* @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<>();

    }

    /**
     * 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);

        try {
            final StandardQueryParser parser = new StandardQueryParser();
            parser.setDefaultOperator(StandardQueryConfigHandler.Operator.AND);

            // Parse with the first field if available, otherwise use "default"
            String defaultField = fields != null && fields.length > 0 ? fields[0] : "default";
            termQueryList = getTermQueryList(parser.parse(q, defaultField), fields);

        final DOMParser parser = getDomParser();
        try (final InputStream in = responseData.getResponseBody()) {
            final InputSource is = new InputSource(in);
            if (responseData.getCharSet() != null) {
                is.setEncoding(responseData.getCharSet());
            }
            parser.parse(is);
        } catch (final Exception e) {

        }
    }

    /**
     * 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() {
        final DOMParser parser = new DOMParser();
        try {
            // feature

 *
 * <p>Usage example:</p>
 * <pre>
 * {@code
 * DefaultContentsParser parser = new DefaultContentsParser();
 * SuggestItem item = parser.parseSearchWords(words, readings, fields, tags, roles, score, readingConverter, normalizer, analyzer, langs);
 * }
 * </pre>
 *
 * @see ContentsParser
 * @see SuggestItem
 * @see ReadingConverter

    /**
     * If true, the parser will be namespace aware.
     */
    protected boolean namespaceAware;

    /**
     * If true, the parser will convert CDATA nodes to Text nodes and append them to the adjacent Text node.
     */
    protected boolean coalescing;

    /**
     * If true, the parser will expand entity reference nodes.
     */

			<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>

- **Fault Tolerance**: Built-in retry mechanisms and error handling
- **Flexible Configuration**: XML-based dependency injection with LastaFlute DI
- **Extensible Architecture**: Plugin system for custom extractors, transformers, and clients
- **Rate Limiting**: Politeness policies and interval controllers
- **URL Filtering**: Regex-based inclusion/exclusion patterns
- **Data Persistence**: Multiple backend options including OpenSearch integration