feat: Add PPTX notes slides (#474)

* feat: Add PPTX notes slides

Presenter notes may have useful information and should also be extracted.

Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>

* feat: Move presenter notes into furniture

Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>

---------

Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>

docling/backend/mspowerpoint_backend.py

@@ -16,6 +16,7 @@ from docling_core.types.doc import (
     TableCell,
     TableData,
 )
+from docling_core.types.doc.document import ContentLayer
 from PIL import Image, UnidentifiedImageError
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
@@ -421,4 +422,21 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
             for shape in slide.shapes:
                 handle_shapes(shape, parent_slide, slide_ind, doc, slide_size)
 
+            # Handle notes slide
+            if slide.has_notes_slide:
+                notes_slide = slide.notes_slide
+                notes_text = notes_slide.notes_text_frame.text.strip()
+                if notes_text:
+                    bbox = BoundingBox(l=0, t=0, r=0, b=0)
+                    prov = ProvenanceItem(
+                        page_no=slide_ind + 1, charspan=[0, len(notes_text)], bbox=bbox
+                    )
+                    doc.add_text(
+                        label=DocItemLabel.TEXT,
+                        parent=parent_slide,
+                        text=notes_text,
+                        prov=prov,
+                        content_layer=ContentLayer.FURNITURE,
+                    )
+
         return doc

tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json

@@ -4,7 +4,7 @@
   "name": "powerpoint_sample",
   "origin": {
     "mimetype": "application/vnd.ms-powerpoint",
-    "binary_hash": 1640759611026400292,
+    "binary_hash": 15572290240354948364,
     "filename": "powerpoint_sample.pptx"
   },
   "furniture": {
@@ -75,6 +75,9 @@
         },
         {
           "$ref": "#/texts/7"
+        },
+        {
+          "$ref": "#/texts/8"
         }
       ],
       "content_layer": "body",
@@ -94,19 +97,22 @@
           "$ref": "#/groups/4"
         },
         {
-          "$ref": "#/texts/15"
+          "$ref": "#/texts/16"
         },
         {
           "$ref": "#/groups/5"
         },
         {
-          "$ref": "#/texts/18"
+          "$ref": "#/texts/19"
         },
         {
           "$ref": "#/groups/6"
         },
         {
           "$ref": "#/groups/7"
+        },
+        {
+          "$ref": "#/texts/26"
         }
       ],
       "content_layer": "body",
@@ -119,14 +125,14 @@
         "$ref": "#/groups/2"
       },
       "children": [
-        {
-          "$ref": "#/texts/8"
-        },
         {
           "$ref": "#/texts/9"
         },
         {
           "$ref": "#/texts/10"
+        },
+        {
+          "$ref": "#/texts/11"
         }
       ],
       "content_layer": "body",
@@ -139,9 +145,6 @@
         "$ref": "#/groups/2"
       },
       "children": [
-        {
-          "$ref": "#/texts/11"
-        },
         {
           "$ref": "#/texts/12"
         },
@@ -150,6 +153,9 @@
         },
         {
           "$ref": "#/texts/14"
+        },
+        {
+          "$ref": "#/texts/15"
         }
       ],
       "content_layer": "body",
@@ -163,10 +169,10 @@
       },
       "children": [
         {
-          "$ref": "#/texts/16"
+          "$ref": "#/texts/17"
         },
         {
-          "$ref": "#/texts/17"
+          "$ref": "#/texts/18"
         }
       ],
       "content_layer": "body",
@@ -179,14 +185,14 @@
         "$ref": "#/groups/2"
       },
       "children": [
-        {
-          "$ref": "#/texts/19"
-        },
         {
           "$ref": "#/texts/20"
         },
         {
           "$ref": "#/texts/21"
+        },
+        {
+          "$ref": "#/texts/22"
         }
       ],
       "content_layer": "body",
@@ -199,14 +205,14 @@
         "$ref": "#/groups/2"
       },
       "children": [
-        {
-          "$ref": "#/texts/22"
-        },
         {
           "$ref": "#/texts/23"
         },
         {
           "$ref": "#/texts/24"
+        },
+        {
+          "$ref": "#/texts/25"
         }
       ],
       "content_layer": "body",
@@ -433,6 +439,33 @@
     },
     {
       "self_ref": "#/texts/8",
+      "parent": {
+        "$ref": "#/groups/1"
+      },
+      "children": [],
+      "content_layer": "furniture",
+      "label": "text",
+      "prov": [
+        {
+          "page_no": 2,
+          "bbox": {
+            "l": 0.0,
+            "t": 0.0,
+            "r": 0.0,
+            "b": 0.0,
+            "coord_origin": "TOPLEFT"
+          },
+          "charspan": [
+            0,
+            31
+          ]
+        }
+      ],
+      "orig": "Some notes on the second slide.",
+      "text": "Some notes on the second slide."
+    },
+    {
+      "self_ref": "#/texts/9",
       "parent": {
         "$ref": "#/groups/3"
       },
@@ -461,7 +494,7 @@
       "marker": "1."
     },
     {
-      "self_ref": "#/texts/9",
+      "self_ref": "#/texts/10",
       "parent": {
         "$ref": "#/groups/3"
       },
@@ -490,7 +523,7 @@
       "marker": "2."
     },
     {
-      "self_ref": "#/texts/10",
+      "self_ref": "#/texts/11",
       "parent": {
         "$ref": "#/groups/3"
       },
@@ -519,7 +552,7 @@
       "marker": "3."
     },
     {
-      "self_ref": "#/texts/11",
+      "self_ref": "#/texts/12",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -548,7 +581,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/12",
+      "self_ref": "#/texts/13",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -577,7 +610,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/13",
+      "self_ref": "#/texts/14",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -606,7 +639,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/14",
+      "self_ref": "#/texts/15",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -635,7 +668,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/15",
+      "self_ref": "#/texts/16",
       "parent": {
         "$ref": "#/groups/2"
       },
@@ -662,7 +695,7 @@
       "text": "Some info:"
     },
     {
-      "self_ref": "#/texts/16",
+      "self_ref": "#/texts/17",
       "parent": {
         "$ref": "#/groups/5"
       },
@@ -691,7 +724,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/17",
+      "self_ref": "#/texts/18",
       "parent": {
         "$ref": "#/groups/5"
       },
@@ -720,7 +753,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/18",
+      "self_ref": "#/texts/19",
       "parent": {
         "$ref": "#/groups/2"
       },
@@ -747,7 +780,7 @@
       "text": "Maybe a list?"
     },
     {
-      "self_ref": "#/texts/19",
+      "self_ref": "#/texts/20",
       "parent": {
         "$ref": "#/groups/6"
       },
@@ -776,7 +809,7 @@
       "marker": "1."
     },
     {
-      "self_ref": "#/texts/20",
+      "self_ref": "#/texts/21",
       "parent": {
         "$ref": "#/groups/6"
       },
@@ -805,7 +838,7 @@
       "marker": "2."
     },
     {
-      "self_ref": "#/texts/21",
+      "self_ref": "#/texts/22",
       "parent": {
         "$ref": "#/groups/6"
       },
@@ -834,7 +867,7 @@
       "marker": "3."
     },
     {
-      "self_ref": "#/texts/22",
+      "self_ref": "#/texts/23",
       "parent": {
         "$ref": "#/groups/7"
       },
@@ -863,7 +896,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/23",
+      "self_ref": "#/texts/24",
       "parent": {
         "$ref": "#/groups/7"
       },
@@ -892,7 +925,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/24",
+      "self_ref": "#/texts/25",
       "parent": {
         "$ref": "#/groups/7"
       },
@@ -919,6 +952,33 @@
       "text": "l3",
       "enumerated": false,
       "marker": "-"
+    },
+    {
+      "self_ref": "#/texts/26",
+      "parent": {
+        "$ref": "#/groups/2"
+      },
+      "children": [],
+      "content_layer": "furniture",
+      "label": "text",
+      "prov": [
+        {
+          "page_no": 3,
+          "bbox": {
+            "l": 0.0,
+            "t": 0.0,
+            "r": 0.0,
+            "b": 0.0,
+            "coord_origin": "TOPLEFT"
+          },
+          "charspan": [
+            0,
+            53
+          ]
+        }
+      ],
+      "orig": "Final notes on the third slide.\nSecond line of notes.",
+      "text": "Final notes on the third slide.\nSecond line of notes."
     }
   ],
   "pictures": [],