/**
 * Standard transformer implementation for the Fess search engine.
 * This transformer handles document transformation and content extraction using
 * the standard Fess file transformation process with support for various content types.
 *
 * <p>It extends AbstractFessFileTransformer to provide file-specific transformation
 * capabilities while using the appropriate extractor for each document type.</p>
 */

    }

    /**
     * Returns the transformation.
     *
     * @return the transformation
     */
    public String getTransformation() {
        return transformation;
    }

    /**
     * Sets the transformation.
     *
     * @param transformation
     *            the transformation
     */
    public void setTransformation(final String transformation) {

import jakarta.annotation.PostConstruct;

/**
 * File transformer implementation for the Fess search engine.
 * This transformer handles file-based document transformation and content extraction
 * using the Fess file transformation process with support for various file types.
 *
 * <p>It extends AbstractFessFileTransformer to provide specialized file processing

/**
 * Implementation of IndexUpdateCallback for handling document indexing operations.
 * This class manages the process of updating the search index with documents from
 * data stores, including bulk operations, document transformation, and error handling.
 */
public class IndexUpdateCallbackImpl implements IndexUpdateCallback {
    private static final Logger logger = LogManager.getLogger(IndexUpdateCallbackImpl.class);

    /**

    //
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(GoAction.class);

    /** Helper for URL path mapping and transformation. */
    @Resource
    protected PathMappingHelper pathMappingHelper;

    // ===================================================================================

/**
 * Interface for transforming and processing crawled documents in Fess.
 * Provides utility methods for URL processing, site extraction, data mapping,
 * and field configuration handling during the document transformation process.
 */
public interface FessTransformer {

    /**
     * Synchronized LRU cache for storing parent URL encodings.
     * Maps session+parent URL keys to their corresponding character encodings.
     */

elasticdump \
  --input=http://old-es-server:9200/my-index \
  --output=documents.json \
  --type=data
```

**Step 2: Convert to Fess Format**

Transform documents to include Fess required fields. Example transformation script:

```python
import json

with open('documents.json', 'r') as infile, \
     open('fess-documents.json', 'w') as outfile:
    for line in infile:
        doc = json.loads(line)

        }
    }

    /**
     * Processes a crawling request for a specific URL.
     * Executes the full crawling pipeline including client execution, rule processing,
     * transformation, and data extraction.
     *
     * @param crawlingConfig the crawling configuration to use
     * @param crawlingInfoId the crawling session ID
     * @param url the URL to process

    return new TransformedEntriesNavigableMap<>(fromMap, transformer);
  }

  /**
   * A transformation of the value of a key-value pair, using both key and value as inputs. To apply
   * the transformation to a map, use {@link Maps#transformEntries(Map, EntryTransformer)}.
   *
   * @param <K> the key type of the input and output entries

 * and components from the Fess Crawler framework, such as {@link CrawlerContainer},
 * {@link UrlConvertHelper}, and {@link EncodingHelper}.
 * </p>
 * <p>
 * The transformation process involves:
 * </p>
 * <ol>
 *   <li>Determining the character set encoding of the HTML content.</li>
 *   <li>Storing the HTML content as data in the {@link ResultData}.</li>