Inferring image DPI from pptx file

Signed-off-by: Maksym Lysak <[email protected]>
DS4SD · Nov 18, 2024 · b132c68 · b132c68
1 parent 2240008
commit b132c68
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/docling/backend/mspowerpoint_backend.py b/docling/backend/mspowerpoint_backend.py
@@ -273,14 +273,16 @@ def handle_pictures(self, shape, parent_slide, slide_ind, doc):
         # Get the image bytes
         image = shape.image
         image_bytes = image.blob
+        im_dpi, _ = image.dpi
+
         # Open it with PIL
         pil_image = Image.open(BytesIO(image_bytes))
 
         # shape has picture
         prov = self.generate_prov(shape, slide_ind, "")
         doc.add_picture(
             parent=parent_slide,
-            image=ImageRef.from_pil(image=pil_image, dpi=72),
+            image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
             caption=None,
             prov=prov,
         )

diff --git a/tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json b/tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json
@@ -127,7 +127,7 @@
       "footnotes": [],
       "image": {
         "mimetype": "image/png",
-        "dpi": 72,
+        "dpi": 300,
         "size": {
           "width": 268.0,
           "height": 268.0