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 +1,375 @@
{
"source_file": "CRH 23196688.pdf",
"total_replacements": 234,
"regex_replacements": 157,
"ner_replacements": 16,
"sweep_replacements": 61,
"entities_found": [
{
"original": "10100541860",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9892317652702332
},
{
"original": "[EMAIL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8114061951637268
},
{
"original": "[PATIENT_4",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.885509192943573
},
{
"original": "[MEDECIN_30",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9088987708091736
},
{
"original": "CEMIPLIMAB",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8483869433403015
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.808475136756897
},
{
"original": "Dufrois",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9919018745422363
},
{
"original": "[PATIENT_",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9798977971076965
},
{
"original": "[MEDECIN_42",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9261439442634583
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9897699356079102
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9457601308822632
},
{
"original": "[MEDECIN_18",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9848803877830505
},
{
"original": "[MEDECIN_43",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9103091955184937
},
{
"original": "MEDEC",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.8166859149932861
},
{
"original": "EUSKALDUNA",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.8862668871879578
},
{
"original": "[MEDECIN_2",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.904394268989563
}
]
}

View File

@@ -0,0 +1,393 @@
{
"source_file": "trackare-23004444-23196688_23004444_23196688.pdf",
"total_replacements": 558,
"regex_replacements": 163,
"ner_replacements": 24,
"sweep_replacements": 371,
"entities_found": [
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23004444",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23196688",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "158056410206201",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64102",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BAYONNE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GUILLEMAUD GUILLEMAUD JAOUEN JAOUEN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.998720109462738
},
{
"original": "[MEDECIN_23",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8427996039390564
},
{
"original": "RICHARD",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9681941866874695
},
{
"original": "NOININ Valérie",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9930025935173035
},
{
"original": "NOCENT-EJNAINI",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.997931182384491
},
{
"original": "ilia GELULE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.868020236492157
},
{
"original": "SABATINI Marielle",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.997833251953125
},
{
"original": "COTRIMOXAZOLE TEVA",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8204014897346497
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9988322257995605
},
{
"original": "Cécilia GELULE",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9756746292114258
},
{
"original": "Valérie SOMMEIL",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9658631086349487
},
{
"original": "Valérie REPAS",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9878919720649719
},
{
"original": "EJNAINI",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9309702515602112
},
{
"original": "SABATINI",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9605934619903564
},
{
"original": "Sheila PELAEZ",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9821351170539856
},
{
"original": "NAHIA GEYRE",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9912528991699219
},
{
"original": "Sheila PELAEZ DEL",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.995925784111023
},
{
"original": "D Sabatini",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9600465893745422
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9596471190452576
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9281946420669556
},
{
"original": "Dufrois",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9860475659370422
},
{
"original": "NOCENT Cecilia",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9362235069274902
},
{
"original": "RECES Anne-marie",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.992293655872345
},
{
"original": "MARIE ALDEA",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.9796172380447388
}
]
}