version: 1 encoding: utf-8 normalization: NFKC whitelist: sections_titres: - DIM - GHM - GHS - RUM - COMPTE - RENDU - DIAGNOSTIC noms_maj_excepts: - Médecin DIM - Praticien conseil org_gpe_keep: true blacklist: force_mask_terms: - CENTRE HOSPITALIER COTE BASQUE - 'Dates du séjour :' - CONCERTATION force_mask_regex: [] kv_labels_preserve: - FINESS - IPP - N° OGC - Etablissement regex_overrides: - name: OGC_court pattern: \b(?:N°\s*)?OGC\s*[:\-]?\s*([A-Za-z0-9\-]{1,3})\b placeholder: '[OGC]' flags: - IGNORECASE flags: case_insensitive: true unicode_word_boundaries: true regex_engine: python