/**
     * 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 null;
    }

    /**
     * Extracts URLs from HTML tag attributes using XPath.
     *
     * @param url the base URL for resolving relative URLs
     * @param document the document to extract URLs from
     * @param xpath the XPath expression to select elements
     * @param attr the attribute name to extract URLs from
     * @param encoding the character encoding to use

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
     */

            }

            return extractData;
        } catch (final OfficeException e) {
            throw new ExtractException("Could not extract a content.", e);
        } finally {
            FileUtil.deleteInBackground(inputFile);
            FileUtil.deleteInBackground(outputFile);
        }
    }

    /**

            } catch (final IOException e) {
                logger.error("Failed to close httpClient.", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>

        private StatObjectResponse statObject;

        /**
         * Constructs a new StorageURLConnection for the specified URL.
         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The storage URL to connect to
         */
        protected StorageURLConnection(final URL url) {
            super(url);

                logger.debug("Logged in {}", originalLoginUrl);
            }
        });

    }

    /**
     * Parses the token page and extracts token information.
     * @param tokenPattern The regex pattern to extract the token.
     * @param responseParams The list to store response parameters.
     * @param entity The HTTP entity containing the token page content.
     */

            }
        }
        return keywords.toArray(new String[keywords.size()]);
    }

    /**
     * Extracts keywords from the given query string based on the specified fields.
     *
     * @param q the query string to parse and extract keywords from
     * @param fields the fields to consider when extracting keywords
     * @return a list of unique keywords extracted from the query string