Moving to root below branch label

git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@2005 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
2025-07-24 17:32:48 +00:00 · 2005-12-08 07:13:07 +00:00
commit e1e6508fec
1095 changed files with 230566 additions and 0 deletions
--- a/source/java/org/alfresco/repo/content/metadata/PdfBoxMetadataExtracter.java
+++ b/source/java/org/alfresco/repo/content/metadata/PdfBoxMetadataExtracter.java
@@ -0,0 +1,91 @@
+/*
+ * 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.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.ContentIOException;
+import org.alfresco.service.cmr.repository.ContentReader;
+import org.alfresco.service.namespace.QName;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.pdfbox.pdmodel.PDDocument;
+import org.pdfbox.pdmodel.PDDocumentInformation;
+
+/**
+ * 
+ * @author Jesper Steen M<>ller
+ */
+public class PdfBoxMetadataExtracter extends AbstractMetadataExtracter
+{
+
+    private static final Log logger = LogFactory.getLog(PdfBoxMetadataExtracter.class);
+
+    public PdfBoxMetadataExtracter()
+    {
+        super(MimetypeMap.MIMETYPE_PDF, 1.0, 1000);
+    }
+
+    public void extract(ContentReader reader, Map<QName, Serializable> destination) throws ContentIOException
+    {
+        if (!MimetypeMap.MIMETYPE_PDF.equals(reader.getMimetype()))
+        {
+            logger.debug("No metadata extracted for " + reader.getMimetype());
+            return;
+        }
+        PDDocument pdf = null;
+        try
+        {
+            // stream the document in
+            pdf = PDDocument.load(reader.getContentInputStream());
+            // Scoop out the metadata
+            PDDocumentInformation docInfo = pdf.getDocumentInformation();
+
+            trimPut(ContentModel.PROP_CREATOR, 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());
+        }
+        catch (IOException e)
+        {
+            throw new ContentIOException("PDF metadata extraction failed: \n" +
+                    "   reader: " + reader);
+        }
+        finally
+        {
+            if (pdf != null)
+            {
+                try
+                {
+                    pdf.close();
+                }
+                catch (Throwable e)
+                {
+                    e.printStackTrace();
+                }
+            }
+        }
+    }
+}