Files
familienarchiv/tools/import-normalizer/ingest.py
Marcel 75b3ca8b9e fix(normalizer): don't coerce boolean cells to 1/0
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>
2026-05-25 14:11:19 +02:00

51 lines
1.8 KiB
Python

"""Read .xlsx sheets into neutral list[list[str]] and map headers to fields."""
import datetime
from pathlib import Path
import openpyxl
def _cell_to_str(value) -> str:
if value is None:
return ""
if isinstance(value, bool): # bool is a subclass of int — handle before the int branch
return str(value)
if isinstance(value, datetime.datetime):
return value.date().isoformat()
if isinstance(value, datetime.date):
return value.isoformat()
if isinstance(value, float) and value.is_integer():
return str(int(value))
if isinstance(value, int):
return str(value)
return str(value).strip()
def read_sheet(path: Path, sheet_name: str) -> list[list[str]]:
wb = openpyxl.load_workbook(path, read_only=True, data_only=True)
if sheet_name not in wb.sheetnames:
raise ValueError(f"Sheet '{sheet_name}' not found in {path.name}; sheets: {wb.sheetnames}")
ws = wb[sheet_name]
rows = [[_cell_to_str(v) for v in row] for row in ws.iter_rows(values_only=True)]
wb.close()
return rows
def _norm_header(text: str) -> str:
return " ".join(text.lower().split())
def build_header_map(header_row: list[str], field_map: dict[str, str], required: set[str]):
"""Return (field->col_index, unknown_headers). Raise ValueError if a required field is missing."""
fields: dict[str, int] = {}
unknown: list[str] = []
for idx, raw in enumerate(header_row):
key = _norm_header(raw)
if key in field_map:
fields[field_map[key]] = idx
elif raw.strip():
unknown.append(raw)
missing = required - set(fields)
if missing:
raise ValueError(f"Required header(s) missing: {sorted(missing)} (found headers: {header_row})")
return fields, unknown