build(deps): bump embedpdf-snippet from 2.3.0 to 2.9.1

.github/workflows/update-embedpdf-snippet.yml

@@ -55,7 +55,7 @@ jobs:
 
       - name: Clone upstream embed-pdf-viewer
         if: steps.gate.outputs.run == 'true'
-        run: git clone --depth 1 --branch main https://github.com/alam00000/bentopdf-embed-pdf-viewer ./_upstream/embed-pdf-viewer
+        run: git clone --depth 1 --branch main https://github.com/embedpdf/embed-pdf-viewer ./_upstream/embed-pdf-viewer
 
       - name: Setup Node
         if: steps.gate.outputs.run == 'true'

src/js/logic/ocr-pdf-page.ts

@@ -121,9 +121,6 @@ async function runOCR() {
   );
   const binarize = (document.getElementById('ocr-binarize') as HTMLInputElement)
     .checked;
-  const embedFullFonts = (
-    document.getElementById('ocr-embed-full-fonts') as HTMLInputElement
-  ).checked;
   const whitelist = (
     document.getElementById('ocr-whitelist') as HTMLInputElement
   ).value;
@@ -157,7 +154,6 @@ async function runOCR() {
       resolution: scale,
       binarize,
       whitelist,
-      embedFullFonts,
       onProgress: updateProgress,
     });
 

src/js/utils/ocr.ts

@@ -16,7 +16,6 @@ export interface OcrOptions {
   resolution: number;
   binarize: boolean;
   whitelist: string;
-  embedFullFonts?: boolean;
   onProgress?: (status: string, progress: number) => void;
 }
 
@@ -132,14 +131,7 @@ export async function performOcr(
   pdfBytes: Uint8Array | ArrayBuffer,
   options: OcrOptions
 ): Promise<OcrResult> {
-  const {
-    language,
-    resolution,
-    binarize,
-    whitelist,
-    embedFullFonts,
-    onProgress,
-  } = options;
+  const { language, resolution, binarize, whitelist, onProgress } = options;
   const progress = onProgress || (() => {});
 
   const worker = await createConfiguredTesseractWorker(
@@ -206,16 +198,14 @@ export async function performOcr(
         getFontForLanguage('eng'),
       ]);
       primaryFont = await newPdfDoc.embedFont(scriptFontBytes, {
-        subset: !embedFullFonts,
+        subset: false,
       });
       latinFont = await newPdfDoc.embedFont(latinFontBytes, {
-        subset: !embedFullFonts,
+        subset: false,
       });
     } else {
       const fontBytes = await getFontForLanguage(primaryLang);
-      primaryFont = await newPdfDoc.embedFont(fontBytes, {
-        subset: !embedFullFonts,
-      });
+      primaryFont = await newPdfDoc.embedFont(fontBytes, { subset: false });
       latinFont = primaryFont;
     }
   } catch (e) {

src/pages/ocr-pdf.html

@@ -259,16 +259,6 @@
                 />
                 Binarize Image (Enhance Contrast for Clean Scans)
               </label>
-              <label
-                class="flex items-center gap-2 text-sm text-gray-300 cursor-pointer"
-              >
-                <input
-                  type="checkbox"
-                  id="ocr-embed-full-fonts"
-                  class="w-4 h-4 rounded text-indigo-600 bg-gray-700 border-gray-600"
-                />
-                Embed Full Fonts (Larger file, better compatibility)
-              </label>
               <!-- Whitelist Presets -->
               <div>
                 <label