mirror of
https://github.com/yacy/yacy_search_server.git
synced 2026-10-25 05:54:15 +00:00
Michael Peter Christen
fed26f33a8
to support the new time parser and search functions in YaCy a high precision detection of date and time on the day is necessary. That requires that the time zone of the document content and the time zone of the user, doing a search, is detected. The time zone of the search request is done automatically using the browsers time zone offset which is delivered to the search request automatically and invisible to the user. The time zone for the content of web pages cannot be detected automatically and must be an attribute of crawl starts. The advanced crawl start now provides an input field to set the time zone in minutes as an offset number. All parsers must get a time zone offset passed, so this required the change of the parser java api. A lot of other changes had been made which corrects the wrong handling of dates in YaCy which was to add a correction based on the time zone of the server. Now no correction is added and all dates in YaCy are UTC/GMT time zone, a normalized time zone for all peers.
115 lines
4.2 KiB
Java
115 lines
4.2 KiB
Java
//bzipParser.java
|
|
//------------------------
|
|
//part of YaCy
|
|
//(C) by Michael Peter Christen; mc@yacy.net
|
|
//first published on http://www.anomic.de
|
|
//Frankfurt, Germany, 2005
|
|
//
|
|
//this file is contributed by Martin Thelian
|
|
//
|
|
// $LastChangedDate$
|
|
// $LastChangedRevision$
|
|
// $LastChangedBy$
|
|
//
|
|
//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.document.parser;
|
|
|
|
import java.io.File;
|
|
import java.io.FileOutputStream;
|
|
import java.io.InputStream;
|
|
|
|
import net.yacy.cora.document.id.AnchorURL;
|
|
import net.yacy.document.AbstractParser;
|
|
import net.yacy.document.Document;
|
|
import net.yacy.document.Parser;
|
|
import net.yacy.document.TextParser;
|
|
import net.yacy.document.VocabularyScraper;
|
|
import net.yacy.kelondro.util.FileUtils;
|
|
|
|
import org.apache.commons.compress.compressors.bzip2.BZip2CompressorInputStream;
|
|
|
|
|
|
public class bzipParser extends AbstractParser implements Parser {
|
|
|
|
public bzipParser() {
|
|
super("Bzip 2 UNIX Compressed File Parser");
|
|
this.SUPPORTED_EXTENSIONS.add("bz2");
|
|
this.SUPPORTED_EXTENSIONS.add("tbz");
|
|
this.SUPPORTED_EXTENSIONS.add("tbz2");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-bzip2");
|
|
this.SUPPORTED_MIME_TYPES.add("application/bzip2");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-bz2");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-bzip");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-stuffit");
|
|
}
|
|
|
|
@Override
|
|
public Document[] parse(
|
|
final AnchorURL location,
|
|
final String mimeType,
|
|
final String charset,
|
|
final VocabularyScraper scraper,
|
|
final int timezoneOffset,
|
|
final InputStream source)
|
|
throws Parser.Failure, InterruptedException {
|
|
|
|
File tempFile = null;
|
|
Document[] docs;
|
|
try {
|
|
/*
|
|
* First we have to consume the first two char from the stream. Otherwise
|
|
* the bzip decompression will fail with a nullpointerException!
|
|
*/
|
|
int b = source.read();
|
|
if (b != 'B') {
|
|
throw new Exception("Invalid bz2 content.");
|
|
}
|
|
b = source.read();
|
|
if (b != 'Z') {
|
|
throw new Exception("Invalid bz2 content.");
|
|
}
|
|
|
|
int read = 0;
|
|
final byte[] data = new byte[1024];
|
|
final BZip2CompressorInputStream zippedContent = new BZip2CompressorInputStream(source);
|
|
|
|
tempFile = File.createTempFile("bunzip","tmp");
|
|
tempFile.deleteOnExit();
|
|
|
|
// creating a temp file to store the uncompressed data
|
|
final FileOutputStream out = new FileOutputStream(tempFile);
|
|
|
|
// reading gzip file and store it uncompressed
|
|
while((read = zippedContent.read(data, 0, 1024)) != -1) {
|
|
out.write(data, 0, read);
|
|
}
|
|
zippedContent.close();
|
|
out.close();
|
|
|
|
// creating a new parser class to parse the unzipped content
|
|
docs = TextParser.parseSource(location, null, null, scraper, timezoneOffset, 999, tempFile);
|
|
} catch (final Exception e) {
|
|
if (e instanceof InterruptedException) throw (InterruptedException) e;
|
|
if (e instanceof Parser.Failure) throw (Parser.Failure) e;
|
|
|
|
throw new Parser.Failure("Unexpected error while parsing bzip file. " + e.getMessage(),location);
|
|
} finally {
|
|
if (tempFile != null) FileUtils.deletedelete(tempFile);
|
|
}
|
|
return docs;
|
|
}
|
|
}
|