officeparser 6.0.7 → 6.1.1

package/dist/index.d.ts

@@ -1,4 +1,3 @@
-#!/usr/bin/env node
 /**
  * officeparser - Universal Office Document Parser
  *
@@ -44,8 +43,9 @@
  * @packageDocumentation
  * @module officeparser
  */
-import { OfficeParser } from './OfficeParser';
-import { OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata } from './types';
+import { OfficeParser } from './OfficeParser.js';
+import { OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata, BreakMetadata } from './types';
 declare const parseOffice: typeof OfficeParser.parseOffice;
-export { OfficeParser, parseOffice, OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata };
+declare const terminateOcr: typeof OfficeParser.terminateOcr;
+export { OfficeParser, parseOffice, terminateOcr, OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata, BreakMetadata, };
 export default OfficeParser;

package/dist/index.js

@@ -1,4 +1,3 @@
-#!/usr/bin/env node
 "use strict";
 /**
  * officeparser - Universal Office Document Parser
@@ -46,63 +45,12 @@
  * @module officeparser
  */
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseOffice = exports.OfficeParser = void 0;
-const OfficeParser_1 = require("./OfficeParser");
-Object.defineProperty(exports, "OfficeParser", { enumerable: true, get: function () { return OfficeParser_1.OfficeParser; } });
-const parseOffice = OfficeParser_1.OfficeParser.parseOffice;
+exports.terminateOcr = exports.parseOffice = exports.OfficeParser = void 0;
+const OfficeParser_js_1 = require("./OfficeParser.js");
+Object.defineProperty(exports, "OfficeParser", { enumerable: true, get: function () { return OfficeParser_js_1.OfficeParser; } });
+const parseOffice = OfficeParser_js_1.OfficeParser.parseOffice;
 exports.parseOffice = parseOffice;
+const terminateOcr = OfficeParser_js_1.OfficeParser.terminateOcr;
+exports.terminateOcr = terminateOcr;
 // Default export for backward compatibility
-exports.default = OfficeParser_1.OfficeParser;
-// CLI handling - allows running as: node index.js file.docx
-if (typeof require !== 'undefined' && typeof module !== 'undefined' && require.main === module) {
-    const args = process.argv.slice(2);
-    let fileArg;
-    let toText = false;
-    const configArgs = [];
-    function isConfigOption(arg) {
-        return arg.startsWith('--') && arg.includes('=');
-    }
-    args.forEach(arg => {
-        if (isConfigOption(arg)) {
-            configArgs.push(arg);
-        }
-        else if (!fileArg) {
-            fileArg = arg;
-        }
-    });
-    if (fileArg) {
-        const config = {};
-        configArgs.forEach(arg => {
-            const [key, value] = arg.split('=');
-            const cleanKey = key.replace('--', '');
-            if (cleanKey === 'toText') {
-                if (value.toLowerCase() === 'true')
-                    toText = true;
-                else if (value.toLowerCase() === 'false')
-                    toText = false;
-                else
-                    console.log(`Invalid value for toText: ${value}`);
-            }
-            // @ts-ignore
-            else if (value.toLowerCase() === 'true')
-                config[cleanKey] = true;
-            // @ts-ignore
-            else if (value.toLowerCase() === 'false')
-                config[cleanKey] = false;
-            // @ts-ignore
-            else
-                config[cleanKey] = value;
-        });
-        OfficeParser_1.OfficeParser.parseOffice(fileArg, config)
-            .then((ast) => {
-            if (toText)
-                console.log(ast.toText());
-            else
-                console.log(JSON.stringify(ast, null, 2));
-        })
-            .catch(console.error);
-    }
-    else {
-        console.log("Usage: node officeparser [file] [--option=value]");
-    }
-}
+exports.default = OfficeParser_js_1.OfficeParser;

package/dist/index.mjs

@@ -0,0 +1,18 @@
+/**
+ * ESM wrapper for officeparser
+ *
+ * AUTO-GENERATED — do not edit manually.
+ * Generated by scripts/generate-esm-wrapper.js during build.
+ *
+ * This file re-exports from the CJS build (dist/index.js) to provide
+ * proper ESM named exports without duplicating the source code.
+ */
+
+import _module from './index.js';
+
+// Named exports
+const { OfficeParser, parseOffice, terminateOcr } = _module;
+export { OfficeParser, parseOffice, terminateOcr };
+
+// Default export
+export default _module.default ?? _module;

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'.
 	 *
@@ -52,14 +90,41 @@ 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;
+	/**
+	 * Flag to include break nodes in the AST.
+	 * This is currently only supported for Word documents. (w:br nodes)
+	 *
+	 * Default is false
+	 */
+	includeBreakNodes?: boolean;
 }
 /**
  * Supported file types for parsing.
@@ -68,7 +133,7 @@ export type SupportedFileType = "docx" | "pptx" | "xlsx" | "odt" | "odp" | "ods"
 /**
  * Types of content nodes in the AST.
  */
-export type OfficeContentNodeType = "paragraph" | "heading" | "table" | "list" | "text" | "image" | "chart" | "drawing" | "slide" | "note" | "sheet" | "row" | "cell" | "page";
+export type OfficeContentNodeType = "paragraph" | "heading" | "table" | "list" | "text" | "image" | "chart" | "drawing" | "slide" | "note" | "sheet" | "row" | "cell" | "page" | "break";
 /**
  * Supported MIME types for attachments.
  */
@@ -171,6 +236,20 @@ export interface SheetMetadata {
 	/** The style of the sheet. */
 	style?: string;
 }
+/**
+ * Detailed indentation information for paragraphs and headings.
+ * Values are typically in twentieths of a point (twips) in OOXML.
+ */
+export interface IndentationMetadata {
+	/** Left indentation. */
+	left?: number;
+	/** Right indentation. */
+	right?: number;
+	/** First line indentation. */
+	firstLine?: number;
+	/** Hanging indentation. */
+	hanging?: number;
+}
 /**
  * Metadata for a heading.
  */
@@ -181,6 +260,8 @@ export interface HeadingMetadata {
 	alignment?: "left" | "center" | "right" | "justify";
 	/** The style of the heading. */
 	style?: string;
+	/** Detailed indentation information. */
+	paragraphIndentation?: IndentationMetadata;
 }
 /**
  * Metadata for a paragraph.
@@ -190,6 +271,8 @@ export interface ParagraphMetadata {
 	alignment?: "left" | "center" | "right" | "justify";
 	/** The style of the paragraph. */
 	style?: string;
+	/** Detailed indentation information. */
+	paragraphIndentation?: IndentationMetadata;
 }
 /**
  * Metadata for a list item.
@@ -205,6 +288,8 @@ export interface ListMetadata {
 	 * @example 0 for top-level items, 1 for first nested level
 	 */
 	indentation: number;
+	/** Detailed indentation information. */
+	paragraphIndentation?: IndentationMetadata;
 	/**
 	 * Text alignment of the list item.
 	 * @example 'left', 'center', 'right', 'justify'
@@ -331,10 +416,35 @@ export interface NoteMetadata {
 	 */
 	noteId?: string;
 }
+/**
+ * Metadata for break nodes.
+ * Used in DOCX files to track line and page breaks.
+ */
+export interface BreakMetadata {
+	/**
+	 * Type of break. The break type determines the next location where
+	 * text shall be placed.
+	 * - 'column': The next text will be placed in the next column.
+	 * - 'page': The next text will be placed on the next page.
+	 * - 'lastRenderedPage': The editing application has inserted a soft break on the last save.
+	 * - 'textWrapping' (default, assumed when not specified): The next text will be placed on the next line.
+	 * - 'carriageReturn': An explicit carriage return (w:cr) equivalent to a hard line break.
+	 */
+	breakType: "column" | "page" | "lastRenderedPage" | "textWrapping" | "carriageReturn";
+	/**
+	 * Specifies the location which shall be used as the next available line when breakType
+	 * has a value of 'textWrapping'. Should be ignored for other break types.
+	 * - 'all': text wrapping break shall advance the text to the next line which spans the full width of the line
+	 * - 'left': text wrapping break shall restart in next text region unblocked on the left
+	 * - 'none': text wrapping break shall advance the text to the next line regardless of any floating objects
+	 * - 'right': text wrapping break shall restart in next text region unblocked on the right
+	 */
+	clear?: "all" | "left" | "none" | "right";
+}
 /**
  * Union type for content metadata.
  */
-export type ContentMetadata = SlideMetadata | SheetMetadata | HeadingMetadata | ListMetadata | CellMetadata | ImageMetadata | ChartMetadata | PageMetadata | ParagraphMetadata | TextMetadata | NoteMetadata | undefined;
+export type ContentMetadata = SlideMetadata | SheetMetadata | HeadingMetadata | ListMetadata | CellMetadata | ImageMetadata | ChartMetadata | PageMetadata | ParagraphMetadata | TextMetadata | NoteMetadata | BreakMetadata | undefined;
 /**
  * Represents a node in the document content tree.
  * This is the core building block of the parsed document structure.
@@ -542,6 +652,16 @@ 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 +788,18 @@ 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,