import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.crawler.Constants;

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.transformer.impl;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.exception.InterruptedRuntimeException;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;

 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.
 * </p>
 *
 * <p>
 * The handler relies on environment variables for configuration:
 * </p>
 * <ul>
 *   <li>{@code STORAGE_ENDPOINT}: The endpoint URL of the MinIO service.</li>
 *   <li>{@code STORAGE_ACCESS_KEY}: The access key for authentication.</li>

        accessResult1.setParentUrl("http://www.parent.com/");
        accessResult1.setRuleId("htmlRule");
        accessResult1.setSessionId("id1");
        accessResult1.setStatus(200);
        accessResult1.setUrl("http://www.id1.com/");

        dataService.store(accessResult1);

        final AccessResult accessResult2 = dataService.getAccessResult("id1", "http://www.id1.com/");
        assertNotNull(accessResult2);

import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**

 * during the conversion process.</p>
 *
 * <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.
 */

 *   <li>org.codelibs.fess.crawler.entity.AccessResultData</li>
 *   <li>org.codelibs.core.lang.StringUtil</li>
 * </ul>
 *
 * @see org.codelibs.fess.crawler.Constants
 * @see org.codelibs.fess.crawler.exception.CrawlerSystemException
 * @see org.codelibs.fess.crawler.entity.AccessResultData
 * @see org.codelibs.core.lang.StringUtil
 */
public final class XmlUtil {

        // Set patterns
        conditionalRule.setUrlPattern("https?://.*\\.example\\.com/.*");
        conditionalRule.setMimeTypePattern("text/.*");

        // Test matching
        ResponseData responseData1 = new ResponseData();
        responseData1.setUrl("http://www.example.com/page");
        responseData1.setMimeType("text/html");
        assertTrue(conditionalRule.match(responseData1));

import org.dbflute.utflute.core.PlainTestCase;

public class HandlerTest extends PlainTestCase {
    @Override
    protected void setUp() throws Exception {
        super.setUp();
        new StandardCrawlerContainer();
    }

    public void test_protocol() throws Exception {
        URL url = new URL("storage:/home/foo");
        assertEquals("storage", url.getProtocol());
    }