officeparser 6.0.7 → 6.1.0

package/README.md

@@ -3,6 +3,8 @@
 A robust, strictly-typed Node.js and Browser library for parsing office files ([`docx`](https://en.wikipedia.org/wiki/Office_Open_XML), [`pptx`](https://en.wikipedia.org/wiki/Office_Open_XML), [`xlsx`](https://en.wikipedia.org/wiki/Office_Open_XML), [`odt`](https://en.wikipedia.org/wiki/OpenDocument), [`odp`](https://en.wikipedia.org/wiki/OpenDocument), [`ods`](https://en.wikipedia.org/wiki/OpenDocument), [`pdf`](https://en.wikipedia.org/wiki/PDF), [`rtf`](https://en.wikipedia.org/wiki/Rich_Text_Format)). It produces a clean, hierarchical Abstract Syntax Tree (AST) with rich metadata, text formatting, and full attachment support.
 
 [![npm version](https://badge.fury.io/js/officeparser.svg)](https://badge.fury.io/js/officeparser)
+[![Total Downloads](https://img.shields.io/npm/dt/officeparser.svg)](https://www.npmjs.com/package/officeparser)
+[![Weekly Downloads](https://img.shields.io/npm/dw/officeparser.svg)](https://www.npmjs.com/package/officeparser)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ---
@@ -22,6 +24,13 @@ A robust, strictly-typed Node.js and Browser library for parsing office files ([
 
 
 #### Update
+* 2026-04-14 - **v6.1.0 Release**: Major Infrastructure & Resource Stability. (Incremental since v6.0.0)
+    - **OCR Scheduler**: Intelligent worker pool that optimizes Tesseract lifecycle across parallel requests. **Note**: By default, Node.js processes stay active for 10s after OCR to keep workers warm (configurable via `ocrConfig.autoTerminateTimeout`); use `terminateOcr()` for immediate CLI/script exit.
+    - **Core Engine**: Replaced legacy zip extraction with `fflate` for significant performance gains and robust browser/edge compatibility.
+    - **Module System**: Full native ESM support with `Node16` resolution and verified browser bundles (Vite/Angular compatible).
+    - **Format Refinements**: Hierarchical PDF coordinate alignment and ODT/RTF list parsing stability.
+    - **Custom Properties**: Added support for extracting custom document metadata across OOXML, ODF, and PDF formats.
+    - **Sponsorship**: Integrated `funding.json` manifest and GitHub Sponsors support.
 * 2025/12/29 - **v6.0.0 Release**: Major overhaul of the library. Transitioned from simple text extraction to a rich **Abstract Syntax Tree (AST)** output.
     - Simplified API: Use `parseOffice` for all parsing needs (returns a Promise).
     - Structured Output: Access hierarchical document structure (paragraphs, headings, tables, lists, etc.).
@@ -82,6 +91,7 @@ npx officeparser /path/to/officeFile.docx --ignoreNotes=true --newlineDelimiter=
 - `--extractAttachments=[true|false]`   Flag to extract images/charts as Base64. Default is false.
 - `--ocr=[true|false]`                  Flag to enable OCR for extracted images. Default is false.
 - `--includeRawContent=[true|false]`    Flag to include raw XML/RTF content in nodes. Default is false.
+- `--verbose=[true|false]`              Show full error stack traces.
 
 
 ## Library Usage
@@ -156,7 +166,7 @@ The `OfficeParserAST` provides a format-agnostic representation of your document
 ```text
 OfficeParserAST
 ├── type: "docx" | "pptx" | "xlsx" | ...
-├── metadata: { author, title, created, modified, ... }
+├── metadata: { author, title, created, modified, ..., customProperties }
 ├── content: [ OfficeContentNode ]
 │   ├── type: "paragraph" | "heading" | "table" | "list" | ...
 │   ├── text: "Concatenated text of this node and all children"
@@ -177,7 +187,7 @@ OfficeParserAST
 ```json
 {
   "type": "docx",
-  "metadata": { "author": "John Doe", "title": "Annual Report" },
+  "metadata": { "author": "John Doe", "title": "Annual Report", "customProperties": { "Department": "Finance" } },
   "content": [
     {
       "type": "heading",
@@ -303,6 +313,16 @@ Formatting can be found at two levels:
 The `ast.metadata` object provides document-wide context:
 - **`styleMap`**: A dictionary of style names to their `TextFormatting` definitions found in the document.
 - **`formatting`**: Document-wide default settings (e.g., default font or font size).
+- **`customProperties`**: A dictionary of user-defined metadata embedded in the document (OOXML `custom.xml`, ODF `meta:user-defined`, or PDF Info dictionary).
+
+### 7. Custom Properties
+You can access custom user-defined metadata that might be embedded in the document:
+
+```javascript
+const ast = await officeParser.parseOffice("contract.docx");
+console.log("Custom Metadata:", ast.metadata.customProperties);
+// Output: { "ProjectID": "ABC-123", "InternalReview": true }
+```
 
 ### Advanced AST Usage
 Beyond using `ast.toText()`, you can interact with the structural data directly:
@@ -403,10 +423,46 @@ Pass an optional config object as the second argument to `parseOffice`.
 | `ignoreNotes` | boolean | `false` | Ignore notes in files like PowerPoint/ODP. |
 | `putNotesAtLast` | boolean | `false` | Put notes text at the end of the document. (Note: Does not work for RTF. It is treated as true always.) |
 | `extractAttachments` | boolean | `false` | Extract images and charts as Base64. |
-| `ocr` | boolean | `false` | Enable OCR for images (requires `extractAttachments: true`). |
-| `ocrLanguage` | string | `eng` | Language for OCR (e.g., 'eng', 'fra'). Supports multiple languages with '+'. See [Language Codes](https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016). |
 | `includeRawContent` | boolean | `false` | Include raw XML/RTF markup in the nodes. |
+| `serializeRawContent` | boolean | `true` | When `includeRawContent` is true, re-serializes raw XML to clean strings. If false, extracts original raw substring. |
+| `preserveXmlWhitespace` | boolean | `false` | When `serializeRawContent` is true, preserves original XML whitespace and line endings. |
+| `ocr` | boolean | `false` | Enable OCR for images (requires `extractAttachments: true`). |
+| `ocrLanguage` | string | `eng` | **Deprecated**: Use `ocrConfig.language` instead. Language for OCR. |
 | `pdfWorkerSrc` | string | `(see below)` | Path to PDF.js worker. Defaults to a CDN link if not provided. |
+| `ocrConfig` | object | `{}` | **OCR Scheduler** configuration for fine-grained worker control. |
+| `ocrConfig.language` | string | `eng` | Language(s) for OCR (e.g., 'eng', 'fra', 'eng+fra'). |
+| `ocrConfig.autoTerminateTimeout` | number | `10000` | Inactivity timeout in milliseconds before workers are killed. |
+| `ocrConfig.workerPath` | string | `undefined` | Path to Tesseract worker script (for offline use). |
+| `ocrConfig.corePath` | string | `undefined` | Path to Tesseract core script (for offline use). |
+| `ocrConfig.langPath` | string | `undefined` | Path for Tesseract language files (for offline use). |
+
+### OCR Scheduler & Resource Management
+If your application uses OCR, `officeParser` utilizes an intelligent **Smart Worker Pool** to maintain a background worker pool and optimize repeated parse requests.
+
+- **Dynamic Affinity**: Workers in the pool persist with their last used language affinity. 
+- **Smart Re-initialization**: If a new language is requested and the pool is full, the manager identifies the **Least Recently Used (LRU)** idle worker and re-initializes it for the new language using the Tesseract.js v5 API. This avoids the overhead of destroying and recreating workers.
+- **Auto-Termination**: Workers are automatically cleaned up after 10 seconds of inactivity (configurable via `ocrConfig.autoTerminateTimeout`).
+
+#### `OfficeParser.terminateOcr()`
+If you have used OCR (`{ ocr: true }`) in a short-lived script (like CLI tools or one-off automation), we recommend explicitly calling `terminateOcr()` after your processing is finished. This bypasses the 10-second idle timer and allows the process to return to the terminal prompt immediately.
+
+> [!NOTE]
+> If OCR was not used, this function is a no-op and does not need to be called.
+
+```js
+const officeParser = require('officeparser');
+
+async function runCleaner() {
+    await officeParser.parseOffice("file.pdf", { ocr: true });
+    // ... process results ...
+
+    // Manually kill OCR workers for an immediate exit
+    await officeParser.terminateOcr();
+}
+```
+
+> [!TIP]
+> This is handled automatically in our own CLI (`npx officeparser ...`). You only need to call this manually if you are using the library in your own custom script and want a snappy exit.
 
 ```js
 const config = {
@@ -449,20 +505,21 @@ officeParser.parseOffice("presentation.pptx", config).then(ast => {
 ```
 
 ## Browser Usage
-The browser bundle exposes the `officeParser` namespace. Include the bundle file available in the release assets.
+The library provides two types of browser bundles in the `dist/` directory:
+1. **`officeparser.browser.iife.js`**: Standard IIFE bundle for direct `<script>` tag usage. Exposes the global `officeParser` namespace.
+2. **`officeparser.browser.mjs`**: Modern ESM bundle for use with `import` statements or modern bundlers.
+
+### Usage (Script Tag)
+Include the IIFE bundle file available in the release assets.
 
 ```html
-<script src="dist/officeparser.browser.js"></script>
+<script src="dist/officeparser.browser.iife.js"></script>
 <script>
     async function handleFile(file) {
         // file can be a File object from an input element or an ArrayBuffer
-        // The browser bundle exposes the global variable `officeParser`
-        // which contains the `OfficeParser` class.
-        
         try {
             const ast = await officeParser.parseOffice(file, { ocr: true });
             console.log(ast.toText());
-            console.log("Metadata:", ast.metadata);
         } catch (error) {
             console.error(error);
         }
@@ -470,8 +527,20 @@ The browser bundle exposes the `officeParser` namespace. Include the bundle file
 </script>
 ```
 
+### Usage (ESM)
+If you are using a modern browser that supports modules or a dev server like Vite:
+
+```html
+<script type="module">
+    import { OfficeParser } from './dist/officeparser.browser.mjs';
+    
+    const ast = await OfficeParser.parseOffice(fileBuffer);
+    console.log(ast.metadata);
+</script>
+```
+
 ### PDF Worker Configuration in Browser
-When using `officeparser` in a browser environment to parse PDF files, you may provide the `pdfWorkerSrc` configuration option. If not provided, it defaults to a CDN link for `pdfjs-dist@5.5.207`.
+When using `officeparser` in a browser environment to parse PDF files, you may provide the `pdfWorkerSrc` configuration option. If not provided, it defaults to a CDN link for `pdfjs-dist@5.6.205`.
 
 ```javascript
 const file = ...; // File object or ArrayBuffer
@@ -481,11 +550,21 @@ const ast = await officeParser.parseOffice(file);
 
 // Or override it with your own path or a different version:
 const ast2 = await officeParser.parseOffice(file, {
-    pdfWorkerSrc: "https://unpkg.com/pdfjs-dist@5.5.207/build/pdf.worker.min.mjs"
+    pdfWorkerSrc: "https://unpkg.com/pdfjs-dist@5.6.205/build/pdf.worker.min.mjs"
 });
 ```
 
-> **Note:** The version of `pdfjs-dist` in the worker source should match the version used by `officeparser` (currently `5.4.530`).
+> **Note:** The version of `pdfjs-dist` in the worker source should match the version used by `officeparser` (currently `5.6.205`).
+
+## Troubleshooting & Common Issues
+
+- **Node.js process stays alive after finishing**: If using OCR, the worker pool stays warm for 10s by default. Use `await terminateOcr()` at the end of your script for a snappy exit.
+- **"Worker not found" in Browser**: Ensure `pdfWorkerSrc` is correctly pointed to the `pdf.worker.min.mjs` file matching version `5.6.205`.
+- **OCR accuracy is low**: Verify your `ocrConfig.language` matches the document content. Note that OCR quality depends on image resolution.
+- **Out of memory on large files**: For massive spreadsheets, consider using `ast.toText()` early and allowing the full AST object to be garbage-collected.
+
+For a comprehensive guide, visit our [Debugging & Troubleshooting Documentation](https://harshankur.github.io/officeParser/#spec/debugging).
+
 
 ## Known Limitations
 1. **ODT/ODS Charts**: Extraction may occasionally show inaccurate data when referencing external cell ranges or complex layout-based data.

package/dist/OfficeParser.d.ts

@@ -32,7 +32,7 @@
  *
  * @module OfficeParser
  */
-import { OfficeParserAST, OfficeParserConfig } from './types';
+import { OfficeParserAST, OfficeParserConfig } from './types.js';
 /**
  * Main parser class providing office document parsing functionality.
  *
@@ -86,4 +86,13 @@ 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>;
 }

package/dist/OfficeParser.js

@@ -33,50 +33,18 @@
  *
  * @module OfficeParser
  */
-var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    var desc = Object.getOwnPropertyDescriptor(m, k);
-    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-      desc = { enumerable: true, get: function() { return m[k]; } };
-    }
-    Object.defineProperty(o, k2, desc);
-}) : (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    o[k2] = m[k];
-}));
-var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
-    Object.defineProperty(o, "default", { enumerable: true, value: v });
-}) : function(o, v) {
-    o["default"] = v;
-});
-var __importStar = (this && this.__importStar) || (function () {
-    var ownKeys = function(o) {
-        ownKeys = Object.getOwnPropertyNames || function (o) {
-            var ar = [];
-            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
-            return ar;
-        };
-        return ownKeys(o);
-    };
-    return function (mod) {
-        if (mod && mod.__esModule) return mod;
-        var result = {};
-        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
-        __setModuleDefault(result, mod);
-        return result;
-    };
-})();
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OfficeParser = void 0;
-const fs = __importStar(require("fs"));
-const ExcelParser_1 = require("./parsers/ExcelParser");
-const OpenOfficeParser_1 = require("./parsers/OpenOfficeParser");
-const PdfParser_1 = require("./parsers/PdfParser");
-const PowerPointParser_1 = require("./parsers/PowerPointParser");
-const RtfParser_1 = require("./parsers/RtfParser");
-const WordParser_1 = require("./parsers/WordParser");
-const errorUtils_1 = require("./utils/errorUtils");
-const moduleLoader_1 = require("./utils/moduleLoader");
+const envUtils_js_1 = require("./utils/envUtils.js");
+const ExcelParser_js_1 = require("./parsers/ExcelParser.js");
+const OpenOfficeParser_js_1 = require("./parsers/OpenOfficeParser.js");
+const PdfParser_js_1 = require("./parsers/PdfParser.js");
+const PowerPointParser_js_1 = require("./parsers/PowerPointParser.js");
+const RtfParser_js_1 = require("./parsers/RtfParser.js");
+const WordParser_js_1 = require("./parsers/WordParser.js");
+const errorUtils_js_1 = require("./utils/errorUtils.js");
+const moduleLoader_js_1 = require("./utils/moduleLoader.js");
+const ocrUtils_js_1 = require("./utils/ocrUtils.js");
 /**
  * Main parser class providing office document parsing functionality.
  *
@@ -148,7 +116,10 @@ class OfficeParser {
             ocr: false,
             ocrLanguage: 'eng',
             includeRawContent: false,
+            serializeRawContent: true,
+            preserveXmlWhitespace: false,
             pdfWorkerSrc: '',
+            ocrConfig: {},
             ...actualConfig
         };
         let buffer = Buffer.alloc(0);
@@ -156,7 +127,7 @@ class OfficeParser {
         let filePath;
         try {
             if (!file) {
-                throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.IMPROPER_ARGUMENTS, internalConfig);
+                throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.IMPROPER_ARGUMENTS, internalConfig);
             }
             if (file instanceof ArrayBuffer) {
                 buffer = Buffer.from(file);
@@ -166,63 +137,79 @@ class OfficeParser {
             }
             else if (typeof file === 'string') {
                 filePath = file;
+                (0, envUtils_js_1.assertNode)('path-parsing');
+                // Safe to use dynamic import here as we've asserted we are in Node.
+                // Modern bundlers will still see this, but our browser builds 
+                // shim 'fs' so it won't crash at build time.
+                const fs = await import('fs');
                 if (!fs.existsSync(file)) {
-                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.FILE_DOES_NOT_EXIST, internalConfig, file);
+                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.FILE_DOES_NOT_EXIST, internalConfig, file);
                 }
                 if (fs.lstatSync(file).isDirectory()) {
-                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.LOCATION_NOT_FOUND, internalConfig, file);
+                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.LOCATION_NOT_FOUND, internalConfig, file);
                 }
                 buffer = fs.readFileSync(file);
                 ext = file.split('.').pop()?.toLowerCase() || '';
             }
             else {
-                throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.INVALID_INPUT, internalConfig);
+                throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.INVALID_INPUT, internalConfig);
             }
             if (!ext) {
-                const { fileTypeFromBuffer } = await (0, moduleLoader_1.loadFileType)();
+                const { fileTypeFromBuffer } = await (0, moduleLoader_js_1.loadFileType)();
                 const type = await fileTypeFromBuffer(buffer);
                 if (type) {
                     ext = type.ext.toLowerCase();
                 }
                 else {
-                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.IMPROPER_BUFFERS, internalConfig);
+                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.IMPROPER_BUFFERS, internalConfig);
                 }
             }
             let result;
             switch (ext) {
                 case 'docx':
-                    result = await (0, WordParser_1.parseWord)(buffer, internalConfig);
+                    result = await (0, WordParser_js_1.parseWord)(buffer, internalConfig);
                     break;
                 case 'pptx':
-                    result = await (0, PowerPointParser_1.parsePowerPoint)(buffer, internalConfig);
+                    result = await (0, PowerPointParser_js_1.parsePowerPoint)(buffer, internalConfig);
                     break;
                 case 'xlsx':
-                    result = await (0, ExcelParser_1.parseExcel)(buffer, internalConfig);
+                    result = await (0, ExcelParser_js_1.parseExcel)(buffer, internalConfig);
                     break;
                 case 'odt':
                 case 'odp':
                 case 'ods':
-                    result = await (0, OpenOfficeParser_1.parseOpenOffice)(buffer, internalConfig);
+                    result = await (0, OpenOfficeParser_js_1.parseOpenOffice)(buffer, internalConfig);
                     break;
                 case 'pdf':
-                    result = await (0, PdfParser_1.parsePdf)(buffer, internalConfig);
+                    result = await (0, PdfParser_js_1.parsePdf)(buffer, internalConfig);
                     break;
                 case 'rtf':
-                    result = await (0, RtfParser_1.parseRtf)(buffer, internalConfig);
+                    result = await (0, RtfParser_js_1.parseRtf)(buffer, internalConfig);
                     break;
                 default:
-                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.EXTENSION_UNSUPPORTED, internalConfig, ext);
+                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.EXTENSION_UNSUPPORTED, internalConfig, ext);
             }
             if (callback)
                 callback(result);
             return result;
         }
         catch (error) {
-            const wrappedError = (0, errorUtils_1.getWrappedError)(error, internalConfig, filePath);
+            const wrappedError = (0, errorUtils_js_1.getWrappedError)(error, internalConfig, filePath);
             if (callback)
                 callback(undefined, wrappedError);
             throw wrappedError;
         }
     }
+    /**
+     * 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 async terminateOcr() {
+        await (0, ocrUtils_js_1.terminateOcr)();
+    }
 }
 exports.OfficeParser = OfficeParser;

package/dist/cli.d.ts

@@ -0,0 +1,20 @@
+#!/usr/bin/env node
+/**
+ * officeparser CLI
+ *
+ * Allows running officeparser from the command line:
+ *   npx officeparser file.docx
+ *   officeparser file.docx --toText=true
+ *   officeparser file.docx --ocr=true --extractAttachments=true
+ *
+ * Options (--key=value):
+ *   --toText=true             Output plain text instead of JSON AST
+ *   --ocr=true                Enable OCR for images
+ *   --ocrLanguage=eng         OCR language (default: eng)
+ *   --extractAttachments=true Extract embedded attachments
+ *   --ignoreNotes=true        Ignore footnotes/endnotes
+ *   --putNotesAtLast=true     Move notes to end of document
+ *   --includeRawContent=true  Include raw content in AST
+ *   --outputErrorToConsole=true  Log errors to console
+ */
+export {};

package/dist/cli.js

@@ -0,0 +1,116 @@
+#!/usr/bin/env node
+"use strict";
+/**
+ * officeparser CLI
+ *
+ * Allows running officeparser from the command line:
+ *   npx officeparser file.docx
+ *   officeparser file.docx --toText=true
+ *   officeparser file.docx --ocr=true --extractAttachments=true
+ *
+ * Options (--key=value):
+ *   --toText=true             Output plain text instead of JSON AST
+ *   --ocr=true                Enable OCR for images
+ *   --ocrLanguage=eng         OCR language (default: eng)
+ *   --extractAttachments=true Extract embedded attachments
+ *   --ignoreNotes=true        Ignore footnotes/endnotes
+ *   --putNotesAtLast=true     Move notes to end of document
+ *   --includeRawContent=true  Include raw content in AST
+ *   --outputErrorToConsole=true  Log errors to console
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+const OfficeParser_js_1 = require("./OfficeParser.js");
+const args = process.argv.slice(2);
+let fileArg;
+let toText = false;
+let verbose = 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('--', '');
+        const lowerValue = value.toLowerCase();
+        const boolValue = lowerValue === 'true' ? true : (lowerValue === 'false' ? false : undefined);
+        if (cleanKey === 'toText') {
+            if (boolValue !== undefined)
+                toText = boolValue;
+            else
+                console.warn(`Invalid value for toText: ${value}`);
+        }
+        else if (cleanKey === 'verbose') {
+            if (boolValue !== undefined)
+                verbose = boolValue;
+            else
+                console.warn(`Invalid value for verbose: ${value}`);
+        }
+        else {
+            // @ts-ignore
+            if (boolValue !== undefined)
+                config[cleanKey] = boolValue;
+            // @ts-ignore
+            else
+                config[cleanKey] = value;
+        }
+    });
+    OfficeParser_js_1.OfficeParser.parseOffice(fileArg, config)
+        .then(async (ast) => {
+        if (toText) {
+            process.stdout.write(ast.toText() + '\n');
+        }
+        else {
+            process.stdout.write(JSON.stringify(ast, null, 2) + '\n');
+        }
+        // Ensure OCR workers are terminated for clean CLI exit
+        if (config.ocr) {
+            await OfficeParser_js_1.OfficeParser.terminateOcr();
+        }
+    })
+        .catch(async (err) => {
+        console.error(`Error parsing file "${fileArg}":`);
+        if (verbose) {
+            console.error(err);
+        }
+        else {
+            console.error(err.message || err);
+            console.error('Use --verbose=true for full stack trace.');
+        }
+        // Ensure OCR workers are terminated even on error
+        if (config.ocr) {
+            await OfficeParser_js_1.OfficeParser.terminateOcr();
+        }
+        process.exit(1);
+    });
+}
+else {
+    console.log('Usage: officeparser <file> [--option=value]');
+    console.log('');
+    console.log('Options:');
+    console.log('  --toText=true                Output plain text instead of JSON AST');
+    console.log('  --ocr=true                   Enable OCR for images');
+    console.log('  --ocrLanguage=eng            OCR language (default: eng)');
+    console.log('  --extractAttachments=true    Extract embedded attachments');
+    console.log('  --ignoreNotes=true           Ignore footnotes/endnotes');
+    console.log('  --putNotesAtLast=true        Move notes to end of document');
+    console.log('  --includeRawContent=true     Include raw content in AST');
+    console.log('  --serializeRawContent=true   Serialize raw XML content (default: true)');
+    console.log('  --preserveXmlWhitespace=true Preserve whitespace in serialized XML (default: false)');
+    console.log('  --verbose=true               Show full error stack traces');
+    console.log('');
+    console.log('Examples:');
+    console.log('  officeparser document.docx');
+    console.log('  officeparser document.docx --toText=true');
+    console.log('  officeparser report.pdf --ocr=true --extractAttachments=true');
+    console.log('  officeparser complex.docx --serializeRawContent=false --includeRawContent=true');
+}

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 { OfficeParser } from './OfficeParser.js';
 import { OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata } 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 };
 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;