<mime-type type="application/xenc+xml">
    <glob pattern="*.xenc"/>
  </mime-type>

  <mime-type type="application/xhtml+xml">
    <!-- The magic priority for xhtml+xml needs to be lower than that of -->
    <!--  files that contain HTML within them, e.g. mime emails -->
    <magic priority="40">
      <match value="&lt;html xmlns=" type="string" offset="0:8192"/>
    </magic>

        xPath = createXPath(f -> {});
    }

    /**
     * Creates an instance of {@link XPath} using the provided {@link Consumer} to configure the {@link XPathFactory}.
     *
     * @param builder a {@link Consumer} that accepts an {@link XPathFactory} and configures it.
     * @return a configured instance of {@link XPath}.
     * @throws CrawlerSystemException if an error occurs while creating the {@link XPath} instance.
     */

import java.io.Serializable;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,

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>

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

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;

/**
 * A fault-tolerant wrapper for CrawlerClient that implements retry logic for failed requests.
 * This client will attempt to execute requests multiple times before giving up, with configurable
 * retry counts and intervals between attempts.
 *

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

/**
 * MimeTypeException is a custom exception class that extends CrawlerSystemException.
 * It is used to indicate exceptions related to MIME type handling during the crawling process.
 * This exception can be thrown with a message, a cause, or both.
 */

        assertNotNull(tokens);
        assertEquals(2, tokens.size());
        assertEquals("test", tokens.get(0).getTerm());
        assertEquals("text", tokens.get(1).getTerm());
        // Check that readings are added
        assertEquals("TEST", ((TestAnalyzeToken) tokens.get(0)).getReading());
        assertEquals("TEXT", ((TestAnalyzeToken) tokens.get(1)).getReading());
    }

    @Test

 * It keeps track of any failures that occur during the operation.
 */
public class SuggestWriterResult {
    /**
     * Constructs a new {@link SuggestWriterResult}.
     */
    public SuggestWriterResult() {
        // nothing
    }

    /**
     * A list of Throwables representing failures that occurred during the operation.
     */

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

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */