JpegMotionPhotoExtractor: Don't emit an image track with no metadata

The current implementation of `JpegMotionPhotoExtractor.sniff` returns
`true` for any image with Exif data (not just motion photos). Improving
this is tracked by b/324033919. In the meantime, when we 'extract' a
non-motion photo with `JpegMotionPhotoExtractor`, the result is
currently a single empty image track and no video track (since there's
no video, since this isn't a motion photo). This 'empty' image track
is usually used to transmit metadata about the video parts of the
image file (in the form of `MotionPhotoMetadata`), but this metadata is
also (understandably) absent for non-motion photos. Therefore there's
no need to emit this image track at all, and it's clearer to emit no
tracks at all when extracting a non-motion photo using
`JpegMotionPhotoExtractor`.

This change also removes a `TODO` that is misplaced, since there's no
image bytes being emitted here (and never was).

PiperOrigin-RevId: 604688053
(cherry picked from commit 7ae3d69e001d0a138f3ebe406b050bc06bd24724)

libraries/extractor/src/main/java/androidx/media3/extractor/jpeg/JpegMotionPhotoExtractor.java

@@ -202,7 +202,7 @@ import org.checkerframework.checker.nullness.qual.MonotonicNonNull;
       if (mp4StartPosition != C.INDEX_UNSET) {
         state = STATE_SNIFFING_MOTION_PHOTO_VIDEO;
       } else {
-        endReadingWithImageTrack();
+        endReading();
       }
     } else if ((marker < 0xFFD0 || marker > 0xFFD9) && marker != 0xFF01) {
       state = STATE_READING_SEGMENT_LENGTH;
@@ -242,7 +242,7 @@ import org.checkerframework.checker.nullness.qual.MonotonicNonNull;
         input.peekFully(
             scratch.getData(), /* offset= */ 0, /* length= */ 1, /* allowEndOfInput= */ true);
     if (!peekedData) {
-      endReadingWithImageTrack();
+      endReading();
     } else {
       input.resetPeekPosition();
       if (mp4Extractor == null) {
@@ -257,7 +257,7 @@ import org.checkerframework.checker.nullness.qual.MonotonicNonNull;
             new StartOffsetExtractorOutput(mp4StartPosition, checkNotNull(extractorOutput)));
         startReadingMotionPhoto();
       } else {
-        endReadingWithImageTrack();
+        endReading();
       }
     }
   }
@@ -267,21 +267,19 @@ import org.checkerframework.checker.nullness.qual.MonotonicNonNull;
     state = STATE_READING_MOTION_PHOTO_VIDEO;
   }
 
-  private void endReadingWithImageTrack() {
+  private void endReading() {
-    outputImageTrack();
     checkNotNull(extractorOutput).endTracks();
     extractorOutput.seekMap(new SeekMap.Unseekable(/* durationUs= */ C.TIME_UNSET));
     state = STATE_ENDED;
   }
 
-  private void outputImageTrack(Metadata.Entry... metadataEntries) {
+  private void outputImageTrack(MotionPhotoMetadata motionPhotoMetadata) {
     TrackOutput imageTrackOutput =
         checkNotNull(extractorOutput).track(IMAGE_TRACK_ID, C.TRACK_TYPE_IMAGE);
-    // TODO(b/289989902): Set the rotationDegrees in format so images can be decoded correctly.
     imageTrackOutput.format(
         new Format.Builder()
             .setContainerMimeType(MimeTypes.IMAGE_JPEG)
-            .setMetadata(new Metadata(metadataEntries))
+            .setMetadata(new Metadata(motionPhotoMetadata))
             .build());
   }
 

libraries/test_data/src/test/assets/extractordumps/jpeg/non-motion-photo-shortened.jpg.0.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/non-motion-photo-shortened.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/pixel-motion-photo-2-hevc-tracks.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/pixel-motion-photo-jfif-segment-shortened.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/pixel-motion-photo-shortened.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/pixel-motion-photo-video-removed-shortened.jpg.0.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/pixel-motion-photo-video-removed-shortened.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true

libraries/test_data/src/test/assets/extractordumps/jpeg/ss-motion-photo-shortened.jpg.unknown_length.dump

@@ -2,11 +2,5 @@ seekMap:
   isSeekable = false
   duration = UNSET TIME
   getPosition(0) = [[timeUs=0, position=0]]
-numberOfTracks = 1
+numberOfTracks = 0
-track 1024:
-  total output bytes = 0
-  sample count = 0
-  format 0:
-    containerMimeType = image/jpeg
-    metadata = entries=[]
 tracksEnded = true