<?xml version="1.0" encoding="UTF-8"?>
<properties>
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
    </parser>
  </parsers>

    /** Whether to extract link URLs as metadata. */
    protected boolean extractLinks = false;

    /** Markdown parser with extensions. */
    protected Parser parser;

    /** Text content renderer. */
    protected TextContentRenderer textRenderer;

    /**
     * Constructs a new MarkdownExtractor and initializes the parser.
     */
    public MarkdownExtractor() {
        super();
        initializeParser();
    }

        final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }

        final Document document = parser.getDocument();
        try {

        }
    }

    /**
     * Creates and configures a DOM parser with the specified features and properties.
     *
     * @return a configured DOM parser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        try {
            final DOMParser parser = new DOMParser();
            // feature

     */
    public static void parse(final SAXParser parser, final InputSource inputSource, final DefaultHandler handler) {
        assertArgumentNotNull("parser", parser);
        assertArgumentNotNull("inputSource", inputSource);
        assertArgumentNotNull("handler", handler);

        try {
            parser.parse(inputSource, handler);
        } catch (final SAXException e) {

     * @return the parsed Query object
     * @throws QueryParseException if the query cannot be parsed
     */
    public Query parse(final String query) {
        return filterChain.parse(query);
    }

    /**
     * Creates a new Lucene query parser with the current configuration.
     * The parser is configured with the default field, analyzer, wildcard settings,
     * and default operator.
     *

     * @param parser the SAX parser to configure
     * @throws SAXNotRecognizedException if the parser doesn't recognize the feature
     * @throws SAXNotSupportedException if the parser doesn't support the feature
     */
    protected void disableExternalResources(final SAXParser parser) throws SAXNotRecognizedException, SAXNotSupportedException {
        try {

    @Resource
    protected CrawlerContainer crawlerContainer;

    /** Map of parser features to configure the DOM parser. */
    protected Map<String, String> featureMap = new HashMap<>();

    /** Map of parser properties to configure the DOM parser. */
    protected Map<String, String> propertyMap = new HashMap<>();

			<artifactId>tika-parser-apple-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-audiovideo-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-cad-module</artifactId>

    }

    /**
     * Creates a parse context.
     *
     * @param parser A parser.
     * @param params A map of parameters.
     * @return a parse context.
     */
    protected ParseContext createParseContext(final Parser parser, final Map<String, String> params) {
        final ParseContext parseContext = new ParseContext();
        parseContext.set(Parser.class, parser);