TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/x-lha", lhaExtractor);

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

     */
    public XPath createXPath(final Consumer<XPathFactory> builder) {
        try {
            final XPathFactory factory = XPathFactory.newInstance();
            builder.accept(factory);
            return factory.newXPath();
        } catch (final Exception e) {
            throw new CrawlerSystemException("Failed to create XPath instance.", e);
        }
    }

    /**

            factory.setExpandEntityReferences(expandEntityRef);
            factory.setIgnoringComments(ignoringComments);
            factory.setIgnoringElementContentWhitespace(ignoringElementContentWhitespace);
            factory.setNamespaceAware(namespaceAware);
            factory.setValidating(validating);
            factory.setXIncludeAware(includeAware);

import jakarta.annotation.PostConstruct;
import jakarta.annotation.Resource;

/**
 * A factory class for managing and creating crawler clients based on URL patterns.
 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    PdfExtractor pdfExtractor = container.getComponent("pdfExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/pdf", pdfExtractor);

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.
 * It also includes a builder for creating extractors.
 *
 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.

    /**
     * The maximum size of the client factory list.
     */
    protected int maxClientFactorySize = 10000;

    /**
     * Registers a CrawlerClientFactory with this creator.
     * All existing client mappings will be loaded into the new factory.
     * @param crawlerClientFactory The CrawlerClientFactory to register.
     */

      <replaceConfiguration name="Treat some Guava Collection factory methods as Deprecated" uuid="82f9f9ab-9c3b-367f-99ad-40841dc13819" description="Many no-argument Guava Collection factory methods are marked in their javadoc &quot;Should be treated as deprecated&quot;.  These should not be used." suppressId="guava-collection-factory" problemDescriptor="Treat some Guava Collection factory methods as Deprecated" text="com.google.common.collect.Lists.newArrayList()" recursive="false"...

        return kanaBuf.toString();
    }

    /**
     * Checks if the tokenizer is enabled.
     * @param factory The tokenizer factory.
     * @return True if the tokenizer is enabled, false otherwise.
     */
    protected boolean isEnableTokenizer(final TokenizerFactory factory) {
        // TODO return factory instanceof JapaneseTokenizerFactory;
        return false;
    }