marcel/familienarchiv
1
0
Fork 0
Code Issues 109 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

fix(normalizer): don't coerce boolean cells to 1/0

Browse Source 
Add bool guard before the int branch in _cell_to_str so True/False
cells are preserved as "True"/"False" instead of "1"/"0". Add two
regression tests covering the fix and missing-sheet error.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-25 14:11:19 +02:00
parent 74c4c390fc
commit 75b3ca8b9e
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/import-normalizer/ingest.py
View File

@@ -7,6 +7,8 @@ import openpyxl
def _cell_to_str(value) -> str: def _cell_to_str(value) -> str:
if value is None: if value is None:
return "" return ""
if isinstance(value, bool): # bool is a subclass of int — handle before the int branch
return str(value)
if isinstance(value, datetime.datetime): if isinstance(value, datetime.datetime):
return value.date().isoformat() return value.date().isoformat()
if isinstance(value, datetime.date): if isinstance(value, datetime.date):

10
tools/import-normalizer/tests/test_ingest.py
View File

@@ -34,3 +34,13 @@ def test_build_header_map_collapses_whitespace_and_case():
def test_build_header_map_missing_required_raises(): def test_build_header_map_missing_required_raises():
with pytest.raises(ValueError, match="index"): with pytest.raises(ValueError, match="index"):
ingest.build_header_map(["Box", "Ort"], {"box": "box", "ort": "location"}, required={"index"}) ingest.build_header_map(["Box", "Ort"], {"box": "box", "ort": "location"}, required={"index"})
def test_read_sheet_bool_not_coerced_to_int(tmp_path):
path = _make_workbook(tmp_path, "S", [["Flag"], [True], [False]])
rows = ingest.read_sheet(path, "S")
assert rows[1] == ["True"] and rows[2] == ["False"] # not "1"/"0"
def test_read_sheet_missing_sheet_raises(tmp_path):
path = _make_workbook(tmp_path, "S", [["A"]])
with pytest.raises(ValueError, match="not found"):
ingest.read_sheet(path, "Nope")