officeparser 6.0.3 → 6.0.6

package/dist/parsers/ExcelParser.d.ts

@@ -21,7 +21,6 @@
  * @module ExcelParser
  * @see https://www.ecma-international.org/publications-and-standards/standards/ecma-376/
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Parses an Excel spreadsheet (.xlsx) and extracts sheets, rows, and cells.

package/dist/parsers/ExcelParser.js

@@ -542,7 +542,7 @@ const parseExcel = async (buffer, config) => {
                                     if (attachment) {
                                         const imageNode = {
                                             type: 'image',
-                                            text: '',
+                                            text: '', // Will be populated by assignAttachmentData
                                             children: [],
                                             metadata: {
                                                 attachmentName: attachment.name || 'unknown',
@@ -562,7 +562,7 @@ const parseExcel = async (buffer, config) => {
                                     if (attachment) {
                                         const chartNode = {
                                             type: 'chart',
-                                            text: '',
+                                            text: '', // Will be populated by assignAttachmentData
                                             children: [],
                                             metadata: {
                                                 attachmentName: chartName

package/dist/parsers/OpenOfficeParser.d.ts

@@ -20,7 +20,6 @@
  *
  * @module OpenOfficeParser
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Parses an OpenOffice document (.odt, .odp, .ods) and extracts content.

package/dist/parsers/OpenOfficeParser.js

@@ -1009,10 +1009,10 @@ const parseOpenOffice = async (buffer, config) => {
                                     // logic for image node
                                     const imageNode = {
                                         type: 'image',
-                                        text: '',
+                                        text: '', // Will be populated by assignAttachmentData
                                         children: [],
                                         metadata: {
-                                            attachmentName: imageHref,
+                                            attachmentName: imageHref, // Might be empty, will resolve in assignAttachmentData
                                             ...(altText ? { altText } : {})
                                         }
                                     };
@@ -1024,7 +1024,7 @@ const parseOpenOffice = async (buffer, config) => {
                                 else if (chartHref) {
                                     const chartNode = {
                                         type: 'chart',
-                                        text: '',
+                                        text: '', // Will be populated by assignAttachmentData
                                         children: [],
                                         metadata: {
                                             attachmentName: chartHref
@@ -1058,7 +1058,7 @@ const parseOpenOffice = async (buffer, config) => {
                             for (let k = 0; k < rowsRepeated; k++) {
                                 const rowNode = {
                                     type: 'row',
-                                    children: JSON.parse(JSON.stringify(cells)),
+                                    children: JSON.parse(JSON.stringify(cells)), // Deep copy for repeated rows
                                     metadata: undefined
                                 };
                                 // Fix row index in metadata for repeated rows
@@ -1173,7 +1173,7 @@ const parseOpenOffice = async (buffer, config) => {
                 const objectId = objFile.path.split('/')[0];
                 const attachment = {
                     type: 'chart',
-                    mimeType: 'application/vnd.oasis.opendocument.chart',
+                    mimeType: 'application/vnd.oasis.opendocument.chart', // Accurate ODF chart type
                     data: objFile.content.toString('base64'),
                     name: objectId,
                     extension: 'xml'

package/dist/parsers/PdfParser.d.ts

@@ -56,7 +56,6 @@
  * @see https://mozilla.github.io/pdf.js/ PDF.js documentation
  * @see https://www.adobe.com/devnet/pdf/pdf_reference.html PDF Reference
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Parses a PDF file and extracts content.

package/dist/parsers/PdfParser.js

@@ -57,34 +57,12 @@
  * @see https://mozilla.github.io/pdf.js/ PDF.js documentation
  * @see https://www.adobe.com/devnet/pdf/pdf_reference.html PDF Reference
  */
-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 (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.parsePdf = void 0;
 const errorUtils_1 = require("../utils/errorUtils");
 const imageUtils_1 = require("../utils/imageUtils");
 const ocrUtils_1 = require("../utils/ocrUtils");
+const moduleLoader_1 = require("../utils/moduleLoader");
 /**
  * Parses PDF creation/modification date strings.
  * PDF dates are in format: D:YYYYMMDDHHmmSSOHH'mm'
@@ -329,25 +307,7 @@ function convertToRgbaBuffer(data, width, height, kind) {
  * @returns Promise resolving to the parsed AST
  */
 const parsePdf = async (buffer, config) => {
-    let pdfjs;
-    // Check if we are in a Node.js environment
-    // @ts-ignore
-    if (typeof window === 'undefined') {
-        // Helper to bypass TS/Webpack/Other transpilers converting import() to require() when compiling to CJS
-        // Defined here to avoid CSP 'unsafe-eval' issues in browser environments
-        const dynamicImport = new Function('specifier', 'return import(specifier)');
-        try {
-            // Use legacy build for Node.js (required for pdfjs-dist v5+)
-            pdfjs = await dynamicImport('pdfjs-dist/legacy/build/pdf.mjs');
-        }
-        catch (e) {
-            // Fallback to standard if legacy not found (e.g. older versions)
-            pdfjs = await dynamicImport('pdfjs-dist');
-        }
-    }
-    else {
-        pdfjs = await Promise.resolve().then(() => __importStar(require('pdfjs-dist')));
-    }
+    const pdfjs = await (0, moduleLoader_1.loadPdfJs)();
     // Configure worker
     if (config.pdfWorkerSrc) {
         pdfjs.GlobalWorkerOptions.workerSrc = config.pdfWorkerSrc;
@@ -357,7 +317,7 @@ const parsePdf = async (buffer, config) => {
         // @ts-ignore
         if (typeof window !== 'undefined') {
             // Browser: Default to CDN
-            pdfjs.GlobalWorkerOptions.workerSrc = 'https://unpkg.com/pdfjs-dist@5.4.530/build/pdf.worker.min.mjs';
+            pdfjs.GlobalWorkerOptions.workerSrc = `https://unpkg.com/pdfjs-dist@${pdfjs.version}/build/pdf.worker.min.mjs`;
         }
         else {
             // Node.js: Try to auto-resolve local worker path to avoid remote fetch errors
@@ -407,7 +367,7 @@ const parsePdf = async (buffer, config) => {
         title: info?.Title || undefined,
         author: info?.Author || undefined,
         subject: info?.Subject || undefined,
-        description: info?.Keywords || undefined,
+        description: info?.Keywords || undefined, // Map Keywords to description as closest match
         created: parsePdfDate(info?.CreationDate),
         modified: parsePdfDate(info?.ModDate),
         // Note: lastModifiedBy is not available in PDF format - there's no concept of "last modifier"

package/dist/parsers/PowerPointParser.d.ts

@@ -21,7 +21,6 @@
  * @module PowerPointParser
  * @see https://www.ecma-international.org/publications-and-standards/standards/ecma-376/
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Parses a PowerPoint presentation (.pptx) and extracts slides and notes.

package/dist/parsers/PowerPointParser.js

@@ -239,7 +239,7 @@ const parsePowerPoint = async (buffer, config) => {
         // Step 6: Build AST node
         const chartNode = {
             type: "chart",
-            text: "",
+            text: "", // chart text gets filled later
             metadata: {
                 attachmentName // name used to link to attachments & chartData
             }
@@ -707,7 +707,7 @@ const parsePowerPoint = async (buffer, config) => {
         for (const chart of chartFiles) {
             const attachment = {
                 type: 'chart',
-                mimeType: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+                mimeType: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', // Generic XML type for now
                 data: chart.content.toString('base64'),
                 name: chart.path.split('/').pop() || '',
                 extension: 'xml'

package/dist/parsers/RtfParser.d.ts

@@ -39,7 +39,6 @@
  * @see https://www.biblioscape.com/rtf15_spec.htm RTF 1.5 Specification
  * @see https://latex2rtf.sourceforge.net/RTF-Spec-1.2.pdf RTF 1.2 Specification
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Represents an RTF group (content enclosed in braces).

package/dist/parsers/RtfParser.js

@@ -151,32 +151,32 @@ class SimpleRtfParser {
                     // Characters 0x80-0x9F in Windows-1252 don't map directly to Unicode
                     // We need to convert them properly
                     const windows1252ToUnicode = {
-                        0x80: 0x20AC,
-                        0x82: 0x201A,
-                        0x83: 0x0192,
-                        0x84: 0x201E,
-                        0x85: 0x2026,
-                        0x86: 0x2020,
-                        0x87: 0x2021,
-                        0x88: 0x02C6,
-                        0x89: 0x2030,
-                        0x8A: 0x0160,
-                        0x8B: 0x2039,
-                        0x8C: 0x0152,
-                        0x8E: 0x017D,
-                        0x91: 0x2018,
-                        0x92: 0x2019,
-                        0x93: 0x201C,
-                        0x94: 0x201D,
-                        0x95: 0x2022,
-                        0x96: 0x2013,
-                        0x97: 0x2014,
-                        0x98: 0x02DC,
-                        0x99: 0x2122,
-                        0x9A: 0x0161,
-                        0x9B: 0x203A,
-                        0x9C: 0x0153,
-                        0x9E: 0x017E,
+                        0x80: 0x20AC, // €
+                        0x82: 0x201A, // ‚
+                        0x83: 0x0192, // ƒ
+                        0x84: 0x201E, // „
+                        0x85: 0x2026, // …
+                        0x86: 0x2020, // †
+                        0x87: 0x2021, // ‡
+                        0x88: 0x02C6, // ˆ
+                        0x89: 0x2030, // ‰
+                        0x8A: 0x0160, // Š
+                        0x8B: 0x2039, // ‹
+                        0x8C: 0x0152, // Œ
+                        0x8E: 0x017D, // Ž
+                        0x91: 0x2018, // '
+                        0x92: 0x2019, // '
+                        0x93: 0x201C, // "
+                        0x94: 0x201D, // "
+                        0x95: 0x2022, // •
+                        0x96: 0x2013, // –
+                        0x97: 0x2014, // —
+                        0x98: 0x02DC, // ˜
+                        0x99: 0x2122, // ™
+                        0x9A: 0x0161, // š
+                        0x9B: 0x203A, // ›
+                        0x9C: 0x0153, // œ
+                        0x9E: 0x017E, // ž
                         0x9F: 0x0178 // Ÿ
                     };
                     const unicodeCode = windows1252ToUnicode[code] || code;
@@ -557,7 +557,7 @@ const parseRtf = async (buffer, config) => {
                 tableId++;
                 const tableNode = {
                     type: 'table',
-                    text: ctx.rows.map(r => r.text).join('\n'),
+                    text: ctx.rows.map(r => r.text).join('\n'), // Aggregate text from rows
                     children: [...ctx.rows]
                 };
                 // If we have a parent table, add this table to the parent's current cell
@@ -1566,7 +1566,7 @@ const parseRtf = async (buffer, config) => {
             // RTF Limitation: No style map available (RTF uses inline styles)
             },
             content: content,
-            attachments: attachments,
+            attachments: attachments, // PNG and JPEG images extracted from \\pict groups
             toText: () => {
                 let text = content.map(c => c.text).join(config.newlineDelimiter ?? '\n');
                 if (config.putNotesAtLast && notes.length > 0) {

package/dist/parsers/WordParser.d.ts

@@ -58,7 +58,6 @@
  * @see https://www.ecma-international.org/publications-and-standards/standards/ecma-376/ OOXML Standard
  * @see https://learn.microsoft.com/en-us/openspecs/office_standards/ms-docx/ [MS-DOCX] Specification
  */
-/// <reference types="node" />
 import { OfficeParserAST, OfficeParserConfig } from '../types';
 /**
  * Parses a Word document (.docx) and extracts content, formatting, and metadata.

package/dist/types.d.ts

@@ -54,7 +54,7 @@ export interface OfficeParserConfig {
      * 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@5.4.530/build/pdf.worker.min.mjs`.
+     * If not provided, it defaults to `https://unpkg.com/pdfjs-dist@5.5.207/build/pdf.worker.min.mjs`.
      * You can override this with your own local path or a different CDN link.
      */
     pdfWorkerSrc?: string;

package/dist/utils/chartUtils.d.ts

@@ -1,4 +1,3 @@
-/// <reference types="node" />
 import { ChartData } from "../types";
 /**
  * Universal chart data extractor that selects logic based on XML content.

package/dist/utils/errorUtils.js

@@ -32,7 +32,7 @@ var OfficeErrorType;
     OfficeErrorType["INVALID_INPUT"] = "INVALID_INPUT";
     /** PDF worker source is missing (required in browser) */
     OfficeErrorType["PDF_WORKER_MISSING"] = "PDF_WORKER_MISSING";
-})(OfficeErrorType = exports.OfficeErrorType || (exports.OfficeErrorType = {}));
+})(OfficeErrorType || (exports.OfficeErrorType = OfficeErrorType = {}));
 /**
  * Lookup table for error messages.
  * Some entries are functions that take parameters to build dynamic messages.

package/dist/utils/imageUtils.d.ts

@@ -6,7 +6,6 @@
  *
  * @module imageUtils
  */
-/// <reference types="node" />
 import { OfficeAttachment } from '../types';
 /**
  * Converts a file extension to its corresponding MIME type.

package/dist/utils/imageUtils.js

@@ -123,10 +123,10 @@ const createAttachment = (name, content) => {
     }
     // Step 4: Create and return the attachment object
     return {
-        type: 'image',
-        mimeType: mime,
-        data: content.toString('base64'),
-        name: name,
+        type: 'image', // All attachments created here are images
+        mimeType: mime, // Cast to our supported MIME types
+        data: content.toString('base64'), // Convert buffer to Base64 string
+        name: name, // Original filename
         extension: ext // File extension for reference
     };
 };

package/dist/utils/moduleLoader.d.ts

@@ -0,0 +1,17 @@
+/**
+ * Module Loader Utility
+ *
+ * Centralizes dynamic imports for ESM-only packages (like file-type and pdfjs-dist)
+ * to maintain CommonJS compatibility while supporting modern ESM dependencies.
+ *
+ * This approach prevents TypeScript from transpiling dynamic import()
+ * into require() when targeting CommonJS.
+ */
+/**
+ * Specialized loader for file-type
+ */
+export declare function loadFileType(): Promise<typeof import('file-type')>;
+/**
+ * Specialized loader for pdfjs-dist
+ */
+export declare function loadPdfJs(): Promise<any>;

package/dist/utils/moduleLoader.js

@@ -0,0 +1,84 @@
+"use strict";
+/**
+ * Module Loader Utility
+ *
+ * Centralizes dynamic imports for ESM-only packages (like file-type and pdfjs-dist)
+ * to maintain CommonJS compatibility while supporting modern ESM dependencies.
+ *
+ * This approach prevents TypeScript from transpiling dynamic import()
+ * into require() when targeting CommonJS.
+ */
+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.loadFileType = loadFileType;
+exports.loadPdfJs = loadPdfJs;
+/**
+ * Dynamically loads an ESM module in a Node.js CJS context.
+ *
+ * @param specifier - The module specifier to load
+ * @returns The loaded module
+ */
+async function loadNodeEsmModule(specifier) {
+    // We use 'new Function' to bypass static analysis of tsc and some bundlers.
+    // This ensures that Node.js sees a real 'import()' at runtime, even in a CJS file.
+    return new Function('s', 'return import(s)')(specifier);
+}
+/**
+ * Specialized loader for file-type
+ */
+async function loadFileType() {
+    if (typeof window === 'undefined') {
+        // Node.js path
+        return loadNodeEsmModule('file-type');
+    }
+    // Browser path: esbuild handles standard dynamic import()
+    return Promise.resolve().then(() => __importStar(require('file-type')));
+}
+/**
+ * Specialized loader for pdfjs-dist
+ */
+async function loadPdfJs() {
+    if (typeof window === 'undefined') {
+        // Node.js environment: require legacy build for stability with ESM-only main
+        try {
+            return await loadNodeEsmModule('pdfjs-dist/legacy/build/pdf.mjs');
+        }
+        catch {
+            return await loadNodeEsmModule('pdfjs-dist');
+        }
+    }
+    // Browser environment: esbuild handles standard static-looking dynamic import()
+    return Promise.resolve().then(() => __importStar(require('pdfjs-dist')));
+}

package/dist/utils/ocrUtils.d.ts

@@ -6,7 +6,6 @@
  *
  * @module ocrUtils
  */
-/// <reference types="node" />
 /**
  * Performs Optical Character Recognition (OCR) on an image to extract text.
  *

package/dist/utils/zipUtils.d.ts

@@ -13,7 +13,6 @@
  *
  * @module zipUtils
  */
-/// <reference types="node" />
 /**
  * Represents a file extracted from a ZIP archive.
  * Contains the file's path within the archive and its content as a Buffer.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "officeparser",
-  "version": "6.0.3",
+  "version": "6.0.6",
   "description": "A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -12,9 +12,10 @@
     "dist"
   ],
   "scripts": {
-    "build": "tsc && node build_browser.js && npm run sync:docs",
+    "build": "npm run sync:versions && npm run build:node && npm run build:browser",
     "build:node": "tsc",
     "build:browser": "node build_browser.js && npm run sync:docs",
+    "sync:versions": "node scripts/sync-pdfjs-versions.js",
     "sync:docs": "mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/",
     "test": "npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts",
     "test:clean": "rm -rf test/results",
@@ -26,7 +27,9 @@
     "type": "git",
     "url": "git+https://github.com/harshankur/officeParser.git"
   },
-  "bin": "dist/index.js",
+  "bin": {
+    "officeparser": "dist/index.js"
+  },
   "keywords": [
     "office",
     "docx",
@@ -64,24 +67,24 @@
   "bugs": {
     "url": "https://github.com/harshankur/officeParser/issues"
   },
-  "homepage": "https://github.com/harshankur/officeParser#readme",
+  "homepage": "https://harshankur.github.io/officeParser/",
   "dependencies": {
-    "@xmldom/xmldom": "^0.8.10",
+    "@xmldom/xmldom": "^0.8.11",
     "concat-stream": "^2.0.0",
-    "file-type": "^16.5.4",
-    "pdfjs-dist": "5.4.530",
-    "tesseract.js": "^6.0.0",
-    "yauzl": "^3.1.3"
+    "file-type": "^19.6.0",
+    "pdfjs-dist": "^5.5.207",
+    "tesseract.js": "^7.0.0",
+    "yauzl": "^3.2.1"
   },
   "devDependencies": {
     "@types/concat-stream": "^2.0.3",
-    "@types/node": "^18.16.1",
-    "@types/xmldom": "^0.1.33",
+    "@types/node": "^22.13.10",
+    "@types/xmldom": "^0.1.34",
     "@types/yauzl": "^2.10.3",
-    "esbuild": "^0.27.0",
+    "esbuild": "^0.27.4",
     "esbuild-plugin-polyfill-node": "^0.3.0",
     "husky": "^9.1.7",
     "tsx": "^4.21.0",
-    "typescript": "^5.0.3"
+    "typescript": "^5.9.3"
   }
 }