marcel/familienarchiv
1
0
Fork 0
Code Issues 108 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

fix(normalizer): treat leading date qualifiers (nach/vor/…) as APPROX

Browse Source 
_preprocess now sets approx=True when a leading marker is stripped; add
_match_year_only so bare years (e.g. "nach 1900" -> "1900") resolve to
1900-01-01/YEAR before being upgraded to APPROX. Strengthen
test_parse_approx_marker_upgrades_precision and add
test_parse_leading_qualifier_is_approx (11 tests, all pass).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-25 13:35:19 +02:00
parent df14e6b1ee
commit cff486dda7
2 changed files with 21 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tools/import-normalizer/dates.py
View File

@@ -72,7 +72,7 @@ _LEADING_MARKERS = re.compile(
def _preprocess(raw: str):
"""Return (cleaned_string, approx_flag)."""
"""Return (cleaned_string, approx_flag). Any uncertainty/qualifier marker -> approx."""
s = (raw or "").strip()
if not s:
return "", False
@@ -82,8 +82,10 @@ def _preprocess(raw: str):
s = re.sub(r"\(\s*\?\s*\)", " ", s) # remove "(?)"
s = s.replace("?", " ")
s = re.sub(r",.*$", "", s) # drop trailing editorial note (", 2. Brief")
s = _LEADING_MARKERS.sub("", s)
s = re.sub(r"\s+", " ", s).strip(" .,")
stripped = _LEADING_MARKERS.sub("", s)
if stripped != s: # a leading qualifier (um/ca/nach/vor/anfang/…) signals approximation
approx = True
s = re.sub(r"\s+", " ", stripped).strip(" .,")
return s, approx
@@ -114,8 +116,17 @@ def _match_numeric(s):
return None
_YEAR_ONLY_RE = re.compile(r"\d{4}")
def _match_year_only(s):
if _YEAR_ONLY_RE.fullmatch(s):
return datetime.date(int(s), 1, 1).isoformat(), Precision.YEAR
return None
# Matchers are tried in order. Later tasks append to this list.
_MATCHERS = [_match_iso, _match_numeric]
_MATCHERS = [_match_iso, _match_numeric, _match_year_only]
def parse_date(raw: str, date_overrides: dict | None = None) -> ParsedDate: