officeparser 6.0.7 → 6.1.0

package/dist/officeparser.browser.d.ts

@@ -1,5 +1,42 @@
 // Generated by dts-bundle-generator v9.5.1
 
+/**
+ * Configuration options for OCR.
+ */
+export interface OcrConfig {
+	/**
+	 * Language for OCR.
+	 * Default is 'eng'.
+	 *
+	 * You can provide multiple languages separated by a `+` sign (e.g., 'eng+fra' for English and French).
+	 * The OCR engine will then attempt to recognize text in any of the specified languages.
+	 *
+	 * See the list of supported languages and their codes here:
+	 * https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016
+	 */
+	language?: string;
+	/**
+	 * Path to the Tesseract worker script.
+	 * Primarily used for offline/air-gapped environments.
+	 */
+	workerPath?: string;
+	/**
+	 * Path to the Tesseract core script.
+	 * Primarily used for offline/air-gapped environments.
+	 */
+	corePath?: string;
+	/**
+	 * Path for Tesseract language files (traineddata).
+	 * Primarily used for offline/air-gapped environments.
+	 */
+	langPath?: string;
+	/**
+	 * Timeout in milliseconds of inactivity before the OCR worker pool is automatically terminated.
+	 * Set to 0 to disable auto-termination.
+	 * Default is 10,000 (10 seconds).
+	 */
+	autoTerminateTimeout?: number;
+}
 /**
  * Configuration options for the OfficeParser.
  */
@@ -42,6 +79,7 @@ export interface OfficeParserConfig {
 	 */
 	ocr?: boolean;
 	/**
+	 * @deprecated Use `ocrConfig.language` instead.
 	 * Language for OCR.
 	 * Default is 'eng'.
 	 *
@@ -52,11 +90,31 @@ export interface OfficeParserConfig {
 	 * https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016
 	 */
 	ocrLanguage?: string;
+	/**
+	 * Shared OCR configuration for worker pooling and offline support.
+	 * If provided, `ocrLanguage` will be ignored in favor of `ocrConfig.language`.
+	 */
+	ocrConfig?: OcrConfig;
+	/**
+	 * Flag to serialize raw content (XML) as clean, formatted strings.
+	 * Only relevant when `includeRawContent` is true.
+	 * Default is true.
+	 *
+	 * If false, the parser will attempt to extract the original raw substring from the
+	 * source document instead of re-serializing the DOM node.
+	 */
+	serializeRawContent?: boolean;
+	/**
+	 * Flag to preserve original XML whitespace and line endings when serializing.
+	 * Only relevant when `includeRawContent` is true and `serializeRawContent` is true.
+	 * Default is false.
+	 */
+	preserveXmlWhitespace?: boolean;
 	/**
 	 * The URL/path to the PDF.js worker script.
 	 *
 	 * **Mandatory** when using PDF parsing in browser environments to avoid worker configuration errors.
-	 * If not provided, it defaults to `https://unpkg.com/pdfjs-dist@5.5.207/build/pdf.worker.min.mjs`.
+	 * If not provided, it defaults to `https://unpkg.com/pdfjs-dist@5.6.205/build/pdf.worker.min.mjs`.
 	 * You can override this with your own local path or a different CDN link.
 	 */
 	pdfWorkerSrc?: string;
@@ -542,6 +600,16 @@ export interface OfficeMetadata {
 	formatting?: Partial<TextFormatting>;
 	/** Style map for styles in the document. */
 	styleMap?: Record<string, Partial<TextFormatting>>;
+	/**
+	 * User-defined custom properties embedded in the document.
+	 * Sources by format:
+	 * - DOCX/XLSX/PPTX: `docProps/custom.xml` (Office custom document properties)
+	 * - ODT/ODP/ODS: `meta:user-defined` elements in `meta.xml`
+	 * - PDF: non-standard entries in the PDF Info dictionary
+	 * RTF does not support custom properties; the `\info` group is not extracted.
+	 * Values are typed as string, number, boolean, or Date where the source format provides type information.
+	 */
+	customProperties?: Record<string, string | number | boolean | Date>;
 }
 /**
  * The Abstract Syntax Tree (AST) returned by the parser.
@@ -668,8 +736,18 @@ export declare class OfficeParser {
 	 * ```
 	 */
 	static parseOffice(file: string | Buffer | ArrayBuffer, configOrCallback?: OfficeParserConfig | ((ast: OfficeParserAST, err?: any) => void), config?: OfficeParserConfig): Promise<OfficeParserAST>;
+	/**
+	 * Terminates all active OCR workers and cleans up resources.
+	 *
+	 * This should be called when the application is shutting down or when OCR
+	 * is no longer needed to prevent memory leaks and orphaned worker processes.
+	 *
+	 * @returns A promise that resolves when all workers have been terminated
+	 */
+	static terminateOcr(): Promise<void>;
 }
 export declare const parseOffice: typeof OfficeParser.parseOffice;
+export declare const terminateOcr: typeof OfficeParser.terminateOcr;
 
 export {
 	OfficeParser as default,