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 +1,867 @@
{
"source_file": "CRH 23152027.pdf",
"total_replacements": 820,
"regex_replacements": 355,
"ner_replacements": 23,
"sweep_replacements": 442,
"entities_found": [
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9967001676559448
},
{
"original": "Eliquis",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8479869961738586
},
{
"original": "[MEDECIN_43",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9153358340263367
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9546232223510742
},
{
"original": "[MEDECIN_26",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9783574938774109
},
{
"original": "[MEDECIN_52",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8997215032577515
},
{
"original": "[MEDECIN_55",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9859792590141296
},
{
"original": "VIGNES Michel",
"replacement": "[MEDECIN_18]",
"source": "ner",
"score": 0.9763203859329224
},
{
"original": "Elisabeth GUINARD",
"replacement": "[MEDECIN_12]",
"source": "ner",
"score": 0.9968934655189514
},
{
"original": "[MEDECIN_29",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9131553769111633
},
{
"original": "Raynaud",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.8210785388946533
},
{
"original": "[MEDECIN_31",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.8218724131584167
},
{
"original": "[MEDECIN_32",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9228588938713074
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.965164303779602
},
{
"original": "[MEDECIN_37",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9324326515197754
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9902291297912598
},
{
"original": "[MEDECIN_44",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9173792600631714
},
{
"original": "[MEDECIN_36",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.917515218257904
},
{
"original": "[MEDECIN_47",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9248995184898376
},
{
"original": "[MEDECIN_48",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.8657015562057495
},
{
"original": "Evans",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.8809908032417297
},
{
"original": "[MEDECIN_51",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9327355027198792
},
{
"original": "[MEDECIN_53",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9689593315124512
}
]
}

View File

@@ -0,0 +1,339 @@
{
"source_file": "trackare-06017599-23152027_06017599_23152027.pdf",
"total_replacements": 358,
"regex_replacements": 96,
"ner_replacements": 19,
"sweep_replacements": 243,
"entities_found": [
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "06017599",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23152027",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "BAYONNE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "JAOUEN JAOUEN BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9948093295097351
},
{
"original": "Pierre SABATIER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9986071586608887
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9053440690040588
},
{
"original": "Anne Christine CURUTCHET",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9978612065315247
},
{
"original": "BICHAREIL Elina",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9468967318534851
},
{
"original": "VALACICLOV",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8939726948738098
},
{
"original": "VILLETTE Paul-Emile Signé",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9978324174880981
},
{
"original": "PLAQUENIL",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9931419491767883
},
{
"original": "VILLETTE Paul-Emile",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9958733320236206
},
{
"original": "VILLETTE Paul-Emile S",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9373622536659241
},
{
"original": "SERESTA",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.8424385190010071
},
{
"original": "Elina",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.8713362216949463
},
{
"original": "Paul-Emile VILLETTE",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9988518357276917
},
{
"original": "Paul-Emile ARW",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9382926821708679
},
{
"original": "Evans",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.8630519509315491
},
{
"original": "Paul-Emile",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.8404685258865356
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.8762304186820984
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.8448502421379089
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.8046985864639282
}
]
}