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 +1,687 @@
{
"source_file": "CRH 23077240.pdf",
"total_replacements": 403,
"regex_replacements": 217,
"ner_replacements": 11,
"sweep_replacements": 175,
"entities_found": [
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004401718",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004401718",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004401718",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004401718",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004401718",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102326468",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100422012",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100673481",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100402527",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10000598366",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10002083912",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "ddemarsy@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "ddemarsy@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "ddemarsy@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "ddemarsy@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "ddemarsy@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "secr.csmed@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.endocrino@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "arajot@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "mauzi@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "mgschwind@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "emauryy@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lritz@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "sbordes-couecou@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "[MEDEC",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.839705228805542
},
{
"original": "] RITZ-QUILLACQ Laurence",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9693486094474792
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9611659049987793
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9916445016860962
},
{
"original": "[MEDECIN_19",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8811845183372498
},
{
"original": "QUILLACQ",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9621496200561523
},
{
"original": "[MEDECIN_30",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9423726797103882
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9832685589790344
},
{
"original": "[MEDECIN_34",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9165102243423462
},
{
"original": "LOUTRE Anne-marie",
"replacement": "[PATIENT_3]",
"source": "ner",
"score": 0.9927999973297119
},
{
"original": "[PATIENT",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.8683153390884399
}
]
}

View File

@@ -0,0 +1,357 @@
{
"source_file": "trackare-BA184895-23077240_BA184895_23077240.pdf",
"total_replacements": 646,
"regex_replacements": 157,
"ner_replacements": 33,
"sweep_replacements": 456,
"entities_found": [
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077240",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "260039935043584",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99350",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BENI MELLAL",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GUILLEMAUD GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9985055923461914
},
{
"original": "Rémi SEGUES",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9983665943145752
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9092980623245239
},
{
"original": "ANNE-MARIE",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9763377904891968
},
{
"original": "RITZ-QUILLACQ Laurence S",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9792212247848511
},
{
"original": "RITZ-QUILLACQ",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9972130656242371
},
{
"original": "DEMARSY Delphine Signé",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9958456158638
},
{
"original": "RITZ-QUILLACQ Laurence Signé",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9968751668930054
},
{
"original": "DEMARSY Delphine S",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.897955060005188
},
{
"original": "MAFFLI Isabelle",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9937935471534729
},
{
"original": "RODRIGUES Amanda",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9971513152122498
},
{
"original": "RITZ-QUILLACQ Laurence",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9980382323265076
},
{
"original": "DEMARSY Delphine",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9982390999794006
},
{
"original": "RITZ- QUILLACQ",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9931142926216125
},
{
"original": "QUILLACQ DR",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9748069047927856
},
{
"original": "RITZ",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9979093074798584
},
{
"original": "QUILLACQ",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9909530878067017
},
{
"original": "Amanda TOILETTE",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9234840273857117
},
{
"original": "Isabelle SOMMEIL",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9847291707992554
},
{
"original": "Amanda REPAS",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9599025249481201
},
{
"original": "Amanda",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.8763071298599243
},
{
"original": "RITZ-QUILLAC",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.8453953862190247
},
{
"original": "DEMARSY",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9763495922088623
},
{
"original": "Aurélie CHAMPRES",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.9927301406860352
},
{
"original": "Me L",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.8011232018470764
},
{
"original": "Bastide",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9191154837608337
},
{
"original": "Mathieu",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9115848541259766
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9534151554107666
},
{
"original": "veunac",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.9874429106712341
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_23]",
"source": "ner",
"score": 0.9758321046829224
},
{
"original": "[MEDECIN_47",
"replacement": "[PERSONNE_24]",
"source": "ner",
"score": 0.9461513757705688
},
{
"original": "LOUTRE FRANCE",
"replacement": "[PERSONNE_25]",
"source": "ner",
"score": 0.8638002872467041
},
{
"original": "Jacques Laffitte",
"replacement": "[PERSONNE_26]",
"source": "ner",
"score": 0.9568946361541748
}
]
}