@CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedPaths;

    /** The document paths to include in search results (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String includedDocPaths;

    /** The document paths to exclude from search results (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")

```

## Advanced Usage

### Index from Existing Documents

```java
import org.codelibs.fess.suggest.index.contents.document.ESSourceReader;

// Index suggestions from existing Elasticsearch documents
DocumentReader reader = new ESSourceReader(
    client,
    suggester.settings(),
    "content-index",        // source index
    "document"             // document type
);

suggester.indexer()

    }

    /**
     * Extracts text from embedded documents in the PDF.
     * @param document the PDF document
     * @param writer the writer to append extracted text to
     */
    protected void extractEmbeddedDocuments(final PDDocument document, final StringWriter writer) {
        final PDDocumentNameDictionary namesDictionary = new PDDocumentNameDictionary(document.getDocumentCatalog());

            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);

    /**
     * The boost value for documents from this web configuration.
     */
    @Required
    @ValidateTypeFailure
    public Float boost;

    /**
     * Whether this web configuration is available for crawling.
     */
    @Required
    @Size(max = 5)
    public String available;

    /**
     * Permissions required to access documents from this configuration.
     */

- **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 org.codelibs.fess.entity.DataStoreParams;
import org.codelibs.fess.util.ComponentUtil;

/**
 * Abstract base class for document ingesters that process and transform documents
 * before they are indexed. Ingesters can be used to modify document content,
 * extract additional metadata, or perform other transformations during the
 * indexing process.
 *

     * @return a map of Path to Document for all discovered POM files
     * @throws IOException if there's an error reading files
     * @throws DomTripException if there's an error parsing XML
     */
    public static Map<Path, Document> discoverPoms(Path startDirectory) throws IOException, DomTripException {
        Map<Path, Document> pomMap = new HashMap<>();

        // Find and load the root POM

import org.codelibs.fess.util.ComponentUtil;

/**
 * A matcher class for applying document boost values based on configurable expressions.
 * This class evaluates match and boost expressions against document data to determine
 * if a document should receive a boost and what boost value to apply. It supports
 * script-based expressions for flexible document scoring.
 *
 */
public class DocBoostMatcher {

    }

    /**
     * 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
     */