ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *
     * @param document The document to parse, represented as a map of field names to values.
     * @param fields The fields to extract from the document.

    <glob pattern="*.itk"/>
    <glob pattern="*.tcl"/>
    <glob pattern="*.tk"/>
    <sub-class-of type="text/plain"/>
  </mime-type>

  <mime-type type="text/x-tika-text-based-message">
    <_comment>Text-based (non-binary) Message</_comment>
  </mime-type>

  <mime-type type="text/x-uuencode">
    <glob pattern="*.uu"/>
  </mime-type>

  <mime-type type="text/x-vbasic">

 *   <li>{@link #getUpdateAlias(String)}: Returns the update alias for the given index.</li>
 *   <li>{@link #createIndexName(String)}: Creates a new index name based on the current date and time.</li>
 *   <li>{@link #getDefaultMappings()}: Returns the default mappings for the suggestion index.</li>

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>

import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

 *   <li>Memory size for temporary file storage</li>
 *   <li>Maximum term sizes for alphanumeric and symbolic terms</li>
 *   <li>Custom Tika configuration</li>
 *   <li>Tesseract OCR configuration for image-based documents</li>
 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *
 * <p>
 * The {@link TikaDetectParser} inner class extends {@link CompositeParser} to provide auto-detection of the MIME type

            });

            connected = true;
        } else {
            logger.warn("Could not connect to {}", address);
        }
    }

    /**
     * Creates a new OpenSearch client based on the configured address.
     *
     * @return The created OpenSearch client.
     */
    protected Client createClient() {
        final String[] hosts =

        try {
            client.disconnect();
        } catch (final IOException e) {
            logger.warn("Failed to close FTPClient", e);
        }
    }

    /**
     * Updates the response data based on the FTP file information.
     * This method handles different file types (files, directories, symbolic links)
     * and populates the response data accordingly.
     *
     * @param uri The original URI being accessed

 * connection timeouts, proxy settings, user agent, request headers, cookie management,
 * and SSL configurations. The client also supports robots.txt parsing and form-based
 * authentication schemes.
 *
 * <p>Key properties and configurations:</p>
 * <ul>
 *   <li>CONNECTION_TIMEOUT_PROPERTY: Connection timeout setting.</li>
 *   <li>SO_TIMEOUT_PROPERTY: Socket timeout setting.</li>

 * </p>
 * <ol>
 *   <li>Determining the character set encoding of the HTML content.</li>
 *   <li>Storing the HTML content as data in the {@link ResultData}.</li>
 *   <li>Extracting child URLs from the HTML content based on configured rules.</li>
 *   <li>Handling redirect URLs specified in the response headers.</li>
 * </ol>
 * <p>
 * The class also provides methods for configuring features and properties of the