* Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations
 * should also handle resource cleanup when the {@link #close()} method is called.</p>
 */
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *

 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>
 * The log level can be set to DEBUG, INFO, WARN, or ERROR, and the class provides methods to check if a specific log level is enabled.
 * </p>
 *
 * <p>

        final String clusterName = UUID.randomUUID().toString();
        runner.onBuild((number, settingsBuilder) -> {
            settingsBuilder.put("http.cors.enabled", true);
            settingsBuilder.put("discovery.type", "single-node");
        }).build(newConfigs().clusterName(clusterName).numOfNode(1));

        // wait for yellow status
        runner.ensureYellow();

 */
package org.codelibs.fess.crawler.entity;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.

import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;

/**
 * PasswordBasedExtractor is an abstract base class for extractors that can handle password-protected files.
 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:
 * <ul>

        runner = new OpenSearchRunner();
        runner.onBuild((number, settingsBuilder) -> {
            settingsBuilder.put("http.cors.enabled", true);
            settingsBuilder.put("discovery.type", "single-node");
            // settingsBuilder.putList("discovery.seed_hosts", "127.0.0.1:9301");
            // settingsBuilder.putList("cluster.initial_master_nodes", "127.0.0.1:9301");
        })

        runner = new OpenSearchRunner();
        runner.onBuild((number, settingsBuilder) -> {
            settingsBuilder.put("http.cors.enabled", true);
            settingsBuilder.put("discovery.type", "single-node");
            // settingsBuilder.putList("discovery.seed_hosts", "127.0.0.1:9301");
            // settingsBuilder.putList("cluster.initial_master_nodes", "127.0.0.1:9301");
        })

        runner = new OpenSearchRunner();
        runner.onBuild((number, settingsBuilder) -> {
            settingsBuilder.put("http.cors.enabled", true);
            settingsBuilder.put("discovery.type", "single-node");
            // settingsBuilder.putList("discovery.seed_hosts", "127.0.0.1:9301");
            // settingsBuilder.putList("cluster.initial_master_nodes", "127.0.0.1:9301");
        })

import org.codelibs.core.timer.TimeoutTarget;

/**
 * HcConnectionMonitorTarget is responsible for monitoring and managing HTTP client connections.
 * It implements the TimeoutTarget interface to handle connection expiration events.
 *
 * <p>This class uses an instance of HttpClientConnectionManager to manage the connections.
 * It closes expired connections and idle connections that have exceeded a specified timeout.
 * </p>

        return xPath.evaluateExpression(expression, contextNode);
    }

    /**
     * Use an XPath string to select a single node.
     *
     * @param contextNode The node to start searching from.
     * @param expression A valid XPath string.
     * @return The first node found that matches the XPath, or null.
     *