inteligr8/alfresco-community-repo
1
0
Fork 0
mirror of https://github.com/Alfresco/alfresco-community-repo.git synced 2025-07-24 17:32:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Big honkin' merge from head. Sheesh!

Browse Source 
git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/BRANCHES/WCM-DEV2/root@3617 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
Britt Park
2006-08-27 01:01:30 +00:00
parent e2c66899cc
commit 8031cc6574
322 changed files with 20776 additions and 6550 deletions
Download Patch File Download Diff File Expand all files Collapse all files

150
source/java/org/alfresco/repo/content/metadata/PdfBoxMetadataExtracter.java
View File

@@ -1,75 +1,75 @@
/*
* Copyright (C) 2005 Jesper Steen M<EFBFBD>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(); }
}
}
}
}
/*
* Copyright (C) 2005 Jesper Steen Møller
*
* 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(); }
}
}
}
}