Skip to content
Open
Show file tree
Hide file tree
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
15 changes: 12 additions & 3 deletions packages/markitdown/src/markitdown/converters/_xlsx_converter.py
Original file line number Diff line number Diff line change
Expand Up @@ -52,12 +52,19 @@ def _read_xlsx_sheets(
repaired_stream = None
try:
try:
sheets = pd.read_excel(file_stream, sheet_name=None, engine="openpyxl")
sheets = pd.read_excel(
file_stream, sheet_name=None, engine="openpyxl", keep_default_na=False
)
except TypeError as exc:
if "showZeroes" not in str(exc):
raise
repaired_stream = _repair_sheetview_show_zeroes(file_stream, start_pos)
sheets = pd.read_excel(repaired_stream, sheet_name=None, engine="openpyxl")
sheets = pd.read_excel(
repaired_stream,
sheet_name=None,
engine="openpyxl",
keep_default_na=False,
)
yield sheets, repaired_stream if repaired_stream is not None else file_stream
finally:
if repaired_stream is not None:
Expand Down Expand Up @@ -237,7 +244,9 @@ def convert(
_xls_dependency_exc_info[2]
)

sheets = pd.read_excel(file_stream, sheet_name=None, engine="xlrd")
sheets = pd.read_excel(
file_stream, sheet_name=None, engine="xlrd", keep_default_na=False
)
md_content = ""
for s in sheets:
md_content += f"## {s}\n"
Expand Down
19 changes: 19 additions & 0 deletions packages/markitdown/tests/test_xlsx.py
Original file line number Diff line number Diff line change
Expand Up @@ -542,3 +542,22 @@ def test_xlsx_show_zeroes_rename_is_scoped_to_sheet_view_tags() -> None:

if __name__ == "__main__":
raise SystemExit(pytest.main([__file__]))


def test_xlsx_blank_cells_and_na_like_text_are_preserved() -> None:
workbook = openpyxl.Workbook()
sheet = workbook.active
sheet.append(["country", "code", "score"])
sheet.append(["Namibia", "NA", 1])
sheet.append(["Unknown", "N/A", None])
sheet.append(["Other", "null", 2])
stream = io.BytesIO()
workbook.save(stream)
stream.seek(0)

markdown = MarkItDown().convert_stream(stream, file_extension=".xlsx").markdown

assert "NaN" not in markdown
assert "| Namibia | NA | 1 |" in markdown
assert "| Unknown | N/A | |" in markdown
assert "| Other | null | 2 |" in markdown