47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
"""Normalize Personendatei 2.xlsx into canonical-persons-tree.json."""
|
|
import argparse
|
|
import datetime
|
|
import json
|
|
import re
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import config
|
|
import dates
|
|
from persons import _strip_accents
|
|
|
|
|
|
def _parse_year(raw: str | None) -> int | None:
|
|
"""Extract a birth/death year from an Excel cell string.
|
|
|
|
Handles four cases:
|
|
1. ISO string (openpyxl date-formatted cell) → parse_date()
|
|
2. Numeric string that is an Excel serial (1-80000) → timedelta conversion
|
|
3. Any other string → parse_date()
|
|
4. Unresolvable → None
|
|
"""
|
|
if raw is None:
|
|
return None
|
|
s = str(raw).strip()
|
|
if not s:
|
|
return None
|
|
|
|
# Try parse_date first (handles ISO, DD.MM.YYYY, year-only, month+year, etc.)
|
|
result = dates.parse_date(s)
|
|
if result.iso:
|
|
year = int(result.iso[:4])
|
|
# Reject years outside 1700-2100 (same guard as expand_year())
|
|
if 1700 <= year <= 2100:
|
|
return year
|
|
|
|
# If it's a pure integer string, try Excel serial conversion.
|
|
# parse_date() may parse large serials like "7568" as year 7568 or other edge cases.
|
|
if re.fullmatch(r"\d+", s):
|
|
n = int(s)
|
|
if 1 <= n <= 80_000:
|
|
d = datetime.date(1899, 12, 30) + datetime.timedelta(days=n)
|
|
if 1700 <= d.year <= 2100:
|
|
return d.year
|
|
|
|
return None
|