fix handling of encrypted PDF-Documents (with default user password "")

- update PDFBox package to current version 0.7.3
- use new security model in PDFBox to "guess" wether we can decrypt a document or not
NOTE: When upgrading to this version make sure the old PDFBox-0.7.2.jar is removed from libx/

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4161 6c8d7289-2bf4-0310-a012-ef5d649a1542

source/de/anomic/plasma/parser/pdf/build.xml

@@ -16,7 +16,7 @@
   	  	  <pathelement location="${build}" />	
   	  	
 		  <!-- main lib needed to parse pdf files -->  	  	
-  		  <pathelement location="${libx}/PDFBox-0.7.2.jar" />        	
+  		  <pathelement location="${libx}/PDFBox-0.7.3.jar" />        	
   	  	</classpath>
   	  </javac>    	
     </target>
@@ -25,7 +25,7 @@
     <target name="zip" depends="compile">
   	  <tar destfile="${parserArchive}" compression="gzip">
   	  	<tarfileset dir="${libx}" 
-  	  				includes="PDFBox-0.7.2.*" 
+  	  				includes="PDFBox-0.7.3.*" 
   	  				prefix="${releaseFileParentDir}/libx/"
 			  	  	dirmode="755" mode="644"/>
   	  	<tarfileset dir="${src}/de/anomic/plasma/parser/${parserShortName}" 
@@ -39,7 +39,7 @@
 
     <target name="copy" depends="compile">
         <copy todir="${release}/libx/">
-             <fileset dir="${libx}" includes="PDFBox-0.7.2.*"/> 
+             <fileset dir="${libx}" includes="PDFBox-0.7.3.*"/> 
         </copy>
         <copy todir="${release}/source/de/anomic/plasma/parser/${parserShortName}">
              <fileset dir="${src}/de/anomic/plasma/parser/${parserShortName}" includes="**/*"/> 

source/de/anomic/plasma/parser/pdf/pdfParser.java

@@ -53,6 +53,7 @@ import java.util.Hashtable;
 import org.pdfbox.pdfparser.PDFParser;
 import org.pdfbox.pdmodel.PDDocument;
 import org.pdfbox.pdmodel.PDDocumentInformation;
+import org.pdfbox.pdmodel.encryption.StandardDecryptionMaterial;
 import org.pdfbox.util.PDFTextStripper;
 
 import de.anomic.plasma.plasmaCrawlEURL;
@@ -77,7 +78,7 @@ public class pdfParser extends AbstractParser implements Parser {
      * @see Parser#getLibxDependences()
      */
     private static final String[] LIBX_DEPENDENCIES = new String[] {
-        "PDFBox-0.7.2.jar"
+        "PDFBox-0.7.3.jar"
     };        
     
     public pdfParser() {        
@@ -119,7 +120,9 @@ public class pdfParser extends AbstractParser implements Parser {
             theDocument = parser.getPDDocument();
             
             if (theDocument.isEncrypted()) {
-                throw new ParserException("Document is encrypted",location,plasmaCrawlEURL.DENIED_DOCUMENT_ENCRYPTED);
+                theDocument.openProtection(new StandardDecryptionMaterial(""));
+                if (!theDocument.getCurrentAccessPermission().canExtractContent())
+                    throw new ParserException("Document is encrypted",location,plasmaCrawlEURL.DENIED_DOCUMENT_ENCRYPTED);
             }
             
             // extracting some metadata