* Constructs a new PathPattern from the given robots.txt path pattern.
         * @param pattern the path pattern string from robots.txt (may contain * and $)
         */
        public PathPattern(final String pattern) {
            this.pattern = pattern;
            this.regexPattern = compilePattern(pattern);
            this.priorityLength = calculatePriorityLength(pattern);
        }

        /**

        }
        if (client == null) {
            throw new CrawlerSystemException("CrawlerClient instance is null. Cannot register null client.");
        }
        clientMap.put(Pattern.compile(regex), client);
    }

    /**
     * Adds a client with a regular expression pattern at a specific position.
     * @param regex The regular expression to match URLs.
     * @param client The CrawlerClient instance.

    /** Format identifier for PDF date parsing */
    private static final String PDF_DATE = "pdf_date";

    /** Regular expression pattern for matching email addresses */
    private static final Pattern EMAIL_ADDRESS_PATTERN =
            Pattern.compile("[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,6}", Pattern.CASE_INSENSITIVE);

    /**
     * Cache for storing resource file modification timestamps to enable cache busting.

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.commonmark.ext.front.matter.YamlFrontMatterExtension;
import org.commonmark.ext.front.matter.YamlFrontMatterVisitor;
import org.commonmark.node.AbstractVisitor;
import org.commonmark.node.Heading;
import org.commonmark.node.Link;
import org.commonmark.node.Node;

                    logger.debug("Using exclude pattern: {}", pattern);
                }
            }
            if (paramMap.get(URL_EXCLUDE_PATTERN) instanceof final Pattern pattern) {
                if (pattern.matcher(url).matches()) {
                    if (logger.isDebugEnabled()) {
                        logger.debug("Skipping URL {} due to exclude pattern: {}", url, pattern);
                    }
                    return false;

            return false;
        }

        Pattern pattern = (Pattern) propMap.get(USER_CODE_PATTERN);
        if (pattern == null) {
            pattern = Pattern.compile(getUserCodePattern());
            propMap.put(USER_CODE_PATTERN, pattern);
        }
        return pattern.matcher(userCode).matches();
    }

    String getQueryCollapseInnerHitsSorts();

            return Constants.TRUE;
        }

        for (final Pattern pattern : includedDocUrlPatterns) {
            if (pattern.matcher(input).matches()) {
                return Constants.TRUE;
            }
        }

        for (final Pattern pattern : excludedDocUrlPatterns) {
            if (pattern.matcher(input).matches()) {
                return Constants.FALSE;
            }
        }

            return Constants.TRUE;
        }

        for (final Pattern pattern : includedDocPathPatterns) {
            if (pattern.matcher(input).matches()) {
                return Constants.TRUE;
            }
        }

        for (final Pattern pattern : excludedDocPathPatterns) {
            if (pattern.matcher(input).matches()) {
                return Constants.FALSE;
            }
        }

     *
     * @param cmdList the command list to add properties to
     * @param regex the regular expression pattern to match property names
     */
    protected void addFessCustomSystemProperties(final List<String> cmdList, final String regex) {
        if (StringUtil.isNotBlank(regex)) {
            final Pattern pattern = Pattern.compile(regex);

     * - Second: List of regex pattern matches (Pattern -> content template)
     */
    protected Map<String, Pair<Map<String, String>, List<Pair<Pattern, String>>>> relatedContentMap = Collections.emptyMap();

    /**
     * Prefix used to identify regex patterns in related content terms.
     * When a term starts with this prefix, it is treated as a regular expression
     * pattern rather than an exact match term.
     */