mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
5fc6524ca8
later - added abstract add, delete, get methods in the triplestore - added generation of triples after auto-annotation - migrated all MultiProtocolURI objects to DigestURI in the parser since the url hash is needed as subject value in the triples in the triple store
112 lines
4.0 KiB
Java
112 lines
4.0 KiB
Java
//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 net.yacy.document.parser;
|
|
|
|
import java.io.InputStream;
|
|
|
|
import net.yacy.cora.document.UTF8;
|
|
import net.yacy.document.AbstractParser;
|
|
import net.yacy.document.Document;
|
|
import net.yacy.document.Parser;
|
|
import net.yacy.kelondro.data.meta.DigestURI;
|
|
|
|
import org.apache.poi.hwpf.extractor.WordExtractor;
|
|
|
|
public class docParser extends AbstractParser implements Parser {
|
|
|
|
public docParser() {
|
|
super("Word Document Parser");
|
|
this.SUPPORTED_EXTENSIONS.add("doc");
|
|
this.SUPPORTED_MIME_TYPES.add("application/msword");
|
|
this.SUPPORTED_MIME_TYPES.add("application/doc");
|
|
this.SUPPORTED_MIME_TYPES.add("appl/text");
|
|
this.SUPPORTED_MIME_TYPES.add("application/vnd.msword");
|
|
this.SUPPORTED_MIME_TYPES.add("application/vnd.ms-word");
|
|
this.SUPPORTED_MIME_TYPES.add("application/winword");
|
|
this.SUPPORTED_MIME_TYPES.add("application/word");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-msw6");
|
|
this.SUPPORTED_MIME_TYPES.add("application/x-msword");
|
|
}
|
|
|
|
public Document[] parse(final DigestURI location, final String mimeType,
|
|
final String charset, final InputStream source)
|
|
throws Parser.Failure, InterruptedException {
|
|
|
|
final WordExtractor extractor;
|
|
|
|
try {
|
|
extractor = new WordExtractor(source);
|
|
} catch (Exception e) {
|
|
throw new Parser.Failure("error in docParser, WordTextExtractorFactory: " + e.getMessage(), location);
|
|
}
|
|
|
|
final StringBuilder contents = new StringBuilder(80);
|
|
try {
|
|
contents.append(extractor.getText().trim());
|
|
contents.append(' ');
|
|
contents.append(extractor.getHeaderText());
|
|
contents.append(' ');
|
|
contents.append(extractor.getFooterText());
|
|
} catch (Exception e) {
|
|
throw new Parser.Failure("error in docParser, getText: " + e.getMessage(), location);
|
|
}
|
|
String title = (contents.length() > 240) ? contents.substring(0,240) : contents.toString().trim();
|
|
title.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();
|
|
}
|
|
|
|
Document[] docs;
|
|
docs = new Document[]{new Document(
|
|
location,
|
|
mimeType,
|
|
"UTF-8",
|
|
this,
|
|
null,
|
|
null,
|
|
title,
|
|
"", // TODO: AUTHOR
|
|
extractor.getDocSummaryInformation().getCompany(), // publisher
|
|
null,
|
|
null,
|
|
0.0f, 0.0f,
|
|
UTF8.getBytes(contents.toString()),
|
|
null,
|
|
null,
|
|
null,
|
|
false)};
|
|
|
|
return docs;
|
|
}
|
|
|
|
}
|