* governing permissions and limitations under the License.
 */
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

import java.io.Closeable;
import java.util.Map;

/**
 * Interface for reading documents and extracting their contents into a map.
 * Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations

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,
 * and obtain the associated response processor.
 */
public interface Rule extends Serializable {

    /**

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>

 * in the suggestion system. Implementations of this interface are used to
 * encapsulate the results of various operations and queries within the system.
 *
 * <p>Classes implementing this interface should provide specific details and
 * data relevant to the type of response they represent.</p>
 */
public interface Response {

import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *

import io.minio.errors.XmlParserException;

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.

import java.net.URLDecoder;
import java.net.UnknownHostException;

import org.apache.http.conn.DnsResolver;

/**
 * The {@code IdnDnsResolver} class implements the {@code DnsResolver} interface
 * to provide DNS resolution with support for Internationalized Domain Names (IDN).
 * It converts Unicode domain names to ASCII Compatible Encoding (ACE) using the
 * {@link java.net.IDN} class.
 *

import org.opensearch.transport.client.Client;

/**
 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * 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

 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *
 * <p>
 * The {@link TikaDetectParser} inner class extends {@link CompositeParser} to provide auto-detection of the MIME type
 * of the document. It also handles zip bomb prevention and embedded document extraction.
 * </p>
 *
 * <p>