import boto3
import pandas as pd
from io import BytesIO

# from dotenv import load_dotenv
#
# load_dotenv()

def list_files_in_s3_folder(bucket_name, folder_path):
    """
    List all files in a specified S3 folder.

    Args:
        bucket_name (str): The name of the S3 bucket.
        folder_path (str): The path to the folder in the S3 bucket.

    Returns:
        list: A list of file names in the specified S3 folder.
    """
    s3_client = boto3.client('s3')

    
    # List objects in the specified S3 folder
    result = s3_client.list_objects_v2(Bucket=bucket_name, Prefix=folder_path)

    
    if 'Contents' not in result:
        return []

    # Extract the file names
    file_names = [item['Key'] for item in result['Contents']]
    
    return file_names


def read_file_from_s3(bucket_name, file_key):
    """
    Read the content of a file from S3 and return it as a byte stream.

    Args:
        bucket_name (str): The name of the S3 bucket.
        file_key (str): The key (path) to the Excel file in the S3 bucket.
    
    Returns:
        BytesIO: The content of the file as a BytesIO.
    """
    s3_client = boto3.client('s3')

    try:
        # Download the file content from S3
        response = s3_client.get_object(Bucket=bucket_name, Key=file_key)
        
        # Read the file content into a pandas DataFrame
        file_content = response['Body'].read()

        # Use BytesIO to read the file content in-memory
        s3_file = BytesIO(file_content)

        return s3_file

    except Exception as e:
        print(f"Error reading file from S3: {e}")
        return None