marcel/familienarchiv
1
0
Fork 0
Code Issues 126 Pull Requests 2 Actions 1 Packages Projects Releases Wiki Activity

feat(nlp-service): wire NLP_FUZZY_THRESHOLD env var with 0-100 validation

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-06-07 15:48:57 +02:00
committed by marcel
parent 778382cd61
commit 98ee6cf587
3 changed files with 43 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
nlp-service/extractor.py
View File

@@ -13,9 +13,10 @@ from person_matcher import PersonMatcher
if TYPE_CHECKING:
pass
# ── Module-level PersonMatcher (set at startup) ───────────────────────────────
# ── Module-level PersonMatcher and fuzzy threshold (set at startup) ──────────
_matcher: PersonMatcher | None = None
_fuzzy_threshold: int = 80
def set_person_matcher(m: PersonMatcher) -> None:
@@ -27,6 +28,11 @@ def get_person_matcher() -> PersonMatcher | None:
return _matcher
def set_fuzzy_threshold(threshold: int) -> None:
global _fuzzy_threshold
_fuzzy_threshold = threshold
# ── Preposition sets ──────────────────────────────────────────────────────────
_SENDER_PREPS: dict[str, frozenset[str]] = {
@@ -155,7 +161,7 @@ def _extract_persons_and_role(
preps = _ALL_PERSON_PREPS[lang]
stops = preps | _DATE_BEFORE[lang] | _DATE_AFTER[lang] | _DATE_BETWEEN[lang] | _EXTRA_SPAN_STOPS[lang]
matches = m.find_in_query(query, preps, stop_tokens=stops)
matches = m.find_in_query(query, preps, stop_tokens=stops, threshold=_fuzzy_threshold)
person_names = [text for text, _ in matches]