mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
788288eb9e
The default schema uses only some of them and the resting search index has now the following properties: - webgraph size will have about 40 times as much entries as default index - the complete index size will increase and may be about the double size of current amount As testing showed, not much indexing performance is lost. The default index will be smaller (moved fields out of it); thus searching can be faster. The new index will cause that some old parts in YaCy can be removed, i.e. specialized webgraph data and the noload crawler. The new index will make it possible to: - search within link texts of linked but not indexed documents (about 20 times of document index in size!!) - get a very detailed link graph - enhance ranking using a complete link graph To get the full access to the new index, the API to solr has now two access points: one with attribute core=collection1 for the default search index and core=webgraph to the new webgraph search index. This is also avaiable for p2p operation but client access is not yet implemented.
108 lines
4.6 KiB
Java
108 lines
4.6 KiB
Java
/**
|
|
* zipParser
|
|
* Copyright 2010 by Michael Peter Christen, mc@yacy.net, Frankfurt am Main, Germany
|
|
* First released 29.6.2010 at http://yacy.net
|
|
*
|
|
* $LastChangedDate$
|
|
* $LastChangedRevision$
|
|
* $LastChangedBy$
|
|
*
|
|
* This library is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2.1 of the License, or (at your option) any later version.
|
|
*
|
|
* This library 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
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public License
|
|
* along with this program in the file lgpl21.txt
|
|
* If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
package net.yacy.document.parser;
|
|
|
|
import java.io.File;
|
|
import java.io.IOException;
|
|
import java.io.InputStream;
|
|
import java.util.ArrayList;
|
|
import java.util.List;
|
|
import java.util.zip.ZipEntry;
|
|
import java.util.zip.ZipInputStream;
|
|
|
|
import net.yacy.document.AbstractParser;
|
|
import net.yacy.document.Document;
|
|
import net.yacy.document.Parser;
|
|
import net.yacy.document.TextParser;
|
|
import net.yacy.kelondro.data.meta.DigestURI;
|
|
import net.yacy.kelondro.util.FileUtils;
|
|
import net.yacy.kelondro.util.MemoryControl;
|
|
|
|
// this is a new implementation of this parser idiom using multiple documents as result set
|
|
|
|
public class zipParser extends AbstractParser implements Parser {
|
|
|
|
public zipParser() {
|
|
super("ZIP File Parser");
|
|
this.SUPPORTED_EXTENSIONS.add("zip");
|
|
this.SUPPORTED_EXTENSIONS.add("jar");
|
|
this.SUPPORTED_EXTENSIONS.add("apk"); // Android package
|
|
this.SUPPORTED_MIME_TYPES.add("application/zip");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-zip");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-zip-compressed");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-compress");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-compressed");
|
|
this.SUPPORTED_MIME_TYPES.add("multipart/x-zip");
|
|
this.SUPPORTED_MIME_TYPES.add("application/java-archive");
|
|
this.SUPPORTED_MIME_TYPES.add("application/vnd.android.package-archive");
|
|
}
|
|
|
|
@Override
|
|
public Document[] parse(final DigestURI url, final String mimeType,
|
|
final String charset, final InputStream source)
|
|
throws Parser.Failure, InterruptedException {
|
|
// check memory for parser
|
|
if (!MemoryControl.request(200 * 1024 * 1024, false))
|
|
throw new Parser.Failure("Not enough Memory available for zip parser: " + MemoryControl.available(), url);
|
|
|
|
Document[] docs = null;
|
|
final List<Document> docacc = new ArrayList<Document>();
|
|
ZipEntry entry;
|
|
final ZipInputStream zis = new ZipInputStream(source);
|
|
File tmp = null;
|
|
|
|
// loop through the elements in the zip file and parse every single file inside
|
|
while (true) {
|
|
try {
|
|
if (zis.available() <= 0) break;
|
|
entry = zis.getNextEntry();
|
|
if (entry == null) break;
|
|
if (entry.isDirectory() || entry.getSize() <= 0) continue;
|
|
final String name = entry.getName();
|
|
final int idx = name.lastIndexOf('.');
|
|
final String mime = TextParser.mimeOf((idx >= 0) ? name.substring(idx + 1) : "");
|
|
try {
|
|
tmp = FileUtils.createTempFile(this.getClass(), name);
|
|
FileUtils.copy(zis, tmp, entry.getSize());
|
|
final DigestURI virtualURL = DigestURI.newURL(url, "#" + name);
|
|
//this.log.logInfo("ZIP file parser: " + virtualURL.toNormalform(false, false));
|
|
docs = TextParser.parseSource(virtualURL, mime, null, tmp);
|
|
if (docs == null) continue;
|
|
for (final Document d: docs) docacc.add(d);
|
|
} catch (final Parser.Failure e) {
|
|
AbstractParser.log.logWarning("ZIP parser entry " + name + ": " + e.getMessage());
|
|
} finally {
|
|
if (tmp != null) FileUtils.deletedelete(tmp);
|
|
}
|
|
} catch (final IOException e) {
|
|
AbstractParser.log.logWarning("ZIP parser:" + e.getMessage());
|
|
break;
|
|
}
|
|
}
|
|
if (docacc.isEmpty()) return null;
|
|
return docacc.toArray(new Document[docacc.size()]);
|
|
}
|
|
}
|