/**
     * The exclude filtering pattern.
     */
    protected String excludeFilteringPattern;

    /**
     * The cached include set.
     */
    protected Set<String> cachedIncludeSet = new LinkedHashSet<>();

    /**
     * The cached exclude set.
     */
    protected Set<String> cachedExcludeSet = new LinkedHashSet<>();

    /**
     * The session ID.
     */

    /** The property name for maximum cached content size. */
    public static final String MAX_CACHED_CONTENT_SIZE = "maxCachedContentSize";

    /** The crawler container. */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /** The initialization parameter map. */
    protected Map<String, Object> initParamMap;

    /** The maximum cached content size in bytes. Default is 1MB. */

 *
 * <p>This factory is typically initialized through dependency injection and can be
 * configured with initialization parameters that are passed to all registered clients.</p>
 *
 * <p>Features:</p>
 * <ul>
 *   <li>Pattern-based client mapping</li>
 *   <li>Ordered client registration</li>
 *   <li>Bulk client registration</li>
 *   <li>Automatic client initialization</li>
 *   <li>Resource cleanup management</li>
 * </ul>
 *
 */

 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <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 {@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>
 *   <li>{@code POST_PROCESSING} - Represents the post-processing state.</li>

- **Fault Tolerance**: Built-in retry mechanisms and error handling
- **Flexible Configuration**: XML-based dependency injection with LastaFlute DI
- **Extensible Architecture**: Plugin system for custom extractors, transformers, and clients
- **Rate Limiting**: Politeness policies and interval controllers
- **URL Filtering**: Regex-based inclusion/exclusion patterns
- **Data Persistence**: Multiple backend options including OpenSearch integration

 */
package org.codelibs.fess.suggest.normalizer;

/**
 * An interface for normalizing text.
 * Implementations of this interface should provide a method to normalize
 * a given text based on the specified field and optional language parameters.
 */
public interface Normalizer {
    /**
     * Normalizes the given text.
     * @param text The text to normalize
     * @param field The field name

 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents
 * or a fixed number. It also allows filtering documents based on their size, using the {@code limitOfDocumentSize}
 * parameter.
 * </p>
 *
 * <p>

 *   <li>Appending alphanumeric characters (0-9, A-Z, a-z) to the buffer.</li>
 *   <li>Appending symbol characters (!-/, :-@, [-`, {-~) to the buffer.</li>
 *   <li>Optionally removing duplicate terms based on a flag.</li>
 *   <li>Limiting the maximum size of alphanumeric and symbol terms.</li>
 * </ul>
 *
 * <p>The {@link TextNormalizeContext} class provides a fluent API to configure the text

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