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

- 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.

tests/ground_truth/pdfs/test_propagation/CRO 23111304.audit.jsonl

@@ -0,0 +1,10 @@
+{"page": 0, "kind": "DATE_NAISSANCE", "original": "Date de naissance: 21/01/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": 0, "kind": "IPP", "original": "07000323", "placeholder": "[IPP]", "bbox_hint": null}
+{"page": 0, "kind": "EPISODE", "original": "N° Episode 23111304", "placeholder": "[EPISODE]", "bbox_hint": null}
+{"page": 1, "kind": "IPP", "original": "07000323", "placeholder": "[IPP]", "bbox_hint": null}
+{"page": 1, "kind": "EPISODE", "original": "N° Episode 23111304", "placeholder": "[EPISODE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "21/01/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "21.01.1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "21-01-1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "21 01 1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "IPP_GLOBAL", "original": "07000323", "placeholder": "[IPP]", "bbox_hint": null}

tests/ground_truth/pdfs/test_propagation/CRO 23111304.pseudonymise.txt

@@ -0,0 +1,56 @@
+N° Finess ✉
+☎ +33(0)156125400
+123456789
+Compte Rendu Opératoire
+Matricule INS : Nature ( )
+Nom de naissance : [NOM]
+1er prénom de naissance : [NOM]
+Sexe : F [DATE_NAISSANCE]
+INTERVENTION
+CHOLECYSTECTOMIE PAR COELIOSCOPIE
+Diagnostic : Pancréatite aigue non sévère sur migration lithiasique ; bili-IRM il y a 48h ne retrouvant pas d'obstacle
+lithiasique au sein de la voie biliaire principale, bilan hépatique en amélioration (cholestase et cytolyse en diminution,
+bilirubine normale).
+Voie d'abord : Laparoscopie.
+Installation : 
+Sous anesthésie générale.
+Décubitus dorsal, bras gauche le long du corps.
+Vérification des points d'appuis.
+Désinfection cutanée et champage stérile selon protocole.
+Check-list.
+Gestes effectués : 
+Création d'un pneumopéritoine par open-laparoscopie sus-ombilicale.
+Introduction d'un trocart de 10 mm sous contrôle de la vue pour insufflation d'un pneumopéritoine à 12 mmHg.
+Mise en place de 2 autres trocarts de 5 mm : 1 en flanc droit et 1 en hypochondre gauche.
+Constatations peropératoires : 
+- La vésicule est en réplétion, non inflammatoire, avec quelques adhérences épiploïques.
+- Le foie est d'aspect normal.
+- Le canal cystique est long.
+Libération prudente des adhérences péri-vésiculaires.
+Abord et dissection du triangle de Callot et de l'infundibulum vésiculaire permettant d'individualiser le canal cystique au
+ras du collet vésiculaire ainsi que l'artère cystique.
+Section du canal cystique après contrôle du moignon cystique restant par 2 clips Hemo-lock de 5 mm.
+Patient(e) : [NOM] [NOM] [NOM]
+IPP : [IPP] / [EPISODE] (MEDECINE GASTRO B2 HC)
+Imprimé le 08/04/2025 à 11 : 14 par Page(s): 1 sur 2N° Finess ✉
+☎ +33(0)156125400
+123456789
+Section de l'artère cystique entre 2 clips Hemo-lock de 5 mm.
+Cholécystectomie rétrograde sans effraction de la paroi.
+Positionnement de la vésicule dans un Endo-bag introduit par le trocart de 10 mm.
+Vérification du lit vésiculaire et réalisation d'hémostase complémentaire ponctuelle.
+Vérification de l'artère et du canal cystique clipés qui retrouve une bonne hémostase et l'absence de fuite biliaire.
+Ablation de tous les trocarts sous contrôle de la vue ce qui permet de vérifier l'absence de saignement au niveau des points
+de ponction.
+Exsufflation de l'ensemble du pneumopéritoine.
+Extériorisation du sac et envoi de la vésicule en analyse anatomopathologique.
+Fermeture aponévrotique de l'orifice de trocart de 10 mm par un point en X de Vicryl 0.
+Fermeture cutanée par du fil résorbable Monocryl 4/0 + colle.
+Drainage : non.
+Bactériologie : non.
+Envoi de la pièce opératoire pour examen anatomopathologique : plusieurs micro-lithiases dans la vésicule ; absence
+de polype vésiculaire ni canal biliaire aberrant.
+Marion PUJOS
+Patient(e) : [NOM] [NOM] [NOM]
+IPP : [IPP] / [EPISODE] (MEDECINE GASTRO B2 HC)
+Imprimé le 08/04/2025 à 11 : 14 par Page(s): 2 sur 2

tests/ground_truth/pdfs/test_propagation/CRO 23117170.audit.jsonl

@@ -0,0 +1,11 @@
+{"page": 0, "kind": "NOM", "original": "Isabelle MARAMBAT", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "111 AVENUE DE L'ADOUR", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "CODE_POSTAL", "original": "64600 ANGLET", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "PIERRE BROCA", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "DATE_NAISSANCE", "original": "Né le 13/06/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "LACLAU LACROUTS", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "LACLAU LACROUTS", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "13.06.1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "13/06/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "13-06-1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "13 06 1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}

tests/ground_truth/pdfs/test_propagation/CRO 23160703.audit.jsonl

@@ -0,0 +1,13 @@
+{"page": 0, "kind": "NOM", "original": "Martine GOMEZ", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "10 rue des augustins", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "JEAN DEAUX", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "36 RUE VICTOR HUGO", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "CODE_POSTAL", "original": "64100 BAYONNE", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
+{"page": 0, "kind": "force_term", "original": "CHCB", "placeholder": "[MASK]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "JEAN DEAUX", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "DATE_NAISSANCE", "original": "Né le 14/04/1953", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "force_term_GLOBAL", "original": "CHCB", "placeholder": "[MASK]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "14-04-1953", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "14/04/1953", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "14 04 1953", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "14.04.1953", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}

tests/ground_truth/pdfs/test_propagation/CRO 23183041.audit.jsonl

@@ -0,0 +1,9 @@
+{"page": 0, "kind": "NOM", "original": "Georges PEPIN", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "1, PLACE PEREIRE", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "CODE_POSTAL", "original": "64100 BAYONNE", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "MARIE-LINE BEDOUET", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "DATE_NAISSANCE", "original": "Née le 12/06/1971", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "12/06/1971", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "12.06.1971", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "12 06 1971", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "12-06-1971", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}

tests/ground_truth/pdfs/test_propagation/CRO 682_23200135.audit.jsonl

@@ -0,0 +1,29 @@
+{"page": 0, "kind": "ETAB", "original": "Pôle de Chirurgie - Anesthésie - Bloc Opératoire", "placeholder": "[MASK]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Romain DIDAILLER", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Floris CAPERA", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Laura ETCHECHOURY", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "35, Avenue Paul Pras", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Renaud GONTIER", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "CODE_POSTAL", "original": "64100 BAYONNE", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Elise CASSAND", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Marie LACLAU-LACROUTS", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ETAB", "original": "Unité Urologie", "placeholder": "[MASK]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Jean-Daniel BADIOLA", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ADRESSE", "original": "7, rue Léonce Goyetche", "placeholder": "[ADRESSE]", "bbox_hint": null}
+{"page": 0, "kind": "CODE_POSTAL", "original": "64500 ST JEAN DE LUZ", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Vincen", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Antoine DOUARD", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "ETAB", "original": "Service Madame Colette DRIDAH", "placeholder": "[MASK]", "bbox_hint": null}
+{"page": 0, "kind": "DATE_NAISSANCE", "original": "Née le 16/06/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Yann LAMMERTYN", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Laurent MASCLE", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Alessandro FALCHETTI", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Florence MAZERES", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Carolin", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Florence MAZERES", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 0, "kind": "NOM", "original": "Bénédicte PONTIER", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": 1, "kind": "NOM", "original": "Florence MAZERES", "placeholder": "[NOM]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "16/06/1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "16 06 1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "16-06-1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
+{"page": -1, "kind": "DATE_NAISSANCE_GLOBAL", "original": "16.06.1948", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}