Examples with XHTMLContentHandler org.apache.tika.sax.XHTMLContentHandler used on opensource projects

Example 61 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class PDFParser method handleXFAOnly.

private void handleXFAOnly(PDDocument pdDocument, ContentHandler handler, Metadata metadata, ParseContext context) throws SAXException, IOException, TikaException {
    XFAExtractor ex = new XFAExtractor();
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    try (InputStream is = new ByteArrayInputStream(pdDocument.getDocumentCatalog().getAcroForm().getXFA().getBytes())) {
        ex.extract(is, xhtml, metadata, context);
    } catch (XMLStreamException e) {
        throw new TikaException("XML error in XFA", e);
    }
    xhtml.endDocument();
}

Example 62 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class CompressorParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    // should not be closed
    if (stream.markSupported()) {
        stream = new CloseShieldInputStream(stream);
    } else {
        // Ensure that the stream supports the mark feature
        stream = new BufferedInputStream(new CloseShieldInputStream(stream));
    }
    CompressorInputStream cis;
    try {
        CompressorParserOptions options = context.get(CompressorParserOptions.class, new CompressorParserOptions() {

            public boolean decompressConcatenated(Metadata metadata) {
                return false;
            }
        });
        CompressorStreamFactory factory = new CompressorStreamFactory(options.decompressConcatenated(metadata), memoryLimitInKb);
        cis = factory.createCompressorInputStream(stream);
    } catch (CompressorException e) {
        if (e.getCause() != null && e.getCause() instanceof MemoryLimitException) {
            throw new TikaMemoryLimitException(e.getMessage());
        }
        throw new TikaException("Unable to uncompress document stream", e);
    }
    MediaType type = getMediaType(cis);
    if (!type.equals(MediaType.OCTET_STREAM)) {
        metadata.set(CONTENT_TYPE, type.toString());
    }
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    try {
        Metadata entrydata = new Metadata();
        String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
        if (name != null) {
            if (name.endsWith(".tbz")) {
                name = name.substring(0, name.length() - 4) + ".tar";
            } else if (name.endsWith(".tbz2")) {
                name = name.substring(0, name.length() - 5) + ".tar";
            } else if (name.endsWith(".bz")) {
                name = name.substring(0, name.length() - 3);
            } else if (name.endsWith(".bz2")) {
                name = name.substring(0, name.length() - 4);
            } else if (name.endsWith(".xz")) {
                name = name.substring(0, name.length() - 3);
            } else if (name.endsWith(".zlib")) {
                name = name.substring(0, name.length() - 5);
            } else if (name.endsWith(".pack")) {
                name = name.substring(0, name.length() - 5);
            } else if (name.length() > 0) {
                name = GzipUtils.getUncompressedFilename(name);
            }
            entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
        }
        // Use the delegate parser to parse the compressed document
        EmbeddedDocumentExtractor extractor = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
        if (extractor.shouldParseEmbedded(entrydata)) {
            extractor.parseEmbedded(cis, xhtml, entrydata, true);
        }
    } finally {
        cis.close();
    }
    xhtml.endDocument();
}

Example 63 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class PackageParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    //lazily load the MediaTypeRegistry at parse time
    //only want to call getDefaultConfig() once, and can't
    //load statically because of the ForkParser
    TikaConfig config = context.get(TikaConfig.class);
    MediaTypeRegistry mediaTypeRegistry = null;
    if (config != null) {
        mediaTypeRegistry = config.getMediaTypeRegistry();
    } else {
        if (bufferedMediaTypeRegistry == null) {
            //buffer this for next time.
            synchronized (lock) {
                //now that we're locked, check again
                if (bufferedMediaTypeRegistry == null) {
                    bufferedMediaTypeRegistry = TikaConfig.getDefaultConfig().getMediaTypeRegistry();
                }
            }
        }
        mediaTypeRegistry = bufferedMediaTypeRegistry;
    }
    // Ensure that the stream supports the mark feature
    if (!stream.markSupported()) {
        stream = new BufferedInputStream(stream);
    }
    TemporaryResources tmp = new TemporaryResources();
    ArchiveInputStream ais = null;
    try {
        ArchiveStreamFactory factory = context.get(ArchiveStreamFactory.class, new ArchiveStreamFactory());
        // At the end we want to close the archive stream to release
        // any associated resources, but the underlying document stream
        // should not be closed
        ais = factory.createArchiveInputStream(new CloseShieldInputStream(stream));
    } catch (StreamingNotSupportedException sne) {
        // Most archive formats work on streams, but a few need files
        if (sne.getFormat().equals(ArchiveStreamFactory.SEVEN_Z)) {
            // Rework as a file, and wrap
            stream.reset();
            TikaInputStream tstream = TikaInputStream.get(stream, tmp);
            // Seven Zip suports passwords, was one given?
            String password = null;
            PasswordProvider provider = context.get(PasswordProvider.class);
            if (provider != null) {
                password = provider.getPassword(metadata);
            }
            SevenZFile sevenz;
            if (password == null) {
                sevenz = new SevenZFile(tstream.getFile());
            } else {
                sevenz = new SevenZFile(tstream.getFile(), password.getBytes("UnicodeLittleUnmarked"));
            }
            // Pending a fix for COMPRESS-269 / TIKA-1525, this bit is a little nasty
            ais = new SevenZWrapper(sevenz);
        } else {
            tmp.close();
            throw new TikaException("Unknown non-streaming format " + sne.getFormat(), sne);
        }
    } catch (ArchiveException e) {
        tmp.close();
        throw new TikaException("Unable to unpack document stream", e);
    }
    updateMediaType(ais, mediaTypeRegistry, metadata);
    // Use the delegate parser to parse the contained document
    EmbeddedDocumentExtractor extractor = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    try {
        ArchiveEntry entry = ais.getNextEntry();
        while (entry != null) {
            if (!entry.isDirectory()) {
                parseEntry(ais, entry, extractor, metadata, xhtml);
            }
            entry = ais.getNextEntry();
        }
    } catch (UnsupportedZipFeatureException zfe) {
        // If it's an encrypted document of unknown password, report as such
        if (zfe.getFeature() == Feature.ENCRYPTION) {
            throw new EncryptedDocumentException(zfe);
        }
        // Otherwise throw the exception
        throw new TikaException("UnsupportedZipFeature", zfe);
    } catch (PasswordRequiredException pre) {
        throw new EncryptedDocumentException(pre);
    } finally {
        ais.close();
        tmp.close();
    }
    xhtml.endDocument();
}

Example 64 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class TXTParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    // Automatically detect the character encoding
    try (AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(stream), metadata, getEncodingDetector(context))) {
        //try to get detected content type; could be a subclass of text/plain
        //such as vcal, etc.
        String incomingMime = metadata.get(Metadata.CONTENT_TYPE);
        MediaType mediaType = MediaType.TEXT_PLAIN;
        if (incomingMime != null) {
            MediaType tmpMediaType = MediaType.parse(incomingMime);
            if (tmpMediaType != null) {
                mediaType = tmpMediaType;
            }
        }
        Charset charset = reader.getCharset();
        MediaType type = new MediaType(mediaType, charset);
        metadata.set(Metadata.CONTENT_TYPE, type.toString());
        // deprecated, see TIKA-431
        metadata.set(Metadata.CONTENT_ENCODING, charset.name());
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        char[] buffer = new char[4096];
        int n = reader.read(buffer);
        while (n != -1) {
            xhtml.characters(buffer, 0, n);
            n = reader.read(buffer);
        }
        xhtml.endElement("p");
        xhtml.endDocument();
    }
}

Example 65 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class OpenDocumentParser method parse.

public void parse(InputStream stream, ContentHandler baseHandler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    // Open the Zip stream
    // Use a File if we can, and an already open zip is even better
    ZipFile zipFile = null;
    ZipInputStream zipStream = null;
    if (stream instanceof TikaInputStream) {
        TikaInputStream tis = (TikaInputStream) stream;
        Object container = ((TikaInputStream) stream).getOpenContainer();
        if (container instanceof ZipFile) {
            zipFile = (ZipFile) container;
        } else if (tis.hasFile()) {
            zipFile = new ZipFile(tis.getFile());
        } else {
            zipStream = new ZipInputStream(stream);
        }
    } else {
        zipStream = new ZipInputStream(stream);
    }
    // Prepare to handle the content
    XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);
    // As we don't know which of the metadata or the content
    //  we'll hit first, catch the endDocument call initially
    EndDocumentShieldingContentHandler handler = new EndDocumentShieldingContentHandler(xhtml);
    if (zipFile != null) {
        try {
            handleZipFile(zipFile, metadata, context, handler);
        } finally {
            //Do we want to close silently == catch an exception here?
            zipFile.close();
        }
    } else {
        try {
            handleZipStream(zipStream, metadata, context, handler);
        } finally {
            //Do we want to close silently == catch an exception here?
            zipStream.close();
        }
    }
    // Only now call the end document
    if (handler.getEndDocumentWasCalled()) {
        handler.reallyEndDocument();
    }
}