Update app.py

on upload dans un datasethuggingface

app.py

@@ -419,14 +419,68 @@ def ComputeStatistics(df):
 
 
 
-DATASET_DIR = Path("/app/uploads/dataset")
+from huggingface_hub import HfApi
 
-@app.get("/list-files/")
-def list_files():
-    if not DATASET_DIR.exists():
-        return {"error": "Directory not found"}
+UPLOAD_DIR = Path("/app/uploads")  # Dossier temporaire pour stocker les chunks
+HF_TOKEN = "hf_your_api_token"  # 🔥 Remplace par ton token Hugging Face
+DATASET_REPO = "your-username/your-dataset"  # 🔥 Remplace par ton dataset
+
+api = HfApi()
+
+@app.post("/upload-dataset/")
+async def upload_file(
+    file: UploadFile = File(...),
+    chunkIndex: int = Form(...),
+    totalChunks: int = Form(...),
+    fileName: str = Form(...),
+    directory: str = Form(...),
+):
+    try:
+        print(f"Received: chunkIndex={chunkIndex}, totalChunks={totalChunks}, fileName={fileName}, directory={directory}")
+        
+        # Créer le dossier temporaire si nécessaire
+        target_dir = UPLOAD_DIR / directory
+        target_dir.mkdir(parents=True, exist_ok=True)
+
+        # Sauvegarder le chunk
+        chunk_path = target_dir / f"{fileName}.part{chunkIndex}"
+        with open(chunk_path, "wb") as f:
+            f.write(await file.read())
+
+        # Reconstruction si dernier chunk reçu
+        if chunkIndex + 1 == totalChunks:
+            final_file_path = target_dir / fileName
+            with open(final_file_path, "wb") as final_file:
+                for i in range(totalChunks):
+                    part_path = target_dir / f"{fileName}.part{i}"
+                    with open(part_path, "rb") as part_file:
+                        final_file.write(part_file.read())
+                    os.remove(part_path)  # Supprimer les chunks après fusion
+            
+            print(f"Final file created: {final_file_path}")
+
+            # 🔥 Upload vers Hugging Face
+            api.upload_file(
+                path_or_fileobj=str(final_file_path),
+                path_in_repo=f"{directory}/{fileName}",  # Stocker dans un sous-dossier du dataset
+                repo_id=DATASET_REPO,
+                repo_type="dataset",
+                token=HF_TOKEN,
+            )
+
+            # Supprimer le fichier local après upload
+            os.remove(final_file_path)
+
+            return {
+                "status": "success",
+                "message": "File uploaded successfully to Hugging Face.",
+                "hf_url": f"https://huggingface.co/datasets/{DATASET_REPO}/blob/main/{directory}/{fileName}"
+            }
+
+        return {"status": "success", "message": "Chunk uploaded successfully."}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Upload failed: {str(e)}")
 
-    files = [f.name for f in DATASET_DIR.iterdir() if f.is_file()]
-    return {"files": files}