mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 07:22:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(msexcel): ignore Mypy checking for _find_images_in_sheet function

Browse Source 
Signed-off-by: Jiun An Tsai <andrew@247365-Macbook.local>
This commit is contained in:
Jiun An Tsai 2025-01-07 15:37:34 +08:00
parent 2b591f9872
commit 8ec3f176eb
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docling/backend/msexcel_backend.py
View File

@ -26,6 +26,7 @@ _log = logging.getLogger(__name__)
from typing import Any, List from typing import Any, List
from PIL import Image
from pydantic import BaseModel from pydantic import BaseModel
@ -326,10 +327,8 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
self, doc: DoclingDocument, sheet: Worksheet self, doc: DoclingDocument, sheet: Worksheet
) -> DoclingDocument: ) -> DoclingDocument:
# FIXME: mypy does not agree with _images ...
"""
# Iterate over images in the sheet # Iterate over images in the sheet
for idx, image in enumerate(sheet._images): # Access embedded images for idx, image in enumerate(sheet._images): # type: ignore
image_bytes = BytesIO(image.ref.blob) image_bytes = BytesIO(image.ref.blob)
pil_image = Image.open(image_bytes) pil_image = Image.open(image_bytes)
@ -339,36 +338,32 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
image=ImageRef.from_pil(image=pil_image, dpi=72), image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None, caption=None,
) )
"""
# FIXME: mypy does not agree with _charts ... for idx, chart in enumerate(sheet._charts): # type: ignore
"""
for idx, chart in enumerate(sheet._charts): # Access embedded charts
chart_path = f"chart_{idx + 1}.png" chart_path = f"chart_{idx + 1}.png"
_log.info( _log.info(
f"Chart found, but dynamic rendering is required for: {chart_path}" f"Chart found, but dynamic rendering is required for: {chart_path}"
) )
_log.info(f"Chart {idx + 1}:") _log.info(f"Chart {idx + 1}:")
# Chart type # Chart type
_log.info(f"Type: {type(chart).__name__}") _log.info(f"Type: {type(chart).__name__}")
# Title # Title
if chart.title: if chart.title:
_log.info(f"Title: {chart.title}") _log.info(f"Title: {chart.title}")
else: else:
_log.info("No title") _log.info("No title")
# Data series # Data series
for series in chart.series: for series in chart.series:
_log.info(" => series ...") _log.info(" => series ...")
_log.info(f"Data Series: {series.title}") _log.info(f"Data Series: {series.title}")
_log.info(f"Values: {series.values}") _log.info(f"Values: {series.values}")
_log.info(f"Categories: {series.categories}") _log.info(f"Categories: {series.categories}")
# Position # Position
# _log.info(f"Anchor Cell: {chart.anchor}") # _log.info(f"Anchor Cell: {chart.anchor}")
"""
return doc return doc