Examples of PDDocumentInformation

org.apache.pdfbox.pdmodel.PDDocumentInformation
This is the document metadata. Each getXXX method will return the entry if it exists or null if it does not exist. If you pass in null for the setXXX method then it will clear the value. @author Ben Litchfield @author Gerardo Ortiz @version $Revision: 1.12 $
org.pdfbox.pdmodel.PDDocumentInformation
This is the document metadata. Each getXXX method will return the entry if it exists or null if it does not exist. If you pass in null for the setXXX method then it will clear the value. @author Ben Litchfield @version $Revision: 1.12 $

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

                }
                else
                {
                    // The pdf doesn't contain any metadata, try to use the
                    // document information instead
                    PDDocumentInformation information = document.getDocumentInformation();
                    if (information != null)
                    {
                        showDocumentInformation(information);
                    }
                }

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        {
            throw new ValidationException("Document provided is null");
        }
        else
        {
            PDDocumentInformation dico = document.getDocumentInformation();
            if (metadata == null)
            {
                throw new ValidationException("Metadata provided are null");
            }
            else

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        {
            throw new ValidationException("Document provided is null");
        }
        else
        {
            PDDocumentInformation dico = document.getDocumentInformation();
            if (metadata == null)
            {
                throw new ValidationException("Metadata provided are null");
            }
            else

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        }
        if (source.isEncrypted())
        {
            throw new IOException("Error: source PDF is encrypted, can't append encrypted PDF documents.");
        }
        PDDocumentInformation destInfo = destination.getDocumentInformation();
        PDDocumentInformation srcInfo = source.getDocumentInformation();
        destInfo.getDictionary().mergeInto(srcInfo.getDictionary());


        PDDocumentCatalog destCatalog = destination.getDocumentCatalog();
        PDDocumentCatalog srcCatalog = source.getDocumentCatalog();


        // use the highest version number for the resulting pdf

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        clearEntry();
        try
        {
                isris = false;
                document = PDDocument.load(file);
                PDDocumentInformation infos = document.getDocumentInformation();


                PDFTextStripper textStripper=new PDFTextStripper();


                pdfletter = new Integer(pdftextletter.getText());
                if( pdfletter < textStripper.getText(document).length())

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

         clearEntry();
         try
            {
                isris = false;
                document = PDDocument.load(file);
                PDDocumentInformation infos = document.getDocumentInformation();


                //System.out.println( "Page Count=" + document.getNumberOfPages() );
                
                pdftitle.setText(infos.getTitle());
                pdfauthor.setText(infos.getAuthor());
                pdfabstract.setText(infos.getSubject());


                if( document != null )
                {
                    document.close();
                }

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        parse(stream, handler, metadata, new ParseContext());
    }


    private void extractMetadata(PDDocument document, Metadata metadata)
            throws TikaException {
        PDDocumentInformation info = document.getDocumentInformation();
        addMetadata(metadata, Metadata.TITLE, info.getTitle());
        addMetadata(metadata, Metadata.AUTHOR, info.getAuthor());
        addMetadata(metadata, Metadata.CREATOR, info.getCreator());
        addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords());
        addMetadata(metadata, "producer", info.getProducer());
        addMetadata(metadata, Metadata.SUBJECT, info.getSubject());
        addMetadata(metadata, "trapped", info.getTrapped());
        try {
            addMetadata(metadata, "created", info.getCreationDate());
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        try {
            Calendar modified = info.getModificationDate(); 
            addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
    }

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        parse(stream, handler, metadata, new ParseContext());
    }


    private void extractMetadata(PDDocument document, Metadata metadata)
            throws TikaException {
        PDDocumentInformation info = document.getDocumentInformation();
        metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
        addMetadata(metadata, Metadata.TITLE, info.getTitle());
        addMetadata(metadata, Metadata.AUTHOR, info.getAuthor());
        addMetadata(metadata, Metadata.CREATOR, info.getCreator());
        addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords());
        addMetadata(metadata, "producer", info.getProducer());
        addMetadata(metadata, Metadata.SUBJECT, info.getSubject());
        addMetadata(metadata, "trapped", info.getTrapped());
        try {
            addMetadata(metadata, "created", info.getCreationDate());
            addMetadata(metadata, Metadata.CREATION_DATE, info.getCreationDate());
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        try {
            Calendar modified = info.getModificationDate(); 
            addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        
        // All remaining metadata is custom
        // Copy this over as-is
        List<String> handledMetadata = Arrays.asList(new String[] {
             "Author", "Creator", "CreationDate", "ModDate",
             "Keywords", "Producer", "Subject", "Title", "Trapped"
        });
        for(COSName key : info.getDictionary().keySet()) {
            String name = key.getName();
            if(! handledMetadata.contains(name)) {
          addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key));
            }
        }
    }

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        }
    }


    private void extractMetadata(PDDocument document, Metadata metadata)
            throws TikaException {
        PDDocumentInformation info = document.getDocumentInformation();
        metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
        addMetadata(metadata, TikaCoreProperties.TITLE, info.getTitle());
        addMetadata(metadata, TikaCoreProperties.CREATOR, info.getAuthor());
        addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
        addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
        addMetadata(metadata, "producer", info.getProducer());
        // TODO: Move to description in Tika 2.0
        addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject());
        addMetadata(metadata, "trapped", info.getTrapped());
        try {
            // TODO Remove these in Tika 2.0
            addMetadata(metadata, "created", info.getCreationDate());
            addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate());
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        try {
            Calendar modified = info.getModificationDate(); 
            addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
            addMetadata(metadata, TikaCoreProperties.MODIFIED, modified);
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        
        // All remaining metadata is custom
        // Copy this over as-is
        List<String> handledMetadata = Arrays.asList(new String[] {
             "Author", "Creator", "CreationDate", "ModDate",
             "Keywords", "Producer", "Subject", "Title", "Trapped"
        });
        for(COSName key : info.getDictionary().keySet()) {
            String name = key.getName();
            if(! handledMetadata.contains(name)) {
          addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key));
            }
        }
    }

View Full Code Here

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

        }
        if (source.isEncrypted())
        {
            throw new IOException("Error: source PDF is encrypted, can't append encrypted PDF documents.");
        }
        PDDocumentInformation destInfo = destination.getDocumentInformation();
        PDDocumentInformation srcInfo = source.getDocumentInformation();
        destInfo.getDictionary().mergeInto(srcInfo.getDictionary());


        PDDocumentCatalog destCatalog = destination.getDocumentCatalog();
        PDDocumentCatalog srcCatalog = source.getDocumentCatalog();


        // use the highest version number for the resulting pdf

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.