import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Utility class for XML-related operations.
 *
 * This class provides methods to escape special characters in XML strings,
 * strip invalid XML characters, and parse XML content into a map of data.

import org.codelibs.fess.crawler.exception.SitemapsException;
import org.xml.sax.Attributes;
import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.

 *
 * <p>Example usage:</p>
 *
 * <pre>{@code
 * UrlConvertHelper helper = new UrlConvertHelper();
 * helper.add("old-domain.com", "new-domain.com");
 * String convertedUrl = helper.convert("http://old-domain.com/path");
 * // convertedUrl will be "http://new-domain.com/path"
 * }</pre>
 */
/**
 * This class is a helper for URL conversion.
 */
public class UrlConvertHelper {

    /**

            final ExtractData data = new ExtractData(content != null ? content : StringUtil.EMPTY);
            final Enumeration<Header> headers = message.getAllHeaders();
            while (headers.hasMoreElements()) {
                final Header header = headers.nextElement();
                data.putValue(header.getName(), header.getValue());
            }
            putValue(data, "Content-ID", message.getContentID());

import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.helper.RobotsTxtHelper;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

import jakarta.annotation.Resource;

/**

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

import org.codelibs.fess.crawler.log.LogType;

/**
 * Interface for logging helper.
 * Provides a method to log messages with a specified log type and additional objects.
 */
public interface LogHelper {

    /**

import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.EncodingHelper;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.helper.RobotsTxtHelper;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.helper.UrlConvertHelper;
import org.codelibs.fess.crawler.helper.impl.LogHelperImpl;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MimeTypeException;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * MimeTypeHelperImpl is a helper class that detects the MIME type of a given input stream or filename.
 * It uses the Apache Tika library to detect the MIME type.
 *
 * <p>
 * This class provides methods to:
 * </p>

import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import io.minio.BucketExistsArgs;
import io.minio.GetObjectArgs;
import io.minio.GetObjectTagsArgs;
import io.minio.ListObjectsArgs;
import io.minio.MinioClient;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.EncodingHelper;
import org.codelibs.fess.crawler.helper.UrlConvertHelper;
import org.codelibs.fess.crawler.util.CharUtil;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;