feat(phase2): Extraction layout-aware multi-colonnes — 322 fuites → 0, -103 FP
Phase 2 de l'amélioration qualité anonymisation :
1. Extraction multi-colonnes (PyMuPDF layout-aware) :
- Nouvelle fonction _extract_page_layout_aware() détecte les layouts
sidebar+corps (typiques des CRH/CRO hospitaliers)
- Remplace pdfplumber comme extraction primaire (PyMuPDF blocks)
- Élimine l'entrelacement de texte entre sidebar et corps médical
- pdfplumber conservé pour les tables et comme fallback
2. Masquage FINESS multiline :
- Détection "N° Finess\n[...]\n640000162" (label et numéro séparés)
- Propagation globale du numéro FINESS sur toutes les pages
- Gestion du format *640000162* (avec astérisques Trackare)
3. Masquage URLs hospitalières (www.ch-xxx.fr)
4. Nettoyage crochets doubles [[PLACEHOLDER]] → [PLACEHOLDER]
Résultats non-régression (30 fichiers audit) :
- Fuites : 322 → 0 (-100%)
- Faux positifs : 113 → 10 (-91%)
- 0 régression fonctionnelle
- OGC 1-59 : 0 fuite soignant, 0 FINESS, 0 lieu de naissance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,13 +1,9 @@
|
||||
{"page": 0, "kind": "force_term", "original": "CENTRE HOSPITALIER COTE BASQUE", "placeholder": "[MASK]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "IPP", "original": "07026002", "placeholder": "[IPP]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "DATE_NAISSANCE", "original": "Date de naissance: 27/09/1985", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "VILLE", "original": "MONTBELIARD", "placeholder": "[VILLE]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "CODE_POSTAL", "original": "Code Postal: 64122", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "ADRESSE", "original": "6 RUE CHANDIRU BAITA Ville de résidence", "placeholder": "[ADRESSE]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "ADRESSE", "original": "6 RUE CHANDIRU BAITA", "placeholder": "[ADRESSE]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "NOM", "original": "Sophie GHECK", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "NOM", "original": "Jon HERNANDORENA", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "ADRESSE", "original": "2, ALLÉE PRESSABURU ", "placeholder": "[ADRESSE]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "CODE_POSTAL", "original": "64122 URRUGNE", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "NOM", "original": "Jon HERNANDORENA", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "TEL", "original": "0612186137", "placeholder": "[TEL]", "bbox_hint": null}
|
||||
{"page": 0, "kind": "DATE_NAISSANCE", "original": "Date de naissance: 27/09/1985", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
|
||||
{"page": 1, "kind": "DATE_NAISSANCE", "original": "Date de naissance: 27/09/1985", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
|
||||
@@ -20,7 +16,6 @@
|
||||
{"page": 4, "kind": "NOM", "original": "Gheck", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 4, "kind": "NOM", "original": "Gheck", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 4, "kind": "DATE_NAISSANCE", "original": "Date de naissance: 27/09/1985", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
|
||||
{"page": 5, "kind": "DOSSIER", "original": "NDANSETRON", "placeholder": "[DOSSIER]", "bbox_hint": null}
|
||||
{"page": 5, "kind": "NOM", "original": "Juliette", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 5, "kind": "NOM", "original": "Juliette", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
{"page": 5, "kind": "NOM", "original": "Juliette", "placeholder": "[NOM]", "bbox_hint": null}
|
||||
|
||||
Reference in New Issue
Block a user