*) Adding content Parser for RPM Files

- at the moment only the metadata is extracted

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@1147 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
theli 19 years ago
parent 0f769215b5
commit 8ed0aaae8d

@ -0,0 +1,55 @@
/* ====================================================================
*
* The Apache Software License, Version 1.1
*
* Copyright (c) 2003 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution, if
* any, must include the following acknowlegement:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowlegement may appear in the software itself,
* if and wherever such third-party acknowlegements normally appear.
*
* 4. The names "The Jakarta Project", "jRPM", and "Apache Software
* Foundation" must not be used to endorse or promote products derived
* from this software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache"
* nor may "Apache" appear in their names without prior written
* permission of the Apache Group.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*
*/

Binary file not shown.

@ -0,0 +1,56 @@
<?xml version="1.0"?>
<project name="YACY - rpmParser" default="dist">
<description>
A class to parse vCard files
</description>
<property name="parserShortName" value="rpm"/>
<property name="parserVersion" value="0.1"/>
<property name="parserLongName" value="yacyContentParser_${parserShortName}"/>
<property name="parserArchive" location="${release}/${parserLongName}_${parserVersion}.tgz"/>
<target name="compile">
<javac srcdir="${src}/de/anomic/plasma/parser/${parserShortName}" destdir="${build}" source="${javacSource}" target="${javacTarget}" debug="true" debuglevel="lines,vars,source">
<classpath>
<pathelement location="${build}" />
<pathelement location="${libx}/jrpm-head.jar" />
<pathelement location="${libx}/log4j-1.2.9.jar"/>
</classpath>
</javac>
</target>
<target name="zip" depends="compile">
<tar destfile="${parserArchive}" compression="gzip">
<tarfileset dir="${libx}"
includes="jrpm-head.*,log4j-1.2.9.jar"
prefix="${releaseDir}/libx/"
dirmode="755" mode="644"/>
<tarfileset dir="${src}/de/anomic/plasma/parser/${parserShortName}"
prefix="${releaseDir}/source/de/anomic/plasma/parser/${parserShortName}"
dirmode="755" mode="644"/>
<tarfileset dir="${build}/de/anomic/plasma/parser/${parserShortName}"
prefix="${releaseDir}/classes/de/anomic/plasma/parser/${parserShortName}"
dirmode="755" mode="644"/>
</tar>
</target>
<target name="copy" depends="compile">
<copy todir="${release}/libx/">
<fileset dir="${libx}" includes="jrpm-head.*,log4j-1.2.9.jar"/>
</copy>
<copy todir="${release}/source/de/anomic/plasma/parser/${parserShortName}">
<fileset dir="${src}/de/anomic/plasma/parser/${parserShortName}" includes="**/*"/>
</copy>
<copy todir="${release}/classes/de/anomic/plasma/parser/${parserShortName}">
<fileset dir="${build}/de/anomic/plasma/parser/${parserShortName}" includes="**/*"/>
</copy>
</target>
<target name="dist" depends="compile,zip" description="Compile and zip the parser"/>
</project>

@ -0,0 +1,181 @@
//rpmParser.java
//------------------------
//part of YaCy
//(C) by Michael Peter Christen; mc@anomic.de
//first published on http://www.anomic.de
//Frankfurt, Germany, 2005
//
//this file is contributed by Martin Thelian
//last major change: 20.11.2005
//
//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.
package de.anomic.plasma.parser.rpm;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.InputStream;
import java.net.URL;
import java.util.HashMap;
import java.util.Hashtable;
import com.jguild.jrpm.io.RPMFile;
import com.jguild.jrpm.io.datatype.DataTypeIf;
import de.anomic.http.httpc;
import de.anomic.plasma.plasmaParserDocument;
import de.anomic.plasma.parser.AbstractParser;
import de.anomic.plasma.parser.Parser;
import de.anomic.plasma.parser.ParserException;
import de.anomic.server.serverFileUtils;
/**
* @author theli
*
*/
public class rpmParser extends AbstractParser implements Parser {
/**
* a list of mime types that are supported by this parser class
* @see #getSupportedMimeTypes()
*/
public static final Hashtable SUPPORTED_MIME_TYPES = new Hashtable();
static {
SUPPORTED_MIME_TYPES.put("application/x-rpm","rpm");
SUPPORTED_MIME_TYPES.put("application/x-redhat packet manager","rpm");
}
/**
* a list of library names that are needed by this parser
* @see Parser#getLibxDependences()
*/
private static final String[] LIBX_DEPENDENCIES = new String[] {"jrpm-head.jar"};
public rpmParser() {
super(LIBX_DEPENDENCIES);
parserName = "rpm Parser";
}
public Hashtable getSupportedMimeTypes() {
return SUPPORTED_MIME_TYPES;
}
public plasmaParserDocument parse(URL location, String mimeType,
InputStream source) throws ParserException {
File dstFile = null;
try {
dstFile = File.createTempFile("rpmParser",".tmp");
serverFileUtils.copy(source,dstFile);
return parse(location,mimeType,dstFile);
} catch (Exception e) {
return null;
} finally {
if (dstFile != null) {dstFile.delete();}
}
}
public plasmaParserDocument parse(URL location, String mimeType, File sourceFile) throws ParserException {
RPMFile rpmFile = null;
try {
String summary = null, description = null, name = sourceFile.getName();
HashMap anchors = new HashMap();
StringBuffer content = new StringBuffer();
// opening the rpm file
rpmFile = new RPMFile(sourceFile);
// parsing the file
rpmFile.parse();
// getting all header names
String[] headerNames = rpmFile.getTagNames();
for (int i=0; i<headerNames.length; i++) {
DataTypeIf tag = rpmFile.getTag(headerNames[i]);
if (tag != null) {
content.append(headerNames[i])
.append(": ")
.append(tag.toString())
.append("\n");
}
if (headerNames[i].equals("N")) name = tag.toString();
else if (headerNames[i].equals("SUMMARY")) summary = tag.toString();
else if (headerNames[i].equals("DESCRIPTION")) description = tag.toString();
else if (headerNames[i].equals("URL")) anchors.put(tag.toString(), tag.toString());
}
// closing the rpm file
rpmFile.close();
rpmFile = null;
plasmaParserDocument theDoc = new plasmaParserDocument(
location,
mimeType,
null,
name,
summary,
null,
description,
content.toString().getBytes(),
anchors,
null);
return theDoc;
} catch (Exception e) {
e.printStackTrace();
throw new ParserException("Unable to parse the rpm file. " + e.getMessage());
} finally {
if (rpmFile != null) try { rpmFile.close(); } catch (Exception e) {}
}
}
public void reset() {
// Nothing todo here at the moment
}
public static void main(String[] args) {
try {
URL contentUrl = new URL(args[0]);
rpmParser testParser = new rpmParser();
byte[] content = httpc.singleGET(contentUrl, 10000, null, null, null);
ByteArrayInputStream input = new ByteArrayInputStream(content);
testParser.parse(contentUrl, "application/x-rpm", input);
} catch (Exception e) {
e.printStackTrace();
}
}
}

@ -394,6 +394,11 @@ public final class plasmaParser {
// nothing todo here at the moment // nothing todo here at the moment
} }
public static void enableAllParsers() {
Set availableMimeTypes = availableParserList.keySet();
setEnabledParserList(availableMimeTypes);
}
public static String[] setEnabledParserList(Set mimeTypeSet) { public static String[] setEnabledParserList(Set mimeTypeSet) {
HashSet newEnabledParsers = new HashSet(); HashSet newEnabledParsers = new HashSet();
@ -810,28 +815,7 @@ public final class plasmaParser {
plasmaParser.initRealtimeParsableMimeTypes("application/xhtml+xml,text/html,text/plain"); plasmaParser.initRealtimeParsableMimeTypes("application/xhtml+xml,text/html,text/plain");
// configure all other supported mimeTypes // configure all other supported mimeTypes
plasmaParser.initParseableMimeTypes( plasmaParser.enableAllParsers();
"application/atom+xml," +
"application/gzip," +
"application/java-archive," +
"application/msword," +
"application/octet-stream," +
"application/pdf," +
"application/rdf+xml," +
"application/rss+xml," +
"application/rtf," +
"application/x-gzip," +
"application/x-tar," +
"application/xml," +
"application/zip," +
"text/rss," +
"text/rtf," +
"text/xml," +
"application/x-bzip2," +
"application/postscript," +
"text/x-vcard," +
"application/vnd.oasis.opendocument.text," +
"application/x-vnd.oasis.opendocument.text");
// parsing the content // parsing the content
plasmaParserDocument document = theParser.parseSource(contentURL, contentMimeType, contentFile); plasmaParserDocument document = theParser.parseSource(contentURL, contentMimeType, contentFile);

Loading…
Cancel
Save