marcel/familienarchiv
1
0
Fork 0
Code Issues 103 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

fix(normalizer): require day-dot in English month-first matcher (structural anti-shadow)

Browse Source 
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-25 13:53:05 +02:00
parent 53a661adb6
commit 59715bdccd
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tools/import-normalizer/dates.py
View File

@@ -157,7 +157,8 @@ def _match_monthname_a(s):
return _build_day_month_year(int(m.group(1)), _lookup_month(m.group(2)), expand_year(m.group(3)))
_MONTH_B_RE = re.compile(r"([A-Za-zÄÖÜäöü]+)\.?\s*(\d{1,2})\.?\s*(\d{2,4})")
# dot after day is REQUIRED so this can't match "Mai 1895" (MONTH YYYY) as day=18
_MONTH_B_RE = re.compile(r"([A-Za-zÄÖÜäöü]+)\.?\s*(\d{1,2})\.\s*(\d{2,4})")
def _match_monthname_b(s):

2
tools/import-normalizer/tests/test_dates.py
View File

@@ -81,7 +81,7 @@ def test_parse_monthname_day_first():
def test_parse_month_year_year_only():
assert dates.parse_date("Mai 1895") == dates.ParsedDate("1895-05-01", Precision.MONTH, "Mai 1895")
assert dates.parse_date("October 1903").iso == "1903-10-01"
assert dates.parse_date("October 1903") == dates.ParsedDate("1903-10-01", Precision.MONTH, "October 1903")
assert dates.parse_date("1905") == dates.ParsedDate("1905-01-01", Precision.YEAR, "1905")
def test_parse_feast_and_season_via_parse_date():