src/services/file_verification.py

from fastapi import HTTPException, UploadFile
import pandas as pd
import io


# Colonnes requises
required_columns = [
    "Header_Length", "Protocol Type", "Time_To_Live", "Rate",
    "fin_flag_number", "syn_flag_number", "rst_flag_number",
    "psh_flag_number", "ack_flag_number", "ece_flag_number",
    "cwr_flag_number", "ack_count", "syn_count", "fin_count",
    "rst_count", "TCP", "UDP", "Tot sum", "Min", "Max", "AVG",
    "Std", "Tot size", "IAT", "Number", "Variance"
]

def file_verification(file: UploadFile) -> pd.DataFrame:
    """
    Vérifie l'extension et les colonnes du fichier CSV, puis retourne un DataFrame valide.
    Lève une HTTPException descriptive en cas d'erreur.
    """
    try:
        print("start verifying file extension")
        if not file.filename.endswith(".csv"):
            raise HTTPException(status_code=400, detail="Le fichier doit être un CSV")
        
        print("Correct file extension")

        # Lecture du CSV depuis le contenu binaire
        contents = file.file.read()
        data = pd.read_csv(io.BytesIO(contents))

        print("start verifying required columns")

        # Vérification des colonnes
        missing_cols = [col for col in required_columns if col not in data.columns]
        if missing_cols:
            raise HTTPException(
                status_code=400,
                detail=f"Colonnes manquantes dans le CSV: {', '.join(missing_cols)}"
            )

        print("file verification successful")
        return data

    except HTTPException:
        raise
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Erreur de lecture du fichier: {e}")