import org.xml.sax.helpers.DefaultHandler;

/**
 * Utility class for XML-related operations.
 *
 * This class provides methods to escape special characters in XML strings,
 * strip invalid XML characters, and parse XML content into a map of data.
 *
 * <p>
 * The class is final and cannot be instantiated.
 * </p>
 *
 * <h2>Methods:</h2>
 * <ul>
 *   <li>{@link #escapeXml(String)}: Escapes special characters in an XML string.</li>

 *
 * <p>
 * The class is responsible for:
 * </p>
 * <ul>
 *   <li>Updating session IDs for URL queues.</li>
 *   <li>Adding new URLs to the queue.</li>
 *   <li>Inserting existing {@link UrlQueueImpl} objects into the queue.</li>
 *   <li>Deleting URL queues associated with a session.</li>
 *   <li>Deleting all URL queues.</li>
 *   <li>Offering a list of URLs to the queue, ensuring duplicates are not added.</li>

 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

        } catch (final Exception e) {
            throw new OpenSearchAccessException("Failed to refresh.", e);
        }
    }

    /**
     * Inserts a single document into the OpenSearch index.
     *
     * @param target The object to insert.
     * @param opType The operation type (CREATE, INDEX, etc.).
     * @return The IndexResponse from OpenSearch.

/**
 * Converts Katakana characters to their corresponding Alphabet representations.
 *
 * <p>
 * This class implements the {@link ReadingConverter} interface and provides a method to convert a given
 * Katakana string into a list of possible Alphabet readings. It uses a predefined mapping of Katakana
 * characters to their Alphabet equivalents, handling both single and double Katakana character combinations.
 * </p>
 *
 * <p>

 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.

import org.opensearch.action.admin.indices.analyze.AnalyzeAction.AnalyzeToken;

/**
 * DefaultContentsParser is an implementation of the ContentsParser interface.
 * It provides methods to parse search words, query logs, and documents into SuggestItem objects.
 *
 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *

            return data;
        } catch (final MessagingException e) {
            throw new ExtractException(e);
        }
    }

    /**
     * Puts a value into the extract data with appropriate type conversion.
     *
     * @param data the extract data to store the value in
     * @param key the key for the value
     * @param value the value to store
     */

        String lang = "en";

        List<AnalyzeToken> tokens = analyzer.analyze(text, field, lang);

        assertNotNull(tokens);
        assertEquals(8, tokens.size()); // "I'm" is split into "I" and "m" by our simple tokenizer
        assertEquals("Hello", tokens.get(0).getTerm());
        assertEquals("world", tokens.get(1).getTerm());
        assertEquals("How", tokens.get(2).getTerm());

        urlQueue.setLastModified(0L);
        urlQueue.setDepth(0);
        urlQueue.setMethod(Constants.GET_METHOD);
        insert(urlQueue);
    }

    /**
     * Inserts a URL queue entry into the OpenSearch index.
     *
     * @param urlQueue The URL queue entry to insert.
     */
    @Override
    public void insert(final OpenSearchUrlQueue urlQueue) {
        try {