*/
package org.codelibs.fess.suggest.constants;

/**
 * This class contains constants for field names used in the Fess Suggest system.
 * These constants represent various field names that are used throughout the application
 * to ensure consistency and avoid hardcoding strings.
 *
 * <ul>
 * <li>{@link #ID} - The unique identifier field.</li>
 * <li>{@link #TEXT} - The text content field.</li>

 * It also provides methods to add custom features and properties to the {@link DOMParser}.
 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**

    protected RuleManager ruleManager;

    /**
     * Controller for managing crawling intervals and delays.
     */
    protected IntervalController intervalController;

    /**
     * Set of robots.txt URLs that have been processed.
     */
    protected Set<String> robotsTxtUrlSet = new LruHashSet<>(10000);

    /**
     * Thread-local storage for sitemaps.
     */

import org.codelibs.core.lang.MethodUtil;

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

/**
 * A container implementation that manages the lifecycle and dependency injection of components
 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:

[![Maven Central](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-suggest/badge.svg)](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-suggest)

A powerful Java library that provides intelligent search suggestion functionality built on top of OpenSearch/Elasticsearch. It offers auto-completion, query suggestions, and popular word analytics for search applications.

## Key Features

import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

import jakarta.annotation.Resource;

/**
 * The {@code CrawlerThread} class represents a thread that executes the crawling process.
 * It is responsible for fetching URLs from the queue, accessing the content,
 * processing the response, and extracting child URLs.
 *
 * <p>

/**
 * Test class for CrawlerStatus enum.
 * Tests all enum functionality including values, valueOf, ordinal, and serialization.
 */
public class CrawlerStatusTest extends PlainTestCase {

    /**
     * Test that all expected enum values exist
     */
    public void test_enumValues() {
        CrawlerStatus[] values = CrawlerStatus.values();

        assertNotNull(values);
        assertEquals(3, values.length);

import org.codelibs.fess.crawler.util.XmlUtil;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.

        final String value = params.get(key);
        if (value == null) {
            return key;
        }
        return value;
    }

    /**
     * Thread to monitor and terminate processes that exceed the timeout.
     */
    protected static class MonitorThread extends Thread {
        private final Process process;

        private final long timeout;

        private boolean finished = false;

    @Override
    public void delete(final String sessionId) {
        deleteBySessionId(sessionId);
    }

    /**
     * Offers multiple URL queue entries for the specified session.
     * Only URLs that don't already exist will be added.
     *
     * @param sessionId The session ID.
     * @param urlQueueList The list of URL queue entries to offer.
     */
    @Override