* based on a map of target strings and their corresponding replacements. It allows
 * adding new conversion rules, setting the entire conversion map, and converting
 * URLs using these rules.</p>
 *
 * <p>The conversion is performed by iterating through the conversion map and applying
 * each replacement rule sequentially. The order of the rules in the map is preserved
 * during the conversion process.</p>

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout

    protected boolean useFilenameOnOctetStream = true;

    /**
     * Creates a new MimeTypeHelperImpl instance.
     * Initializes the MimeTypes instance using the default configuration.
     * @throws CrawlerSystemException if the MIME types configuration cannot be loaded
     */
    public MimeTypeHelperImpl() {
        try {

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

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

    private static final Logger logger = LogManager.getLogger(ApiExtractor.class);

    /** The URL of the API endpoint. */

 *
 * <p>Default settings and array settings can be customized using:</p>
 * <ul>
 *   <li>{@link #defaultSettings()}</li>
 *   <li>{@link #defaultArraySettings()}</li>
 * </ul>
 *
 * <p>Index settings can be loaded from a JSON file using:</p>
 * <ul>
 *   <li>{@link #loadIndexSettings()}</li>
 * </ul>
 *
 * <p>A builder for SuggestSettings can be obtained using:</p>
 * <ul>
 *   <li>{@link #builder()}</li>
 * </ul>
 *

 *   <li>Managing singleton instances with lifecycle hooks</li>
 *   <li>Creating prototype instances on demand</li>
 *   <li>Dependency injection using {@code @Resource} annotation</li>
 *   <li>Lifecycle management using {@code @PostConstruct} and {@code @PreDestroy} annotations</li>
 * </ul>
 *
 * <p>Components can be registered in two ways:
 * <ul>

- **CrawlerContext**: Execution context and configuration
- **CrawlerThread**: Individual crawler thread implementation

#### Client Architecture
- **HcHttpClient**: HTTP/HTTPS client using Apache HttpComponents
- **FileSystemClient**: File system access
- **FtpClient**: FTP protocol support
- **SmbClient**: SMB/CIFS network shares
- **StorageClient**: Cloud storage integration

        final ReadingConverterChain chain = new ReadingConverterChain();
        chain.addConverter(new KatakanaToAlphabetConverter());
        return chain;
    }

    /**
     * Creates a default normalizer using the provided client and suggest settings.
     * The normalizer chain includes an AnalyzerNormalizer.
     *
     * @param client the client to be used for creating the normalizer

            });
            return extractData;
        } finally {
            xpathAPI.remove();
        }
    }

    /**
     * Extracts strings from a document using the specified XPath expression.
     *
     * @param document the DOM document to extract strings from
     * @param path the XPath expression to evaluate
     * @return an array of strings extracted from the document

                        }
                    }
                }
                throw new ExtractException("Failed to extract the content using available extractors.");
            }

            @Override
            public int getWeight() {
                return extractors[0].getWeight();
            }
        };
    }

    /**