*   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *
 * <p>
 * The MIME type detection is based on the {@code tika-mimetypes.xml} resource, which is loaded during initialization.
 * </p>
 *
 * <p>
 * Usage:
 * </p>

    }

    /**
     * Returns the preload size for charset detection.
     * @return The preload size for charset detection.
     */
    public int getPreloadSizeForCharset() {
        return preloadSizeForCharset;
    }

    /**
     * Sets the preload size for charset detection.
     * @param preloadSizeForCharset The preload size for charset detection to set.
     */

        timeout = 420,
        channel = "experiments",
    ),
    FLAKINESS_DETECTION(
        displayName = "Performance Test Flakiness Detection",
        timeout = 600,
        defaultBaselines = "flakiness-detection-commit",
        channel = "flakiness-detection",
        extraParameters = "--checks none --rerun --cross-version-only",
    ),
    AD_HOC(
        displayName = "AdHoc Performance Test",

      matrix:
        # Override automatic language detection by changing the below list
        # Supported options are ['csharp', 'cpp', 'go', 'java', 'javascript', 'python']
        language: ['java', 'javascript']
        # Learn more...
        # https://docs.github.com/en/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#overriding-automatic-language-detection

    steps:
    - name: Checkout repository

    /**
     * Checks if automatic UTF-8 encoding detection is enabled.
     *
     * @return True if auto-detection is enabled, false otherwise
     */
    public boolean isAutodetectEncoding() {
        return autodetectEncoding;
    }

    /**
     * Sets whether automatic UTF-8 encoding detection is enabled.
     *
     * @param autodetectEncoding True to enable auto-detection, false to disable
     */

package org.codelibs.fess.crawler.helper;

import java.io.InputStream;
import java.util.Map;

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**
     * Determines the content type of the given input stream and filename.
     * @param is the input stream to analyze

 * for configuring the extraction parameters and handling the underlying complexities of content processing,
 * such as MIME type detection, extractor selection, and content length validation.
 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {

            }
            failureConditions {
                // We have test-retry to handle the crash in tests
                javaCrash = false
                // We want to see the flaky tests for flakiness detection
                supportTestRetry = (performanceTestBuildSpec.type != PerformanceTestType.FLAKINESS_DETECTION)
            }
            if (testProjects.isNotEmpty()) {
                steps {

        private static final long serialVersionUID = 1L;

        /**
         * The type detector used by this parser to auto-detect the type of a
         * document.
         */
        private final Detector detector; // always set in the constructor

        /**
         * Creates an auto-detecting parser instance using the default Tika
         * configuration.
         */

 * It also integrates with other Fess Crawler components, such as {@link ContentLengthHelper} and
 * {@link MimeTypeHelper}, to handle content length checks and MIME type detection.
 * </p>
 *
 * <p>
 * The class uses JCIFS properties to configure the SMB connection.
 * </p>
 *
 * <p>
 * Usage example:
 * </p>
 *
 * <pre>
 * {@code