch networks git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4765 6c8d7289-2bf4-0310-a012-ef5d649a1542
17 years ago
public String resolve(String host) {
Seed seed;
int p;
String subdom = null;
if (host.endsWith(".yacyh")) {
// this is not functional at the moment
// caused by lowecasing of hashes at the browser client
p = host.indexOf('.');
if ((p > 0) && (p != (host.length() - 6))) {
subdom = host.substring(0, p);
host = host.substring(p + 1);
}
// check if we have a b64-hash or a hex-hash
String hash = host.substring(0, host.length() - 6);
if (hash.length() > Word.commonHashLength) {
// this is probably a hex-hash
hash = Seed.hexHash2b64Hash(hash);
}
// check remote seeds
seed = getConnected(hash); // checks only remote, not local
// check local seed
if (seed == null) {
if (this.mySeed == null) initMySeed();
if (hash.equals(this.mySeed.hash))
seed = this.mySeed;
else return null;
}
return seed.getPublicAddress() + ((subdom == null) ? "" : ("/" + subdom));
} else if (host.endsWith(".yacy")) {
// identify subdomain
p = host.indexOf('.');
if ((p > 0) && (p != (host.length() - 5))) {
subdom = host.substring(0, p); // no double-dot attack possible, the subdom cannot have ".." in it
host = host.substring(p + 1); // if ever, the double-dots are here but do not harm
}
// identify domain
final String domain = host.substring(0, host.length() - 5).toLowerCase();
seed = lookupByName(domain);
if (seed == null) return null;
if (this.mySeed == null) initMySeed();
if ((seed == this.mySeed) && (!(seed.isOnline()))) {
// take local ip instead of external
return Switchboard.getSwitchboard().myPublicIP() + ":" + Switchboard.getSwitchboard().getConfig("port", "8090") + ((subdom == null) ? "" : ("/" + subdom));
}
return seed.getPublicAddress() + ((subdom == null) ? "" : ("/" + subdom));
} else {
return null;
}
}
public String targetAddress(final String targetHash) {
// find target address
String address;
if (targetHash.equals(mySeed().hash)) {
address = mySeed().getClusterAddress();
} else {
final Seed targetSeed = getConnected(targetHash);
if (targetSeed == null) { return null; }
address = targetSeed.getClusterAddress();
}
if (address == null) address = "localhost:8090";
return address;
}
private class seedEnum implements Iterator<Seed> {
13 years ago
private Iterator<Map.Entry<byte[], Map<String, String>>> it;
private Seed nextSeed;
private final MapDataMining database;
private double minVersion;
private seedEnum(final boolean up, final boolean rot, final byte[] firstKey, final byte[] secondKey, final MapDataMining database, final double minVersion) {
this.database = database;
this.minVersion = minVersion;
try {
13 years ago
this.it = (firstKey == null) ? database.entries(up, rot) : database.entries(up, rot, firstKey, secondKey);
double version;
while (true) {
this.nextSeed = internalNext();
if (this.nextSeed == null) break;
version = this.nextSeed.getVersion();
if (version >= this.minVersion || version == 0.0) break; // include 0.0 to access always developer peers
}
} catch (final IOException e) {
ConcurrentLog.logException(e);
Network.log.severe("ERROR seedLinEnum: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
if (database == SeedDB.this.seedActiveDB) SeedDB.this.seedActiveDB = resetSeedTable(SeedDB.this.seedActiveDB, SeedDB.this.seedActiveDBFile);
if (database == SeedDB.this.seedPassiveDB) SeedDB.this.seedPassiveDB = resetSeedTable(SeedDB.this.seedPassiveDB, SeedDB.this.seedPassiveDBFile);
this.it = null;
} catch (final kelondroException e) {
ConcurrentLog.logException(e);
Network.log.severe("ERROR seedLinEnum: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
if (database == SeedDB.this.seedActiveDB) SeedDB.this.seedActiveDB = resetSeedTable(SeedDB.this.seedActiveDB, SeedDB.this.seedActiveDBFile);
if (database == SeedDB.this.seedPassiveDB) SeedDB.this.seedPassiveDB = resetSeedTable(SeedDB.this.seedPassiveDB, SeedDB.this.seedPassiveDBFile);
this.it = null;
}
}
private seedEnum(final boolean up, final String field, final MapDataMining database) {
this.database = database;
try {
13 years ago
this.it = database.entries(up, field);
this.nextSeed = internalNext();
} catch (final kelondroException e) {
ConcurrentLog.logException(e);
Network.log.severe("ERROR seedLinEnum: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
if (database == SeedDB.this.seedActiveDB) SeedDB.this.seedActiveDB = resetSeedTable(SeedDB.this.seedActiveDB, SeedDB.this.seedActiveDBFile);
if (database == SeedDB.this.seedPassiveDB) SeedDB.this.seedPassiveDB = resetSeedTable(SeedDB.this.seedPassiveDB, SeedDB.this.seedPassiveDBFile);
if (database == SeedDB.this.seedPotentialDB) SeedDB.this.seedPotentialDB = resetSeedTable(SeedDB.this.seedPotentialDB, SeedDB.this.seedPotentialDBFile);
this.it = null;
}
}
@Override
public boolean hasNext() {
return (this.nextSeed != null);
}
private Seed internalNext() {
if (this.it == null || !(this.it.hasNext())) return null;
try {
13 years ago
Map.Entry<byte[], Map<String, String>> dna0;
ConcurrentHashMap<String, String> dna;
while (this.it.hasNext()) {
try {
dna0 = this.it.next();
} catch (final OutOfMemoryError e) {
ConcurrentLog.logException(e);
dna0 = null;
}
assert dna0 != null;
if (dna0 == null) continue;
13 years ago
if (dna0.getValue() instanceof ConcurrentHashMap) {
dna = (ConcurrentHashMap<String, String>) dna0.getValue();
} else {
dna = new ConcurrentHashMap<String, String>();
13 years ago
dna.putAll(dna0.getValue());
}
13 years ago
if (dna0.getKey() == null) continue; // bad seed
final String hash = UTF8.String(dna0.getKey());
return new Seed(hash, dna);
}
return null;
} catch (final Exception e) {
ConcurrentLog.logException(e);
Network.log.severe("ERROR internalNext: seed.db corrupt (" + e.getMessage() + "); resetting seed.db", e);
if (this.database == SeedDB.this.seedActiveDB) SeedDB.this.seedActiveDB = resetSeedTable(SeedDB.this.seedActiveDB, SeedDB.this.seedActiveDBFile);
if (this.database == SeedDB.this.seedPassiveDB) SeedDB.this.seedPassiveDB = resetSeedTable(SeedDB.this.seedPassiveDB, SeedDB.this.seedPassiveDBFile);
if (this.database == SeedDB.this.seedPotentialDB) SeedDB.this.seedPotentialDB = resetSeedTable(SeedDB.this.seedPotentialDB, SeedDB.this.seedPotentialDBFile);
return null;
}
}
@Override
public Seed next() {
final Seed seed = this.nextSeed;
double version;
try {while (true) {
this.nextSeed = internalNext();
if (this.nextSeed == null) break;
version = this.nextSeed.getVersion();
if (version >= this.minVersion || version == 0.0) break; // include 0.0 to access always developer peers
}} catch (final kelondroException e) {
ConcurrentLog.logException(e);
// emergency reset
Network.log.severe("seed-db emergency reset", e);
this.database.clear();
this.nextSeed = null;
return null;
}
return seed;
}
@Override
public void remove() {
throw new UnsupportedOperationException();
}
}
}