import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**

- **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

import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.

 */
package org.codelibs.fess.crawler.client.ftp;

import java.util.ArrayList;
import java.util.List;

/**
 * Holds a list of FtpAuthentication objects and provides methods to add and retrieve them based on a given path.
 * This class is designed to manage FTP authentication details for different paths.
 */
public class FtpAuthenticationHolder {
    List<FtpAuthentication> authenticationList = new ArrayList<>();

    /**

     *
     * @throws IOException if an I/O error occurs during initialization.
     */
    void init() throws IOException;

    /**
     * Converts the given text into a list of readings based on the specified field and languages.
     *
     * @param text the text to be converted.
     * @param field the field to be used for conversion.
     * @param langs the languages to be used for conversion.

import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

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}