unpdf 0.7.1 → 0.9.0

package/README.md

@@ -9,11 +9,16 @@ This library is also intended as a modern alternative to the unmaintained but st
 ## Features
 
 - 🏗️ Works in Node.js, browser and workers
-- 🪭 Includes serverless build of PDF.js ([`unpdf/pdfjs`](./package.json#L45))
+- 🪭 Includes serverless build of PDF.js ([`unpdf/pdfjs`](./package.json#L34))
 - 💬 Extract text and images from PDFs
 - 🧱 Opt-in to legacy PDF.js build
 - 💨 Zero dependencies
 
+## PDF.js Compatibility
+
+> [!NOTE]
+> This package is currently using PDF.js v4.0.189.
+
 ## Installation
 
 Run the following command to add `unpdf` to your project.
@@ -50,40 +55,20 @@ const pdf = await getDocumentProxy(new Uint8Array(pdf));
 const { totalPages, text } = await extractText(pdf, { mergePages: true });
 ```
 
-### Use Legacy Or Custom PDF.js Build
-
-Generally, you don't need to worry about the PDF.js build. `unpdf` ships with a serverless build of the latest PDF.js version. However, if you want to use the official PDF.js version or the legacy build, you can define a custom PDF.js module.
-
-```ts
-// Before using any other methods, define the PDF.js module
-import { defineUnPDFConfig } from "unpdf";
-
-defineUnPDFConfig({
-  // Use the legacy build
-  pdfjs: () => import("pdfjs-dist/legacy/build/pdf.js"),
-});
+### Access the PDF.js API
 
-// Now, you can use the other methods
-// …
-```
+This will return the resolved PDF.js module and gives full access to the PDF.js API, like:
 
-### Access the PDF.js Module
+- `getDocument`
+- `version`
+- … and all other methods
 
-This will return the resolved PDF.js module. If no build is defined, the serverless build bundled with `unpdf` will be initialized.
+Especially useful for platforms like 🦕 Deno or if you want to use the PDF.js API directly. If no custom build was defined beforehand, the serverless build bundled with `unpdf` will be initialized.
 
 ```ts
 import { getResolvedPDFJS } from "unpdf";
 
-const { version } = await getResolvedPDFJS();
-```
-
-### Use Serverless PDF.js Build In 🦕 Deno
-
-Instead of using the methods provided by `unpdf`, you can directly import the serverless PDF.js build in Deno. This is useful if you want to use the PDF.js API directly.
-
-```ts
-import { getDocument } from "https://esm.sh/unpdf/pdfjs";
-
+const { getDocument } = await getResolvedPDFJS();
 const data = Deno.readFileSync("dummy.pdf");
 const doc = await getDocument(data).promise;
 
@@ -97,18 +82,35 @@ for (let i = 1; i <= doc.numPages; i++) {
 }
 ```
 
+### Use Official or Legacy PDF.js Build
+
+Generally speaking, you don't need to worry about the PDF.js build. `unpdf` ships with a serverless build of the latest PDF.js version. However, if you want to use the official PDF.js version or the legacy build, you can define a custom PDF.js module.
+
+```ts
+// Before using any other methods, define the PDF.js module
+import { defineUnPDFConfig } from "unpdf";
+
+defineUnPDFConfig({
+  // Use the official PDF.js build (make sure to install it first)
+  pdfjs: () => import("pdfjs-dist"),
+});
+
+// Now, you can use the other methods
+// …
+```
+
 ## Config
 
 ```ts
 interface UnPDFConfiguration {
   /**
-   * By default, UnPDF will use the latest version of PDF.js. If you want to
-   * use an older version or the legacy build, set a promise that resolves to
-   * the PDF.js module.
+   * By default, UnPDF will use the latest version of PDF.js compiled for
+   * serverless environments. If you want to use a different version, you can
+   * provide a custom resolver function.
    *
    * @example
-   * // Use the legacy build
-   * () => import('pdfjs-dist/legacy/build/pdf.js')
+   * // Use the official PDF.js build (make sure to install it first)
+   * () => import('pdfjs-dist')
    */
   pdfjs?: () => Promise<PDFJS>;
 }
@@ -194,31 +196,22 @@ declare function renderPageAsImage(
   data: BinaryData | PDFDocumentProxy,
   pageNumber: number,
   options?: {
-    canvas?: () => Promise<typeof "canvas">;
+    canvas?: () => Promise<typeof import("canvas")>;
     /** @default 1 */
-    scale?: number
+    scale?: number;
     width?: number;
     height?: number;
   },
 ): Promise<ArrayBuffer>;
 ```
 
-### `extractImages`
-
-```ts
-function extractImages(
-  data: BinaryData | PDFDocumentProxy,
-  pageNumber: number,
-): Promise<Uint8ClampedArray[]>;
-```
-
 ## FAQ
 
-### Why Is `canvas` A Peer Dependency?
+### Why Is `canvas` An Optional Dependency?
 
 The official PDF.js library depends on the `canvas` module for Node.js environments, which [doesn't work inside worker threads](https://github.com/Automattic/node-canvas/issues/1394). That's why `unpdf` ships with a serverless build of PDF.js that mocks the `canvas` module.
 
-However, to render PDF pages as images, you need to install the `canvas` module in Node.js environments. That's why `canvas` is a peer dependency.
+However, to render PDF pages as images in Node.js environments, you need to install the `canvas` module. That's why it is a peer dependency.
 
 ## License
 

package/dist/index.cjs

@@ -25,6 +25,10 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
   if (pdfjsResolver) {
     try {
       const _import = await pdfjsResolver();
+      if ("resolvePDFJS" in _import) {
+        resolvedModule = await _import.resolvePDFJS();
+        return;
+      }
       resolvedModule = _import.default || _import;
       return;
     } catch {
@@ -34,7 +38,8 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
     }
   }
   try {
-    resolvedModule = await import('unpdf/pdfjs');
+    const { resolvePDFJS } = await import('unpdf/pdfjs');
+    resolvedModule = await resolvePDFJS();
   } catch {
     throw new Error(
       "PDF.js is not available. Please add the package as a dependency."

package/dist/index.d.cts

@@ -26,13 +26,13 @@ declare function renderPageAsImage$1(data: BinaryData | PDFDocumentProxy, pageNu
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
-     * By default, UnPDF will use the latest version of PDF.js. If you want to
-     * use an older version or the legacy build, set a promise that resolves to
-     * the PDF.js module.
+     * By default, UnPDF will use the latest version of PDF.js compiled for
+     * serverless environments. If you want to use a different version, you can
+     * provide a custom resolver function.
      *
      * @example
-     * // Use the legacy build
-     * () => import('pdfjs-dist/legacy/build/pdf.js')
+     * // Use the official PDF.js build (make sure to install it first)
+     * () => import('pdfjs-dist')
      */
     pdfjs?: () => Promise<any>;
 }

package/dist/index.d.mts

@@ -26,13 +26,13 @@ declare function renderPageAsImage$1(data: BinaryData | PDFDocumentProxy, pageNu
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
-     * By default, UnPDF will use the latest version of PDF.js. If you want to
-     * use an older version or the legacy build, set a promise that resolves to
-     * the PDF.js module.
+     * By default, UnPDF will use the latest version of PDF.js compiled for
+     * serverless environments. If you want to use a different version, you can
+     * provide a custom resolver function.
      *
      * @example
-     * // Use the legacy build
-     * () => import('pdfjs-dist/legacy/build/pdf.js')
+     * // Use the official PDF.js build (make sure to install it first)
+     * () => import('pdfjs-dist')
      */
     pdfjs?: () => Promise<any>;
 }

package/dist/index.d.ts

@@ -26,13 +26,13 @@ declare function renderPageAsImage$1(data: BinaryData | PDFDocumentProxy, pageNu
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
-     * By default, UnPDF will use the latest version of PDF.js. If you want to
-     * use an older version or the legacy build, set a promise that resolves to
-     * the PDF.js module.
+     * By default, UnPDF will use the latest version of PDF.js compiled for
+     * serverless environments. If you want to use a different version, you can
+     * provide a custom resolver function.
      *
      * @example
-     * // Use the legacy build
-     * () => import('pdfjs-dist/legacy/build/pdf.js')
+     * // Use the official PDF.js build (make sure to install it first)
+     * () => import('pdfjs-dist')
      */
     pdfjs?: () => Promise<any>;
 }

package/dist/index.mjs

@@ -23,6 +23,10 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
   if (pdfjsResolver) {
     try {
       const _import = await pdfjsResolver();
+      if ("resolvePDFJS" in _import) {
+        resolvedModule = await _import.resolvePDFJS();
+        return;
+      }
       resolvedModule = _import.default || _import;
       return;
     } catch {
@@ -32,7 +36,8 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
     }
   }
   try {
-    resolvedModule = await import('unpdf/pdfjs');
+    const { resolvePDFJS } = await import('unpdf/pdfjs');
+    resolvedModule = await resolvePDFJS();
   } catch {
     throw new Error(
       "PDF.js is not available. Please add the package as a dependency."

package/dist/pdfjs.d.mts

@@ -1 +1,3 @@
-export * from './types/src/pdf.d.ts'
+import * as PDFJS from './types/src/pdf'
+declare function resolvePDFJS(): Promise<typeof PDFJS>
+export { resolvePDFJS }

package/dist/pdfjs.d.ts

@@ -1 +1,3 @@
-export * from './types/src/pdf.d.ts'
+import * as PDFJS from './types/src/pdf'
+declare function resolvePDFJS(): Promise<typeof PDFJS>
+export { resolvePDFJS }