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

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

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

Introduction

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

Prototype

public String getKeywords()

Source Link

Document

This will get the keywords of the document.

Usage

From source file:PDFConverter.java

License:Apache License

/**
 * Implementation is informed by PDFBox authors.
 *
 * @param doc//  w ww .  j av  a 2  s  .  c o m
 * @return
 * @throws IOException
 */
@Override
public synchronized ConvertedDocument convert(java.io.File doc) throws IOException {

    /*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *      http://www.apache.org/licenses/LICENSE-2.0
     *
     * 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.
     */
    /**
     * Adapted from LucenePDFDocument.java from PDFBox lucene project
     *
     * This class is used to create a document for the lucene search engine.
     * This should easily plug into the IndexHTML or IndexFiles that comes
     * with the lucene project. This class will populate the following
     * fields.
     * <table> <tr> <th>Lucene Field Name</th> <th>Description</th> </tr>
     * <tr>
     * <td>path</td> <td>File system path if loaded from a file</td> </tr>
     * <tr>
     * <td>url</td> <td>URL to PDF document</td> </tr> <tr>
     * <td>contents</td>
     * <td>Entire contents of PDF document, indexed but not stored</td>
     * </tr>
     * <tr> <td>summary</td> <td>First 500 characters of content</td> </tr>
     * <tr>
     * <td>modified</td> <td>The modified date/time according to the url or
     * path</td> </tr> <tr> <td>uid</td> <td>A unique identifier for the
     * Lucene document.</td> </tr> <tr> <td>CreationDate</td> <td>From PDF
     * meta-data if available</td> </tr> <tr> <td>Creator</td> <td>From PDF
     * meta-data if available</td> </tr> <tr> <td>Keywords</td> <td>From PDF
     * meta-data if available</td> </tr> <tr> <td>ModificationDate</td>
     * <td>From PDF meta-data if available</td> </tr> <tr> <td>Producer</td>
     * <td>From PDF meta-data if available</td> </tr> <tr> <td>Subject</td>
     * <td>From PDF meta-data if available</td> </tr> <tr> <td>Trapped</td>
     * <td>From PDF meta-data if available</td> </tr> <tr>
     * <td>Encrypted</td> <td>From PDF meta-data if available</td> </tr>
     * </table>
     *
     * @author <a href="mailto:ben@benlitchfield.com">Ben Litchfield</a>
     * @version $Revision: 1.23 $
     *
     * @throws IOException If there is an error parsing the document.
     */
    PDDocument pdfDocument = null;
    ConvertedDocument textdoc = new ConvertedDocument(doc);

    try {
        pdfDocument = PDDocument.load(doc);

        if (pdfDocument.isEncrypted()) {
            //Just try using the default password and move on
            // Even if the doc is encrypted, apparently you can try. Throw exception if it fails.
            textdoc.addProperty("encrypted", "YES");
        }

        //create a writer where to append the text content.
        StringWriter writer = new StringWriter();
        stripper.resetEngine();
        stripper.writeText(pdfDocument, writer);

        PDDocumentInformation info = pdfDocument.getDocumentInformation();
        if (info != null) {
            textdoc.addAuthor(info.getAuthor());
            try {
                textdoc.addCreateDate(info.getCreationDate());
            } catch (IOException io) {
                //ignore, bad date but continue with indexing
            }
            textdoc.addProperty("creator_tool", info.getCreator());
            textdoc.addProperty("keywords", info.getKeywords());
            /* try {
             metadata.add("ModificationDate", info.getModificationDate());
             } catch (IOException io) {
             //ignore, bad date but continue with indexing
             } */
            //metadata.add("Producer", info.getProducer());
            textdoc.addProperty("subject", info.getSubject());
            String ttl = info.getTitle();
            if (ttl == null || "untitled".equalsIgnoreCase(ttl)) {
                ttl = textdoc.filename;
            }
            textdoc.addTitle(ttl);
            // metadata.add("Trapped", info.getTrapped());

            // TODO: Character set is what?
            textdoc.setEncoding("UTF-8");
        }

        // Note: the buffer to string operation is costless;
        // the char array value of the writer buffer and the content string
        // is shared as long as the buffer content is not modified, which will
        // not occur here.
        textdoc.setText(writer.getBuffer().toString());

        return textdoc;

    } finally {
        if (pdfDocument != null) {
            pdfDocument.close();
        }
    }
}

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

License:Open Source License

/**
 * Executes the flow item./*from  w  w w.j a  va 2s .  co  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.github.joemcintyre.pdffinish.PDFFinish.java

License:Open Source License

/**
 * Show metadata from PDF document.//from   w w w.j av  a  2s. 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);
    }/*from ww  w  .j a  v  a  2s.  co 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/*  w  w w  . java  2  s  .co 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));
    }/* w  w  w. java  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.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  om*/
    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());
    }/*w w  w  .  j  a  v  a  2s . c om*/
}

From source file:ddf.catalog.transformer.input.pdf.PdfInputTransformer.java

License:Open Source License

/**
 * @param pdfDocument PDF document// w  w  w  .ja  v  a2 s .  c  om
 * @param metacard    A mutable metacard to add the extracted data to
 */
private void extractPdfMetadata(PDDocument pdfDocument, MetacardImpl metacard) {

    PDDocumentInformation documentInformation = pdfDocument.getDocumentInformation();

    setDateIfNotNull(documentInformation.getCreationDate(), metacard, Metacard.CREATED);

    setDateIfNotNull(documentInformation.getModificationDate(), metacard, Metacard.MODIFIED);

    if (usePdfTitleAsTitle) {
        setIfNotBlank(documentInformation.getTitle(), metacard, Metacard.TITLE);
    }

    setIfNotBlank(documentInformation.getAuthor(), metacard, Contact.CREATOR_NAME);

    setIfNotBlank(documentInformation.getSubject(), metacard, Metacard.DESCRIPTION);

    setIfNotBlank(documentInformation.getKeywords(), metacard, Topic.KEYWORD);

}

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 www .  j  a  va2 s.c o m
 * @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();
}