// IndexControl_p.java // ----------------------- // part of the AnomicHTTPD caching proxy // (C) by Michael Peter Christen; mc@anomic.de // first published on http://www.anomic.de // Frankfurt, Germany, 2004 // // $LastChangedDate$ // $LastChangedRevision$ // $LastChangedBy$ // // 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 // // Using this software in any meaning (reading, learning, copying, compiling, // running) means that you agree that the Author(s) is (are) not responsible // for cost, loss of data or any harm that may be caused directly or indirectly // by usage of this softare or this documentation. The usage of this software // is on your own risk. The installation and usage (starting/running) of this // software may allow other people or application to access your computer and // any attached devices and is highly dependent on the configuration of the // software which must be done by the user of the software; the author(s) is // (are) also not responsible for proper configuration and usage of the // software, even if provoked by documentation provided together with // the software. // // Any changes to this file according to the GPL as documented in the file // gpl.txt aside this file in the shipment you received can be done to the // lines that follows this copyright notice here, but changes must not be // done inside the copyright notive above. A re-distribution must contain // the intact and unchanged copyright notice. // Contributions and changes to the program code must be marked as such. // You must compile this file with // javac -classpath .:../classes IndexControl_p.java // if the shell's current path is HTROOT import java.io.IOException; import java.net.MalformedURLException; import java.net.URL; import java.util.Enumeration; import java.util.HashSet; import java.util.HashMap; import java.util.Iterator; import java.util.TreeMap; import de.anomic.htmlFilter.htmlFilterContentScraper; import de.anomic.http.httpHeader; import de.anomic.plasma.plasmaCrawlLURL; import de.anomic.plasma.plasmaSwitchboard; import de.anomic.plasma.plasmaURL; import de.anomic.plasma.plasmaWordIndexEntity; import de.anomic.plasma.plasmaWordIndexEntry; import de.anomic.server.serverObjects; import de.anomic.server.serverSwitch; import de.anomic.yacy.yacyClient; import de.anomic.yacy.yacyCore; import de.anomic.yacy.yacySeed; public class IndexControl_p { public static serverObjects respond(httpHeader header, serverObjects post, serverSwitch env) { // return variable that accumulates replacements plasmaSwitchboard switchboard = (plasmaSwitchboard) env; serverObjects prop = new serverObjects(); if (post == null || env == null) { prop.put("keystring", ""); prop.put("keyhash", ""); prop.put("urlstring", ""); prop.put("urlhash", ""); prop.put("result", ""); prop.put("wcount", Integer.toString(switchboard.wordIndex.size())); prop.put("ucount", Integer.toString(switchboard.urlPool.loadedURL.size())); prop.put("otherHosts", ""); prop.put("indexDistributeChecked", (switchboard.getConfig("allowDistributeIndex", "true").equals("true")) ? "checked" : ""); prop.put("indexDistributeWhileCrawling", (switchboard.getConfig("allowDistributeIndexWhileCrawling", "true").equals("true")) ? "checked" : ""); prop.put("indexReceiveChecked", (switchboard.getConfig("allowReceiveIndex", "true").equals("true")) ? "checked" : ""); prop.put("indexReceiveBlockBlacklistChecked", (switchboard.getConfig("indexReceiveBlockBlacklist", "true").equals("true")) ? "checked" : ""); return prop; // be save } // default values String keystring = ((String) post.get("keystring")).trim(); String keyhash = ((String) post.get("keyhash")).trim(); String urlstring = ((String) post.get("urlstring")).trim(); String urlhash = ((String) post.get("urlhash")).trim(); if (!urlstring.startsWith("http://") && !urlstring.startsWith("https://")) { urlstring = "http://" + urlstring; } prop.put("keystring", keystring); prop.put("keyhash", keyhash); prop.put("urlstring", urlstring); prop.put("urlhash", urlhash); prop.put("result", ""); // read values from checkboxes String[] urlx = post.getAll("urlhx.*"); boolean delurl = post.containsKey("delurl"); boolean delurlref = post.containsKey("delurlref"); // System.out.println("DEBUG CHECK: " + ((delurl) ? "delurl" : "") + " " + ((delurlref) ? "delurlref" : "")); // DHT control if (post.containsKey("setIndexTransmission")) { if (post.get("indexDistribute", "").equals("on")) { switchboard.setConfig("allowDistributeIndex", "true"); switchboard.indexDistribution.enable(); } else { switchboard.setConfig("allowDistributeIndex", "false"); switchboard.indexDistribution.disable(); } if (post.containsKey("indexDistributeWhileCrawling")) { switchboard.setConfig("allowDistributeIndexWhileCrawling", "true"); switchboard.indexDistribution.enableWhileCrawling(); } else { switchboard.setConfig("allowDistributeIndexWhileCrawling", "false"); switchboard.indexDistribution.disableWhileCrawling(); } if (post.get("indexReceive", "").equals("on")) { switchboard.setConfig("allowReceiveIndex", "true"); yacyCore.seedDB.mySeed.setFlagAcceptRemoteIndex(true); } else { switchboard.setConfig("allowReceiveIndex", "false"); yacyCore.seedDB.mySeed.setFlagAcceptRemoteIndex(false); } if (post.get("indexReceiveBlockBlacklist", "").equals("on")) { switchboard.setConfig("indexReceiveBlockBlacklist", "true"); } else { switchboard.setConfig("indexReceiveBlockBlacklist", "false"); } } // delete word if (post.containsKey("keyhashdeleteall")) { if (delurl || delurlref) { // generate an urlx array plasmaWordIndexEntity index = null; try { index = switchboard.wordIndex.getEntity(keyhash, true); Iterator en = index.elements(true); int i = 0; urlx = new String[index.size()]; while (en.hasNext()) { urlx[i++] = ((plasmaWordIndexEntry) en.next()).getUrlHash(); } index.close(); index = null; } catch (IOException e) { urlx = new String[0]; } finally { if (index != null) try { index.close(); } catch (Exception e) {} } } if (delurlref) { for (int i = 0; i < urlx.length; i++) { switchboard.removeAllUrlReferences(urlx[i], true); } } if (delurl || delurlref) { for (int i = 0; i < urlx.length; i++) { switchboard.urlPool.loadedURL.remove(urlx[i]); } } switchboard.wordIndex.deleteIndex(keyhash); post.remove("keyhashdeleteall"); if (keystring.length() > 0 && plasmaWordIndexEntry.word2hash(keystring).equals(keyhash)) { post.put("keystringsearch", "generated"); } else { post.put("keyhashsearch", "generated"); } } // delete selected URLs if (post.containsKey("keyhashdelete")) { if (delurlref) { for (int i = 0; i < urlx.length; i++) { switchboard.removeAllUrlReferences(urlx[i], true); } } if (delurl || delurlref) { for (int i = 0; i < urlx.length; i++) { switchboard.urlPool.loadedURL.remove(urlx[i]); } } switchboard.wordIndex.removeEntries(keyhash, urlx, true); // this shall lead to a presentation of the list; so handle that the remaining program // thinks that it was called for a list presentation post.remove("keyhashdelete"); if (keystring.length() > 0 && plasmaWordIndexEntry.word2hash(keystring).equals(keyhash)) { post.put("keystringsearch", "generated"); } else { post.put("keyhashsearch", "generated"); // prop.put("result", "Delete of relation of url hashes " + result + " to key hash " + keyhash); } } if (post.containsKey("urlhashdeleteall")) { int i = switchboard.removeAllUrlReferences(urlhash, true); prop.put("result", "Deleted URL and " + i + " references from " + i + " word indexes."); } if (post.containsKey("urlhashdelete")) { plasmaCrawlLURL.Entry entry = switchboard.urlPool.loadedURL.getEntry(urlhash); URL url = entry.url(); if (url == null) { prop.put("result", "No Entry for URL hash " + urlhash + "; nothing deleted."); } else { urlstring = htmlFilterContentScraper.urlNormalform(url); prop.put("urlstring", ""); switchboard.urlPool.loadedURL.remove(urlhash); prop.put("result", "Removed URL " + urlstring); } } if (post.containsKey("keystringsearch")) { keyhash = plasmaWordIndexEntry.word2hash(keystring); prop.put("keyhash", keyhash); prop.put("urlstring", ""); prop.put("urlhash", ""); prop.put("result", genUrlList(switchboard, keyhash, keystring)); } if (post.containsKey("keyhashsearch")) { if (keystring.length() == 0 || !plasmaWordIndexEntry.word2hash(keystring).equals(keyhash)) { prop.put("keystring", ""); } prop.put("urlstring", ""); prop.put("urlhash", ""); prop.put("result", genUrlList(switchboard, keyhash, "")); } // transfer to other peer if (post.containsKey("keyhashtransfer")) { if (keystring.length() == 0 || !plasmaWordIndexEntry.word2hash(keystring).equals(keyhash)) { prop.put("keystring", ""); } prop.put("urlstring", ""); prop.put("urlhash", ""); plasmaWordIndexEntity[] indexes = new plasmaWordIndexEntity[1]; String result; long starttime = System.currentTimeMillis(); indexes[0] = switchboard.wordIndex.getEntity(keyhash, true); // built urlCache Iterator urlIter = indexes[0].elements(true); HashMap knownURLs = new HashMap(); HashSet unknownURLEntries = new HashSet(); plasmaWordIndexEntry indexEntry; plasmaCrawlLURL.Entry lurl; while (urlIter.hasNext()) { indexEntry = (plasmaWordIndexEntry) urlIter.next(); lurl = switchboard.urlPool.loadedURL.getEntry(indexEntry.getUrlHash()); if (lurl == null) { unknownURLEntries.add(indexEntry.getUrlHash()); } else { if (lurl.toString() == null) { switchboard.urlPool.loadedURL.remove(indexEntry.getUrlHash()); unknownURLEntries.add(indexEntry.getUrlHash()); } else { knownURLs.put(indexEntry.getUrlHash(), lurl); } } } // now delete all entries that have no url entry Iterator hashIter = unknownURLEntries.iterator(); while (hashIter.hasNext()) { try { indexes[0].removeEntry((String) hashIter.next(), false); } catch (IOException e) {} } // use whats remaining String gzipBody = switchboard.getConfig("indexControl.gzipBody","false"); int timeout = (int) switchboard.getConfigLong("indexControl.timeout",60000); result = yacyClient.transferIndex ( yacyCore.seedDB.getConnected(post.get("hostHash", "")), indexes, knownURLs, "true".equalsIgnoreCase(gzipBody), timeout); prop.put("result", (result == null) ? ("Successfully transferred " + indexes[0].size() + " words in " + ((System.currentTimeMillis() - starttime) / 1000) + " seconds") : result); try {indexes[0].close();} catch (IOException e) {} } // generate list if (post.containsKey("keyhashsimilar")) { final Iterator hashIt = switchboard.wordIndex.wordHashes(keyhash, true, true); StringBuffer result = new StringBuffer("Sequential List of Word-Hashes:
"); String hash; int i = 0; while (hashIt.hasNext() && i < 256) { hash = (String) hashIt.next(); result.append("").append(hash).append(" ") .append(((i + 1) % 8 == 0) ? "
" : ""); i++; } prop.put("result", result); } if (post.containsKey("urlstringsearch")) { try { URL url = new URL(urlstring); urlhash = plasmaURL.urlHash(url); prop.put("urlhash", urlhash); plasmaCrawlLURL.Entry entry = switchboard.urlPool.loadedURL.getEntry(urlhash); prop.put("result", genUrlProfile(switchboard, entry, urlhash)); } catch (MalformedURLException e) { prop.put("urlstring", "wrong url: " + urlstring); prop.put("urlhash", ""); } } if (post.containsKey("urlhashsearch")) { plasmaCrawlLURL.Entry entry = switchboard.urlPool.loadedURL.getEntry(urlhash); URL url = entry.url(); if (url == null) { prop.put("result", "No Entry for URL hash " + urlhash); } else { urlstring = url.toString(); prop.put("urlstring", urlstring); prop.put("result", genUrlProfile(switchboard, entry, urlhash)); } } // generate list if (post.containsKey("urlhashsimilar")) { try { final Iterator hashIt = switchboard.urlPool.loadedURL.urlHashes(urlhash, true); StringBuffer result = new StringBuffer("Sequential List of URL-Hashes:
"); String hash; int i = 0; while (hashIt.hasNext() && i < 256) { hash = (String) hashIt.next(); result.append("").append(hash).append(" ") .append(((i + 1) % 8 == 0) ? "
" : ""); i++; } prop.put("result", result.toString()); } catch (IOException e) { prop.put("result", "Error: " + e.getMessage()); } } // list known hosts yacySeed seed; int hc = 0; if (yacyCore.seedDB != null && yacyCore.seedDB.sizeConnected() > 0) { Enumeration e = yacyCore.dhtAgent.getAcceptRemoteIndexSeeds(keyhash); while (e.hasMoreElements()) { seed = (yacySeed) e.nextElement(); if (seed != null) { prop.put("hosts_" + hc + "_hosthash", seed.hash); prop.put("hosts_" + hc + "_hostname", /*seed.hash + " " +*/ seed.get(yacySeed.NAME, "nameless")); hc++; } } prop.put("hosts", Integer.toString(hc)); } else { prop.put("hosts", "0"); } // insert constants prop.put("wcount", Integer.toString(switchboard.wordIndex.size())); prop.put("ucount", Integer.toString(switchboard.urlPool.loadedURL.size())); prop.put("indexDistributeChecked", (switchboard.getConfig("allowDistributeIndex", "true").equals("true")) ? "checked" : ""); prop.put("indexDistributeWhileCrawling", (switchboard.getConfig("allowDistributeIndexWhileCrawling", "true").equals("true")) ? "checked" : ""); prop.put("indexReceiveChecked", (switchboard.getConfig("allowReceiveIndex", "true").equals("true")) ? "checked" : ""); prop.put("indexReceiveBlockBlacklistChecked", (switchboard.getConfig("indexReceiveBlockBlacklist", "true").equals("true")) ? "checked" : ""); // return rewrite properties return prop; } public static String genUrlProfile(plasmaSwitchboard switchboard, plasmaCrawlLURL.Entry entry, String urlhash) { if (entry == null) { return "No entry found for URL-hash " + urlhash; } URL url = entry.url(); if (url == null) { return "No entry found for URL-hash " + urlhash; } String result = "" + "" + "" + "" + "" + "" + "" + "" + "" + "" + "" + "" + "" + "" + "
URL String" + htmlFilterContentScraper.urlNormalform(url) + "
Hash" + urlhash + "
Description" + entry.descr() + "
Modified-Date" + entry.moddate() + "
Loaded-Date" + entry.loaddate() + "
Referrer" + switchboard.urlPool.loadedURL.getEntry(entry.referrerHash()).url() + "
Doctype" + entry.doctype() + "
Copy-Count" + entry.copyCount() + "
Local-Flag" + entry.local() + "
Quality" + entry.quality() + "
Language" + entry.language() + "
Size" + entry.size() + "
Words" + entry.wordCount() + "

"; result += "
" + "" + "" + "" + "" + "
" + " this may produce unresolved references at other word indexes but they do not harm

" + "
" + " delete the reference to this url at every other word where the reference exists (very extensive, but prevents unresolved references)
" + "
"; return result; } public static String genUrlList(plasmaSwitchboard switchboard, String keyhash, String keystring) { // search for a word hash and generate a list of url links plasmaWordIndexEntity index = null; try { index = switchboard.wordIndex.getEntity(keyhash, true); final StringBuffer result = new StringBuffer(1024); if (index.size() == 0) { result.append("No URL entries related to this word hash ").append(keyhash).append("."); } else { final Iterator en = index.elements(true); result.append("URL entries related to this word hash ").append(keyhash).append("

"); result.append("
"); String us, uh; int i = 0; final TreeMap tm = new TreeMap(); while (en.hasNext()) { uh = ((plasmaWordIndexEntry)en.next()).getUrlHash(); if (switchboard.urlPool.loadedURL.exists(uh)) { us = switchboard.urlPool.loadedURL.getEntry(uh).url().toString(); tm.put(us, uh); } else { tm.put("", uh); } } final Iterator iter = tm.keySet().iterator(); result.ensureCapacity((tm.size() + 2) * 384); while (iter.hasNext()) { us = iter.next().toString(); uh = (String)tm.get(us); result.append(""); if (us.length() > 0) { result.append("") .append(uh).append(" ").append(us).append("
"); } else { result.append("").append(uh).append(" <unresolved URL Hash>
"); } } result.append("") .append("") .append("") .append("") .append("
Reference Deletion


") .append("

") .append("
  (= delete Word)
") .append("
") .append("

") .append("delete also the referenced URL itself (reasonable and recommended, may produce unresolved references at other word indexes but they do not harm)") .append("
") .append("

") .append("for every resolveable and deleted URL reference, delete the same reference at every other word where the reference exists (very extensive, but prevents further unresolved references)") .append("

"); } index.close(); index = null; return result.toString(); } catch (IOException e) { return ""; } finally { if (index != null) try { index.close(); index = null; } catch (Exception e) {}; } } }