Benjamin Admin 0c5f1fd7a4 feat(rag): regulation_short Casing-Normalisierung am Ingest-Rand ...

Der Re-Ingest leitet regulation_short z.T. via title()-Casing aus Dateinamen ab
('dsgvo'->'Dsgvo', 'osha otm'->'Osha Otm') -> falsche Akronyme im Payload UND im
article_label ('Art. 37 Dsgvo'). NEU: normalize_regulation_short() in legal_metadata,
token-basiert mit kuratiertem Akronym-Set -> nur gelistete Akronyme werden gross,
legitimes Mixed-Case (GeschGehG, MuSchG, GoBD, MiCA, eIDAS, EuGH) bleibt unberuehrt.
Angewandt am Ingest-Rand in documents.py (greift fuer Payload-Feld + display_name).
+13 Tests gruen. Bestandsdaten brauchen separaten einmaligen Qdrant-Patch.

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

2026-06-21 18:31:45 +02:00

..

__init__.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

conftest.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

test_document_upload.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

test_embedding_client.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

test_html_stripping.py

fix(rag): HTML charset detection + opening block tag newlines

2026-05-02 08:35:47 +02:00

test_legal_metadata.py

feat(rag): regulation_short Casing-Normalisierung am Ingest-Rand

2026-06-21 18:31:45 +02:00