feat: pipeline T2A - anonymisation, extraction CIM-10 et intégration edsnlp

Pipeline complet de traitement de documents médicaux PDF :
- Extraction texte (pdfplumber) et classification (Trackare/CRH)
- Anonymisation multi-couche (regex + NER CamemBERT + sweep)
- Extraction médicale CIM-10 hybride : edsnlp (AP-HP) enrichit les
  diagnostics, médicaments (codes ATC via Romedi) et négation,
  avec fallback regex pour les patterns spécifiques
- Fix sentencepiece pinné à <0.2.0 pour compatibilité CamemBERT

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/config.py

@@ -0,0 +1,99 @@
+"""Configuration globale et modèles de données pour le pipeline T2A."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+# --- Chemins ---
+
+BASE_DIR = Path(__file__).resolve().parent.parent
+INPUT_DIR = BASE_DIR / "input"
+OUTPUT_DIR = BASE_DIR / "output"
+ANONYMIZED_DIR = OUTPUT_DIR / "anonymized"
+STRUCTURED_DIR = OUTPUT_DIR / "structured"
+REPORTS_DIR = OUTPUT_DIR / "reports"
+
+for d in (INPUT_DIR, ANONYMIZED_DIR, STRUCTURED_DIR, REPORTS_DIR):
+    d.mkdir(parents=True, exist_ok=True)
+
+
+# --- Configuration anonymisation ---
+
+KEEP_ESTABLISHMENT_NAME = True
+NER_MODEL = "Jean-Baptiste/camembert-ner"
+NER_CONFIDENCE_THRESHOLD = 0.80
+
+
+# --- Modèles de données CIM-10 ---
+
+
+class Sejour(BaseModel):
+    sexe: Optional[str] = None
+    age: Optional[int] = None
+    date_entree: Optional[str] = None
+    date_sortie: Optional[str] = None
+    duree_sejour: Optional[int] = None
+    mode_entree: Optional[str] = None
+    mode_sortie: Optional[str] = None
+    imc: Optional[float] = None
+    poids: Optional[float] = None
+    taille: Optional[float] = None
+
+
+class Diagnostic(BaseModel):
+    texte: str
+    cim10_suggestion: Optional[str] = None
+
+
+class ActeCCAM(BaseModel):
+    texte: str
+    code_ccam_suggestion: Optional[str] = None
+    date: Optional[str] = None
+
+
+class Traitement(BaseModel):
+    medicament: str
+    posologie: Optional[str] = None
+    code_atc: Optional[str] = None
+
+
+class BiologieCle(BaseModel):
+    test: str
+    valeur: Optional[str] = None
+    anomalie: Optional[bool] = None
+
+
+class Imagerie(BaseModel):
+    type: str
+    conclusion: Optional[str] = None
+    score: Optional[str] = None
+
+
+class DossierMedical(BaseModel):
+    source_file: str = ""
+    document_type: str = ""
+    sejour: Sejour = Field(default_factory=Sejour)
+    diagnostic_principal: Optional[Diagnostic] = None
+    diagnostics_associes: list[Diagnostic] = Field(default_factory=list)
+    actes_ccam: list[ActeCCAM] = Field(default_factory=list)
+    antecedents: list[str] = Field(default_factory=list)
+    traitements_sortie: list[Traitement] = Field(default_factory=list)
+    biologie_cle: list[BiologieCle] = Field(default_factory=list)
+    imagerie: list[Imagerie] = Field(default_factory=list)
+    complications: list[str] = Field(default_factory=list)
+
+
+# --- Rapport d'anonymisation ---
+
+
+class AnonymizationReport(BaseModel):
+    source_file: str
+    total_replacements: int = 0
+    regex_replacements: int = 0
+    ner_replacements: int = 0
+    sweep_replacements: int = 0
+    entities_found: list[dict] = Field(default_factory=list)