timothy <******@****.***> 1748612313 +0900

Sebastián Ramírez <******@****.***> 1731896744 +0100

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
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *

        } catch (final MessagingException e) {
            throw new ExtractException(e);
        }
    }

    /**
     * Puts a value into the extract data with appropriate type conversion.
     *
     * @param data the extract data to store the value in
     * @param key the key for the value
     * @param value the value to store
     */

    /**
     * Sets the MIME type of the content to extract.
     *
     * @param mimeType the MIME type to set
     * @return this builder instance for method chaining
     */
    public ExtractorBuilder mimeType(final String mimeType) {
        this.mimeType = mimeType;
        return this;
    }

    /**
     * Sets the filename of the content to extract.
     *
     * @param filename the filename to set

     * @return the resource group SIDs array
     */
    public SID[] getResourceGroupSids() {
        return this.resourceGroupSids;
    }

    /**
     * Returns an array of extra SIDs associated with the user.
     * @return the extra SIDs array
     */
    public SID[] getExtraSids() {
        return this.extraSids;
    }

    /**
     * Returns the user account control flags.

 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */

            ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *
     * @param document The document to parse, represented as a map of field names to values.
     * @param fields The fields to extract from the document.
     * @param tagFieldNames The names of the fields that contain tags.

     *
     * @return the logger instance
     */
    Logger getLogger();

    /**
     * Extracts the host name from a URL string.
     * Removes protocol and path components to return just the hostname.
     *
     * @param u the URL string to extract host from
     * @return the host name, or empty string if URL is blank, or unknown hostname if parsing fails
     */

    hashed_password = user_dict["hashed_password"],
)
```

/// info | Información

Para una explicación más completa de `**user_dict` revisa en [la documentación para **Extra Models**](../extra-models.md#about-user_indict){.internal-link target=_blank}.

///

## Devolver el token

El response del endpoint `token` debe ser un objeto JSON.