*) updated PPT and XLS parsers to use new Apache POI library *) added new Visio (VSD) parser git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6145 6c8d7289-2bf4-0310-a012-ef5d649a1542pull/1/head
parent
a10c8022d1
commit
457b6c0d6d
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -0,0 +1,66 @@
|
||||
<?xml version="1.0"?>
|
||||
<project name="YACY - vsdParser" default="dist">
|
||||
<description>A class to parse ppt files</description>
|
||||
|
||||
<!-- the parsers short name -->
|
||||
<property name="parserShortName" value="vsd"/>
|
||||
|
||||
<!-- parser version number -->
|
||||
<property name="parserVersion" value="0.1"/>
|
||||
|
||||
<property name="parserLongName" value="yacyContentParser_${parserShortName}"/>
|
||||
<property name="parserArchive" location="${release}/${parserLongName}_${parserVersion}.tgz"/>
|
||||
|
||||
<!-- compile the sources of this parser -->
|
||||
<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}" />
|
||||
|
||||
<!-- libraries needed by this parser -->
|
||||
<pathelement location="${libx}/poi-3.2-FINAL-20081019.jar" />
|
||||
<pathelement location="${libx}/poi-scratchpad-3.2-FINAL-20081019.jar" />
|
||||
</classpath>
|
||||
</javac>
|
||||
</target>
|
||||
|
||||
<!-- add all parts of this parser into a single zip file -->
|
||||
<target name="zip" depends="compile">
|
||||
<tar destfile="${parserArchive}" compression="gzip">
|
||||
<!-- needed libraries and license files of these libs -->
|
||||
<tarfileset dir="${libx}"
|
||||
includes="poi-*.*"
|
||||
prefix="${releaseFileParentDir}/libx/"
|
||||
dirmode="755" mode="644"/>
|
||||
<!-- source files of this parser -->
|
||||
<tarfileset dir="${src}/de/anomic/plasma/parser/${parserShortName}"
|
||||
prefix="${releaseFileParentDir}/source/de/anomic/plasma/parser/${parserShortName}"
|
||||
dirmode="755" mode="644"/>
|
||||
<!-- class files of this parser -->
|
||||
<tarfileset dir="${build}/de/anomic/plasma/parser/${parserShortName}"
|
||||
prefix="${releaseFileParentDir}/classes/de/anomic/plasma/parser/${parserShortName}"
|
||||
dirmode="755" mode="644"/>
|
||||
</tar>
|
||||
</target>
|
||||
|
||||
<!-- just copy all parts of this parser into the release directory -->
|
||||
<target name="copy" depends="compile">
|
||||
<!-- copy needed libs -->
|
||||
<copy todir="${release}/libx/">
|
||||
<fileset dir="${libx}" includes="poi-*.*"/>
|
||||
</copy>
|
||||
|
||||
<!-- copy source code files -->
|
||||
<copy todir="${release}/source/de/anomic/plasma/parser/${parserShortName}">
|
||||
<fileset dir="${src}/de/anomic/plasma/parser/${parserShortName}" includes="**/*"/>
|
||||
</copy>
|
||||
|
||||
<!-- copy compiled classes -->
|
||||
<copy todir="${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 +1,160 @@
|
||||
//vsdParser.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 Marc Nause
|
||||
//
|
||||
// $LastChangedDate$
|
||||
// $LastChangedRevision$
|
||||
// $LastChangedBy$
|
||||
//
|
||||
//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 de.anomic.plasma.parser.vsd;
|
||||
|
||||
import java.io.InputStream;
|
||||
import java.util.Hashtable;
|
||||
|
||||
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.yacy.yacyURL;
|
||||
import org.apache.poi.hdgf.extractor.VisioTextExtractor;
|
||||
import org.apache.poi.hpsf.SummaryInformation;
|
||||
|
||||
public class vsdParser extends AbstractParser implements Parser {
|
||||
|
||||
/**
|
||||
* a list of mime types that are supported by this parser class
|
||||
* @see #getSupportedMimeTypes()
|
||||
*/
|
||||
public static final Hashtable<String, String> SUPPORTED_MIME_TYPES = new Hashtable<String, String>();
|
||||
static {
|
||||
SUPPORTED_MIME_TYPES.put("application/visio","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("application/x-visio","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("application/vnd.visio","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("application/visio.drawing","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("application/vsd","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("application/x-vsd","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("image/x-vsd","vsd");
|
||||
SUPPORTED_MIME_TYPES.put("zz-application/zz-winassoc-vsd","vsd");
|
||||
}
|
||||
|
||||
/**
|
||||
* a list of library names that are needed by this parser
|
||||
* @see Parser#getLibxDependences()
|
||||
*/
|
||||
private static final String[] LIBX_DEPENDENCIES = new String[] {
|
||||
"poi-3.2-FINAL-20081019.jar",
|
||||
"poi-scratchpad-3.2-FINAL-20081019.jar",
|
||||
};
|
||||
|
||||
public vsdParser() {
|
||||
super(LIBX_DEPENDENCIES);
|
||||
this.parserName = "Microsoft Visio Parser";
|
||||
this.parserVersionNr = "0.1";
|
||||
}
|
||||
|
||||
/**
|
||||
* returns a hashtable containing the mimetypes that are supported by this class
|
||||
*/
|
||||
public Hashtable<String, String> getSupportedMimeTypes() {
|
||||
return SUPPORTED_MIME_TYPES;
|
||||
}
|
||||
|
||||
/*
|
||||
* parses the source documents and returns a plasmaParserDocument containing
|
||||
* all extracted information about the parsed document
|
||||
*/
|
||||
public plasmaParserDocument parse(final yacyURL location, final String mimeType, final String charset, final InputStream source) throws ParserException, InterruptedException {
|
||||
|
||||
plasmaParserDocument theDoc = null;
|
||||
|
||||
try {
|
||||
String contents = "";
|
||||
SummaryInformation summary = null;
|
||||
try {
|
||||
VisioTextExtractor extractor = new VisioTextExtractor(source);
|
||||
contents = extractor.getText();
|
||||
summary = extractor.getSummaryInformation();
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
|
||||
String author = null;
|
||||
String[] keywords = null;
|
||||
String title = null;
|
||||
if (summary != null) {
|
||||
author = summary.getAuthor();
|
||||
if (summary.getKeywords() != null) {
|
||||
keywords = summary.getKeywords().split("[ ,;]");
|
||||
}
|
||||
title = summary.getTitle();
|
||||
}
|
||||
|
||||
String abstrct = null;
|
||||
abstrct = ((contents.length() > 80)? contents.substring(0, 80):contents.trim()).
|
||||
replaceAll("\r\n"," ").
|
||||
replaceAll("\n"," ").
|
||||
replaceAll("\r"," ").
|
||||
replaceAll("\t"," ");
|
||||
|
||||
if (title == null) {
|
||||
title = abstrct;
|
||||
}
|
||||
|
||||
// As the result of parsing this function must return a plasmaParserDocument object
|
||||
theDoc = new plasmaParserDocument(
|
||||
location, // url of the source document
|
||||
mimeType, // the documents mime type
|
||||
"UTF-8", // charset of the document text
|
||||
null, // language
|
||||
keywords,
|
||||
title,
|
||||
author,
|
||||
null, // an array of section headlines
|
||||
abstrct, // an abstract
|
||||
contents.getBytes("UTF-8"), // the parsed document text
|
||||
null, // a map of extracted anchors
|
||||
null); // a treeset of image URLs
|
||||
return theDoc;
|
||||
} catch (final Exception e) {
|
||||
if (e instanceof InterruptedException) throw (InterruptedException) e;
|
||||
|
||||
// if an unexpected error occures just log the error and raise a new ParserException
|
||||
final String errorMsg = "Unable to parse the vsd document '" + location + "':" + e.getMessage();
|
||||
this.theLogger.logSevere(errorMsg);
|
||||
throw new ParserException(errorMsg, location);
|
||||
} finally {
|
||||
if (theDoc == null) {
|
||||
// if an unexpected error occures just log the error and raise a new ParserException
|
||||
final String errorMsg = "Unable to parse the vsd document '" + location + "': possibly out of memory";
|
||||
this.theLogger.logSevere(errorMsg);
|
||||
throw new ParserException(errorMsg, location);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public void reset() {
|
||||
// this code is executed if the parser class is returned into the parser pool
|
||||
super.reset();
|
||||
|
||||
}
|
||||
}
|
Loading…
Reference in new issue