mirror of
https://github.com/Alfresco/alfresco-community-repo.git
synced 2025-07-24 17:32:48 +00:00
Updated PdfBoxMetadataExtracter to new mappable format
git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@5928 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
@@ -27,29 +27,47 @@ package org.alfresco.repo.content.metadata;
|
|||||||
import java.io.IOException;
|
import java.io.IOException;
|
||||||
import java.io.InputStream;
|
import java.io.InputStream;
|
||||||
import java.io.Serializable;
|
import java.io.Serializable;
|
||||||
|
import java.util.Arrays;
|
||||||
import java.util.Calendar;
|
import java.util.Calendar;
|
||||||
|
import java.util.HashSet;
|
||||||
import java.util.Map;
|
import java.util.Map;
|
||||||
|
|
||||||
import org.alfresco.model.ContentModel;
|
|
||||||
import org.alfresco.repo.content.MimetypeMap;
|
import org.alfresco.repo.content.MimetypeMap;
|
||||||
import org.alfresco.service.cmr.repository.ContentReader;
|
import org.alfresco.service.cmr.repository.ContentReader;
|
||||||
import org.alfresco.service.namespace.QName;
|
|
||||||
import org.pdfbox.pdmodel.PDDocument;
|
import org.pdfbox.pdmodel.PDDocument;
|
||||||
import org.pdfbox.pdmodel.PDDocumentInformation;
|
import org.pdfbox.pdmodel.PDDocumentInformation;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
* Metadata extractor for the PDF documents.
|
||||||
|
* <pre>
|
||||||
|
* <b>author:</b> -- cm:author
|
||||||
|
* <b>title:</b> -- cm:title
|
||||||
|
* <b>subject:</b> -- cm:description
|
||||||
|
* <b>created:</b> -- cm:created
|
||||||
|
* </pre>
|
||||||
*
|
*
|
||||||
* @author Jesper Steen Møller
|
* @author Jesper Steen Møller
|
||||||
|
* @author Derek Hulley
|
||||||
*/
|
*/
|
||||||
public class PdfBoxMetadataExtracter extends AbstractMetadataExtracter
|
public class PdfBoxMetadataExtracter extends AbstractMappingMetadataExtracter
|
||||||
{
|
{
|
||||||
|
private static final String KEY_AUTHOR = "author";
|
||||||
|
private static final String KEY_TITLE = "title";
|
||||||
|
private static final String KEY_SUBJECT = "subject";
|
||||||
|
private static final String KEY_CREATED = "created";
|
||||||
|
|
||||||
|
public static String[] SUPPORTED_MIMETYPES = new String[] {MimetypeMap.MIMETYPE_PDF };
|
||||||
|
|
||||||
public PdfBoxMetadataExtracter()
|
public PdfBoxMetadataExtracter()
|
||||||
{
|
{
|
||||||
super(MimetypeMap.MIMETYPE_PDF, 1.0, 1000);
|
super(new HashSet<String>(Arrays.asList(SUPPORTED_MIMETYPES)));
|
||||||
}
|
}
|
||||||
|
|
||||||
public void extractInternal(ContentReader reader, Map<QName, Serializable> destination) throws Throwable
|
@Override
|
||||||
|
public Map<String, Serializable> extractRaw(ContentReader reader) throws Throwable
|
||||||
{
|
{
|
||||||
|
Map<String, Serializable> rawProperties = newRawMap();
|
||||||
|
|
||||||
PDDocument pdf = null;
|
PDDocument pdf = null;
|
||||||
InputStream is = null;
|
InputStream is = null;
|
||||||
try
|
try
|
||||||
@@ -62,13 +80,15 @@ public class PdfBoxMetadataExtracter extends AbstractMetadataExtracter
|
|||||||
// Scoop out the metadata
|
// Scoop out the metadata
|
||||||
PDDocumentInformation docInfo = pdf.getDocumentInformation();
|
PDDocumentInformation docInfo = pdf.getDocumentInformation();
|
||||||
|
|
||||||
trimPut(ContentModel.PROP_AUTHOR, docInfo.getAuthor(), destination);
|
putRawValue(KEY_AUTHOR, docInfo.getAuthor(), rawProperties);
|
||||||
trimPut(ContentModel.PROP_TITLE, docInfo.getTitle(), destination);
|
putRawValue(KEY_TITLE, docInfo.getTitle(), rawProperties);
|
||||||
trimPut(ContentModel.PROP_DESCRIPTION, docInfo.getSubject(), destination);
|
putRawValue(KEY_SUBJECT, docInfo.getSubject(), rawProperties);
|
||||||
|
|
||||||
Calendar created = docInfo.getCreationDate();
|
Calendar created = docInfo.getCreationDate();
|
||||||
if (created != null)
|
if (created != null)
|
||||||
destination.put(ContentModel.PROP_CREATED, created.getTime());
|
{
|
||||||
|
putRawValue(KEY_CREATED, created.getTime(), rawProperties);
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
finally
|
finally
|
||||||
@@ -82,5 +102,7 @@ public class PdfBoxMetadataExtracter extends AbstractMetadataExtracter
|
|||||||
try { pdf.close(); } catch (Throwable e) { e.printStackTrace(); }
|
try { pdf.close(); } catch (Throwable e) { e.printStackTrace(); }
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
// Done
|
||||||
|
return rawProperties;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@@ -0,0 +1,13 @@
|
|||||||
|
#
|
||||||
|
# PdfBoxMetadataExtracter - default mapping
|
||||||
|
#
|
||||||
|
# author: Derek Hulley
|
||||||
|
|
||||||
|
# Namespaces
|
||||||
|
namespace.prefix.cm=http://www.alfresco.org/model/content/1.0
|
||||||
|
|
||||||
|
# Mappings
|
||||||
|
author=cm:author
|
||||||
|
title=cm:title
|
||||||
|
subject=cm:description
|
||||||
|
created=cm:created
|
@@ -9,13 +9,14 @@ import org.alfresco.repo.content.MimetypeMap;
|
|||||||
*/
|
*/
|
||||||
public class PdfBoxMetadataExtracterTest extends AbstractMetadataExtracterTest
|
public class PdfBoxMetadataExtracterTest extends AbstractMetadataExtracterTest
|
||||||
{
|
{
|
||||||
private MetadataExtracter extracter;
|
private PdfBoxMetadataExtracter extracter;
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public void setUp() throws Exception
|
public void setUp() throws Exception
|
||||||
{
|
{
|
||||||
super.setUp();
|
super.setUp();
|
||||||
extracter = new PdfBoxMetadataExtracter();
|
extracter = new PdfBoxMetadataExtracter();
|
||||||
|
extracter.register();
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
@@ -26,14 +27,13 @@ public class PdfBoxMetadataExtracterTest extends AbstractMetadataExtracterTest
|
|||||||
return extracter;
|
return extracter;
|
||||||
}
|
}
|
||||||
|
|
||||||
public void testReliability() throws Exception
|
public void testSupports() throws Exception
|
||||||
{
|
{
|
||||||
double reliability = 0.0;
|
for (String mimetype : PdfBoxMetadataExtracter.SUPPORTED_MIMETYPES)
|
||||||
reliability = extracter.getReliability(MimetypeMap.MIMETYPE_TEXT_PLAIN);
|
{
|
||||||
assertEquals("Mimetype should not be supported", 0.0, reliability);
|
boolean supports = extracter.isSupported(mimetype);
|
||||||
|
assertTrue("Mimetype should be supported: " + mimetype, supports);
|
||||||
reliability = extracter.getReliability(MimetypeMap.MIMETYPE_PDF);
|
}
|
||||||
assertEquals("Mimetype should be supported", 1.0, reliability);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
public void testPdfExtraction() throws Exception
|
public void testPdfExtraction() throws Exception
|
||||||
|
Reference in New Issue
Block a user