crawler.document.append.filename=false
# Maximum size of alphanumeric terms in documents.
crawler.document.max.alphanum.term.size=20
# Maximum size of symbol terms in documents.
crawler.document.max.symbol.term.size=10
# Whether to remove duplicate terms in documents.
crawler.document.duplicate.term.removed=false
# Unicode space characters for document parsing.

    public void test_execute_success() {
        String result = updateLabelJob.execute();
        assertNotNull(result);
        assertTrue(result.contains("3 docs")); // 3 documents processed
        assertFalse(result.contains("exception"));
    }

    // Test execute() method with query builder
    public void test_execute_withQueryBuilder() {

        }
    }

    /**
     * Checks if a document exists in the OpenSearch index for the given session ID and URL.
     *
     * @param sessionId The session ID of the document.
     * @param url The URL of the document.
     * @return true if the document exists, false otherwise.
     * @throws OpenSearchAccessException if the existence check fails.
     */

- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files

import jakarta.validation.constraints.Size;

/**
 * Form class for editing boost document configurations in the admin interface.
 * This form extends CreateForm to include fields necessary for updating existing boost document entries,
 * including tracking information for optimistic locking and audit trails.
 * Boost documents are used to increase the relevance score of specific documents in search results.
 *
 */
public class EditForm extends CreateForm {

            final CountDownLatch latch = new CountDownLatch(1);

            logger.info("Parsing words from indexed documents.");
            suggestHelper.indexFromDocuments(ret -> {
                logger.info("Success indexing from documents.");
                latch.countDown();
            }, t -> {
                logger.error("Failed to update suggest index.", t);

  /**
   * As described in <a href="http://www.ietf.org/rfc/rfc3023.txt">RFC 3023</a>, this constant
   * ({@code text/xml}) is used for XML documents that are "readable by casual users." {@link
   * #APPLICATION_XML_UTF_8} is provided for documents that are intended for applications.
   */
  public static final MediaType XML_UTF_8 = createConstantUtf8(TEXT_TYPE, "xml");

  /**

    }

    /**
     * Scrolls through all documents in the specified index and applies the callback function to each hit.
     *
     * @param index the name of the index to scroll through
     * @param callback the function to apply to each search hit, returning true to continue or false to stop
     * @return the number of documents processed
     */

     */
    public long getAllWordsNum() {
        return suggester.getAllWordsNum();
    }

    /**
     * Gets the number of words from documents in the suggest index.
     *
     * @return The number of document words.
     */
    public long getDocumentWordsNum() {
        return suggester.getDocumentWordsNum();
    }

    /**

    }

    public void test_builder_withDocuments() {
        // Test builder with adding documents
        Map<String, Object> doc1 = new HashMap<>();
        doc1.put("id", "1");
        doc1.put("title", "Document 1");

        Map<String, Object> doc2 = new HashMap<>();
        doc2.put("id", "2");
        doc2.put("title", "Document 2");