Dom/anonymisation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Propagation globale sélective v2 - Normalisation dates + Multi-pass

Browse Source 
- Normalisation agressive des dates : génère 4 variations (/, ., -, espaces)
- Remplacement multi-pass : avec/sans contexte 'Né(e) le'
- Amélioration force_term : case-insensitive + word boundaries
- Outil de validation post-anonymisation
- Tests : 162 CRO, 0 fuite dates, 0 fuite CHCB (100% succès)
- Temps: 0.1s/doc

Résout les 36 CRO avec fuites identifiées dans l'audit initial.
This commit is contained in:
Domi31tls
2026-03-02 12:22:58 +01:00
parent 871221ea56
commit f92da4d54e
251 changed files with 4676 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tests/ground_truth/pdfs/test_all_cro/CRO 23159905.audit.jsonl Normal file
View File

@@ -0,0 +1,32 @@
{"page": 0, "kind": "NOM", "original": "Maria BISCAY-SALLABERRY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64780 IRISSARRY", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "REMI COSSU", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "ADRESSE", "original": "200 CHEMIN SORHABIETA", "placeholder": "[ADRESSE]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64640 IHOLDY", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Joe FADDOUL", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "DOSSIER", "original": "Dossier : 23159905", "placeholder": "[DOSSIER]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "FADDOUL Joe", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "CUCUPHAT Pierre-Lou", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "DATE_NAISSANCE", "original": "né le 07/08/1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "COSSU Rémi", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "COSSU", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "BEGUE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "COSSU", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "COSSU", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "Joe FADDOUL", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "DATE_NAISSANCE", "original": "Date de naissance : 07/08/1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": 0, "kind": "DATE_NAISSANCE", "original": "né le 07/08/1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": 0, "kind": "ADRESSE", "original": "200 CHEMIN SORHABIETA\n", "placeholder": "[ADRESSE]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64780 IRISSARRY\nMr REMI COSSU", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64640 IHOLDY\nMadame", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "DOSSIER", "original": "Dossier : 23159905", "placeholder": "[DOSSIER]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Maria BISCAY-SALLABERRY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Joe FADDOUL", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "COSSU Prénom", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "FADDOUL Joe", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "CUCUPHAT Pierre-Lou", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "COSSU Rémi", "placeholder": "[NOM]", "bbox_hint": null}
{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "07/08/1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "07.08.1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "07-08-1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "07 08 1999", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}