Move the EXIF-block replacement into JpegStream (PR 19356 follow-up)

Currently we modify the EXIF-block in place, which may end up "breaking" the JPEG-data of the original PDF document since e.g. saving it from the viewer no longer contains the real EXIF-block.
Hence the EXIF-block replacement is moved into the `JpegStream` class, such that we can copy the data before doing the replacement.

src/core/jpeg_stream.js

@@ -163,10 +163,23 @@ class JpegStream extends DecodeStream {
       if (!bytes) {
         return null;
       }
-      const data = this.#skipUselessBytes(bytes);
-      if (!JpegImage.canUseImageDecoder(data, jpegOptions.colorTransform)) {
+      let data = this.#skipUselessBytes(bytes);
+      const useImageDecoder = JpegImage.canUseImageDecoder(
+        data,
+        jpegOptions.colorTransform
+      );
+      if (!useImageDecoder) {
         return null;
       }
+      if (useImageDecoder.exifStart) {
+        // Replace the entire EXIF-block with dummy data, to ensure that a
+        // non-default EXIF orientation won't cause the image to be rotated
+        // when using `ImageDecoder` (fixes bug1942064.pdf).
+        //
+        // Copy the data first, to avoid modifying the original PDF document.
+        data = data.slice();
+        data.fill(0x00, useImageDecoder.exifStart, useImageDecoder.exifEnd);
+      }
       decoder = new ImageDecoder({
         data,
         type: "image/jpeg",

src/core/jpg.js

@@ -782,8 +782,11 @@ function readDataBlock(data, offset) {
   }
 
   const array = data.subarray(offset, endOffset);
-  offset += array.length;
-  return { appData: array, newOffset: offset };
+  return {
+    appData: array,
+    oldOffset: offset,
+    newOffset: offset + array.length,
+  };
 }
 
 function skipData(data, offset) {
@@ -805,6 +808,7 @@ class JpegImage {
   }
 
   static canUseImageDecoder(data, colorTransform = -1) {
+    let exifOffsets = null;
     let offset = 0;
     let numComponents = null;
     let fileMarker = readUint16(data, offset);
@@ -820,7 +824,7 @@ class JpegImage {
         case 0xffe1: // APP1 - Exif
           // TODO: Remove this once https://github.com/w3c/webcodecs/issues/870
           //       is fixed.
-          const { appData, newOffset } = readDataBlock(data, offset);
+          const { appData, oldOffset, newOffset } = readDataBlock(data, offset);
           offset = newOffset;
 
           // 'Exif\x00\x00'
@@ -832,10 +836,12 @@ class JpegImage {
             appData[4] === 0 &&
             appData[5] === 0
           ) {
-            // Replace the entire EXIF-block with dummy data, to ensure that a
-            // non-default EXIF orientation won't cause the image to be rotated
-            // when using `ImageDecoder` (fixes bug1942064.pdf).
-            appData.fill(0x00, 6);
+            if (exifOffsets) {
+              throw new JpegError("Duplicate EXIF-blocks found.");
+            }
+            // Don't do the EXIF-block replacement here, see `JpegStream`,
+            // since that can modify the original PDF document.
+            exifOffsets = { exifStart: oldOffset + 6, exifEnd: newOffset };
           }
           fileMarker = readUint16(data, offset);
           offset += 2;
@@ -861,12 +867,12 @@ class JpegImage {
       offset += 2;
     }
     if (numComponents === 4) {
-      return false;
+      return null;
     }
     if (numComponents === 3 && colorTransform === 0) {
-      return false;
+      return null;
     }
-    return true;
+    return exifOffsets || {};
   }
 
   parse(data, { dnlScanLines = null } = {}) {

test/unit/api_spec.js

@@ -2235,6 +2235,29 @@ describe("api", function () {
       expect(data.length).toEqual(basicApiFileLength);
     });
 
+    it("gets data from PDF document with JPEG image containing EXIF-data (bug 1942064)", async function () {
+      const typedArrayPdf = await DefaultFileReaderFactory.fetch({
+        path: TEST_PDFS_PATH + "bug1942064.pdf",
+      });
+
+      // Sanity check to make sure that we fetched the entire PDF file.
+      expect(typedArrayPdf instanceof Uint8Array).toEqual(true);
+      expect(typedArrayPdf.length).toEqual(10719);
+
+      const loadingTask = getDocument(typedArrayPdf.slice());
+      const pdfDoc = await loadingTask.promise;
+      const page = await pdfDoc.getPage(1);
+      // Trigger parsing of the JPEG image.
+      await page.getOperatorList();
+
+      const data = await pdfDoc.getData();
+      expect(data instanceof Uint8Array).toEqual(true);
+      // Ensure that the EXIF-block wasn't modified.
+      expect(typedArrayPdf).toEqual(data);
+
+      await loadingTask.destroy();
+    });
+
     it("gets download info", async function () {
       const downloadInfo = await pdfDocument.getDownloadInfo();
       expect(downloadInfo).toEqual({ length: basicApiFileLength });