* hostnames or URLs to be treated as equivalent for crawling and indexing purposes.
 * It maintains a list of DuplicateHost rules and applies them to URLs.
 *
 */
public class DuplicateHostHelper {
    private static final Logger logger = LogManager.getLogger(DuplicateHostHelper.class);

    /** List of duplicate host rules for URL conversion */

    /** HTTP status code for OK */
    private static final int HTTP_STATUS_OK = 200;

    /**
     * Cache for client rules mapping client names to their corresponding URL patterns.
     * This cache improves performance by avoiding repeated parsing of client configuration rules.
     * The key is the rule string, and the value is a pair containing the client name and compiled pattern.
     */

    }

    /**
     * Gets the map of child URL extraction rules.
     *
     * @return the child URL rule map
     */
    public Map<String, String> getChildUrlRuleMap() {
        return childUrlRuleMap;
    }

    /**
     * Sets the map of child URL extraction rules.
     *
     * @param childUrlRuleMap the child URL rule map to set
     */

            ComponentUtil.getCrawlingConfigHelper().remove(sid);
            deleteCrawlData(sid);
        }
    }

    /**
     * Gets the list of available boost document rules.
     *
     * @return List of boost document rules that are currently available
     */
    protected List<BoostDocumentRule> getAvailableBoostDocumentRuleList() {

    private static final int UTF8_BOM_SIZE = 3;

    /** Flag indicating whether content should be pruned */
    public boolean prunedContent = true;

    /** Map containing URL conversion rules (regex patterns to replacement strings) */
    protected Map<String, String> convertUrlMap = new LinkedHashMap<>();

    /** Fess configuration instance */
    protected FessConfig fessConfig;

    }

    /**
     * Adds a document boost matcher rule for enhancing document relevance scores.
     *
     * @param rule the document boost matcher rule to add
     */
    public void addDocBoostMatcher(final DocBoostMatcher rule) {
        docBoostMatcherList.add(rule);
    }

    /**
     * Sets the list of crawler instances that this updater will manage.
     *

import org.dbflute.optional.OptionalEntity;

/**
 * Manages a dictionary file for stemmer overrides.
 * This class handles reading, parsing, and updating files that contain
 * stemmer override rules, where each rule maps an input word to an
 * output stem. The file format is expected to be `input => output`.
 *
 * The class provides methods for retrieving, adding, updating, and

            final Rule rule = ruleManager.getRule(responseData);
            if (rule == null) {
                throw new CrawlingAccessException("No url rule for " + url);
            }
            responseData.setRuleId(rule.getRuleId());
            final ResponseProcessor responseProcessor = rule.getResponseProcessor();

 * This class provides functionality to load, parse, and manage character mapping
 * rules that define how input characters should be transformed to output characters
 * during text analysis and search processing.
 *
 * Character mapping files contain mapping rules in the format:
 * input1,input2,... => output
 */
public class CharMappingFile extends DictionaryFile<CharMappingItem> {

        for (final UnaryOperator<String> rule : docSettingRewriteRuleList) {
            source = rule.apply(source);
        }
        return source;
    }

    /**
     * Adds a rewrite rule for document settings.
     *
     * @param rule the rewrite rule to apply to document settings
     */
    public void addDocumentSettingRewriteRule(final UnaryOperator<String> rule) {
        docSettingRewriteRuleList.add(rule);