75b3ca8b9e
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>
47 lines
1.7 KiB
Python
47 lines
1.7 KiB
Python
import datetime
|
|
import openpyxl
|
|
import pytest
|
|
import ingest
|
|
|
|
def _make_workbook(tmp_path, sheet_name, rows):
|
|
wb = openpyxl.Workbook()
|
|
ws = wb.active
|
|
ws.title = sheet_name
|
|
for r in rows:
|
|
ws.append(r)
|
|
path = tmp_path / "wb.xlsx"
|
|
wb.save(path)
|
|
return path
|
|
|
|
def test_read_sheet_converts_cells(tmp_path):
|
|
path = _make_workbook(tmp_path, "S", [
|
|
["Index", "Datum"],
|
|
["W-0001", datetime.datetime(1888, 2, 15)],
|
|
["W-0002", 1],
|
|
])
|
|
rows = ingest.read_sheet(path, "S")
|
|
assert rows[0] == ["Index", "Datum"]
|
|
assert rows[1] == ["W-0001", "1888-02-15"] # Excel date -> ISO string
|
|
assert rows[2] == ["W-0002", "1"] # integer -> plain string
|
|
|
|
def test_build_header_map_collapses_whitespace_and_case():
|
|
header = ["Index", "Datum des Briefes", "EmpfängerIn", "Mystery"]
|
|
field_map = {"index": "index", "datum des briefes": "date", "empfängerin": "receivers"}
|
|
fields, unknown = ingest.build_header_map(header, field_map, required={"index"})
|
|
assert fields == {"index": 0, "date": 1, "receivers": 2}
|
|
assert unknown == ["Mystery"]
|
|
|
|
def test_build_header_map_missing_required_raises():
|
|
with pytest.raises(ValueError, match="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")
|