officeparser 6.0.7 → 6.1.1

package/dist/utils/zipUtils.js

@@ -14,13 +14,9 @@
  *
  * @module zipUtils
  */
-var __importDefault = (this && this.__importDefault) || function (mod) {
-    return (mod && mod.__esModule) ? mod : { "default": mod };
-};
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.extractFiles = void 0;
-const yauzl_1 = __importDefault(require("yauzl"));
-const concat_stream_1 = __importDefault(require("concat-stream"));
+const fflate_1 = require("fflate");
 /**
  * Extracts files from a ZIP archive with optional filtering.
  *
@@ -62,50 +58,13 @@ const concat_stream_1 = __importDefault(require("concat-stream"));
  */
 const extractFiles = (zipInput, filterFn) => {
     return new Promise((resolve, reject) => {
-        // Step 1: Open the ZIP archive from the buffer
-        // lazyEntries: true means we manually control when to read each entry (better memory usage)
-        yauzl_1.default.fromBuffer(zipInput, { lazyEntries: true }, (err, zipfile) => {
+        (0, fflate_1.unzip)(new Uint8Array(zipInput.buffer, zipInput.byteOffset, zipInput.byteLength), { filter: (file) => filterFn(file.name) }, (err, decompressed) => {
             if (err)
                 return reject(err);
-            if (!zipfile)
-                return reject(new Error("Failed to open zip file"));
-            // Array to collect all extracted files
-            const extractedFiles = [];
-            // Step 2: Start reading the first entry
-            // This triggers the 'entry' event
-            zipfile.readEntry();
-            // Step 3: Handle each entry (file or directory) in the ZIP
-            zipfile.on('entry', (entry) => {
-                // Step 3a: Check if this file should be extracted using the filter function
-                if (filterFn(entry.fileName)) {
-                    // Step 3b: Open a read stream for this entry
-                    zipfile.openReadStream(entry, (err, readStream) => {
-                        if (err)
-                            return reject(err);
-                        if (!readStream)
-                            return reject(new Error("Failed to open read stream"));
-                        // Step 3c: Pipe the stream through concat to collect all data into a single Buffer
-                        // This is necessary because streams deliver data in chunks
-                        readStream.pipe((0, concat_stream_1.default)((data) => {
-                            // Step 3d: Add the extracted file to our results
-                            extractedFiles.push({
-                                path: entry.fileName,
-                                content: data
-                            });
-                            // Step 3e: Continue to the next entry
-                            zipfile.readEntry();
-                        }));
-                    });
-                }
-                else {
-                    // Step 3f: Skip this entry and move to the next one
-                    zipfile.readEntry();
-                }
-            });
-            // Step 4: All entries have been processed
-            zipfile.on('end', () => resolve(extractedFiles));
-            // Step 5: Handle any errors during extraction
-            zipfile.on('error', reject);
+            resolve(Object.entries(decompressed).map(([path, data]) => ({
+                path,
+                content: Buffer.from(data)
+            })));
         });
     });
 };

package/package.json

@@ -1,9 +1,20 @@
 {
   "name": "officeparser",
-  "version": "6.0.7",
+  "version": "6.1.1",
   "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.",
+  "funding": "https://github.com/sponsors/harshankur",
   "main": "dist/index.js",
+  "module": "dist/index.mjs",
   "types": "dist/index.d.ts",
+  "browser": "./dist/officeparser.browser.mjs",
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "browser": "./dist/officeparser.browser.mjs",
+      "import": "./dist/index.mjs",
+      "require": "./dist/index.js"
+    }
+  },
   "sideEffects": false,
   "engines": {
     "node": ">=18.0.0"
@@ -12,15 +23,21 @@
     "dist"
   ],
   "scripts": {
-    "build": "npm run sync:versions && npm run build:node && npm run build:browser:types && npm run build:browser",
+    "build": "npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser",
     "build:node": "tsc",
+    "build:esm-wrapper": "node scripts/generate-esm-wrapper.js",
     "build:browser:types": "dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts",
     "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",
+    "sync:docs": "mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/",
+    "test": "npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser",
+    "test:baseline": "npm run test baseline",
+    "test:parser": "npx tsx test/testOfficeParser.ts",
+    "test:artifacts": "npx tsx test/testShippingArtifacts.ts",
+    "test:license": "npm run sbom && node scripts/validate-licenses.js",
     "test:clean": "rm -rf test/results",
     "clean": "rm -rf dist && npm run test:clean",
+    "sbom": "npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev",
     "prepublishOnly": "npm run build",
     "prepare": "husky"
   },
@@ -29,7 +46,7 @@
     "url": "git+https://github.com/harshankur/officeParser.git"
   },
   "bin": {
-    "officeparser": "dist/index.js"
+    "officeparser": "dist/cli.js"
   },
   "publishConfig": {
     "access": "public",
@@ -74,22 +91,20 @@
   },
   "homepage": "https://officeparser.harshankur.com",
   "dependencies": {
-    "@xmldom/xmldom": "^0.8.11",
-    "concat-stream": "^2.0.0",
-    "file-type": "^21.3.4",
-    "pdfjs-dist": "^5.5.207",
-    "tesseract.js": "^7.0.0",
-    "yauzl": "^3.2.1"
+    "@xmldom/xmldom": "^0.9.10",
+    "fflate": "^0.8.2",
+    "file-type": "^22.0.1",
+    "pdfjs-dist": "5.6.205",
+    "tesseract.js": "^7.0.0"
   },
   "devDependencies": {
-    "@types/concat-stream": "^2.0.3",
-    "@types/node": "^22.15.5",
-    "@types/xmldom": "^0.1.34",
-    "@types/yauzl": "^2.10.3",
+    "@types/node": "^25.5.0",
+    "buffer": "^6.0.3",
     "dts-bundle-generator": "^9.5.1",
     "esbuild": "^0.27.4",
-    "esbuild-plugin-polyfill-node": "^0.3.0",
+    "esbuild-plugins-node-modules-polyfill": "^1.8.1",
     "husky": "^9.1.7",
+    "process": "^0.11.10",
     "tsx": "^4.21.0",
     "typescript": "^6.0.2"
   }