feat: reimport pdf

2026-01-22 21:23:46 +01:00
parent 981fabcc27
commit 4f0ca67dc4
13 changed files with 1068 additions and 14 deletions
--- a/src/plesna_gerance/api/routes/documents.py
+++ b/src/plesna_gerance/api/routes/documents.py
@@ -3,13 +3,15 @@
 import json
 from datetime import datetime

-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, Depends, HTTPException, File, UploadFile, Form
+from fastapi.responses import Response, JSONResponse
 from sqlalchemy.orm import Session
 from sqlalchemy import func, select

-from ...database import get_session, DatabaseService
+from ...database import get_session, DatabaseService, storage
 from ...database.models import Document, Immeuble, Lot, Locataire, Revenu, Depense
 from ...database.service import DuplicateDocumentError
+from ...extractor import extract_compte_rendu
 from ..schemas import SaveRequest, SaveResponse, DocumentSummary

 router = APIRouter(prefix="/api", tags=["documents"])
@@ -64,6 +66,80 @@ async def save_document(
        )


+@router.post("/save-with-pdf", response_model=SaveResponse)
+async def save_document_with_pdf(
+    pdf_file: UploadFile = File(..., description="Fichier PDF original"),
+    data: str = Form(..., description="Donnees JSON extraites"),
+    depenses_tags: str | None = Form(None, description="Tags JSON pour les depenses"),
+    overwrite: bool = Form(False, description="Ecraser si existant"),
+    session: Session = Depends(get_session),
+) -> SaveResponse:
+    """Sauvegarde les donnees extraites avec le fichier PDF original.
+
+    Cette version stocke le PDF et le JSON sur le disque pour tracabilite.
+
+    - **pdf_file**: Fichier PDF original (multipart)
+    - **data**: Donnees JSON extraites (string JSON)
+    - **depenses_tags**: Tags JSON pour les depenses (optionnel)
+    - **overwrite**: Si True, ecrase le document existant
+    """
+    # Parse JSON data
+    try:
+        parsed_data = json.loads(data)
+    except json.JSONDecodeError as e:
+        raise HTTPException(status_code=400, detail=f"JSON invalide pour data: {e}")
+
+    # Parse depenses_tags if provided
+    parsed_tags = None
+    if depenses_tags:
+        try:
+            parsed_tags = json.loads(depenses_tags)
+        except json.JSONDecodeError as e:
+            raise HTTPException(
+                status_code=400, detail=f"JSON invalide pour depenses_tags: {e}"
+            )
+
+    # Read PDF content
+    try:
+        pdf_content = await pdf_file.read()
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Erreur lecture du PDF: {str(e)}")
+
+    try:
+        db_service = DatabaseService(session)
+        document = db_service.save_document(
+            data=parsed_data,
+            source_file=pdf_file.filename,
+            pdf_content=pdf_content,
+            depenses_tags=parsed_tags,
+            overwrite=overwrite,
+        )
+
+        return SaveResponse(
+            success=True,
+            message="Document sauvegarde avec succes (PDF et JSON stockes)",
+            document_id=document.id,
+            reference=document.reference,
+            date=str(document.date),
+        )
+
+    except DuplicateDocumentError as e:
+        return SaveResponse(
+            success=False,
+            message=f"Document deja existant: reference={e.reference}, date={e.date}",
+            reference=e.reference,
+            date=str(e.date),
+        )
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+
+    except Exception as e:
+        raise HTTPException(
+            status_code=500, detail=f"Erreur lors de la sauvegarde: {str(e)}"
+        )
+
+
@router.get("/stats")
 async def get_stats(
    session: Session = Depends(get_session),
@@ -110,6 +186,8 @@ async def list_documents(
            solde_montant=doc.solde_montant,
            solde_type=doc.solde_type,
            created_at=doc.created_at.isoformat() if doc.created_at else None,
+            has_pdf=doc.pdf_path is not None,
+            has_json=doc.json_path is not None,
        )
        for doc in documents
    ]
@@ -157,6 +235,8 @@ async def get_document(
        },
        "json_data": json.loads(document.json_data) if document.json_data else None,
        "created_at": document.created_at.isoformat() if document.created_at else None,
+        "has_pdf": document.pdf_path is not None,
+        "has_json": document.json_path is not None,
    }


@@ -189,3 +269,135 @@ async def check_duplicate(
        "reference": reference,
        "date": date,
    }
+
+
+@router.get("/documents/{document_id}/pdf")
+async def download_document_pdf(
+    document_id: int,
+    session: Session = Depends(get_session),
+) -> Response:
+    """Telecharge le fichier PDF original d'un document.
+
+    Retourne le fichier PDF si disponible, sinon erreur 404.
+    """
+    db_service = DatabaseService(session)
+    document = db_service.get_document_by_id(document_id)
+
+    if not document:
+        raise HTTPException(status_code=404, detail="Document non trouve")
+
+    if not document.pdf_path:
+        raise HTTPException(
+            status_code=404,
+            detail="Fichier PDF non disponible pour ce document",
+        )
+
+    try:
+        pdf_content = storage.read_pdf(document.pdf_path)
+        filename = document.source_file or f"{document.reference}.pdf"
+        return Response(
+            content=pdf_content,
+            media_type="application/pdf",
+            headers={"Content-Disposition": f'inline; filename="{filename}"'},
+        )
+    except FileNotFoundError:
+        raise HTTPException(
+            status_code=404,
+            detail="Fichier PDF introuvable sur le disque",
+        )
+
+
+@router.get("/documents/{document_id}/json")
+async def download_document_json(
+    document_id: int,
+    session: Session = Depends(get_session),
+) -> Response:
+    """Telecharge le fichier JSON extrait d'un document.
+
+    Retourne le fichier JSON si disponible sur disque,
+    sinon retourne le json_data de la base de donnees.
+    """
+    db_service = DatabaseService(session)
+    document = db_service.get_document_by_id(document_id)
+
+    if not document:
+        raise HTTPException(status_code=404, detail="Document non trouve")
+
+    filename = f"{document.reference}_{document.date}.json"
+
+    # Try to read from storage first
+    if document.json_path:
+        try:
+            json_data = storage.read_json(document.json_path)
+            return JSONResponse(
+                content=json_data,
+                headers={"Content-Disposition": f'attachment; filename="{filename}"'},
+            )
+        except FileNotFoundError:
+            pass  # Fall back to database
+
+    # Fall back to json_data in database
+    if document.json_data:
+        json_data = json.loads(document.json_data)
+        return JSONResponse(
+            content=json_data,
+            headers={"Content-Disposition": f'attachment; filename="{filename}"'},
+        )
+
+    raise HTTPException(
+        status_code=404,
+        detail="Donnees JSON non disponibles pour ce document",
+    )
+
+
+@router.post("/documents/{document_id}/re-extract")
+async def re_extract_document(
+    document_id: int,
+    session: Session = Depends(get_session),
+) -> dict:
+    """Re-extrait les donnees depuis le PDF stocke.
+
+    Utile pour corriger l'extraction apres amelioration des parsers.
+    Ne modifie pas automatiquement la base - retourne les nouvelles donnees
+    pour validation par l'utilisateur.
+
+    Retourne les donnees re-extraites du PDF.
+    """
+    db_service = DatabaseService(session)
+    document = db_service.get_document_by_id(document_id)
+
+    if not document:
+        raise HTTPException(status_code=404, detail="Document non trouve")
+
+    if not document.pdf_path:
+        raise HTTPException(
+            status_code=404,
+            detail="Fichier PDF non disponible pour ce document - re-extraction impossible",
+        )
+
+    # Get absolute path
+    pdf_full_path = storage.get_absolute_path(document.pdf_path)
+
+    if not pdf_full_path.exists():
+        raise HTTPException(
+            status_code=404,
+            detail="Fichier PDF introuvable sur le disque",
+        )
+
+    # Re-extract
+    try:
+        new_data = extract_compte_rendu(str(pdf_full_path))
+    except Exception as e:
+        raise HTTPException(
+            status_code=422,
+            detail=f"Erreur lors de la re-extraction: {str(e)}",
+        )
+
+    return {
+        "document_id": document_id,
+        "reference": document.reference,
+        "date": str(document.date),
+        "original_json_path": document.json_path,
+        "re_extracted_data": new_data,
+        "message": "Donnees re-extraites. Utilisez PUT /api/documents/{id} pour mettre a jour.",
+    }