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

Introduction

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

Prototype

public String getTrapped() 

Source Link

Document

This will get the trapped value for the document.

Usage

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

License:Open Source License

/**
 * Executes the flow item./*from  w  ww . j  a  v a  2  s .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.openkm.util.metadata.MetadataExtractor.java

License:Open Source License

/**
 * Extract metadata from PDF/*from   ww w.  j  a  v a  2s . 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.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  av a2s  . c  om
}

---

From source file:fr.univ_tours.etu.searcher.LucenePDFDocument.java

License:Apache License

/**
 * This will add the contents to the lucene document.
 *
 * @param document The document to add the contents to.
 * @param is The stream to get the contents from.
 * @param documentLocation The location of the document, used just for debug messages.
 *
 * @throws IOException If there is an error parsing the document.
 *///from w w  w  .  jav  a 2 s. co m
private void addContent(Document document, InputStream is, String documentLocation) throws IOException {
    PDDocument pdfDocument = null;
    try {
        pdfDocument = PDDocument.load(is);

        // create a writer where to append the text content.
        StringWriter writer = new StringWriter();
        if (stripper == null) {
            stripper = new PDFTextStripper();
        }
        stripper.writeText(pdfDocument, writer);

        // 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.
        String contents = writer.getBuffer().toString();

        StringReader reader = new StringReader(contents);

        // Add the tag-stripped contents as a Reader-valued Text field so it will
        // get tokenized and indexed.
        addTextField(document, "contents", reader);

        PDDocumentInformation info = pdfDocument.getDocumentInformation();
        if (info != null) {
            addTextField(document, "Author", info.getAuthor());
            addTextField(document, "CreationDate", info.getCreationDate());
            addTextField(document, "Creator", info.getCreator());
            addTextField(document, "Keywords", info.getKeywords());
            addTextField(document, "ModificationDate", info.getModificationDate());
            addTextField(document, "Producer", info.getProducer());
            addTextField(document, "Subject", info.getSubject());
            addTextField(document, "Title", info.getTitle());
            addTextField(document, "Trapped", info.getTrapped());
        }
        int summarySize = Math.min(contents.length(), 1500);
        String summary = contents.substring(0, summarySize);
        // Add the summary as an UnIndexed field, so that it is stored and returned
        // with hit documents for display.
        addUnindexedField(document, "summary", summary);
    } finally {
        if (pdfDocument != null) {
            pdfDocument.close();
        }
    }
}

---

From source file:mj.ocraptor.extraction.tika.parser.pdf.PDFParser.java

License:Apache License

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 {/*from   w w  w  .  j  ava 2  s  .  co m*/
        // 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));
        }
    }
}

---

From source file:org.apache.tika.parser.pdf.EnhancedPDFParser.java

License:Apache License

@SuppressWarnings("deprecation")
private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException {

    XMPMetadata xmp = null;/*www.  j a v a 2  s  .c o  m*/
    XMPSchemaDublinCore dcSchema = null;
    try {
        if (document.getDocumentCatalog().getMetadata() != null) {
            xmp = XMPMetadata.load(document.getDocumentCatalog().getMetadata().exportXMPMetadata());
        }
        if (xmp != null) {
            dcSchema = xmp.getDublinCoreSchema();
        }
    } catch (IOException e) {
        //swallow
    }
    PDDocumentInformation info = document.getDocumentInformation();
    metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
    extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema);
    addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
    addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
    addMetadata(metadata, "producer", info.getProducer());
    extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema);

    // TODO: Move to description in Tika 2.0
    addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject());
    addMetadata(metadata, "trapped", info.getTrapped());
    // TODO Remove these in Tika 2.0
    addMetadata(metadata, "created", info.getCreationDate());
    addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate());
    Calendar modified = info.getModificationDate();
    addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
    addMetadata(metadata, TikaCoreProperties.MODIFIED, modified);

    // All remaining metadata is custom
    // Copy this over as-is
    List<String> handledMetadata = Arrays.asList("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));
        }
    }

    //try to get the various versions
    //Caveats:
    //    there is currently a fair amount of redundancy
    //    TikaCoreProperties.FORMAT can be multivalued
    //    There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion        
    metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion()));
    metadata.add(TikaCoreProperties.FORMAT.getName(),
            MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion()));

    try {
        if (xmp != null) {
            xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class);
            XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class);
            if (pdfaxmp != null) {
                metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart()));
                if (pdfaxmp.getConformance() != null) {
                    metadata.set("pdfaid:conformance", pdfaxmp.getConformance());
                    String version = "A-" + pdfaxmp.getPart()
                            + pdfaxmp.getConformance().toLowerCase(Locale.ROOT);
                    metadata.set("pdfa:PDFVersion", version);
                    metadata.add(TikaCoreProperties.FORMAT.getName(),
                            MEDIA_TYPE.toString() + "; version=\"" + version + "\"");
                }
            }
            // TODO WARN if this XMP version is inconsistent with document header version?          
        }
    } catch (IOException e) {
        metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e);
    }
    //TODO: Let's try to move this into PDFBox.
    //Attempt to determine Adobe extension level, if present:
    COSDictionary root = document.getDocumentCatalog().getCOSObject();
    COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions"));
    if (extensions != null) {
        for (COSName extName : extensions.keySet()) {
            // If it's an Adobe one, interpret it to determine the extension level:
            if (extName.equals(COSName.getPDFName("ADBE"))) {
                COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName);
                if (adobeExt != null) {
                    String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion"));
                    int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel"));
                    //-1 is sentinel value that something went wrong in getInt
                    if (el != -1) {
                        metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el);
                        metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\""
                                + baseVersion + " Adobe Extension Level " + el + "\"");
                    }
                }
            } else {
                // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'.
                metadata.set("pdf:foundNonAdobeExtensionName", extName.getName());
            }
        }
    }
}

---

From source file:org.apache.tika.parser.pdf.PDFParser.java

License:Apache License

private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException {

    //first extract AccessPermissions
    AccessPermission ap = document.getCurrentAccessPermission();
    metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY,
            Boolean.toString(ap.canExtractForAccessibility()));
    metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent()));
    metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument()));
    metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm()));
    metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify()));
    metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations()));
    metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint()));
    metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded()));

    //now go for the XMP
    org.apache.jempbox.xmp.XMPMetadata xmp = null;
    XMPSchemaDublinCore dcSchema = null;
    XMPSchemaMediaManagement mmSchema = null;
    try {//from  w  w  w .  ja  v a 2  s  . c o  m
        if (document.getDocumentCatalog().getMetadata() != null) {
            xmp = document.getDocumentCatalog().getMetadata().exportXMPMetadata();
        }
    } catch (IOException e) {
    }

    if (xmp != null) {
        try {
            dcSchema = xmp.getDublinCoreSchema();
        } catch (IOException e) {
        }

        JempboxExtractor.extractXMPMM(xmp, metadata);
    }

    PDDocumentInformation info = document.getDocumentInformation();
    metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
    extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema);
    addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
    addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
    addMetadata(metadata, "producer", info.getProducer());
    extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema);

    // 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("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));
        }
    }

    //try to get the various versions
    //Caveats:
    //    there is currently a fair amount of redundancy
    //    TikaCoreProperties.FORMAT can be multivalued
    //    There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion        
    metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion()));
    metadata.add(TikaCoreProperties.FORMAT.getName(),
            MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion()));

    try {
        if (xmp != null) {
            xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class);
            XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class);
            if (pdfaxmp != null) {
                if (pdfaxmp.getPart() != null) {
                    metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart()));
                }
                if (pdfaxmp.getConformance() != null) {
                    metadata.set("pdfaid:conformance", pdfaxmp.getConformance());
                    String version = "A-" + pdfaxmp.getPart()
                            + pdfaxmp.getConformance().toLowerCase(Locale.ROOT);
                    metadata.set("pdfa:PDFVersion", version);
                    metadata.add(TikaCoreProperties.FORMAT.getName(),
                            MEDIA_TYPE.toString() + "; version=\"" + version + "\"");
                }
            }
            // TODO WARN if this XMP version is inconsistent with document header version?          
        }
    } catch (IOException e) {
        metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e);
    }
    //TODO: Let's try to move this into PDFBox.
    //Attempt to determine Adobe extension level, if present:
    COSDictionary root = document.getDocumentCatalog().getCOSDictionary();
    COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions"));
    if (extensions != null) {
        for (COSName extName : extensions.keySet()) {
            // If it's an Adobe one, interpret it to determine the extension level:
            if (extName.equals(COSName.getPDFName("ADBE"))) {
                COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName);
                if (adobeExt != null) {
                    String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion"));
                    int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel"));
                    //-1 is sentinel value that something went wrong in getInt
                    if (el != -1) {
                        metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el);
                        metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\""
                                + baseVersion + " Adobe Extension Level " + el + "\"");
                    }
                }
            } else {
                // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'.
                metadata.set("pdf:foundNonAdobeExtensionName", extName.getName());
            }
        }
    }
}

---

From source file:org.apache.tika.parser.pdf.PDFPureJavaParser.java

License:Apache License

private void extractMetadata(PDDocument document, Metadata metadata, ParseContext context)
        throws TikaException {

    //first extract AccessPermissions
    AccessPermission ap = document.getCurrentAccessPermission();
    metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY,
            Boolean.toString(ap.canExtractForAccessibility()));
    metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent()));
    metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument()));
    metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm()));
    metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify()));
    metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations()));
    metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint()));
    metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded()));

    //now go for the XMP
    Document dom = loadDOM(document.getDocumentCatalog().getMetadata(), metadata, context);

    XMPMetadata xmp = null;//from www . ja v a  2 s . co m
    if (dom != null) {
        xmp = new XMPMetadata(dom);
    }
    XMPSchemaDublinCore dcSchema = null;

    /*if (xmp != null) {
    try {
        dcSchema = xmp.getDublinCoreSchema();
    } catch (IOException e) {}
            
    JempboxExtractor.extractXMPMM(xmp, metadata);
    }*/

    PDDocumentInformation info = document.getDocumentInformation();
    metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
    extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema);
    addMetadata(metadata, PDF.DOC_INFO_TITLE, info.getTitle());
    extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema);
    addMetadata(metadata, PDF.DOC_INFO_CREATOR, info.getAuthor());
    extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema);
    addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
    addMetadata(metadata, PDF.DOC_INFO_CREATOR_TOOL, info.getCreator());
    addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
    addMetadata(metadata, PDF.DOC_INFO_KEY_WORDS, info.getKeywords());
    addMetadata(metadata, "producer", info.getProducer());
    addMetadata(metadata, PDF.DOC_INFO_PRODUCER, info.getProducer());
    extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema);

    addMetadata(metadata, PDF.DOC_INFO_SUBJECT, info.getSubject());

    // TODO: Move to description in Tika 2.0
    addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject());
    addMetadata(metadata, "trapped", info.getTrapped());
    addMetadata(metadata, PDF.DOC_INFO_TRAPPED, info.getTrapped());
    // TODO Remove these in Tika 2.0
    addMetadata(metadata, "created", info.getCreationDate());
    addMetadata(metadata, PDF.DOC_INFO_CREATED, info.getCreationDate());
    addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate());
    Calendar modified = info.getModificationDate();
    addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
    addMetadata(metadata, TikaCoreProperties.MODIFIED, modified);
    addMetadata(metadata, PDF.DOC_INFO_MODIFICATION_DATE, info.getModificationDate());

    // All remaining metadata is custom
    // Copy this over as-is
    List<String> handledMetadata = Arrays.asList("Author", "Creator", "CreationDate", "ModDate", "Keywords",
            "Producer", "Subject", "Title", "Trapped");
    for (COSName key : info.getCOSObject().keySet()) {
        String name = key.getName();
        if (!handledMetadata.contains(name)) {
            addMetadata(metadata, name, info.getCOSObject().getDictionaryObject(key));
            addMetadata(metadata, PDF.PDF_DOC_INFO_CUSTOM_PREFIX + name,
                    info.getCOSObject().getDictionaryObject(key));
        }
    }

    //try to get the various versions
    //Caveats:
    //    there is currently a fair amount of redundancy
    //    TikaCoreProperties.FORMAT can be multivalued
    //    There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion
    metadata.set(PDF.PDF_VERSION, Float.toString(document.getDocument().getVersion()));
    metadata.add(TikaCoreProperties.FORMAT.getName(),
            MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion()));

    try {
        if (xmp != null) {
            xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class);
            XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class);
            if (pdfaxmp != null) {
                if (pdfaxmp.getPart() != null) {
                    metadata.set(PDF.PDFAID_PART, Integer.toString(pdfaxmp.getPart()));
                }
                if (pdfaxmp.getConformance() != null) {
                    metadata.set(PDF.PDFAID_CONFORMANCE, pdfaxmp.getConformance());
                    String version = "A-" + pdfaxmp.getPart()
                            + pdfaxmp.getConformance().toLowerCase(Locale.ROOT);
                    metadata.set(PDF.PDFA_VERSION, version);
                    metadata.add(TikaCoreProperties.FORMAT.getName(),
                            MEDIA_TYPE.toString() + "; version=\"" + version + "\"");
                }
            }
            // TODO WARN if this XMP version is inconsistent with document header version?          
        }
    } catch (IOException e) {
        metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e);
    }
    //TODO: Let's try to move this into PDFBox.
    //Attempt to determine Adobe extension level, if present:
    COSDictionary root = document.getDocumentCatalog().getCOSObject();
    COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions"));
    if (extensions != null) {
        for (COSName extName : extensions.keySet()) {
            // If it's an Adobe one, interpret it to determine the extension level:
            if (extName.equals(COSName.getPDFName("ADBE"))) {
                COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName);
                if (adobeExt != null) {
                    String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion"));
                    int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel"));
                    //-1 is sentinel value that something went wrong in getInt
                    if (el != -1) {
                        metadata.set(PDF.PDF_EXTENSION_VERSION, baseVersion + " Adobe Extension Level " + el);
                        metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\""
                                + baseVersion + " Adobe Extension Level " + el + "\"");
                    }
                }
            } else {
                // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'.
                metadata.set("pdf:foundNonAdobeExtensionName", extName.getName());
            }
        }
    }
}

---

From source file:org.apache.tika.parser.pdf18.PDFParser.java

License:Apache License

private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException {

    //first extract AccessPermissions
    AccessPermission ap = document.getCurrentAccessPermission();
    metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY,
            Boolean.toString(ap.canExtractForAccessibility()));
    metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent()));
    metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument()));
    metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm()));
    metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify()));
    metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations()));
    metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint()));
    metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded()));

    //now go for the XMP
    org.apache.jempbox.xmp.XMPMetadata xmp = null;
    XMPSchemaDublinCore dcSchema = null;
    XMPSchemaMediaManagement mmSchema = null;
    try {// w w  w . ja v  a2 s .  c  o  m
        if (document.getDocumentCatalog().getMetadata() != null) {
            xmp = document.getDocumentCatalog().getMetadata().exportXMPMetadata();
        }
    } catch (IOException e) {
    }

    if (xmp != null) {
        try {
            dcSchema = xmp.getDublinCoreSchema();
        } catch (IOException e) {
        }

        JempboxExtractor.extractXMPMM(xmp, metadata);
    }

    PDDocumentInformation info = document.getDocumentInformation();
    metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
    extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema);
    extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema);
    addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
    addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
    addMetadata(metadata, "producer", info.getProducer());
    extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema);

    // 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("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));
        }
    }

    //try to get the various versions
    //Caveats:
    //    there is currently a fair amount of redundancy
    //    TikaCoreProperties.FORMAT can be multivalued
    //    There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion
    metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion()));
    metadata.add(TikaCoreProperties.FORMAT.getName(),
            MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion()));

    try {
        if (xmp != null) {
            xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class);
            XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class);
            if (pdfaxmp != null) {
                if (pdfaxmp.getPart() != null) {
                    metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart()));
                }
                if (pdfaxmp.getConformance() != null) {
                    metadata.set("pdfaid:conformance", pdfaxmp.getConformance());
                    String version = "A-" + pdfaxmp.getPart()
                            + pdfaxmp.getConformance().toLowerCase(Locale.ROOT);
                    metadata.set("pdfa:PDFVersion", version);
                    metadata.add(TikaCoreProperties.FORMAT.getName(),
                            MEDIA_TYPE.toString() + "; version=\"" + version + "\"");
                }
            }
            // TODO WARN if this XMP version is inconsistent with document header version?
        }
    } catch (IOException e) {
        metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e);
    }
    //TODO: Let's try to move this into PDFBox.
    //Attempt to determine Adobe extension level, if present:
    COSDictionary root = document.getDocumentCatalog().getCOSDictionary();
    COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions"));
    if (extensions != null) {
        for (COSName extName : extensions.keySet()) {
            // If it's an Adobe one, interpret it to determine the extension level:
            if (extName.equals(COSName.getPDFName("ADBE"))) {
                COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName);
                if (adobeExt != null) {
                    String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion"));
                    int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel"));
                    //-1 is sentinel value that something went wrong in getInt
                    if (el != -1) {
                        metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el);
                        metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\""
                                + baseVersion + " Adobe Extension Level " + el + "\"");
                    }
                }
            } else {
                // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'.
                metadata.set("pdf:foundNonAdobeExtensionName", extName.getName());
            }
        }
    }
}

---

From source file:org.knoesis.matvocab.indexer.LucenePDFDocument.java

License:Apache License

/**
 * This will add the contents to the lucene document.
 *
 * @param document The document to add the contents to.
 * @param is The stream to get the contents from.
 * @param documentLocation The location of the document, used just for debug messages.
 *
 * @throws IOException If there is an error parsing the document.
 *///from www.j  ava  2  s.  c  om
private void addContent(Document document, InputStream is, String documentLocation, PDFTextStripper stripper)
        throws IOException {
    PDDocument pdfDocument = null;
    try {
        pdfDocument = PDDocument.load(is);

        if (pdfDocument.isEncrypted()) {
            //Just try using the default password and move on
            pdfDocument.decrypt("");
        }

        //create a writer where to append the text content.
        StringWriter writer = new StringWriter();
        if (stripper == null) {
            stripper = new PDFTextStripper();
        } else {
            stripper.resetEngine();
        }
        stripper.writeText(pdfDocument, writer);

        // 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.
        String contents = writer.getBuffer().toString();
        // Add the tag-stripped contents as a Reader-valued Text field so it will
        // get tokenized and indexed.
        addField(document, "contents", contents);

        addField(document, "stemmedcontents", contents);

        PDDocumentInformation info = pdfDocument.getDocumentInformation();
        if (info != null) {
            addField(document, "Author", info.getAuthor());
            try {
                addField(document, "CreationDate", info.getCreationDate());
            } catch (IOException io) {
                //ignore, bad date but continue with indexing
            }
            addField(document, "Creator", info.getCreator());
            addField(document, "Keywords", info.getKeywords());
            try {
                addField(document, "ModificationDate", info.getModificationDate());
            } catch (IOException io) {
                //ignore, bad date but continue with indexing
            }
            addField(document, "Producer", info.getProducer());
            addField(document, "Subject", info.getSubject());
            addField(document, "Title", info.getTitle());
            addField(document, "Trapped", info.getTrapped());
        }
        int summarySize = Math.min(contents.length(), 500);
        String summary = contents.substring(0, summarySize);
        // Add the summary as an UnIndexed field, so that it is stored and returned
        // with hit documents for display.
        addField(document, "summary", summary);
        addField(document, "numpages", String.valueOf(pdfDocument.getNumberOfPages()));
    } catch (CryptographyException e) {
        throw new IOException("Error decrypting document(" + documentLocation + "): " + e);
    } catch (InvalidPasswordException e) {
        //they didn't suppply a password and the default of "" was wrong.
        throw new IOException(
                "Error: The document(" + documentLocation + ") is encrypted and will not be indexed.");
    } finally {
        if (pdfDocument != null) {
            pdfDocument.close();
        }
    }
}

---

• «
• 1
• 2
• »