yacy_search_server/source/de/anomic/document/parser/docParser.java

117 lines
4.2 KiB
Java
Raw Normal View History

//docParser.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 de.anomic.document.parser;
import java.io.InputStream;
import java.util.Hashtable;
import org.textmining.extraction.TextExtractor;
import org.textmining.extraction.word.WordTextExtractorFactory;
import de.anomic.document.AbstractParser;
import de.anomic.document.Parser;
import de.anomic.document.ParserException;
import de.anomic.document.Document;
import de.anomic.yacy.yacyURL;
public class docParser 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/msword","doc");
SUPPORTED_MIME_TYPES.put("application/doc","doc");
SUPPORTED_MIME_TYPES.put("appl/text","doc");
SUPPORTED_MIME_TYPES.put("application/vnd.msword","doc");
SUPPORTED_MIME_TYPES.put("application/vnd.ms-word","doc");
SUPPORTED_MIME_TYPES.put("application/winword","doc");
SUPPORTED_MIME_TYPES.put("application/word","doc");
SUPPORTED_MIME_TYPES.put("application/x-msw6","doc");
SUPPORTED_MIME_TYPES.put("application/x-msword","doc");
}
public docParser() {
super();
this.parserName = "Word Document Parser";
}
public Document parse(final yacyURL location, final String mimeType, final String charset,
final InputStream source) throws ParserException, InterruptedException {
try {
final WordTextExtractorFactory extractorFactory = new WordTextExtractorFactory();
final TextExtractor extractor = extractorFactory.textExtractor(source);
final String contents = extractor.getText().trim();
String title = contents.replaceAll("\r"," ").replaceAll("\n"," ").replaceAll("\t"," ").trim();
if (title.length() > 80) title = title.substring(0, 80);
int l = title.length();
while (true) {
title = title.replaceAll(" ", " ");
if (title.length() == l) break;
l = title.length();
}
final Document theDoc = new Document(
location,
mimeType,
"UTF-8",
null,
null,
title,
"", // TODO: AUTHOR
null,
null,
contents.getBytes("UTF-8"),
null,
null);
return theDoc;
} catch (final Exception e) {
e.printStackTrace();
if (e instanceof InterruptedException) throw (InterruptedException) e;
if (e instanceof ParserException) throw (ParserException) e;
throw new ParserException("Unexpected error while parsing doc file. " + e.getMessage(),location);
}
}
public java.util.Hashtable<String, String> getSupportedMimeTypes() {
return docParser.SUPPORTED_MIME_TYPES;
}
@Override
public void reset() {
// Nothing todo here at the moment
*) plasmaHTCache: - method loadResourceContent defined as deprecated. Please do not use this function to avoid OutOfMemory Exceptions when loading large files - new function getResourceContentStream to get an inputstream of a cache file - new function getResourceContentLength to get the size of a cached file *) httpc.java: - Bugfix: resource content was loaded into memory even if this was not requested *) Crawler: - new option to hold loaded resource content in memory - adding option to use the worker class without the worker pool (needed by the snippet fetcher) *) plasmaSnippetCache - snippet loader does not use a crawl-worker from pool but uses a newly created instance to avoid blocking by normal crawling activity. - now operates on streams instead of byte arrays to avoid OutOfMemory Exceptions when operating on large files - snippet loader now forces the crawl-worker to keep the loaded resource in memory to avoid IO *) plasmaCondenser: adding new function getWords that can directly operate on input streams *) Parsers - keep resource in memory whenever possible (to avoid IO) - when parsing from stream the content length must be passed to the parser function now. this length value is needed by the parsers to decide if the parsed resource content is to large to hold it in memory and must be stored to file - AbstractParser.java: new function to pass the contentLength of a resource to the parsers git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2701 6c8d7289-2bf4-0310-a012-ef5d649a1542
2006-10-03 13:05:48 +02:00
super.reset();
}
}