From 388f2ee19584ad171027a9e6d8d523feb8a1a54f Mon Sep 17 00:00:00 2001
From: Sumit-5002 <173078713+Sumit-5002@users.noreply.github.com>
Date: Sat, 28 Mar 2026 06:24:06 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20Bolt:=20Parallelized=20PDF=20to=20J?=
 =?UTF-8?q?PG=20conversion=20with=20Blob=20optimization?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Refactored the `pdfToJpg` service to use chunked parallel rendering (concurrency of 4) and replaced `canvas.toDataURL()` with `canvas.toBlob()`.

Improvements:
- Reduces total conversion time for multi-page PDFs by processing pages in parallel chunks.
- Eliminates CPU and memory overhead of Base64 encoding by using binary Blobs directly with JSZip.
- Maintains accurate progress reporting during concurrent processing.
---
 .jules/bolt.md                        |  4 +++
 src/services/pdf/pdfImageConverter.js | 49 +++++++++++++++++++++------
 2 files changed, 43 insertions(+), 10 deletions(-)

diff --git a/.jules/bolt.md b/.jules/bolt.md
index b732f64..05d9d3c 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -25,3 +25,7 @@
 ## 2026-03-26 - Optimized Line Number Rendering in TextToolRunner
 **Learning:** Rendering line numbers by mapping over an array of indices to create individual `div` elements (e.g., `{lines.map((_, i) => <div key={i}>{i+1}</div>)}`) creates O(N) DOM nodes. This becomes a significant performance bottleneck for large text files, increasing memory usage and React reconciliation time. Using a single `div` with `white-space: pre` and a newline-separated string reduces DOM nodes to O(1) per editor.
 **Action:** Always prefer a single pre-formatted string for line numbers or similar repeating indicators instead of individual DOM nodes per line to ensure consistent performance with large inputs.
+
+## 2026-03-28 - Parallelized and Blob-Optimized PDF to JPG Conversion
+**Learning:** Sequential page rendering in `pdfToJpg` creates a linear bottleneck for large PDFs. Furthermore, using `canvas.toDataURL()` incurs significant overhead due to Base64 encoding/decoding, which is unnecessary since `JSZip` can handle Blobs directly.
+**Action:** Implement chunked parallel rendering (concurrency of 4) for PDF pages and switch from `toDataURL()` to `toBlob()` to minimize CPU and memory usage during batch image extraction.
diff --git a/src/services/pdf/pdfImageConverter.js b/src/services/pdf/pdfImageConverter.js
index 6fe8add..8b08ea9 100644
--- a/src/services/pdf/pdfImageConverter.js
+++ b/src/services/pdf/pdfImageConverter.js
@@ -15,20 +15,49 @@ export const imagesToPDF = async (files, onProgress) => {
     return pdf.save();
 };
 
+/**
+ * Converts a PDF into individual JPG images and downloads them as a ZIP file.
+ * Optimized with chunked parallel rendering and Blob usage (Bolt ⚡).
+ */
 export const pdfToJpg = async (file, onProgress) => {
     const pdf = await pdfjs.getDocument({ data: await file.arrayBuffer() }).promise;
     const zip = new JSZip();
-    for (let i = 1; i <= pdf.numPages; i++) {
-        if (onProgress) onProgress((i / pdf.numPages) * 100);
-        const page = await pdf.getPage(i);
-        const viewport = page.getViewport({ scale: 2.0 });
-        const canvas = document.createElement('canvas');
-        canvas.width = viewport.width; canvas.height = viewport.height;
-        await page.render({ canvasContext: canvas.getContext('2d'), viewport }).promise;
-        const b64 = canvas.toDataURL('image/jpeg', 0.9).split(',')[1];
-        zip.file(`page_${i}.jpg`, b64, { base64: true });
+    const numPages = pdf.numPages;
+    const CHUNK_SIZE = 4;
+
+    for (let i = 1; i <= numPages; i += CHUNK_SIZE) {
+        const chunk = [];
+        for (let j = i; j < i + CHUNK_SIZE && j <= numPages; j++) {
+            chunk.push(j);
+        }
+
+        // Render pages in parallel chunks to optimize performance while controlling memory usage
+        await Promise.all(chunk.map(async (pageNum) => {
+            const page = await pdf.getPage(pageNum);
+            const viewport = page.getViewport({ scale: 2.0 });
+            const canvas = document.createElement('canvas');
+            const context = canvas.getContext('2d');
+            canvas.width = viewport.width;
+            canvas.height = viewport.height;
+
+            await page.render({ canvasContext: context, viewport }).promise;
+
+            // Use toBlob instead of toDataURL to avoid Base64 encoding overhead (Bolt ⚡)
+            return new Promise((resolve) => {
+                canvas.toBlob((blob) => {
+                    zip.file(`page_${pageNum}.jpg`, blob);
+                    resolve();
+                }, 'image/jpeg', 0.9);
+            });
+        }));
+
+        if (onProgress) {
+            const completed = Math.min(i + CHUNK_SIZE - 1, numPages);
+            onProgress((completed / numPages) * 100);
+        }
     }
-    if (onProgress) onProgress(95); // Zipping takes a bit
+
+    if (onProgress) onProgress(95); // Zipping phase
     const blob = await zip.generateAsync({ type: 'blob' });
     if (onProgress) onProgress(100);
     downloadBlob(blob, file.name.replace('.pdf', '_images.zip'));