unpdf 0.8.0 → 0.10.0

package/README.md

@@ -9,7 +9,7 @@ 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
@@ -55,40 +55,20 @@ const pdf = await getDocumentProxy(new Uint8Array(pdf));
 const { totalPages, text } = await extractText(pdf, { mergePages: true });
 ```
 
-### Use Legacy Or Custom PDF.js Build
+### Access the PDF.js API
 
-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.
+This will return the resolved PDF.js module and gives full access to the PDF.js API, like:
 
-```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"),
-});
-
-// Now, you can use the other methods
-// …
-```
+- `getDocument`
+- `version`
+- … and all other methods
 
-### Access the PDF.js Module
-
-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;
 
@@ -102,18 +82,36 @@ 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 method, define the PDF.js module
+// if you need another PDF.js build
+import { configureUnPDF } from "unpdf";
+
+configureUnPDF({
+  // 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>;
 }
@@ -121,12 +119,12 @@ interface UnPDFConfiguration {
 
 ## Methods
 
-### `defineUnPDFConfig`
+### `configureUnPDF`
 
 Define a custom PDF.js module, like the legacy build. Make sure to call this method before using any other methods.
 
 ```ts
-function defineUnPDFConfig(config: UnPDFConfiguration): Promise<void>;
+function configureUnPDF(config: UnPDFConfiguration): Promise<void>;
 ```
 
 ### `getResolvedPDFJS`
@@ -175,9 +173,9 @@ In order to use this method, you have to meet the following requirements:
 **Example**
 
 ```ts
-import { defineUnPDFConfig, renderPageAsImage } from "unpdf";
+import { configureUnPDF, renderPageAsImage } from "unpdf";
 
-defineUnPDFConfig({
+configureUnPDF({
   // Use the official PDF.js build
   pdfjs: () => import("pdfjs-dist"),
 });

package/dist/index.cjs

@@ -8,6 +8,8 @@ async function getDocumentProxy(data, options = {}) {
   const pdf = await getDocument({
     data,
     isEvalSupported: false,
+    // See: https://github.com/mozilla/pdf.js/issues/4244#issuecomment-1479534301
+    useSystemFonts: true,
     ...options
   }).promise;
   return pdf;
@@ -25,6 +27,10 @@ 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 +40,8 @@ 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."
@@ -135,7 +142,8 @@ async function createIsomorphicCanvasFactory(canvas) {
         canvas2.width = width;
         canvas2.height = height;
         return canvas2;
-      } else if (isNode) {
+      }
+      if (isNode) {
         if (!_canvas) {
           throw new Error('Failed to resolve "canvas" package.');
         }
@@ -170,13 +178,14 @@ async function createIsomorphicCanvasFactory(canvas) {
   };
 }
 
-async function defineUnPDFConfig(options) {
+async function configureUnPDF(options) {
   const { pdfjs } = { ...options };
   if (pdfjs) {
     await resolvePDFJSImports(pdfjs, { force: true });
   }
 }
 
+const defineUnPDFConfig = configureUnPDF;
 const getMeta = async (...args) => {
   await resolvePDFJSImports();
   return await getMeta$1(...args);
@@ -185,7 +194,6 @@ const extractText = async (...args) => {
   await resolvePDFJSImports();
   return await extractText$1(...args);
 };
-const extractPDFText = extractText;
 const extractImages = async (...args) => {
   await resolvePDFJSImports();
   return await extractImages$1(...args);
@@ -195,9 +203,9 @@ const renderPageAsImage = async (...args) => {
   return await renderPageAsImage$1(...args);
 };
 
+exports.configureUnPDF = configureUnPDF;
 exports.defineUnPDFConfig = defineUnPDFConfig;
 exports.extractImages = extractImages;
-exports.extractPDFText = extractPDFText;
 exports.extractText = extractText;
 exports.getDocumentProxy = getDocumentProxy;
 exports.getMeta = getMeta;

package/dist/index.d.cts

@@ -26,24 +26,25 @@ 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>;
 }
 
-declare function defineUnPDFConfig(options: UnPDFConfiguration): Promise<void>;
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
 
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
  * Applies the following defaults:
  * - `isEvalSupported: false`
+ * - `useSystemFonts: true`
  */
 declare function getDocumentProxy(data: BinaryData, options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
@@ -51,11 +52,12 @@ declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force
     force?: boolean | undefined;
 }): Promise<void>;
 
+/** @deprecated Use `configureUnPDF` instead */
+declare const defineUnPDFConfig: typeof configureUnPDF;
+
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
-/** @deprecated Use `extractText` instead. */
-declare const extractPDFText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 
-export { defineUnPDFConfig, extractImages, extractPDFText, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };
+export { configureUnPDF, defineUnPDFConfig, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };

package/dist/index.d.mts

@@ -26,24 +26,25 @@ 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>;
 }
 
-declare function defineUnPDFConfig(options: UnPDFConfiguration): Promise<void>;
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
 
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
  * Applies the following defaults:
  * - `isEvalSupported: false`
+ * - `useSystemFonts: true`
  */
 declare function getDocumentProxy(data: BinaryData, options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
@@ -51,11 +52,12 @@ declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force
     force?: boolean | undefined;
 }): Promise<void>;
 
+/** @deprecated Use `configureUnPDF` instead */
+declare const defineUnPDFConfig: typeof configureUnPDF;
+
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
-/** @deprecated Use `extractText` instead. */
-declare const extractPDFText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 
-export { defineUnPDFConfig, extractImages, extractPDFText, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };
+export { configureUnPDF, defineUnPDFConfig, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };

package/dist/index.d.ts

@@ -26,24 +26,25 @@ 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>;
 }
 
-declare function defineUnPDFConfig(options: UnPDFConfiguration): Promise<void>;
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
 
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
  * Applies the following defaults:
  * - `isEvalSupported: false`
+ * - `useSystemFonts: true`
  */
 declare function getDocumentProxy(data: BinaryData, options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
@@ -51,11 +52,12 @@ declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force
     force?: boolean | undefined;
 }): Promise<void>;
 
+/** @deprecated Use `configureUnPDF` instead */
+declare const defineUnPDFConfig: typeof configureUnPDF;
+
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
-/** @deprecated Use `extractText` instead. */
-declare const extractPDFText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 
-export { defineUnPDFConfig, extractImages, extractPDFText, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };
+export { configureUnPDF, defineUnPDFConfig, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };

package/dist/index.mjs

@@ -6,6 +6,8 @@ async function getDocumentProxy(data, options = {}) {
   const pdf = await getDocument({
     data,
     isEvalSupported: false,
+    // See: https://github.com/mozilla/pdf.js/issues/4244#issuecomment-1479534301
+    useSystemFonts: true,
     ...options
   }).promise;
   return pdf;
@@ -23,6 +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 {
@@ -32,7 +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."
@@ -133,7 +140,8 @@ async function createIsomorphicCanvasFactory(canvas) {
         canvas2.width = width;
         canvas2.height = height;
         return canvas2;
-      } else if (isNode) {
+      }
+      if (isNode) {
         if (!_canvas) {
           throw new Error('Failed to resolve "canvas" package.');
         }
@@ -168,13 +176,14 @@ async function createIsomorphicCanvasFactory(canvas) {
   };
 }
 
-async function defineUnPDFConfig(options) {
+async function configureUnPDF(options) {
   const { pdfjs } = { ...options };
   if (pdfjs) {
     await resolvePDFJSImports(pdfjs, { force: true });
   }
 }
 
+const defineUnPDFConfig = configureUnPDF;
 const getMeta = async (...args) => {
   await resolvePDFJSImports();
   return await getMeta$1(...args);
@@ -183,7 +192,6 @@ const extractText = async (...args) => {
   await resolvePDFJSImports();
   return await extractText$1(...args);
 };
-const extractPDFText = extractText;
 const extractImages = async (...args) => {
   await resolvePDFJSImports();
   return await extractImages$1(...args);
@@ -193,4 +201,4 @@ const renderPageAsImage = async (...args) => {
   return await renderPageAsImage$1(...args);
 };
 
-export { defineUnPDFConfig, extractImages, extractPDFText, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };
+export { configureUnPDF, defineUnPDFConfig, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };

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 }