}
        }
        return SSLConnectionSocketFactory.getSocketFactory();
    }

    /**
     * Builds the cookie specification registry.
     *
     * @return The configured cookie specification registry
     */
    protected Lookup<CookieSpecProvider> buildCookieSpecRegistry() {
        if (cookieSpecRegistry != null) {
            return cookieSpecRegistry;
        }

                extractFile(ent.getKey(), embeddedFile, writer);
            }
        }
    }

    /**
     * Gets the embedded file from a file specification, trying different platform-specific variants.
     * @param fileSpec the file specification
     * @return the embedded file, or null if not found
     */
    protected PDEmbeddedFile getEmbeddedFile(final PDComplexFileSpecification fileSpec) {

        );
    }

    /**
     * Strips invalid XML characters from the input string.
     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD

 * This class manages the rules defined in a robots.txt file, including user agent directives,
 * allowed/disallowed paths, crawl delays, and sitemap URLs.
 *
 * <p>The robots.txt protocol is implemented according to the standard specification,
 * supporting pattern matching for user agents, path-based access control, and crawl delay settings.</p>
 *
 * <p>Key features:</p>
 * <ul>
 *   <li>Supports multiple user-agent directives with pattern matching</li>

  <mime-type type="application/vnd.ms-wpl">
    <glob pattern="*.wpl"/>
  </mime-type>
  <mime-type type="application/vnd.ms-xpsdocument">
    <alias type="application/oxps"/>
    <_comment>Open XML Paper Specification</_comment>
    <glob pattern="*.xps"/>
    <glob pattern="*.oxps"/>
    <sub-class-of type="application/x-tika-ooxml"/>
  </mime-type>

  <mime-type type="application/vnd.msa-disk-image">

import org.codelibs.fess.crawler.entity.RobotsTxt;
import org.codelibs.fess.crawler.entity.RobotsTxt.Directive;
import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *