mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: deal with chartsheets in workbooks (#2433)

Browse Source 
* fix(xlsx): deal with chartsheets in workbooks

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* tests(xlsx): align test file names

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-10-10 15:06:38 +02:00
committed by GitHub
parent f11f8c0a81
commit cce18b2ff7
14 changed files with 718 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tests/test_backend_msexcel.py
View File

@@ -79,7 +79,7 @@ def test_pages(documents) -> None:
documents: The paths and converted documents.
"""
# number of pages from the backend method
path = next(item for item in get_excel_paths() if item.stem == "test-01")
path = next(item for item in get_excel_paths() if item.stem == "xlsx_01")
in_doc = InputDocument(
path_or_stream=path,
format=InputFormat.XLSX,
@@ -90,7 +90,7 @@ def test_pages(documents) -> None:
assert backend.page_count() == 4
# number of pages from the converted document
doc = next(item for path, item in documents if path.stem == "test-01")
doc = next(item for path, item in documents if path.stem == "xlsx_01")
assert len(doc.pages) == 4
# page sizes as number of cells
@@ -98,3 +98,18 @@ def test_pages(documents) -> None:
assert doc.pages.get(2).size.as_tuple() == (9.0, 18.0)
assert doc.pages.get(3).size.as_tuple() == (13.0, 36.0)
assert doc.pages.get(4).size.as_tuple() == (0.0, 0.0)
def test_chartsheet(documents) -> None:
"""Test the conversion of Chartsheets.
Args:
documents: The paths and converted documents.
"""
doc = next(item for path, item in documents if path.stem == "xlsx_03_chartsheet")
assert len(doc.pages) == 2
# Chartseet content is for now ignored
assert doc.groups[1].name == "sheet: Duck Chart"
assert doc.pages[2].size.height == 0
assert doc.pages[2].size.width == 0