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

Example 1 with ContentHandlerDecorator

use of org.apache.tika.sax.ContentHandlerDecorator in project lucene-solr by apache.

the class TikaEntityProcessor method getHtmlHandler.

private static ContentHandler getHtmlHandler(Writer writer) throws TransformerConfigurationException {
    SAXTransformerFactory factory = (SAXTransformerFactory) TransformerFactory.newInstance();
    TransformerHandler handler = factory.newTransformerHandler();
    handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
    handler.setResult(new StreamResult(writer));
    return new ContentHandlerDecorator(handler) {

        @Override
        public void startElement(String uri, String localName, String name, Attributes atts) throws SAXException {
            if (XHTMLContentHandler.XHTML.equals(uri)) {
                uri = null;
            }
            if (!"head".equals(localName)) {
                super.startElement(uri, localName, name, atts);
            }
        }

        @Override
        public void endElement(String uri, String localName, String name) throws SAXException {
            if (XHTMLContentHandler.XHTML.equals(uri)) {
                uri = null;
            }
            if (!"head".equals(localName)) {
                super.endElement(uri, localName, name);
            }
        }

        @Override
        public void startPrefixMapping(String prefix, String uri) {
        /*no op*/
        }

        @Override
        public void endPrefixMapping(String prefix) {
        /*no op*/
        }
    };
}

Example 2 with ContentHandlerDecorator

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

the class ContentHandlerExample method parseToPlainTextChunks.

/**
     * Example of extracting the plain text in chunks, with each chunk
     * of no more than a certain maximum size
     */
public List<String> parseToPlainTextChunks() throws IOException, SAXException, TikaException {
    final List<String> chunks = new ArrayList<>();
    chunks.add("");
    ContentHandlerDecorator handler = new ContentHandlerDecorator() {

        @Override
        public void characters(char[] ch, int start, int length) {
            String lastChunk = chunks.get(chunks.size() - 1);
            String thisStr = new String(ch, start, length);
            if (lastChunk.length() + length > MAXIMUM_TEXT_CHUNK_SIZE) {
                chunks.add(thisStr);
            } else {
                chunks.set(chunks.size() - 1, lastChunk + thisStr);
            }
        }
    };
    AutoDetectParser parser = new AutoDetectParser();
    Metadata metadata = new Metadata();
    try (InputStream stream = ContentHandlerExample.class.getResourceAsStream("test2.doc")) {
        parser.parse(stream, handler, metadata);
        return chunks;
    }
}

Example 3 with ContentHandlerDecorator

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

the class TikaGUI method getHtmlHandler.

/**
     * Creates and returns a content handler that turns XHTML input to
     * simplified HTML output that can be correctly parsed and displayed
     * by {@link JEditorPane}.
     * <p>
     * The returned content handler is set to output <code>html</code>
     * to the given writer. The XHTML namespace is removed from the output
     * to prevent the serializer from using the &lt;tag/&gt; empty element
     * syntax that causes extra "&gt;" characters to be displayed.
     * The &lt;head&gt; tags are dropped to prevent the serializer from
     * generating a &lt;META&gt; content type tag that makes
     * {@link JEditorPane} fail thinking that the document character set
     * is inconsistent.
     * <p>
     * Additionally, it will use ImageSavingParser to re-write embedded:(image) 
     * image links to be file:///(temporary file) so that they can be loaded.
     *
     * @param writer output writer
     * @return HTML content handler
     * @throws TransformerConfigurationException if an error occurs
     */
private ContentHandler getHtmlHandler(Writer writer) throws TransformerConfigurationException {
    SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
    TransformerHandler handler = factory.newTransformerHandler();
    handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
    handler.setResult(new StreamResult(writer));
    return new ContentHandlerDecorator(handler) {

        @Override
        public void startElement(String uri, String localName, String name, Attributes atts) throws SAXException {
            if (XHTMLContentHandler.XHTML.equals(uri)) {
                uri = null;
            }
            if (!"head".equals(localName)) {
                if ("img".equals(localName)) {
                    AttributesImpl newAttrs;
                    if (atts instanceof AttributesImpl) {
                        newAttrs = (AttributesImpl) atts;
                    } else {
                        newAttrs = new AttributesImpl(atts);
                    }
                    for (int i = 0; i < newAttrs.getLength(); i++) {
                        if ("src".equals(newAttrs.getLocalName(i))) {
                            String src = newAttrs.getValue(i);
                            if (src.startsWith("embedded:")) {
                                String filename = src.substring(src.indexOf(':') + 1);
                                try {
                                    File img = imageParser.requestSave(filename);
                                    String newSrc = img.toURI().toString();
                                    newAttrs.setValue(i, newSrc);
                                } catch (IOException e) {
                                    System.err.println("Error creating temp image file " + filename);
                                // The html viewer will show a broken image too to alert them
                                }
                            }
                        }
                    }
                    super.startElement(uri, localName, name, newAttrs);
                } else {
                    super.startElement(uri, localName, name, atts);
                }
            }
        }

        @Override
        public void endElement(String uri, String localName, String name) throws SAXException {
            if (XHTMLContentHandler.XHTML.equals(uri)) {
                uri = null;
            }
            if (!"head".equals(localName)) {
                super.endElement(uri, localName, name);
            }
        }

        @Override
        public void startPrefixMapping(String prefix, String uri) {
        }

        @Override
        public void endPrefixMapping(String prefix) {
        }
    };
}