or will be superfluous or subject of complete redesign after the migration to solr. Removing these things now will make the transition to solr more simple.pull/1/head
Michael Peter Christen
13 years ago
parent
6f1ddb2519
commit
3bcd9d622b
@ -1,108 +0,0 @@
|
||||
//-----------------------
|
||||
//part of the AnomicHTTPD caching proxy
|
||||
//(C) by Michael Peter Christen; mc@yacy.net
|
||||
//first published on http://www.anomic.de
|
||||
//Frankfurt, Germany, 2005
|
||||
//
|
||||
//This file is contributed by Matthias Soehnholz
|
||||
//
|
||||
// $LastChangedDate$
|
||||
// $LastChangedRevision$
|
||||
// $LastChangedBy$
|
||||
//
|
||||
//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
|
||||
|
||||
import net.yacy.cora.document.ASCII;
|
||||
import net.yacy.cora.protocol.RequestHeader;
|
||||
import net.yacy.search.Switchboard;
|
||||
import net.yacy.search.index.MetadataRepository;
|
||||
import net.yacy.search.index.Segment;
|
||||
import de.anomic.server.serverObjects;
|
||||
import de.anomic.server.serverSwitch;
|
||||
|
||||
public class IndexCleaner_p {
|
||||
private static MetadataRepository.BlacklistCleaner urldbCleanerThread = null;
|
||||
private static Segment.ReferenceCleaner indexCleanerThread = null;
|
||||
|
||||
public static serverObjects respond(@SuppressWarnings("unused") final RequestHeader header, final serverObjects post, final serverSwitch env) {
|
||||
final serverObjects prop = new serverObjects();
|
||||
final Switchboard sb = (Switchboard) env;
|
||||
prop.put("title", "DbCleanup_p");
|
||||
|
||||
// get segment
|
||||
Segment indexSegment = sb.index;
|
||||
|
||||
if (post!=null) {
|
||||
if (post.get("action").equals("ustart")) {
|
||||
if (urldbCleanerThread==null || !urldbCleanerThread.isAlive()) {
|
||||
urldbCleanerThread = indexSegment.urlMetadata().getBlacklistCleaner(Switchboard.urlBlacklist, sb.crawlStacker);
|
||||
urldbCleanerThread.start();
|
||||
}
|
||||
else {
|
||||
urldbCleanerThread.endPause();
|
||||
}
|
||||
}
|
||||
else if (post.get("action").equals("ustop") && (urldbCleanerThread!=null)) {
|
||||
urldbCleanerThread.abort();
|
||||
}
|
||||
else if (post.get("action").equals("upause") && (urldbCleanerThread!=null)) {
|
||||
urldbCleanerThread.pause();
|
||||
}
|
||||
else if (post.get("action").equals("rstart")) {
|
||||
if (indexCleanerThread==null || !indexCleanerThread.isAlive()) {
|
||||
indexCleanerThread = indexSegment.getReferenceCleaner(post.get("wordHash","AAAAAAAAAAAA").getBytes());
|
||||
indexCleanerThread.start();
|
||||
}
|
||||
else {
|
||||
indexCleanerThread.endPause();
|
||||
}
|
||||
}
|
||||
else if (post.get("action").equals("rstop") && (indexCleanerThread!=null)) {
|
||||
indexCleanerThread.abort();
|
||||
}
|
||||
else if (post.get("action").equals("rpause") && (indexCleanerThread!=null)) {
|
||||
indexCleanerThread.pause();
|
||||
}
|
||||
prop.put("LOCATION","");
|
||||
return prop;
|
||||
}
|
||||
if (urldbCleanerThread!=null) {
|
||||
prop.put("urldb", "1");
|
||||
prop.putNum("urldb_percentUrls", ((double)urldbCleanerThread.totalSearchedUrls/indexSegment.urlMetadata().size())*100);
|
||||
prop.putNum("urldb_blacklisted", urldbCleanerThread.blacklistedUrls);
|
||||
prop.putNum("urldb_total", urldbCleanerThread.totalSearchedUrls);
|
||||
prop.putHTML("urldb_lastBlacklistedUrl", urldbCleanerThread.lastBlacklistedUrl);
|
||||
prop.put("urldb_lastBlacklistedHash", urldbCleanerThread.lastBlacklistedHash);
|
||||
prop.putHTML("urldb_lastUrl", urldbCleanerThread.lastUrl);
|
||||
prop.put("urldb_lastHash", urldbCleanerThread.lastHash);
|
||||
prop.put("urldb_threadAlive", Boolean.toString(urldbCleanerThread.isAlive()));
|
||||
prop.put("urldb_threadToString", urldbCleanerThread.toString());
|
||||
final double percent = ((double)urldbCleanerThread.blacklistedUrls/urldbCleanerThread.totalSearchedUrls)*100;
|
||||
prop.putNum("urldb_percent", percent);
|
||||
}
|
||||
if (indexCleanerThread!=null) {
|
||||
prop.put("rwidb", "1");
|
||||
prop.put("rwidb_threadAlive", Boolean.toString(indexCleanerThread.isAlive()));
|
||||
prop.put("rwidb_threadToString", indexCleanerThread.toString());
|
||||
prop.putNum("rwidb_RWIcountstart", indexCleanerThread.rwiCountAtStart);
|
||||
prop.putNum("rwidb_RWIcountnow", indexCleanerThread.rwisize());
|
||||
prop.put("rwidb_wordHashNow", (indexCleanerThread.wordHashNow == null) ? "NULL" : ASCII.String(indexCleanerThread.wordHashNow));
|
||||
prop.put("rwidb_lastWordHash", (indexCleanerThread.lastWordHash == null) ? "null" : ASCII.String(indexCleanerThread.lastWordHash));
|
||||
prop.putNum("rwidb_lastDeletionCounter", indexCleanerThread.lastDeletionCounter);
|
||||
|
||||
}
|
||||
return prop;
|
||||
}
|
||||
}
|
||||
@ -1,108 +0,0 @@
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml">
|
||||
<head>
|
||||
<title>YaCy '#[clientname]#': Index Cleaner</title>
|
||||
#%env/templates/metas.template%#
|
||||
</head>
|
||||
<body id="IndexControlCleaner">
|
||||
<div id="fullcontent">
|
||||
#(inline)##%env/templates/header.template%#
|
||||
|
||||
<h2>Steering of API Actions</h2>
|
||||
<p>This table shows search results that had been sorted out from the search result display because their content had not been verified.
|
||||
This means that the searched word does not appear on the search page.
|
||||
</p>::#(/inline)#
|
||||
#(showtable)#::
|
||||
<form action="IndexControlCleaner_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8" id="cleanerlist">
|
||||
<fieldset>
|
||||
<legend><label for="apilist">Recorded Actions</label></legend>
|
||||
<p><span id="resCounter" style="display: inline;">
|
||||
#(navigation)#
|
||||
::
|
||||
#(left)#<img src="env/grafics/navdl.gif" alt="no previous page" />::<a href="Table_API_p.html?startRecord=#[startRecord]#&maximumRecords=#[maximumRecords]#&inline=#(inline)#false::true#(/inline)#&filter=#[filter]#" target="_self"><img src="env/grafics/navsl.gif" alt="previous page" /></a>#(/left)#
|
||||
#[startRecord]#-#[to]# of #[of]#
|
||||
#(right)#<img src="env/grafics/navdr.gif" alt="no next page" />::<a href="Table_API_p.html?startRecord=#[startRecord]#&maximumRecords=#[maximumRecords]#&inline=#(inline)#false::true#(/inline)#&filter=#[filter]#" target="_self"><img src="env/grafics/navsr.gif" alt="next page" /></a>#(/right)#
|
||||
<img src="env/grafics/nave.gif" alt="" />
|
||||
#(/navigation)#
|
||||
<div>
|
||||
<input type="hidden" name="startRecord" value="#[startRecord]#" />
|
||||
<input type="hidden" name="maximumRecords" value="#[maximumRecords]#" />
|
||||
<input type="hidden" name="inline" value="#(inline)#false::true#(/inline)#" />
|
||||
<input type="hidden" name="filter" value="#[filter]#" />
|
||||
<input type="text" name="query" value="#[query]#" style="font-size:16px;float:left;border:0px;height:20px;background-image:url('env/grafics/find.gif');background-repeat:no-repeat;background-position:right top;" />
|
||||
</div>
|
||||
</span><br/></p>
|
||||
<p style="clear:both;">
|
||||
<table class="sortable" border="0" cellpadding="2" cellspacing="1">
|
||||
<tr class="TableHeader" valign="bottom">
|
||||
<th class="sorttable_nosort"><input type="checkbox" id="allswitch" onclick="checkAll(this.form.id, this.checked);" /></th>
|
||||
<th>Type</th>
|
||||
<th width="100">Comment</th>
|
||||
<th>Call<br/>Count</th>
|
||||
<th>Recording<br/>Date</th>
|
||||
<th>Last Exec<br/>Date</th>
|
||||
<th>Next Exec<br/>Date</th>
|
||||
<th class="sorttable_nosort">Scheduler</th>
|
||||
#(inline)#<th class="sorttable_nosort">URL</th>::#(/inline)#
|
||||
</tr>
|
||||
#{list}#
|
||||
<tr class="TableCell#(dark)#Light::Dark::Summary#(/dark)#">
|
||||
<td align="left"><input type="checkbox" name="item_#[count]#" value="mark_#[pk]#" /></td>
|
||||
<td>#[type]#</td>
|
||||
<td>#[comment]#</td>
|
||||
<td>#[callcount]#</td>
|
||||
<td>#[dateRecording]#</td>
|
||||
<td>#[dateLastExec]#</td>
|
||||
<td>#[dateNextExec]#</td>
|
||||
<td>
|
||||
#(scheduler)#
|
||||
<form action="Table_API_p.html" method="post" enctype="multipart/form-data" id="modify_repeat" accept-charset="UTF-8">
|
||||
<select name="repeat_select" onchange='this.form.submit()'>
|
||||
<option value="off" selected="selected">no repetition</option>
|
||||
<option value="on">activate scheduler</option>
|
||||
</select>
|
||||
<input type="hidden" name="pk" value="#[pk]#" />
|
||||
<input type="hidden" name="inline" value="#[inline]#" />
|
||||
<input type="hidden" name="filter" value="#[filter]#" />
|
||||
</form>
|
||||
::
|
||||
<form action="Table_API_p.html" method="post" enctype="multipart/form-data" id="modify_repeat">
|
||||
<table><tr><td>
|
||||
<select name="repeat_time" onchange='this.form.submit()'>
|
||||
#{scale}#
|
||||
<option value="#[time]#" #(selected)#::selected="selected"#(/selected)#>#[time]#</option>
|
||||
#{/scale}#
|
||||
</select>
|
||||
</td><td>
|
||||
<select name="repeat_unit" onchange='this.form.submit()'>
|
||||
<option value="selminutes" #(selectedMinutes)#::selected="selected"#(/selectedMinutes)#>minutes</option>
|
||||
<option value="selhours" #(selectedHours)#::selected="selected"#(/selectedHours)#>hours</option>
|
||||
<option value="seldays" #(selectedDays)#::selected="selected"#(/selectedDays)#>days</option>
|
||||
</select>
|
||||
</td></tr></table>
|
||||
<input type="hidden" name="pk" value="#[pk]#" />
|
||||
<input type="hidden" name="inline" value="#[inline]#" />
|
||||
<input type="hidden" name="filter" value="#[filter]#" />
|
||||
<noscript><input type="submit" value="Submit" /></noscript>
|
||||
</form>
|
||||
#(/scheduler)#
|
||||
</td>
|
||||
#(inline)#<td>#[url]#</td>::#(/inline)#
|
||||
</tr>
|
||||
#{/list}#
|
||||
</fieldset>
|
||||
</table>
|
||||
</p>
|
||||
<p>
|
||||
<input type="hidden" name="num" value="#[num]#" />
|
||||
<input type="submit" name="deletefromindex" value="Delete selected references from the search index" />
|
||||
<input type="submit" name="deleterows" value="Delete selected entries from the list" />
|
||||
</p>
|
||||
|
||||
</form>
|
||||
#(/showtable)#
|
||||
</div>
|
||||
#%env/templates/footer.template%#
|
||||
</body>
|
||||
</html>
|
||||
|
||||
@ -1,564 +0,0 @@
|
||||
// URLAnalysis.java
|
||||
// (C) 2009 by Michael Peter Christen; mc@yacy.net, Frankfurt a. M., Germany
|
||||
// first published 24.02.2009 on http://yacy.net
|
||||
//
|
||||
// This is a part of YaCy, a peer-to-peer based web search engine
|
||||
//
|
||||
// $LastChangedDate$
|
||||
// $LastChangedRevision$
|
||||
// $LastChangedBy$
|
||||
//
|
||||
// LICENSE
|
||||
//
|
||||
// This program is free software; you can redistribute it and/or modify
|
||||
// it under the terms of the GNU General Public License as published by
|
||||
// the Free Software Foundation; either version 2 of the License, or
|
||||
// (at your option) any later version.
|
||||
//
|
||||
// This program is distributed in the hope that it will be useful,
|
||||
// but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
// GNU General Public License for more details.
|
||||
//
|
||||
// You should have received a copy of the GNU General Public License
|
||||
// along with this program; if not, write to the Free Software
|
||||
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
||||
|
||||
|
||||
package de.anomic.data;
|
||||
|
||||
import java.io.BufferedInputStream;
|
||||
import java.io.BufferedOutputStream;
|
||||
import java.io.BufferedReader;
|
||||
import java.io.File;
|
||||
import java.io.FileInputStream;
|
||||
import java.io.FileOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.io.OutputStream;
|
||||
import java.net.MalformedURLException;
|
||||
import java.util.HashSet;
|
||||
import java.util.Iterator;
|
||||
import java.util.Map;
|
||||
import java.util.Set;
|
||||
import java.util.TreeMap;
|
||||
import java.util.TreeSet;
|
||||
import java.util.concurrent.ArrayBlockingQueue;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
import java.util.regex.Pattern;
|
||||
import java.util.zip.GZIPInputStream;
|
||||
import java.util.zip.GZIPOutputStream;
|
||||
|
||||
import net.yacy.cora.document.UTF8;
|
||||
import net.yacy.kelondro.data.meta.DigestURI;
|
||||
import net.yacy.kelondro.data.meta.URIMetadataRow;
|
||||
import net.yacy.kelondro.data.word.WordReferenceRow;
|
||||
import net.yacy.kelondro.index.HandleMap;
|
||||
import net.yacy.kelondro.index.HandleSet;
|
||||
import net.yacy.kelondro.index.RowSpaceExceededException;
|
||||
import net.yacy.kelondro.logging.Log;
|
||||
import net.yacy.kelondro.order.Base64Order;
|
||||
import net.yacy.kelondro.rwi.ReferenceContainerArray;
|
||||
import net.yacy.kelondro.util.MemoryControl;
|
||||
import net.yacy.search.index.MetadataRepository;
|
||||
import net.yacy.search.index.Segment;
|
||||
import net.yacy.search.index.MetadataRepository.Export;
|
||||
|
||||
public class URLAnalysis {
|
||||
|
||||
private static final Pattern patternMinus = Pattern.compile("-");
|
||||
|
||||
/**
|
||||
* processes to analyse URL lists
|
||||
*/
|
||||
|
||||
private static DigestURI poison = null;
|
||||
static {
|
||||
try {
|
||||
poison = new DigestURI("http://poison.org/poison");
|
||||
} catch (final MalformedURLException e) {
|
||||
poison = null;
|
||||
}
|
||||
}
|
||||
|
||||
public static class splitter extends Thread {
|
||||
|
||||
private final ArrayBlockingQueue<DigestURI> in;
|
||||
private final ConcurrentHashMap<String, Integer> out;
|
||||
|
||||
public splitter(final ArrayBlockingQueue<DigestURI> in, final ConcurrentHashMap<String, Integer> out) {
|
||||
this.in = in;
|
||||
this.out = out;
|
||||
}
|
||||
|
||||
@Override
|
||||
public void run() {
|
||||
try {
|
||||
DigestURI url;
|
||||
final Pattern p = Pattern.compile("~|\\(|\\)|\\+|-|@|:|%|\\.|;|_");
|
||||
while (true) {
|
||||
try {
|
||||
url = this.in.take();
|
||||
if (url == poison) break;
|
||||
update(patternMinus.matcher(url.getHost()).replaceAll("\\.").split("\\."));
|
||||
update(p.matcher(url.getPath()).replaceAll("/").split("/"));
|
||||
} catch (final InterruptedException e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
}
|
||||
} catch (final Exception e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
}
|
||||
|
||||
private void update(final String[] s) {
|
||||
Integer c;
|
||||
for (final String t: s) {
|
||||
if (t.isEmpty()) continue;
|
||||
c = this.out.get(t);
|
||||
this.out.put(t, (c == null) ? 1 : c.intValue() + 1);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public static void cleanup(final ConcurrentHashMap<String, Integer> stat) {
|
||||
Map.Entry<String, Integer> entry;
|
||||
int c, low = Integer.MAX_VALUE;
|
||||
Iterator<Map.Entry<String, Integer>> i = stat.entrySet().iterator();
|
||||
while (i.hasNext()) {
|
||||
entry = i.next();
|
||||
c = entry.getValue().intValue();
|
||||
if (c == 1) {
|
||||
i.remove();
|
||||
} else {
|
||||
if (c < low) low = c;
|
||||
}
|
||||
}
|
||||
i = stat.entrySet().iterator();
|
||||
while (i.hasNext()) {
|
||||
entry = i.next();
|
||||
c = entry.getValue().intValue();
|
||||
if (c == low) {
|
||||
i.remove();
|
||||
}
|
||||
}
|
||||
Runtime.getRuntime().gc();
|
||||
}
|
||||
|
||||
public static void genstat(final String urlfile) {
|
||||
|
||||
final boolean gz = urlfile.endsWith(".gz");
|
||||
final String analysis = (gz) ? urlfile.substring(0, urlfile.length() - 3) + ".stats.gz" : urlfile + ".stats";
|
||||
final long cleanuplimit = Math.max(50 * 1024 * 1024, MemoryControl.available() / 8);
|
||||
|
||||
// start threads
|
||||
final ArrayBlockingQueue<DigestURI> in = new ArrayBlockingQueue<DigestURI>(1000);
|
||||
final ConcurrentHashMap<String, Integer> out = new ConcurrentHashMap<String, Integer>();
|
||||
for (int i = 0, available = Runtime.getRuntime().availableProcessors(); i < available; i++) new splitter(in, out).start();
|
||||
final splitter spl = new splitter(in, out);
|
||||
spl.start();
|
||||
|
||||
// put urls in queue
|
||||
final File infile = new File(urlfile);
|
||||
final File outfile = new File(analysis);
|
||||
BufferedReader reader = null;
|
||||
long time = System.currentTimeMillis();
|
||||
final long start = time;
|
||||
int count = 0;
|
||||
|
||||
System.out.println("start processing");
|
||||
try {
|
||||
InputStream is = new BufferedInputStream(new FileInputStream(infile));
|
||||
if (gz) is = new GZIPInputStream(is);
|
||||
reader = new BufferedReader(new InputStreamReader(is));
|
||||
String line;
|
||||
while ((line = reader.readLine()) != null) {
|
||||
line = line.trim();
|
||||
if (line.length() > 0) {
|
||||
try {
|
||||
final DigestURI url = new DigestURI(line);
|
||||
in.put(url);
|
||||
} catch (final InterruptedException e) {
|
||||
Log.logException(e);
|
||||
} catch (final MalformedURLException e) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
count++;
|
||||
if (System.currentTimeMillis() - time > 1000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("processed " + count + " urls, " + (MemoryControl.available() / 1024 / 1024) + " mb left, " + count * 1000L / (time - start) + " url/second");
|
||||
if (MemoryControl.available() < cleanuplimit) {
|
||||
System.out.println("starting cleanup, " + out.size() + " entries in statistic");
|
||||
cleanup(out);
|
||||
System.out.println("finished cleanup, " + out.size() + " entries in statistic left, " + (MemoryControl.available() / 1024 / 1024) + " mb left");
|
||||
}
|
||||
}
|
||||
}
|
||||
reader.close();
|
||||
} catch (final IOException e) {
|
||||
Log.logException(e);
|
||||
} finally {
|
||||
if (reader != null) try { reader.close(); } catch (final Exception e) {}
|
||||
}
|
||||
|
||||
// stop threads
|
||||
System.out.println("stopping threads");
|
||||
for (int i = 0, available = Runtime.getRuntime().availableProcessors() + 1; i < available; i++) try {
|
||||
in.put(poison);
|
||||
} catch (final InterruptedException e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
try {
|
||||
spl.join();
|
||||
} catch (final InterruptedException e1) {
|
||||
Log.logException(e1);
|
||||
}
|
||||
|
||||
// generate statistics
|
||||
System.out.println("start processing results");
|
||||
final TreeMap<String, Integer> results = new TreeMap<String, Integer>();
|
||||
count = 0;
|
||||
Map.Entry<String, Integer> entry;
|
||||
final Iterator<Map.Entry<String, Integer>> i = out.entrySet().iterator();
|
||||
while (i.hasNext()) {
|
||||
entry = i.next();
|
||||
results.put(num(entry.getValue().intValue() * (entry.getKey().length() - 1)) + " - " + entry.getKey(), entry.getValue());
|
||||
count++;
|
||||
i.remove(); // free memory
|
||||
if (System.currentTimeMillis() - time > 10000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("processed " + count + " results, " + (MemoryControl.available() / 1024 / 1024) + " mb left");
|
||||
}
|
||||
}
|
||||
|
||||
// write statistics
|
||||
System.out.println("start writing results");
|
||||
try {
|
||||
OutputStream os = new BufferedOutputStream(new FileOutputStream(outfile));
|
||||
if (gz) os = new GZIPOutputStream(os);
|
||||
count = 0;
|
||||
for (final Map.Entry<String, Integer> e: results.entrySet()) {
|
||||
os.write(UTF8.getBytes(e.getKey()));
|
||||
os.write(new byte[]{'\t'});
|
||||
os.write(UTF8.getBytes(Integer.toString(e.getValue())));
|
||||
os.write(new byte[]{'\n'});
|
||||
count++;
|
||||
if (System.currentTimeMillis() - time > 10000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("wrote " + count + " lines.");
|
||||
}
|
||||
}
|
||||
os.close();
|
||||
} catch (final IOException e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
|
||||
System.out.println("finished");
|
||||
}
|
||||
|
||||
public static void genhost(final String urlfile) {
|
||||
|
||||
final boolean gz = urlfile.endsWith(".gz");
|
||||
final String trunk = (gz) ? urlfile.substring(0, urlfile.length() - 3) + ".host" : urlfile + ".host";
|
||||
final HashSet<String> hosts = new HashSet<String>();
|
||||
final File infile = new File(urlfile);
|
||||
BufferedReader reader = null;
|
||||
long time = System.currentTimeMillis();
|
||||
final long start = time;
|
||||
int count = 0;
|
||||
|
||||
System.out.println("start processing");
|
||||
try {
|
||||
InputStream is = new BufferedInputStream(new FileInputStream(infile));
|
||||
if (gz) is = new GZIPInputStream(is);
|
||||
reader = new BufferedReader(new InputStreamReader(is));
|
||||
String line;
|
||||
while ((line = reader.readLine()) != null) {
|
||||
line = line.trim();
|
||||
if (line.length() > 0) {
|
||||
try {
|
||||
final DigestURI url = new DigestURI(line);
|
||||
hosts.add(url.getHost());
|
||||
} catch (final MalformedURLException e) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
count++;
|
||||
if (System.currentTimeMillis() - time > 1000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("processed " + count + " urls, " + (MemoryControl.available() / 1024 / 1024) + " mb left, " + count * 1000L / (time - start) + " url/second");
|
||||
}
|
||||
}
|
||||
reader.close();
|
||||
} catch (final IOException e) {
|
||||
Log.logException(e);
|
||||
} finally {
|
||||
if (reader != null) try { reader.close(); } catch (final Exception e) {}
|
||||
}
|
||||
|
||||
// copy everything into a TreeSet to order it
|
||||
System.out.println("start processing results");
|
||||
final TreeSet<String> results = new TreeSet<String>();
|
||||
count = 0;
|
||||
final Iterator<String> i = hosts.iterator();
|
||||
while (i.hasNext()) {
|
||||
results.add(i.next());
|
||||
count++;
|
||||
i.remove(); // free memory
|
||||
if (System.currentTimeMillis() - time > 10000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("processed " + count + " results, " + (MemoryControl.available() / 1024 / 1024) + " mb left");
|
||||
}
|
||||
}
|
||||
|
||||
// write hosts
|
||||
writeSet(trunk, gz, results);
|
||||
|
||||
System.out.println("finished");
|
||||
}
|
||||
|
||||
private static void writeSet(final String trunk, final boolean gz, final Set<String> set) {
|
||||
|
||||
// write hosts
|
||||
System.out.println("start writing results");
|
||||
final File outfile = new File(trunk + ((gz) ? ".gz" : ""));
|
||||
long time = System.currentTimeMillis();
|
||||
try {
|
||||
OutputStream os = new BufferedOutputStream(new FileOutputStream(outfile));
|
||||
if (gz) os = new GZIPOutputStream(os);
|
||||
int count = 0;
|
||||
for (final String h: set) {
|
||||
os.write(UTF8.getBytes(h));
|
||||
os.write(new byte[]{'\n'});
|
||||
count++;
|
||||
if (System.currentTimeMillis() - time > 10000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("wrote " + count + " lines.");
|
||||
}
|
||||
}
|
||||
os.close();
|
||||
} catch (final IOException e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
|
||||
System.out.println("finished writing results");
|
||||
}
|
||||
|
||||
public static void sortsplit(final String urlfile) {
|
||||
|
||||
final boolean gz = urlfile.endsWith(".gz");
|
||||
final String trunk = ((gz) ? urlfile.substring(0, urlfile.length() - 3) : urlfile) + ".sort";
|
||||
final File infile = new File(urlfile);
|
||||
final TreeSet<String> urls = new TreeSet<String>();
|
||||
BufferedReader reader = null;
|
||||
long time = System.currentTimeMillis();
|
||||
final long start = time;
|
||||
int count = 0;
|
||||
int filecount = 0;
|
||||
final long cleanuplimit = Math.max(50 * 1024 * 1024, MemoryControl.available() / 8);
|
||||
|
||||
System.out.println("start processing");
|
||||
try {
|
||||
InputStream is = new BufferedInputStream(new FileInputStream(infile));
|
||||
if (gz) is = new GZIPInputStream(is);
|
||||
reader = new BufferedReader(new InputStreamReader(is));
|
||||
String line;
|
||||
while ((line = reader.readLine()) != null) {
|
||||
line = line.trim();
|
||||
if (line.length() > 0) {
|
||||
try {
|
||||
final DigestURI url = new DigestURI(line);
|
||||
urls.add(url.toNormalform(true, true));
|
||||
} catch (final MalformedURLException e) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
count++;
|
||||
if (System.currentTimeMillis() - time > 1000) {
|
||||
time = System.currentTimeMillis();
|
||||
System.out.println("processed " + count + " urls, " + (MemoryControl.available() / 1024 / 1024) + " mb left, " + count * 1000L / (time - start) + " url/second");
|
||||
}
|
||||
if (MemoryControl.available() < cleanuplimit) {
|
||||
writeSet(trunk + "." + filecount, gz, urls);
|
||||
filecount++;
|
||||
urls.clear();
|
||||
Runtime.getRuntime().gc();
|
||||
}
|
||||
}
|
||||
reader.close();
|
||||
} catch (final IOException e) {
|
||||
Log.logException(e);
|
||||
} finally {
|
||||
if (reader != null) try { reader.close(); } catch (final Exception e) {}
|
||||
}
|
||||
|
||||
// write hosts
|
||||
writeSet(trunk + "." + filecount, gz, urls);
|
||||
|
||||
System.out.println("finished");
|
||||
}
|
||||
|
||||
public static void incell(final File cellPath, final String statisticPath) {
|
||||
try {
|
||||
final HandleMap idx = ReferenceContainerArray.referenceHashes(
|
||||
cellPath,
|
||||
Segment.wordReferenceFactory,
|
||||
Base64Order.enhancedCoder,
|
||||
WordReferenceRow.urlEntryRow);
|
||||
System.out.println("INDEX REFERENCE COLLECTION starting dump of statistics");
|
||||
idx.dump(new File(statisticPath));
|
||||
System.out.println("INDEX REFERENCE COLLECTION finished dump, wrote " + idx.size() + " entries to " + statisticPath);
|
||||
idx.close();
|
||||
} catch (final Exception e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
}
|
||||
|
||||
public static int diffurlcol(final String metadataPath, final String statisticFile, final String diffFile) throws IOException, RowSpaceExceededException {
|
||||
System.out.println("INDEX DIFF URL-COL startup");
|
||||
final HandleMap idx = new HandleMap(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, 4, new File(statisticFile));
|
||||
final MetadataRepository mr = new MetadataRepository(new File(metadataPath));
|
||||
mr.connectUrlDb(Segment.UrlDbName, false, false);
|
||||
final HandleSet hs = new HandleSet(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, 1000000);
|
||||
System.out.println("INDEX DIFF URL-COL loaded dump, starting diff");
|
||||
final long start = System.currentTimeMillis();
|
||||
long update = start - 7000;
|
||||
int count = 0;
|
||||
for (final byte[] refhash: mr) {
|
||||
if (idx.get(refhash) == -1) {
|
||||
// the key exists as urlhash in the URL database, but not in the collection as referenced urlhash
|
||||
hs.put(refhash);
|
||||
}
|
||||
count++;
|
||||
if (System.currentTimeMillis() - update > 10000) {
|
||||
System.out.println("INDEX DIFF URL-COL running, checked " + count + ", found " + hs.size() + " missing references so far, " + (((System.currentTimeMillis() - start) * (mr.size() - count) / count) / 60000) + " minutes remaining");
|
||||
update = System.currentTimeMillis();
|
||||
}
|
||||
}
|
||||
idx.close();
|
||||
mr.close();
|
||||
System.out.println("INDEX DIFF URL-COL finished diff, starting dump to " + diffFile);
|
||||
count = hs.dump(new File(diffFile));
|
||||
System.out.println("INDEX DIFF URL-COL finished dump, wrote " + count + " references that occur in the URL-DB, but not in the collection-dump");
|
||||
return count;
|
||||
}
|
||||
|
||||
public static void export(final String metadataPath, final int format, final String export, final String diffFile) throws IOException, RowSpaceExceededException {
|
||||
// format: 0=text, 1=html, 2=rss/xml
|
||||
System.out.println("URL EXPORT startup");
|
||||
final MetadataRepository mr = new MetadataRepository(new File(metadataPath));
|
||||
mr.connectUrlDb(Segment.UrlDbName, false, false);
|
||||
final HandleSet hs = (diffFile == null) ? null : new HandleSet(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, new File(diffFile));
|
||||
System.out.println("URL EXPORT loaded dump, starting export");
|
||||
final Export e = mr.export(new File(export), ".*", hs, format, false);
|
||||
try {
|
||||
e.join();
|
||||
} catch (final InterruptedException e1) {
|
||||
Log.logException(e1);
|
||||
}
|
||||
System.out.println("URL EXPORT finished export, wrote " + ((hs == null) ? mr.size() : hs.size()) + " entries");
|
||||
}
|
||||
|
||||
public static void delete(final String metadataPath, final String diffFile) throws IOException, RowSpaceExceededException {
|
||||
System.out.println("URL DELETE startup");
|
||||
final MetadataRepository mr = new MetadataRepository(new File(metadataPath));
|
||||
mr.connectUrlDb(Segment.UrlDbName, false, false);
|
||||
final int mrSize = mr.size();
|
||||
final HandleSet hs = new HandleSet(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, new File(diffFile));
|
||||
System.out.println("URL DELETE loaded dump, starting deletion of " + hs.size() + " entries from " + mrSize);
|
||||
for (final byte[] refhash: hs) {
|
||||
mr.remove(refhash);
|
||||
}
|
||||
System.out.println("URL DELETE finished deletions, " + mr.size() + " entries left in URL database");
|
||||
}
|
||||
|
||||
public static void main(final String[] args) {
|
||||
if (args[0].equals("-stat") && args.length >= 2) {
|
||||
// generate a statistics about common words in file, store to <file>.stat
|
||||
// example:
|
||||
// java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -stat DATA/EXPORT/urls1.txt.gz
|
||||
for (int i = 1; i < args.length; i++) genstat(args[i]);
|
||||
} else if (args[0].equals("-host") && args.length >= 2) {
|
||||
// generate a file <file>.host containing only the hosts of the urls
|
||||
for (int i = 1; i < args.length; i++) genhost(args[i]);
|
||||
} else if (args[0].equals("-sort") && args.length >= 2) {
|
||||
// generate file <file>.x.sort with sorted lists and split the file in smaller pieces
|
||||
for (int i = 1; i < args.length; i++) sortsplit(args[i]);
|
||||
} else if (args[0].equals("-incell") && args.length >= 2) {
|
||||
// generate a dump of all referenced URL hashes from a given RICELL
|
||||
// example:
|
||||
// java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -incell DATA/INDEX/freeworld/TEXT/RICELL used.dump
|
||||
incell(new File(args[1]), args[2]);
|
||||
} else if (args[0].equals("-diffurlcol") && args.length >= 3) {
|
||||
// make a diff-file that contains hashes from the url database that do not occur in the collection reference dump
|
||||
// example:
|
||||
// java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -diffurlcol DATA/INDEX/freeworld/TEXT/METADATA used.dump diffurlcol.dump
|
||||
try {
|
||||
diffurlcol(args[1], args[2], args[3]);
|
||||
} catch (final Exception e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
} else if (args[0].equals("-export") && args.length >= 4) {
|
||||
// export a url-list file
|
||||
// example:
|
||||
// java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -export DATA/INDEX/freeworld/TEXT xml urls.xml diffurlcol.dump
|
||||
// instead of 'xml' (which is in fact a rss), the format can also be 'text' and 'html'
|
||||
final int format = (args[2].equals("xml")) ? 2 : (args[2].equals("html")) ? 1 : 0;
|
||||
try {
|
||||
export(args[1], format, args[3], (args.length >= 5) ? args[4] : null);
|
||||
} catch (final Exception e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
} else if (args[0].equals("-delete") && args.length >= 3) {
|
||||
// delete from URLs as given by urlreference diff dump
|
||||
// example:
|
||||
// java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -delete DATA/INDEX/freeworld/TEXT diffurlcol.dump
|
||||
// instead of 'xml' (which is in fact a rss), the format can also be 'text' and 'html'
|
||||
try {
|
||||
delete(args[1], args[2]);
|
||||
} catch (final Exception e) {
|
||||
Log.logException(e);
|
||||
}
|
||||
} else {
|
||||
System.out.println("usage:");
|
||||
System.out.println();
|
||||
System.out.println("-stat <file> ");
|
||||
System.out.println(" generate a statistics about common words in file, store to <file>.stat");
|
||||
System.out.println();
|
||||
System.out.println("-host <file>");
|
||||
System.out.println(" generate a file <file>.host containing only the hosts of the urls");
|
||||
System.out.println();
|
||||
System.out.println("-sort <file>");
|
||||
System.out.println(" generate file <file>.x.sort with sorted lists and split the file in smaller pieces");
|
||||
System.out.println();
|
||||
System.out.println("-incollection <path-to-RICOLLECTION> <file>");
|
||||
System.out.println(" generate a dump of all referenced URL hashes");
|
||||
System.out.println();
|
||||
System.out.println("-diffurlcol <path-to-URL-DB> <dump-from-incollection> <diff-dump>");
|
||||
System.out.println(" find URLs that occur in url-db but not in collections");
|
||||
System.out.println();
|
||||
System.out.println("-export <path-to-URL-DB> <format text|html|xml> <export-file> <diff-dump>");
|
||||
System.out.println(" export urls to file. the last argument can be omitted, then all urls are exported");
|
||||
System.out.println();
|
||||
System.out.println("-delete <path-to-URL-DB> <diff-dump>");
|
||||
System.out.println(" delete all urls that are listed in the diff-dump from the url-db");
|
||||
System.out.println();
|
||||
System.out.println("to do a complete clean-up of the url database, start the following:");
|
||||
System.out.println();
|
||||
System.out.println("java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -incollection DATA/INDEX/freeworld/TEXT/RICOLLECTION used.dump");
|
||||
System.out.println("java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -diffurlcol DATA/INDEX/freeworld/TEXT used.dump diffurlcol.dump");
|
||||
System.out.println("java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -export DATA/INDEX/freeworld/TEXT xml urls.xml diffurlcol.dump");
|
||||
System.out.println("java -Xmx1000m -cp classes de.anomic.data.URLAnalysis -delete DATA/INDEX/freeworld/TEXT diffurlcol.dump");
|
||||
System.out.println();
|
||||
}
|
||||
System.exit(0); // kill remaining threads
|
||||
}
|
||||
|
||||
private static final String num(final int i) {
|
||||
final StringBuilder s = new StringBuilder(Integer.toString(i));
|
||||
while (s.length() < 9) s.insert(0, "0");
|
||||
return s.toString();
|
||||
}
|
||||
}
|
||||
Loading…
Reference in new issue