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

Introduction

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

Prototype

public Set<String> getMetadataKeys() 

Source Link

Document

This will get the keys of all metadata information fields for the document.

Usage

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

License:Open Source License

/**
 * Executes the flow item./*from   www.j  av  a2s.  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:org.codelibs.fess.crawler.extractor.impl.PdfExtractor.java

License:Apache License

private void extractMetadata(final PDDocument document, final ExtractData extractData) {
    final PDDocumentInformation info = document.getDocumentInformation();
    if (info == null) {
        return;//from  w  ww.  j  a  v  a  2s  .com
    }

    for (final String key : info.getMetadataKeys()) {
        final String value = info.getCustomMetadataValue(key);
        addMetadata(extractData, key, value);
    }
}

---

From source file:org.pdfmetamodifier.MetadataHelper.java

License:Apache License

/**
 * Convert Metadata object to list of lines.
 * /*from ww  w .  j  a v a 2 s .com*/
 * @param metadata
 *            Source Metadata object.
 * @return list of lines with Metadata representation.
 */
public static List<String> metadataToLineList(final PDDocumentInformation documentInformation) {
    final List<String> lineList = new ArrayList<>();

    if (documentInformation != null) {
        final List<String> matadataKeys = new ArrayList<>(documentInformation.getMetadataKeys());
        Collections.sort(matadataKeys);

        for (String key : matadataKeys) {
            final String value = documentInformation.getCustomMetadataValue(key);
            if (value != null) {
                lineList.add(String.format(METADATA_LINE_TEMPLATE, key, value));
            }
        }
    }

    return lineList;
}

---