Skip to content
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions docling/backend/mspowerpoint_backend.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@

from docling_core.types.doc import (
BoundingBox,
ChartData,
CoordOrigin,
DocItemLabel,
DoclingDocument,
Expand All @@ -19,6 +20,7 @@
from docling_core.types.doc.document import ContentLayer
from PIL import Image, UnidentifiedImageError
from pptx import Presentation
from pptx.chart.chart import Chart
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
from pptx.oxml.text import CT_TextLineBreak

Expand Down Expand Up @@ -317,6 +319,32 @@ def handle_tables(self, shape, parent_slide, slide_ind, doc, slide_size):
doc.add_table(parent=parent_slide, data=data, prov=prov)
return

def handle_chart(self, shape, parent_slide, slide_ind, doc, slide_size) -> None:
# Handling charts
if shape.has_chart:
prov = self.generate_prov(shape, slide_ind, "", slide_size)
chart: Chart = shape.chart

series = [
(s.name, list(s.values)) for s in chart.series if s.values is not None
]

categories = []
for plot in chart.plots:
for cat in plot.categories:
categories.append(cat)

data = ChartData(
title=chart.chart_title.text_frame.text,
kind=chart.chart_type.name,
is_categorical=len(categories) > 0,
categories=categories,
series=series,
)

doc.add_chart(parent=parent_slide, data=data, prov=prov)
return

def walk_linear(self, pptx_obj, doc) -> DoclingDocument:
# Units of size in PPTX by default are EMU units (English Metric Units)
slide_width = pptx_obj.slide_width
Expand All @@ -342,6 +370,9 @@ def handle_shapes(shape, parent_slide, slide_ind, doc, slide_size):
if shape.has_table:
# Handle Tables
self.handle_tables(shape, parent_slide, slide_ind, doc, slide_size)
if shape.has_chart:
# Handle Charts
self.handle_chart(shape, parent_slide, slide_ind, doc, slide_size)
if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
# Handle Pictures
if hasattr(shape, "image"):
Expand Down
Loading