mirror of
https://github.com/Alfresco/alfresco-community-repo.git
synced 2025-06-02 17:35:18 +00:00
e31e027039
- expects .msg files in native Outlook format - uses POI library for the parsing of the horrid OLE2 compound document format - extracts addressee(s), sent date and originator email address ...for the future - could be modified and used as a transformer to allow full-text indexing of Outlook format emails . Add new aspect "emailed" to the contentmodel to support properties for above extractor git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@3387 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
76 lines
2.4 KiB
Java
76 lines
2.4 KiB
Java
/*
|
||
* Copyright (C) 2005 Jesper Steen M<>ller
|
||
*
|
||
* Licensed under the Mozilla Public License version 1.1
|
||
* with a permitted attribution clause. You may obtain a
|
||
* copy of the License at
|
||
*
|
||
* http://www.alfresco.org/legal/license.txt
|
||
*
|
||
* Unless required by applicable law or agreed to in writing,
|
||
* software distributed under the License is distributed on an
|
||
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
|
||
* either express or implied. See the License for the specific
|
||
* language governing permissions and limitations under the
|
||
* License.
|
||
*/
|
||
package org.alfresco.repo.content.metadata;
|
||
|
||
import java.io.IOException;
|
||
import java.io.InputStream;
|
||
import java.io.Serializable;
|
||
import java.util.Calendar;
|
||
import java.util.Map;
|
||
|
||
import org.alfresco.model.ContentModel;
|
||
import org.alfresco.repo.content.MimetypeMap;
|
||
import org.alfresco.service.cmr.repository.ContentReader;
|
||
import org.alfresco.service.namespace.QName;
|
||
import org.pdfbox.pdmodel.PDDocument;
|
||
import org.pdfbox.pdmodel.PDDocumentInformation;
|
||
|
||
/**
|
||
*
|
||
* @author Jesper Steen Møller
|
||
*/
|
||
public class PdfBoxMetadataExtracter extends AbstractMetadataExtracter
|
||
{
|
||
public PdfBoxMetadataExtracter()
|
||
{
|
||
super(MimetypeMap.MIMETYPE_PDF, 1.0, 1000);
|
||
}
|
||
|
||
public void extractInternal(ContentReader reader, Map<QName, Serializable> destination) throws Throwable
|
||
{
|
||
PDDocument pdf = null;
|
||
InputStream is = null;
|
||
try
|
||
{
|
||
is = reader.getContentInputStream();
|
||
// stream the document in
|
||
pdf = PDDocument.load(is);
|
||
// Scoop out the metadata
|
||
PDDocumentInformation docInfo = pdf.getDocumentInformation();
|
||
|
||
trimPut(ContentModel.PROP_AUTHOR, docInfo.getAuthor(), destination);
|
||
trimPut(ContentModel.PROP_TITLE, docInfo.getTitle(), destination);
|
||
trimPut(ContentModel.PROP_DESCRIPTION, docInfo.getSubject(), destination);
|
||
|
||
Calendar created = docInfo.getCreationDate();
|
||
if (created != null)
|
||
destination.put(ContentModel.PROP_CREATED, created.getTime());
|
||
}
|
||
finally
|
||
{
|
||
if (is != null)
|
||
{
|
||
try { is.close(); } catch (IOException e) {}
|
||
}
|
||
if (pdf != null)
|
||
{
|
||
try { pdf.close(); } catch (Throwable e) { e.printStackTrace(); }
|
||
}
|
||
}
|
||
}
|
||
}
|