package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

    /**
     * Pattern for XML encoding.
     */
    protected Pattern xmlEncodingPattern =

    /**
     * Creates a new NTLMSchemeProvider instance.
     */
    public NTLMSchemeProvider() {
        super();
    }

    /**
     * Creates a new NTLMScheme instance.
     * @param context The HTTP context.
     * @return A new NTLMScheme instance.
     */
    @Override
    public AuthScheme create(final HttpContext context) {

        protected T instance;

        /**
         * The destroyer function to be called when the component is destroyed.
         */
        protected Consumer<T> destroyer;

        /**
         * Creates a new ComponentHolder with the specified instance and destroyer.
         * @param instance the component instance to hold
         * @param destroyer the destroyer function for cleanup (can be null)
         */

 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.
 * These RequestData objects are added to a set of child URLs, which are then
 * passed to a {@link ChildUrlsException} to be processed by the crawler.
 * </p>
 *
 * <p>

    private final Map<String, TesseractOCRConfig> tesseractOCRConfigMap = new ConcurrentHashMap<>();

    private final Map<String, PDFParserConfig> pdfParserConfigMap = new ConcurrentHashMap<>();

    /**
     * Creates a new TikaExtractor instance.
     */
    public TikaExtractor() {
        super();
    }

    /**
     * Initializes this component.
     */
    @PostConstruct
    public void init() {

/**
 * OpenSearchUrlQueue is an implementation of {@link UrlQueue} for OpenSearch.
 */
public class OpenSearchUrlQueue extends UrlQueueImpl<String> implements ToXContent {

    /**
     * Creates a new instance of OpenSearchUrlQueue.
     */
    public OpenSearchUrlQueue() {
        // NOP
    }

    /**
     * Field name for ID.
     */
    public static final String ID = "id";

    /**

    private static final long serialVersionUID = 1L;

    /**
     * The list of child URLs.
     */
    private final Set<RequestData> childUrlList;

    /**
     * Creates a new instance of ChildUrlsException.
     * @param childUrlList The list of child URLs.
     * @param description The description of the exception.
     */

    private static final long serialVersionUID = 1L;

    /**
     * Creates a new instance of OpenSearchAccessException.
     *
     * @param message the detail message
     */
    public OpenSearchAccessException(final String message) {
        super(message);
    }

    /**
     * Creates a new instance of OpenSearchAccessException.
     *
     * @param message the detail message

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {
        super();
    }

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.

 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**
     * Creates a new TextExtractor instance.
     */
    public TextExtractor() {
        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {