Example usage for org.apache.pdfbox.pdmodel PDDocumentInformation getProducer

List of usage examples for org.apache.pdfbox.pdmodel PDDocumentInformation getProducer

  1. HOME
  2. Java
  3. org.apache.pdfbox
  4. org.apache.pdfbox.pdmodel.*
  5. PDDocumentInformation
  6. getProducer

Introduction

In this page you can find the example usage for org.apache.pdfbox.pdmodel PDDocumentInformation getProducer.

Prototype

public String getProducer()

Source Link

Document

This will get the producer of the document.

Usage

From source file:PDFExtractMetadata.java

License:Apache License

private static void showDocumentInformation(PDDocumentInformation information) {
    display("Title:", information.getTitle());
    display("Subject:", information.getSubject());
    display("Author:", information.getAuthor());
    display("Creator:", information.getCreator());
    display("Producer:", information.getProducer());
}

From source file:adams.flow.transformer.PDFMetaData.java

License:Open Source License

/**
 * Executes the flow item./*from   w w  w .ja va  2 s .c  o  m*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    File file;
    SpreadSheet sheet;
    PDDocument document;
    PDDocumentInformation info;
    Row row;
    Set<String> keys;

    result = null;

    // get file
    if (m_InputToken.getPayload() instanceof File)
        file = (File) m_InputToken.getPayload();
    else
        file = new PlaceholderFile((String) m_InputToken.getPayload());

    sheet = new DefaultSpreadSheet();
    sheet.setDataRowClass(SparseDataRow.class);
    sheet.setName("Meta-Data: " + file.getAbsolutePath());

    try {
        row = sheet.addRow();
        document = PDDocument.load(file.getAbsoluteFile());
        info = document.getDocumentInformation();

        addCell(row, "Title", info.getTitle());
        addCell(row, "Subject", info.getSubject());
        addCell(row, "Author", info.getAuthor());
        addCell(row, "Keywords", info.getKeywords());
        addCell(row, "Producer", info.getProducer());
        addCell(row, "Creation Date", info.getCreationDate());
        addCell(row, "Modification Date", info.getModificationDate());
        addCell(row, "Creator", info.getCreator());
        addCell(row, "Trapped", info.getTrapped());
        keys = info.getMetadataKeys();
        for (String key : keys)
            addCell(row, "Meta-" + key, info.getCustomMetadataValue(key));
    } catch (Exception e) {
        result = handleException("Failed to extract meta-data: ", e);
    }

    if (result == null)
        m_OutputToken = new Token(sheet);

    return result;
}

From source file:com.esri.geoportal.commons.pdf.PdfUtils.java

License:Apache License

/**
 * Reads metadata values from a PDF file.
 * /* w ww . j  a  v  a 2 s . com*/
 * @param rawBytes the PDF to read
 * @param defaultTitle title to be used if the PDF metadata doesn't have one
 * @param geometryServiceUrl url of a <a href="https://developers.arcgis.com/rest/services-reference/geometry-service.htm">geometry service</a> for reprojecting coordinates. 
 * 
 * @return metadata properties or null if the PDF cannot be read.
 * 
 * @throws IOException on parsing error
 */
public static Properties readMetadata(byte[] rawBytes, String defaultTitle, String geometryServiceUrl)
        throws IOException {
    Properties ret = new Properties();

    // Attempt to read in the PDF file
    try (PDDocument document = PDDocument.load(rawBytes)) {

        // See if we can read the PDF
        if (!document.isEncrypted()) {
            // Get document metadata
            PDDocumentInformation info = document.getDocumentInformation();

            if (info != null) {

                if (info.getTitle() != null) {
                    ret.put(PROP_TITLE, info.getTitle());
                } else {
                    ret.put(PROP_TITLE, defaultTitle);
                }

                if (info.getSubject() != null) {
                    ret.put(PROP_SUBJECT, info.getSubject());
                } else {

                    StringBuilder psudoSubject = new StringBuilder("");
                    psudoSubject.append("\nAuthor: " + info.getAuthor());
                    psudoSubject.append("\nCreator: " + info.getCreator());
                    psudoSubject.append("\nProducer: " + info.getProducer());

                    ret.put(PROP_SUBJECT, psudoSubject.toString());
                }

                if (info.getModificationDate() != null) {
                    ret.put(PROP_MODIFICATION_DATE, info.getModificationDate().getTime());
                } else {
                    ret.put(PROP_MODIFICATION_DATE, info.getCreationDate().getTime());
                }
            } else {
                LOG.warn("Got null metadata for PDF file");
                return null;
            }

            // Attempt to read in geospatial PDF data
            COSObject measure = document.getDocument().getObjectByType(COSName.getPDFName("Measure"));
            String bBox = null;
            if (measure != null) {
                // This is a Geospatial PDF (i.e. Adobe's standard)
                COSDictionary dictionary = (COSDictionary) measure.getObject();

                float[] coords = ((COSArray) dictionary.getItem("GPTS")).toFloatArray();

                bBox = generateBbox(coords);
            } else {
                PDPage page = document.getPage(0);
                if (page.getCOSObject().containsKey(COSName.getPDFName("LGIDict"))) {
                    // This is a GeoPDF (i.e. TerraGo's standard)
                    bBox = extractGeoPDFProps(page, geometryServiceUrl);
                }
            }

            if (bBox != null) {
                ret.put(PROP_BBOX, bBox);
            }

        } else {
            LOG.warn("Cannot read encrypted PDF file");
            return null;
        }

    } catch (IOException ex) {
        LOG.error("Exception reading PDF", ex);
        throw ex;
    }

    return ret;
}

From source file:com.github.joemcintyre.pdffinish.PDFFinish.java

License:Open Source License

/**
 * Show metadata from PDF document./*w w  w  .  j  a  va 2 s.  c  om*/
 * 
 * @param document Loaded PDF document.
 */
private static void showMetadata(PDDocument document) throws IOException {
    PDDocumentInformation info = document.getDocumentInformation();
    System.out.println("Title: " + info.getTitle());
    System.out.println("Author: " + info.getAuthor());
    System.out.println("Subject: " + info.getSubject());
    System.out.println("Keywords: " + info.getKeywords());
    System.out.println("Creator: " + info.getCreator());
    System.out.println("Producer: " + info.getProducer());
    System.out.println("Creation Date: " + info.getCreationDate());
    System.out.println("Modification Date: " + info.getModificationDate());
}

From source file:com.jaeksoft.searchlib.parser.PdfParser.java

License:Open Source License

private void extractMetaData(ParserResultItem result, PDDocument pdf) throws IOException {
    PDDocumentInformation info = pdf.getDocumentInformation();
    if (info != null) {
        result.addField(ParserFieldEnum.title, info.getTitle());
        result.addField(ParserFieldEnum.subject, info.getSubject());
        result.addField(ParserFieldEnum.author, info.getAuthor());
        result.addField(ParserFieldEnum.producer, info.getProducer());
        result.addField(ParserFieldEnum.keywords, info.getKeywords());
        String d = getDate(getCreationDate(info));
        if (d != null)
            result.addField(ParserFieldEnum.creation_date, d);
        d = getDate(getModificationDate(info));
        if (d != null)
            result.addField(ParserFieldEnum.modification_date, d);
    }//  w  w  w .j  a  va 2 s  . c  o m
    int pages = pdf.getNumberOfPages();
    result.addField(ParserFieldEnum.number_of_pages, pages);
    PDDocumentCatalog catalog = pdf.getDocumentCatalog();
    if (catalog != null) {
        result.addField(ParserFieldEnum.language, catalog.getLanguage());
    }
}

From source file:com.openkm.util.metadata.MetadataExtractor.java

License:Open Source License

/**
 * Extract metadata from PDF/* ww w  .j  a v  a 2  s . c  o m*/
 */
public static PdfMetadata pdfExtractor(InputStream is) throws IOException {
    PDDocument doc = PDDocument.load(is);
    PDDocumentInformation info = doc.getDocumentInformation();
    PdfMetadata md = new PdfMetadata();

    md.setNumberOfPages(doc.getNumberOfPages());
    md.setTitle(info.getTitle());
    md.setAuthor(info.getAuthor());
    md.setSubject(info.getSubject());
    md.setKeywords(info.getKeywords());
    md.setCreator(info.getCreator());
    md.setProducer(info.getProducer());
    md.setTrapped(info.getTrapped());
    md.setCreationDate(info.getCreationDate());
    md.setModificationDate(info.getModificationDate());

    log.info("pdfExtractor: {}", md);
    return md;
}

From source file:com.opensearchserver.extractor.parser.PdfBox.java

License:Apache License

private void extractMetaData(PDDocument pdf) throws IOException {
    PDDocumentInformation info = pdf.getDocumentInformation();
    if (info != null) {
        metas.add(TITLE, info.getTitle());
        metas.add(SUBJECT, info.getSubject());
        metas.add(AUTHOR, info.getAuthor());
        metas.add(PRODUCER, info.getProducer());
        metas.add(KEYWORDS, info.getKeywords());
        metas.add(CREATION_DATE, getDate(getCreationDate(info)));
        metas.add(MODIFICATION_DATE, getModificationDate(info));
    }/*from   ww w.  ja v a2  s.c  o m*/
    int pages = pdf.getNumberOfPages();
    metas.add(NUMBER_OF_PAGES, pages);
    PDDocumentCatalog catalog = pdf.getDocumentCatalog();
    if (catalog != null)
        metas.add(LANGUAGE, catalog.getLanguage());
}

From source file:com.qwazr.library.pdfbox.PdfBoxParser.java

License:Apache License

private void extractMetaData(final PDDocument pdf, final ParserFieldsBuilder metas) {
    metas.set(MIME_TYPE, DEFAULT_MIMETYPES[0]);
    final PDDocumentInformation info = pdf.getDocumentInformation();
    if (info != null) {
        metas.add(TITLE, info.getTitle());
        metas.add(SUBJECT, info.getSubject());
        metas.add(AUTHOR, info.getAuthor());
        metas.add(PRODUCER, info.getProducer());
        metas.add(KEYWORDS, info.getKeywords());
        metas.add(CREATION_DATE, info.getCreationDate());
        metas.add(MODIFICATION_DATE, info.getModificationDate());
    }//from  w w  w  . ja  v a 2  s .  c  o  m
    int pages = pdf.getNumberOfPages();
    metas.add(NUMBER_OF_PAGES, pages);
    PDDocumentCatalog catalog = pdf.getDocumentCatalog();
    if (catalog != null)
        metas.add(LANGUAGE, catalog.getLanguage());
}

From source file:com.wintindustries.pdffilter.pdfcore.PDFTester.java

static public void printMetadata(PDDocument document) throws IOException {
    PDDocumentInformation info = document.getDocumentInformation();
    PDDocumentCatalog cat = document.getDocumentCatalog();
    PDMetadata metadata = cat.getMetadata();
    System.out.println("Page Count=" + document.getNumberOfPages());
    System.out.println("Title=" + info.getTitle());
    System.out.println("Author=" + info.getAuthor());
    System.out.println("Subject=" + info.getSubject());
    System.out.println("Keywords=" + info.getKeywords());
    System.out.println("Creator=" + info.getCreator());
    System.out.println("Producer=" + info.getProducer());
    System.out.println("Creation Date=" + formatDate(info.getCreationDate()));
    System.out.println("Modification Date=" + formatDate(info.getModificationDate()));
    System.out.println("Trapped=" + info.getTrapped());
    if (metadata != null) {
        System.out.println("Metadata=" + metadata.getInputStreamAsString());
    }//from ww w.  j ava 2 s. c o  m
}

From source file:de.offis.health.icardea.cied.pdf.extractor.PDFApachePDFBoxExtractor.java

License:Apache License

/**
 * This method will return the key and value pairs stored in the PDF
 * information. It's the basic information like title, subject, author,
 * creator, keywords, producer (meaning application) as well as creation
 * and modification date. The method is provided for debugging purposes.
 * /*from w  w w .  j a  v a 2s.c om*/
 * @return Returns <code>key=value</code> pair line by line (using system
 * dependent newline).
 */
@SuppressWarnings("unused")
private String getPdfInfo() {
    StringBuffer stringBuffer = new StringBuffer();
    if (pdfDocument != null) {
        PDDocumentInformation pdfInfo = pdfDocument.getDocumentInformation();

        // Title
        if (pdfInfo.getTitle() != null) {
            stringBuffer.append("Title");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getTitle());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // Subject
        if (pdfInfo.getSubject() != null) {
            stringBuffer.append("Subject");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getSubject());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // Keywords
        if (pdfInfo.getKeywords() != null) {
            stringBuffer.append("Keywords");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getKeywords());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // Author
        if (pdfInfo.getAuthor() != null) {
            stringBuffer.append("Author");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getAuthor());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // Producer
        if (pdfInfo.getProducer() != null) {
            stringBuffer.append("Producer");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getProducer());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // Creator
        if (pdfInfo.getCreator() != null) {
            stringBuffer.append("Creator");
            stringBuffer.append("=");
            stringBuffer.append(pdfInfo.getCreator());
            stringBuffer.append(GlobalTools.LINESEPARATOR);
        } // end if

        // CreationDate
        try {
            if (pdfInfo.getCreationDate() != null) {
                stringBuffer.append("CreationDate");
                stringBuffer.append("=");
                stringBuffer.append(GlobalTools.calendar2String(pdfInfo.getCreationDate(),
                        GlobalTools.DATE_FORMAT_STRING_ISO8601));
                stringBuffer.append(GlobalTools.LINESEPARATOR);
            } // end if
        } catch (IOException ex) {
        } // end try..catch

        // ModDate
        try {
            if (pdfInfo.getModificationDate() != null) {
                stringBuffer.append("ModDate");
                stringBuffer.append("=");
                stringBuffer.append(GlobalTools.calendar2String(pdfInfo.getModificationDate(),
                        GlobalTools.DATE_FORMAT_STRING_ISO8601));
                stringBuffer.append(GlobalTools.LINESEPARATOR);
            } // end if
        } catch (IOException ex) {
        } // end try..catch
    } // end if

    return stringBuffer.toString();
}