mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Move presenter notes into furniture

Browse Source 
Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>
This commit is contained in:
Maciej Wieczorek 2025-03-19 11:59:55 +01:00
parent 378db72f2e
commit 4c5b0f7894
4 changed files with 28 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docling/backend/mspowerpoint_backend.py
View File

@ -16,6 +16,7 @@ from docling_core.types.doc import (
TableCell, TableCell,
TableData, TableData,
) )
from docling_core.types.doc.document import ContentLayer
from PIL import Image, UnidentifiedImageError from PIL import Image, UnidentifiedImageError
from pptx import Presentation from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
@ -435,6 +436,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
parent=parent_slide, parent=parent_slide,
text=notes_text, text=notes_text,
prov=prov, prov=prov,
content_layer=ContentLayer.FURNITURE,
) )
return doc return doc

49
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.itxt
View File

@ -10,29 +10,26 @@ item-0 at level 0: unspecified: group _root_
item-9 at level 2: paragraph: Bar item-9 at level 2: paragraph: Bar
item-10 at level 2: paragraph: And baz things item-10 at level 2: paragraph: And baz things
item-11 at level 2: paragraph: A rectangle shape with this text inside. item-11 at level 2: paragraph: A rectangle shape with this text inside.
item-12 at level 2: text: Some notes on the second slide. item-12 at level 1: chapter: group slide-2
item-13 at level 1: chapter: group slide-2 item-13 at level 2: ordered_list: group list
item-14 at level 2: ordered_list: group list item-14 at level 3: list_item: List item4
item-15 at level 3: list_item: List item4 item-15 at level 3: list_item: List item5
item-16 at level 3: list_item: List item5 item-16 at level 3: list_item: List item6
item-17 at level 3: list_item: List item6 item-17 at level 2: list: group list
item-18 at level 2: list: group list item-18 at level 3: list_item: I1
item-19 at level 3: list_item: I1 item-19 at level 3: list_item: I2
item-20 at level 3: list_item: I2 item-20 at level 3: list_item: I3
item-21 at level 3: list_item: I3 item-21 at level 3: list_item: I4
item-22 at level 3: list_item: I4 item-22 at level 2: paragraph: Some info:
item-23 at level 2: paragraph: Some info: item-23 at level 2: list: group list
item-24 at level 2: list: group list item-24 at level 3: list_item: Item A
item-25 at level 3: list_item: Item A item-25 at level 3: list_item: Item B
item-26 at level 3: list_item: Item B item-26 at level 2: paragraph: Maybe a list?
item-27 at level 2: paragraph: Maybe a list? item-27 at level 2: ordered_list: group list
item-28 at level 2: ordered_list: group list item-28 at level 3: list_item: List1
item-29 at level 3: list_item: List1 item-29 at level 3: list_item: List2
item-30 at level 3: list_item: List2 item-30 at level 3: list_item: List3
item-31 at level 3: list_item: List3 item-31 at level 2: list: group list
item-32 at level 2: list: group list item-32 at level 3: list_item: l1
item-33 at level 3: list_item: l1 item-33 at level 3: list_item: l2
item-34 at level 3: list_item: l2 item-34 at level 3: list_item: l3
item-35 at level 3: list_item: l3
item-36 at level 2: text: Final notes on the third slide.
Second line of notes.

2
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
View File

@ -443,6 +443,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "furniture",
"label": "text", "label": "text",
"prov": [ "prov": [
{ {
@ -958,6 +959,7 @@
"$ref": "#/groups/2" "$ref": "#/groups/2"
}, },
"children": [], "children": [],
"content_layer": "furniture",
"label": "text", "label": "text",
"prov": [ "prov": [
{ {

7
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.md
View File

@ -25,8 +25,6 @@ And baz things
A rectangle shape with this text inside. A rectangle shape with this text inside.
Some notes on the second slide.
1. List item4 1. List item4
2. List item5 2. List item5
3. List item6 3. List item6
@ -49,7 +47,4 @@ Maybe a list?
- l1 - l1
- l2 - l2
- l3 - l3
Final notes on the third slide.
Second line of notes.