Examples of EmbeddedDocumentExtractor

org.apache.tika.extractor.EmbeddedDocumentExtractor
Helper class for parsers of package archives or other compound document formats that support embedded or attached component documents. @since Apache Tika 0.8

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

    public PackageExtractor(
            ContentHandler handler, Metadata metadata, ParseContext context) {
        this.handler = handler;
        this.metadata = metadata;


        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);


        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

    private TikaConfig tikaConfig;
    private MimeTypes mimeTypes;
    private Detector detector;


    protected AbstractPOIFSExtractor(ParseContext context) {
        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);


        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

    private final EmbeddedDocumentExtractor embeddedExtractor;


    public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor) {
        this.extractor = extractor;


        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);


        if (ex==null) {
            embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            embeddedExtractor = ex;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

        if (!type.equals(MediaType.OCTET_STREAM)) {
            metadata.set(CONTENT_TYPE, type.toString());
        }


        // Use the delegate parser to parse the contained document
        EmbeddedDocumentExtractor extractor = context.get(
                EmbeddedDocumentExtractor.class,
                new ParsingEmbeddedDocumentExtractor(context));


        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor


    public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor, String type) {
        this.extractor = extractor;
        this.type = type;


        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);


        if (ex==null) {
            embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            embeddedExtractor = ex;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

    private final EmbeddedDocumentExtractor embeddedExtractor;


    public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor) {
        this.extractor = extractor;


        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);


        if (ex==null) {
            embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            embeddedExtractor = ex;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

        if (!type.equals(MediaType.OCTET_STREAM)) {
            metadata.set(CONTENT_TYPE, type.toString());
        }


        // Use the delegate parser to parse the contained document
        EmbeddedDocumentExtractor extractor = context.get(
                EmbeddedDocumentExtractor.class,
                new ParsingEmbeddedDocumentExtractor(context));


        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

                    metadata.set(Metadata.CONTENT_TYPE, "image/png");
                }
                metadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE, 
                        TikaCoreProperties.EmbeddedResourceType.INLINE.toString());


                EmbeddedDocumentExtractor extractor =
                        getEmbeddedDocumentExtractor();
                if (extractor.shouldParseEmbedded(metadata)) {
                    ByteArrayOutputStream buffer = new ByteArrayOutputStream();
                    try {
                        image.write2OutputStream(buffer);
                        image.clear();
                        extractor.parseEmbedded(
                                new ByteArrayInputStream(buffer.toByteArray()),
                                new EmbeddedContentHandler(handler),
                                metadata, false);
                    } catch (IOException e) {
                        // could not extract this image, so just skip it...

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

        }
        resources.clear();
    }


    protected EmbeddedDocumentExtractor getEmbeddedDocumentExtractor() {
        EmbeddedDocumentExtractor extractor =
                context.get(EmbeddedDocumentExtractor.class);
        if (extractor == null) {
            extractor = new ParsingEmbeddedDocumentExtractor(context);
        }
        return extractor;

View Full Code Here

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

            throws IOException, SAXException, TikaException {
        if (embeddedFileNames == null || embeddedFileNames.isEmpty()) {
            return;
        }


        EmbeddedDocumentExtractor extractor = getEmbeddedDocumentExtractor();
        for (Map.Entry<String,COSObjectable> ent : embeddedFileNames.entrySet()) {
            PDComplexFileSpecification spec = (PDComplexFileSpecification) ent.getValue();
            if (spec == null) {
                //skip silently
                continue;

View Full Code Here

0 1 2 3 4

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.