* 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
     */

                        } catch (final Exception e) {
                            failedEntries++;
                            if (logger.isDebugEnabled()) {
                                logger.debug("Failed to extract content from archive entry: {}", filename, e);
                            }
                        }
                    }
                }
            }
        } catch (final MaxLengthExceededException e) {

            return new ExtractData(excelExtractor.getText());
        } catch (final IOException e) {
            throw new ExtractException("Failed to extract text from Excel document.", e);
        }
    }

            return new ExtractData(wordExtractor.getText());
        } catch (final IOException e) {
            throw new ExtractException("Failed to extract text from Word document.", e);
        }
    }

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.

                        } catch (final Exception e) {
                            failedEntries++;
                            if (logger.isDebugEnabled()) {
                                logger.debug("Failed to extract content from archive entry: {}", filename, e);
                            }
                        }
                    }
                }
            }
        } catch (final MaxLengthExceededException e) {

        if (in == null) {
            throw new CrawlerSystemException("Microsoft Visio input stream is null. Cannot extract text from null input.");
        }
        try {
            @SuppressWarnings("resource")
            final VisioTextExtractor visioTextExtractor = new VisioTextExtractor(in);
            return new ExtractData(visioTextExtractor.getText());
        } catch (final IOException e) {

# Returns:
#   None
function cp_normalized_srcjar() {
  src_jar="$1"
  dest_jar="$2"
  tmp_dir=$(mktemp -d)
  cp "${src_jar}" "${tmp_dir}/orig.jar"
  pushd "${tmp_dir}"
  # Extract any src/ files
  jar -xf "${tmp_dir}/orig.jar" src/
  # Extract any org/ files under src/main/java
  (mkdir -p src/main/java && cd src/main/java && jar -xf "${tmp_dir}/orig.jar" org/)
  # Repackage src/
  jar -cMf "${tmp_dir}/new.jar" src
  popd

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The GCS URL to connect to
         */
        protected GcsURLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The S3 URL to connect to
         */
        protected S3URLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;