import io.minio.errors.XmlParserException;

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.

 *   <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
 * of the document. It also handles zip bomb prevention and embedded document extraction.
 * </p>
 *
 * <p>

import org.codelibs.core.stream.StreamUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * The FormScheme class implements the AuthScheme interface to provide
 * form-based authentication for HTTP clients. It handles the process of
 * obtaining a token and logging in using the provided credentials.
 *
 * <p>This class supports both GET and POST methods for token and login
 * requests. It also allows for the replacement of placeholders in URLs and

          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *

     */
    public void setUserAgent(final String userAgent) {
        this.userAgent = userAgent;
    }

    /**
     * Sets the credentials provider.
     * @param credentialsProvider The credentials provider.
     */
    public void setCredentialsProvider(final CredentialsProvider credentialsProvider) {
        this.credentialsProvider = credentialsProvider;
    }

    /**

 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:
 * <ul>
 *   <li>Registering and retrieving components by name</li>
 *   <li>Managing singleton instances with lifecycle hooks</li>
 *   <li>Creating prototype instances on demand</li>

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>

 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>
 * This class provides several configuration options to customize the XML parsing process, such as:
 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>

import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * 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,