* to provide DNS resolution with support for Internationalized Domain Names (IDN).
 * It converts Unicode domain names to ASCII Compatible Encoding (ACE) using the
 * {@link java.net.IDN} class.
 *
 * <p>This class allows setting a custom flag for the IDN conversion and a custom
 * encoding for URL decoding.</p>
 *
 * <p>Example usage:</p>
 * <pre>
 * {@code

public class RequestData {
    /**
     * HTTP methods supported for crawling requests.
     */
    public enum Method {
        /** HTTP GET method. */
        GET,
        /** HTTP POST method. */
        POST,
        /** HTTP HEAD method. */
        HEAD;
    }

    /** The HTTP method for this request. */
    private Method method;

    /** The URL for this request. */
    private String url;

 *   <li>Password-protected PDF support</li>
 *   <li>Configurable timeout for extraction process</li>
 * </ul>
 *
 * @author shinsuke
 */
public class PdfExtractor extends PasswordBasedExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PdfExtractor.class);

    /** Timeout for PDF extraction in milliseconds (default: 30 seconds). */

    /**
     * Log level constant for debug messages.
     */
    public static final String DEBUG = "DEBUG";

    /**
     * Log level constant for info messages.
     */
    public static final String INFO = "INFO";

    /**
     * Log level constant for warning messages.
     */
    public static final String WARN = "WARN";

    /**
     * Log level constant for error messages.
     */

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.opensearch.extension.analysis;

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.

        assertEquals(5, response.getTotal());

        for (int i = 0; i < 5; i++) {
            assertEquals(2, response.getNum());
            boolean find = false;
            final String checkStr = "クエリー" + i;
            for (int j = 0; j < 1000; j++) {
                if (response.getWords().contains(checkStr)) {
                    find = true;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.util;

/**
 * Configuration class for OpenSearch crawler settings.
 * This class provides configuration for index names, shards, and replicas
 * for the queue, data, and filter indices used by the crawler.
 */

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * The class CrawlerSystemException is a runtime exception that is thrown when a system error occurs during crawling.
 * It extends the RuntimeException class and provides constructors for creating exceptions with a message, a cause, or both.

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client;

import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;

/**
 * A wrapper class for CrawlerClientFactory that delegates operations to an underlying factory instance.