chore: add .gitignore

This commit is contained in:
dom
2026-03-05 00:37:34 +01:00
parent da34bdc8d7
commit d2e0fec97d
2087 changed files with 1485338 additions and 14 deletions

View File

@@ -0,0 +1,615 @@
{
"source_file": "CRH 23222062.pdf",
"total_replacements": 699,
"regex_replacements": 301,
"ner_replacements": 11,
"sweep_replacements": 387,
"entities_found": [
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": ".GUILNGAR",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.844345211982727
},
{
"original": "MARGUERITE Caroline",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9923909306526184
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9116657376289368
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9281936883926392
},
{
"original": "A.GUILNGAR",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9327138066291809
},
{
"original": "M. [MEDECIN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8771122694015503
},
{
"original": "[MEDECIN_36",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9072927832603455
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9462074637413025
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9714690446853638
},
{
"original": "BOUDIER A",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.943162202835083
},
{
"original": "FOIS Chantal C",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9072545766830444
}
]
}

View File

@@ -0,0 +1,39 @@
{
"source_file": "CRO 23222062.pdf",
"total_replacements": 13,
"regex_replacements": 5,
"ner_replacements": 5,
"sweep_replacements": 3,
"entities_found": [
{
"original": "CHANTAL BORYS",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9647846817970276
},
{
"original": "Callot",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8316116333007812
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9674819707870483
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9772942066192627
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9917036890983582
}
]
}

View File

@@ -0,0 +1,429 @@
{
"source_file": "trackare-99229043-23222062_99229043_23222062.pdf",
"total_replacements": 758,
"regex_replacements": 164,
"ner_replacements": 18,
"sweep_replacements": 576,
"entities_found": [
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99229043",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23222062",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "257034731006405",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "257034731006405",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "47310",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "47310",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "TONNEINS",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "JAOUEN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9975626468658447
},
{
"original": "Marion BEVIERE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9986013174057007
},
{
"original": "Rémi SEGUES",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9987854957580566
},
{
"original": "PELTIER Tristan",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9859827160835266
},
{
"original": "CHANTAL",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9830318093299866
},
{
"original": "GABON Annabelle",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9766160845756531
},
{
"original": "NIVET Dorothée",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9972927570343018
},
{
"original": "LESAFFRE Gaëtan",
"replacement": "[MEDECIN_21]",
"source": "ner",
"score": 0.9909195899963379
},
{
"original": "Admin",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.8462809920310974
},
{
"original": "Annabelle",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9077004790306091
},
{
"original": "LESAFFRE",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9287128448486328
},
{
"original": "Gaëtan A JEUN",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9755434989929199
},
{
"original": "Camille JOUMAA",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9961415529251099
},
{
"original": "Gaëtan LESAFFRE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9958641529083252
},
{
"original": "LESAFF",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9253430962562561
},
{
"original": "Gaëtan ALTIZIDE AR",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9812148809432983
},
{
"original": "Gaëtan ALTIZIDE ARW",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9661797285079956
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9838869571685791
}
]
}