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 +1,81 @@
{
"source_file": "BACTERIO 23111304.pdf",
"total_replacements": 22,
"regex_replacements": 10,
"ner_replacements": 11,
"sweep_replacements": 1,
"entities_found": [
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "[MEDECIN_12",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8729923367500305
},
{
"original": "THAALBI Asma",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9966022372245789
},
{
"original": "GENDRE Juliette",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9957298636436462
},
{
"original": "URTIZVEREA Marie",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9856418967247009
},
{
"original": "DECOEUR Lucie",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9968544244766235
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9387772679328918
},
{
"original": "MONIER Laurie Assistant",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9169272184371948
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9512264132499695
},
{
"original": "GUILLEMAUD Julien",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.998238205909729
},
{
"original": "LEYSSENE David",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9977700114250183
},
{
"original": "Jacques Loëb",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9729740619659424
}
]
}

View File

@@ -0,0 +1,285 @@
{
"source_file": "CRH 23111304.pdf",
"total_replacements": 306,
"regex_replacements": 146,
"ner_replacements": 0,
"sweep_replacements": 160,
"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": "10002111572",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10002111572",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"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": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"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": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"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": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"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": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
}
]
}

View File

@@ -0,0 +1,15 @@
{
"source_file": "CRO 23111304.pdf",
"total_replacements": 10,
"regex_replacements": 8,
"ner_replacements": 1,
"sweep_replacements": 1,
"entities_found": [
{
"original": "Marion PUJOS",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9858075976371765
}
]
}

View File

@@ -0,0 +1,501 @@
{
"source_file": "trackare-07000323-23111304_07000323_23111304.pdf",
"total_replacements": 761,
"regex_replacements": 181,
"ner_replacements": 32,
"sweep_replacements": 548,
"entities_found": [
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07000323",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23111304",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CIBOURE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "DEROURE BURTIN BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9822848439216614
},
{
"original": "Lucie DECOEUR CURUTCHET CURUTCHET",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9254113435745239
},
{
"original": "URTIZVEREA EICHE MARIE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8862279653549194
},
{
"original": "GENDRE Juliette",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9944695234298706
},
{
"original": "GUILNGAR Anne",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9955964088439941
},
{
"original": "ROSIER Alexandre S",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8827023506164551
},
{
"original": "SOL VERGEZ Magali",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.956055760383606
},
{
"original": "ONDANSETRON AGT",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8900871276855469
},
{
"original": "VERGEZ Magali",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.995144784450531
},
{
"original": "Patricia BOROTRA",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9963185787200928
},
{
"original": "POMMIES Héloise",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9749085307121277
},
{
"original": "SAUTIER Aurore",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.983967125415802
},
{
"original": "TELMISARTAN/HCTZ ACC ROSIER Alexandre",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9252758026123047
},
{
"original": "Magali Signé",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9906765818595886
},
{
"original": "ONDANSETRON",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9322177171707153
},
{
"original": "GENDRE Juliette Signé",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9890196323394775
},
{
"original": "GENDRE Juliette S",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9766837954521179
},
{
"original": "VERGEZ Magali Signé",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9631794095039368
},
{
"original": "Patricia SOMMEIL",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.8715105056762695
},
{
"original": "SAUTIER",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9639441967010498
},
{
"original": "Marion PUJOS",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.949836254119873
},
{
"original": "BOUDIER",
"replacement": "[PATIENT_9]",
"source": "ner",
"score": 0.9220497012138367
},
{
"original": "CAZELLES-BOUDIER",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9844774603843689
},
{
"original": "Juliette GENDRE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9986761212348938
},
{
"original": "Franck LARTIGUE",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.9945442080497742
},
{
"original": "Anne-Laure SORIN",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9975032210350037
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9633520841598511
},
{
"original": "Pujos",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.8769471049308777
},
{
"original": "[MEDECIN_45",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.9207087755203247
},
{
"original": "I Bennis",
"replacement": "[PERSONNE_23]",
"source": "ner",
"score": 0.9896556735038757
},
{
"original": "[MEDECIN_48",
"replacement": "[PERSONNE_24]",
"source": "ner",
"score": 0.8310108184814453
},
{
"original": "[MEDECIN_49",
"replacement": "[PERSONNE_25]",
"source": "ner",
"score": 0.9911224246025085
}
]
}