* governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.request;

/**
 * The Response interface serves as a marker interface for all response types
 * in the suggestion system. Implementations of this interface are used to
 * encapsulate the results of various operations and queries within the system.
 *

 * </pre>
 */
public class MimeTypeHelperImpl implements MimeTypeHelper {
    /** The resource name for the MIME types configuration file. */
    protected static final String MIME_TYPES_RESOURCE_NAME = "/org/codelibs/fess/crawler/mime/tika-mimetypes.xml";

    /** The MimeTypes instance for detecting MIME types. */
    protected MimeTypes mimeTypes;

    /** Whether to use the filename for MIME type detection. */

import java.util.Map;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * Helper class for managing content length limits based on MIME types.
 * It allows setting default and MIME type-specific maximum content lengths.
 * The class provides methods to add, retrieve, and manage these limits.
 */
public class ContentLengthHelper {
    /**

     * @return The result data body.
     */
    protected String getResultDataBody(final String name, final String value) {
        // TODO: Support other XML footer types
        // TODO: Support other field types and trimming options
        return "<field name=\"" + XmlUtil.escapeXml(name) + "\">" + trimSpace(XmlUtil.escapeXml(value != null ? value : "")) + "</field>\n";
    }

    /**
     * Returns the result data body for multiple values.

 * either express or implied. See the License for the specific language
 * 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 {

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

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>
 * Constants:
 * </p>
 * <ul>
 *   <li>{@code PRE_PROCESSING} - Represents the pre-processing state.</li>

 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *

        }

        // Verify results
        assertTrue(exceptions.isEmpty());
        assertEquals(threadCount * destroysPerThread, destroyCount.get());
    }

    /**
     * Test with different component types
     */
    public void test_differentComponentTypes() throws Exception {
        // Test with String component
        container.singleton("stringComponent", "TestString");

 * This class provides methods for logging various events during the crawling process.
 * It uses Log4j2 for logging.
 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>

 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>