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 +1,675 @@
{
"source_file": "CRH 23075530.pdf",
"total_replacements": 363,
"regex_replacements": 221,
"ner_replacements": 15,
"sweep_replacements": 127,
"entities_found": [
{
"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": "10004401716",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10004401716",
"replacement": "[CODE_BARRE_1]",
"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": "[MEDECIN_",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9923322200775146
},
{
"original": "[MEDECIN_21",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9618238210678101
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9681676626205444
},
{
"original": "Devaux",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9953846335411072
},
{
"original": "[MEDECIN_19",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9689444303512573
},
{
"original": "[MEDEC",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9238582849502563
},
{
"original": "[MEDECIN_18",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.899200439453125
},
{
"original": "[MEDECIN_20",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8936278223991394
},
{
"original": "[MEDECIN_22",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9228649139404297
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9909365773200989
},
{
"original": "QUILLACQ",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.8134925365447998
},
{
"original": "[MEDECIN_15",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9412944912910461
},
{
"original": "Laurence RITZ QUILLACQ",
"replacement": "[MEDECIN_18]",
"source": "ner",
"score": 0.9980672001838684
},
{
"original": "SAUQUILLO Maria",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9955001473426819
},
{
"original": "[MEDECIN_39",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9722389578819275
}
]
}

View File

@@ -0,0 +1,399 @@
{
"source_file": "trackare-17022120-23075530_17022120_23075530.pdf",
"total_replacements": 487,
"regex_replacements": 122,
"ner_replacements": 29,
"sweep_replacements": 336,
"entities_found": [
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "17022120",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23075530",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "LA HABANA",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "Laura BERHO",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9986212253570557
},
{
"original": "Irma Gracie MENDIVIL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9990820288658142
},
{
"original": "DEMARSY Delphine Signé",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9985458850860596
},
{
"original": "CETIRIZINE ARW",
"replacement": "[MEDECIN_12]",
"source": "ner",
"score": 0.9684242010116577
},
{
"original": "DEMARSY Delphine",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9965143203735352
},
{
"original": "Laura BERHO Signé",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9621251821517944
},
{
"original": "Laura BERHO S",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8739609718322754
},
{
"original": "VAGINALE",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.8682982325553894
},
{
"original": "DEMARSY Delphine S",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9547497034072876
},
{
"original": "10MG DEMARSY Delphine",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9600606560707092
},
{
"original": "SERESTA",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9827814102172852
},
{
"original": "SACHET",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9700483679771423
},
{
"original": "GAVISCON SUSP BUV SACHET",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9797765016555786
},
{
"original": "MG DEMARSY Delphine",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9790266156196594
},
{
"original": "CUTANEE DEMARSY",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9329230189323425
},
{
"original": "Delphine",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9644707441329956
},
{
"original": "DEMARSY DR",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9067092537879944
},
{
"original": "DEMARSY",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9593009352684021
},
{
"original": "Laura TOILETTE",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9928886294364929
},
{
"original": "Laura SOMMEIL",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9969625473022461
},
{
"original": "Irma Gracie SOMMEIL",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9945496320724487
},
{
"original": "Laura REPAS",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9956108927726746
},
{
"original": "Laura Signé",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.8433255553245544
},
{
"original": "Ellle",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.9427500367164612
},
{
"original": "OLHAGARAY",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9868647456169128
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9893506765365601
},
{
"original": "breton",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9859398603439331
},
{
"original": "Devaux",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9902982711791992
},
{
"original": "[MEDECIN_3",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9500458836555481
}
]
}