feat(normalizer): month/year, feast/season, range matchers + overrides

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

tools/import-normalizer/dates.py

@@ -157,8 +157,85 @@ def _match_monthname_a(s):
     return _build_day_month_year(int(m.group(1)), _lookup_month(m.group(2)), expand_year(m.group(3)))
 
 
-# Matchers are tried in order. Later tasks append to this list.
-_MATCHERS = [_match_iso, _match_numeric, _match_roman, _match_monthname_a]
+_MONTH_B_RE = re.compile(r"([A-Za-zÄÖÜäöü]+)\.?\s*(\d{1,2})\.?\s*(\d{2,4})")
+
+
+def _match_monthname_b(s):
+    m = _MONTH_B_RE.fullmatch(s)
+    if not m:
+        return None
+    return _build_day_month_year(int(m.group(2)), _lookup_month(m.group(1)), expand_year(m.group(3)))
+
+
+_MONTH_YEAR_RE = re.compile(r"([A-Za-zÄÖÜäöü]+)\.?\s+(\d{2,4})")
+_TOKEN_YEAR_RE = re.compile(r"(.+?)\.?\s+(\d{2,4})")
+_YEAR_ONLY_RE = re.compile(r"\d{4}")
+_RANGE_YY_RE = re.compile(r"(\d{4})\s*/\s*\d{2}")
+_RANGE_HYPHEN_RE = re.compile(r"(.*\d)\s*[-–]\s*\d.*")
+# Intra-month day range, e.g. "7./8. Sept.1923" — require a dot before the slash so it
+# does NOT swallow slash-as-dot single dates like "17/6. 1916" (which has no dot before "/").
+_RANGE_DAY_RE = re.compile(r"(\d{1,2})\./(\d{1,2})\.\s*(.+)")
+
+
+def _match_month_year(s):
+    m = _MONTH_YEAR_RE.fullmatch(s)
+    if not m:
+        return None
+    month = _lookup_month(m.group(1))
+    year = expand_year(m.group(2))
+    if not month or year is None:
+        return None
+    return datetime.date(year, month, 1).isoformat(), Precision.MONTH
+
+
+def _match_feast_season(s):
+    m = _TOKEN_YEAR_RE.fullmatch(s)
+    if not m:
+        return None
+    year = expand_year(m.group(2))
+    if year is None:
+        return None
+    return resolve_feast_or_season(m.group(1), year)
+
+
+def _match_year_only(s):
+    if _YEAR_ONLY_RE.fullmatch(s):
+        return datetime.date(int(s), 1, 1).isoformat(), Precision.YEAR
+    return None
+
+
+def _match_range(s):
+    m = _RANGE_YY_RE.fullmatch(s)
+    if m:
+        return datetime.date(int(m.group(1)), 1, 1).isoformat(), Precision.RANGE
+    m = _RANGE_DAY_RE.fullmatch(s)
+    if m:
+        first = f"{m.group(1)}.{m.group(3)}"  # "7." + "Sept.1923" -> "7.Sept.1923"
+        for matcher in (_match_numeric, _match_monthname_a):
+            r = matcher(first)
+            if r:
+                return r[0], Precision.RANGE
+    m = _RANGE_HYPHEN_RE.fullmatch(s)
+    if m:
+        start = m.group(1).strip()
+        for matcher in (_match_numeric, _match_roman, _match_monthname_a, _match_year_only):
+            r = matcher(start)
+            if r:
+                return r[0], Precision.RANGE
+    return None
+
+
+_MATCHERS = [
+    _match_iso,
+    _match_range,
+    _match_numeric,
+    _match_roman,
+    _match_monthname_a,
+    _match_month_year,
+    _match_monthname_b,
+    _match_feast_season,
+    _match_year_only,
+]
 
 
 def parse_date(raw: str, date_overrides: dict | None = None) -> ParsedDate: