From fea0a99a95d97e72687f48f8174d31102655483e Mon Sep 17 00:00:00 2001
From: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com>
Date: Thu, 30 Jan 2025 14:58:27 +0100
Subject: [PATCH] fix: Fix for the crash when encountering WMF images in pptx
 and docx (#837)

* Fix for the crash when encountering WMF images in pptx and docx backends on non Windows platforms

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated faq

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
---
 docling/backend/mspowerpoint_backend.py | 9 ++++-----
 docling/backend/msword_backend.py       | 4 ++--
 docs/faq.md                             | 8 ++++++++
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/docling/backend/mspowerpoint_backend.py b/docling/backend/mspowerpoint_backend.py
index 995969d..aecebdc 100644
--- a/docling/backend/mspowerpoint_backend.py
+++ b/docling/backend/mspowerpoint_backend.py
@@ -271,13 +271,12 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
         return
 
     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
         try:
+            # Get the image bytes
+            image = shape.image
+            image_bytes = image.blob
+            im_dpi, _ = image.dpi
             pil_image = Image.open(BytesIO(image_bytes))
 
             # shape has picture
diff --git a/docling/backend/msword_backend.py b/docling/backend/msword_backend.py
index f8148d5..0af3db5 100644
--- a/docling/backend/msword_backend.py
+++ b/docling/backend/msword_backend.py
@@ -520,11 +520,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 image_data = image_part.blob  # Get the binary image data
             return image_data
 
-        image_data = get_docx_image(element, drawing_blip)
-        image_bytes = BytesIO(image_data)
         level = self.get_level()
         # Open the BytesIO object with PIL to create an Image
         try:
+            image_data = get_docx_image(element, drawing_blip)
+            image_bytes = BytesIO(image_data)
             pil_image = Image.open(image_bytes)
             doc.add_picture(
                 parent=self.parents[level - 1],
diff --git a/docs/faq.md b/docs/faq.md
index 96e12ed..d8b85cd 100644
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -151,3 +151,11 @@ This is a collection of FAQ collected from the user questions on <https://github
     pipeline_options = PdfPipelineOptions()
     pipeline_options.ocr_options.lang = ["fr", "de", "es", "en"]  # example of languages for EasyOCR
     ```
+
+
+??? Some images are missing from MS Word and Powerpoint"
+
+    ### Some images are missing from MS Word and Powerpoint
+
+    The image processing library used by Docling is able to handle embedded WMF images only on Windows platform.
+    If you are on other operaring systems, these images will be ignored.