* It extends the RuntimeException class and provides constructors for creating exceptions with a message, a cause, or both.
 * It also provides a protected constructor that allows to specify whether or not suppression is enabled or stack trace is writable.
 */
public class CrawlerSystemException extends RuntimeException {

    private static final long serialVersionUID = 1L;

    /**

 * </p>
 * <p>
 * The class supports various XPath result types, including BOOLEAN, NUMBER, STRING, NODESET, and NODE.
 * It also provides options to trim whitespace from extracted values and to specify the character encoding for the output.
 * </p>
 * <p>
 * The {@link #getData(AccessResultData)} method allows retrieving the transformed data as a String (XML content),
 * a Map, or an instance of a specified class.
 * </p>

 * FileTransformer stores the content of a crawled resource as a file on the file system.
 * It extends HtmlTransformer and provides functionality to:
 * </p>
 * <ul>
 *     <li>Specify a base directory for storing files.</li>
 *     <li>Generate file paths from URLs, replacing special characters.</li>
 *     <li>Handle duplicated file paths by appending a counter.</li>
 *     <li>Store the file path in the result data.</li>

 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.util;

/**
 * Utility class for character-related operations.
 */
public final class CharUtil {

 * 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.
 *
 * <p>
 * The class is final and cannot be instantiated.
 * </p>
 *
 * <h2>Methods:</h2>
 * <ul>
 *   <li>{@link #escapeXml(String)}: Escapes special characters in an XML string.</li>

 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper.impl;

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;

        assertNotNull(urlFilter);
    }

    /**
     * Test special characters in URL patterns
     */
    public void test_specialCharactersInPatterns() {
        String sessionId = "test-session-018";
        urlFilter.init(sessionId);

        // Test patterns with special regex characters
        urlFilter.addInclude("https://example\\.com/\\?.*");

    protected long defaultMaxLength = 10L * 1024L * 1024L;

    /** Map to store maximum content lengths for specific MIME types */
    protected Map<String, Long> maxLengthMap = new HashMap<>();

    /**
     * Adds a maximum content length for a specific MIME type.
     * @param mimeType The MIME type for which to set the maximum length
     * @param maxLength The maximum content length in bytes

 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.analysis;

import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;

 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.rule.impl;

import org.codelibs.fess.crawler.container.CrawlerContainer;