// TIKA-216: Zip bomb prevention
                final SecureContentHandler sch = new SecureContentHandler(handler, tis);

                sch.setMaximumCompressionRatio(maxCompressionRatio);
                sch.setOutputThreshold(maxUncompressionSize);

                //pass self to handle embedded documents if
                //the caller hasn't specified one.

            disableExternalResources(parser);
            parser.parse(in, handler);
        } catch (final Exception e) {
            throw new SitemapsException("Could not parse XML Sitemaps Index.", e);
        }
        return handler.getSitemapSet();
    }

    /**
     * SAX handler for parsing XML sitemap indexes.
     */

 *
 * <p>
 * This class provides methods to:
 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *

)|)$/;function Z(){return!0}function $(){return!1}function _(){try{return l.activeElement}catch(a){}}n.event={global:{},add:function(a,b,c,d,e){var f,g,h,i,j,k,l,m,o,p,q,r=L.get(a);if(r){c.handler&&(f=c,c=f.handler,e=f.selector),c.guid||(c.guid=n.guid++),(i=r.events)||(i=r.events={}),(g=r.handle)||(g=r.handle=function(b){return typeof n!==U&&n.event.triggered!==b.type?n.event.dispatch.apply(a,arguments):void 0}),b=(b||"").match(E)||[""],j=b.length;while(j--)h=Y.exec(b[j])||[],o=q=h[1],p=(h[2]||"...

     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**
     * The priority of this URL relative to other URLs on your site. Valid

import jakarta.annotation.PostConstruct;
import jakarta.annotation.Resource;

/**
 * A factory class for managing and creating crawler clients based on URL patterns.
 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns

<tbody>
<tr>
<td align="left" style="padding:0;margin:0;line-height:1px;font-size:1px;">

 * It extends HtmlTransformer and provides functionality to:
 * </p>
 * <ul>
 *     <li>Specify a base directory for storing files.</li>
 *     <li>Generate file paths from URLs, replacing special characters.</li>
 *     <li>Handle duplicated file paths by appending a counter.</li>
 *     <li>Store the file path in the result data.</li>
 *     <li>Retrieve the stored file as a File object.</li>
 * </ul>
 *
 * <p>

 * retry counts and intervals between attempts.
 *
 * <p>The client supports a RequestListener interface to monitor the request lifecycle and handle
 * exceptions during retries.</p>
 *
 * <p>Key features:</p>
 * <ul>
 *   <li>Configurable maximum retry attempts</li>
 *   <li>Adjustable interval between retries</li>
 *   <li>Exception tracking and aggregation</li>

 *   <li>Handle timeouts during SMB operations.</li>
 * </ul>
 *
 * <p>
 * The client uses a {@link SmbAuthenticationHolder} to manage SMB authentication credentials.
 * It also integrates with other Fess Crawler components, such as {@link ContentLengthHelper} and
 * {@link MimeTypeHelper}, to handle content length checks and MIME type detection.
 * </p>
 *
 * <p>