diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/extract_lambda.py | 22 | ||||
| -rw-r--r-- | src/load_lambda.py | 280 | ||||
| -rw-r--r-- | src/transform_lambda.py | 2 | ||||
| -rw-r--r-- | src/transform_lambda/dataframes.py | 307 | ||||
| -rw-r--r-- | src/transform_lambda/transform_lambda.py | 223 |
5 files changed, 826 insertions, 8 deletions
diff --git a/src/extract_lambda.py b/src/extract_lambda.py index 24f0981..b20c99d 100644 --- a/src/extract_lambda.py +++ b/src/extract_lambda.py @@ -99,24 +99,35 @@ def connect_to_database() -> Connection: raise DBConnectionException("Failed to connect to database") -def extract_bucket(client=boto3.client("s3")): +def extract_bucket(client=None): + if client is None: + client = boto3.client("s3") response = client.list_buckets() extract_bucket_filter = [ bucket["Name"] for bucket in response["Buckets"] if "extract" in bucket["Name"] ] + if not extract_bucket_filter: + raise ValueError("No extract_bucket found") + return extract_bucket_filter[0] -def list_existing_s3_files(bucket_name=extract_bucket(), client=boto3.client("s3")): +def list_existing_s3_files(bucket_name=None, client=None): """Creates a dictionary and populates it with the results of listing the contents of the s3 bucket, then returns the populated dictionary """ + logging.info("Listing existing S3 files") existing_files = {} try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = extract_bucket(client) + response = client.list_objects_v2(Bucket=bucket_name) if "Contents" in response: @@ -132,8 +143,11 @@ def list_existing_s3_files(bucket_name=extract_bucket(), client=boto3.client("s3 logger.error("The bucket is empty") return None - except ClientError as e: - logger.error(f"Error listing S3 objects: {e}") + except ValueError as ve: + logger.error(f"Error listing S3 objects: {ve}") + raise + except ClientError as ce: + logger.error(f"Error listing S3 objects: {ce}") return existing_files diff --git a/src/load_lambda.py b/src/load_lambda.py index c6a8e60..86189dc 100644 --- a/src/load_lambda.py +++ b/src/load_lambda.py @@ -1,2 +1,278 @@ -def lambda_handler(): - pass +import boto3 +from botocore.exceptions import ClientError +import pandas as pd +import pyarrow.parquet as pq +from io import BytesIO +import logging +import json +import traceback +from sqlalchemy import create_engine +from datetime import datetime as dt +import re + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.INFO, +) +# logging.getLogger("botocore").setLevel(logging.INFO) +# logging.getLogger('sqlalchemy.engine').setLevel(logging.DEBUG) + + +def lambda_handler(event, context): + try: + uploaded_tables = upload_dfs_to_database() + if uploaded_tables["not_uploaded"]: + return { + "statusCode": 200, + "body": json.dumps("No dataframes were uploaded."), + } + elif uploaded_tables["uploaded"]: + return { + "statusCode": 200, + "body": json.dumps( + f"""The following dataframes were uploaded successfully: + {uploaded_tables["uploaded"]} .""" + ), + } + else: + logger.error(f"error", exc_info=True) + return {"error"} + except Exception as e: + logger.error({e}, exc_info=True) + return {"statusCode": 500, "body": {e}} + + +def retrieve_secrets(client=None, secret_name=None): + session = boto3.session.Session() + region_name = "eu-west-2" + + if secret_name == None: + secret_name = "bentley-RDS-credentials" + if client == None: + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error( + f"Failed to retrieve secret {secret_name}: {str(e)}", exc_info=True + ) + raise e + except KeyError: + logger.error( + f"Secret {secret_name} does not contain a SecretString", exc_info=True + ) + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + + +# connect to database, slightly different way of doing it, to allow manipulation through pandas + + +def connect_to_db_and_return_engine(sm_secret=None): + if sm_secret is None: + sm_secret = json.loads(retrieve_secrets()) + + try: + secrets = sm_secret + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + conn_str = f"postgresql+pg8000://{user}:{password}@{host}:{port}/{database}" + # interface between python (pandas) and SQL + engine = create_engine(conn_str) + return engine + except Exception as e: + logger.error(f"Interface error: {e}", exc_info=True) + raise RuntimeError("Failed to create database engine") + + +# get transform bucket +def get_transform_bucket(client=None): + if client is None: + client = boto3.client("s3") + try: + response = client.list_buckets() + except ClientError as e: + logger.error(f"Error listing S3 buckets: {e}", exc_info=True) + raise RuntimeError("Error listing S3 buckets") + + transform_bucket_filter = [ + bucket["Name"] + for bucket in response["Buckets"] + if "transform" in bucket["Name"] + ] + + if not transform_bucket_filter: + logger.error("No transform bucket found", exc_info=True) + raise ValueError("No transform bucket found") + + return transform_bucket_filter[0] + + +# list and then retrieve parquet files from S3 bucket +# convert parquet files into dataframes +# return a dictionary of dataframes with name as key, and dataframe object as value + + +def get_latest_timestamp(existing_files): + if existing_files: + all_datetimes = [] + for file_name in existing_files: + match = re.search(r"\/(.+/).+_(.+)\.parquet", file_name) + if match: + datetime_str = "".join(match.group(1, 2)) + all_datetimes.append(dt.strptime(datetime_str, "%Y/%m/%d/%H:%M:%S")) + return max(all_datetimes) if all_datetimes else dt.min + return existing_files + + +def convert_parquet_files_to_dfs(bucket_name=None, client=None): + mutable_df_dict = [ + "dim_currency", + "fact_sales_order", + "fact_purchase_order", + "fact_payment", + ] + + try: + if client is None: + client = boto3.client("s3") + if bucket_name is None: + bucket_name = get_transform_bucket() + files = client.list_objects_v2(Bucket=bucket_name) + + dfs = {} + if "Contents" in files: + s3_key_list = [file["Key"] for file in files["Contents"]] + immutables_l = [] + mutables_d = {prefix: [] for prefix in mutable_df_dict} + for tab, s3_key in mutables_d.items(): + for file in s3_key_list: + if tab in file: + s3_key.append(file) + elif "2024" not in file: + immutables_l.append(file) + else: + continue + immutables_l = list(set(immutables_l)) + latest_s3_keys = [] + for k, v in mutables_d.items(): + latest_s3_keys.append( + dt.strftime( + get_latest_timestamp(v), f"{k}/%Y/%m/%d/{k}_%H:%M:%S.parquet" + ) + ) + for file_key in immutables_l + latest_s3_keys: + try: + file_obj = client.get_object(Bucket=bucket_name, Key=file_key) + parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read())) + df = parquet_file.read().to_pandas() + # >> can't do 'any' (default) because we lose rows in dim_location + df_without_nulls = df.dropna(how="all") + # print("df_without_nulls", df_without_nulls) + # print("type", type(df_without_nulls)) + # print(df_without_nulls.columns) + dfs[file_key] = df_without_nulls + except ClientError as e: + logger.error( + f"Unable to retrieve S3 object {file_key}: {e}", exc_info=True + ) + except Exception as e: + logger.error( + f"Unable to process file {file_key}: {e}", exc_info=True + ) + else: + logger.error(f"No files found in {bucket_name}.", exc_info=True) + return {} + except ValueError as value_error: + logger.error(f"Unable to list objects: {value_error}", exc_info=True) + raise + except ClientError as client_error: + logger.error(f"Unable to list objects: {client_error}", exc_info=True) + raise + return dfs + + +def upload_dfs_to_database(): + upload_status = {"uploaded": [], "not_uploaded": []} + dict_of_dfs = convert_parquet_files_to_dfs() + db_engine = connect_to_db_and_return_engine() + immutable_df_dict = [ + "dim_counterparty.parquet", + "dim_date.parquet", # this needs to be mutable + "dim_location.parquet", + "dim_staff.parquet", + "dim_design.parquet", + "dim_transaction.parquet", # This one was missing, + "dim_payment_type.parquet", + ] + mutable_df_dict = [ + "dim_currency", + "fact_sales_order", + "fact_purchase_order", + "fact_payment", + ] + with db_engine.begin() as connection: + for file_name, df in dict_of_dfs.items(): + print(df.dtypes, "dtypes") + print(df.head()) + print(file_name, "<<< FILE NAME") + print(immutable_df_dict, "<<<IMMUTABLE_DF_DICT") + if file_name in immutable_df_dict: + table_name = file_name.split(".")[0] + print(table_name, "<<<<<") + try: + df.to_sql( + table_name, + con=connection, + schema="project_team_2", + if_exists="append", + index=False, + ) + upload_status["uploaded"].append(table_name) + print(upload_status) + except Exception as e: + logger.error( + f"Error uploading dataframe {file_name} to database: {e}", + exc_info=True, + ) + raise + elif file_name.split("/")[0] in mutable_df_dict: + table_name = file_name.split("/")[0] + print(table_name, "<<<<<<<TABLE NAME") + try: + df.to_sql( + table_name, + con=connection, + schema="project_team_2", + if_exists="append", + index=False, + ) + upload_status["uploaded"].append(table_name) + except Exception as e: + logger.error( + f"Error uploading dataframe {file_name} to database: {e}", + exc_info=True, + ) + raise + else: + upload_status["not_uploaded"].append(file_name) + logger.error( + f"{file_name} does not correspond with table in database", + exc_info=True, + ) + print(upload_status) + db_engine.dispose() + return upload_status + + +if __name__ == "__main__": + lambda_handler(None, None) diff --git a/src/transform_lambda.py b/src/transform_lambda.py deleted file mode 100644 index c6a8e60..0000000 --- a/src/transform_lambda.py +++ /dev/null @@ -1,2 +0,0 @@ -def lambda_handler(): - pass diff --git a/src/transform_lambda/dataframes.py b/src/transform_lambda/dataframes.py new file mode 100644 index 0000000..6de58e7 --- /dev/null +++ b/src/transform_lambda/dataframes.py @@ -0,0 +1,307 @@ +import pandas as pd +from bs4 import BeautifulSoup +import requests + +# Table names: +# fact_sales_order +# fact_purchase_orders +# fact_payment +# dim_transaction +# dim_staff +# dim_payment_type +# dim_location +# dim_design +# dim_date +# dim_currency +# dim_counterparty + + +# no test, same as fact_payment +def create_fact_sales_order(dict_of_df): + df_sales = dict_of_df["sales_order"].rename(columns={"staff_id": "sales_staff_id"}) + + df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date + df_sales["created_time"] = ( + df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["last_updated_date"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.date + ) + df_sales["last_updated_time"] = ( + df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_sales["agreed_delivery_date"] = pd.to_datetime( + df_sales["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_sales["agreed_payment_date"] = pd.to_datetime( + df_sales["agreed_payment_date"], format="%Y-%m-%d" + ) + fact_sales = df_sales.loc[ + :, + [ + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id", + ], + ] + fact_sales.convert_dtypes() + fact_sales.index = pd.RangeIndex(1, len(fact_sales.index) + 1) + fact_sales.index.name = "sales_record_id" + fact_sales.reset_index(inplace=True) + fact_sales.dropna(inplace=True) + return fact_sales + + +# no test, same as fact_payment + + +def create_fact_purchase_orders(dict_of_df): + df_po = dict_of_df["purchase_order"] + df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date + df_po["created_time"] = ( + df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date + df_po["last_updated_time"] = ( + df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_po["agreed_delivery_date"] = pd.to_datetime( + df_po["agreed_delivery_date"], format="%Y-%m-%d" + ) + df_po["agreed_payment_date"] = pd.to_datetime( + df_po["agreed_payment_date"], format="%Y-%m-%d" + ) + fact_purchase_order = df_po.loc[ + :, + [ + "purchase_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "staff_id", + "counterparty_id", + "item_code", + "item_quantity", + "item_unit_price", + "currency_id", + "agreed_delivery_date", + "agreed_payment_date", + "agreed_delivery_location_id", + ], + ] + fact_purchase_order.convert_dtypes() + fact_purchase_order.index = pd.RangeIndex(1, len(fact_purchase_order.index) + 1) + fact_purchase_order.index.name = "purchase_record_id" + fact_purchase_order.reset_index(inplace=True) + fact_purchase_order.dropna(inplace=True) + return fact_purchase_order + + +# test passed + + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment["created_date"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.date + ) + df_payment["created_time"] = ( + df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["last_updated_date"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.date + ) + df_payment["last_updated_time"] = ( + df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time + ) + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d" + ) + fact_payment = df_payment.loc[ + :, + [ + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] + fact_payment.convert_dtypes() + fact_payment.index = pd.RangeIndex(1, len(fact_payment.index) + 1) + fact_payment.index.name = "payment_record_id" + fact_payment.reset_index(inplace=True) + fact_payment.dropna(inplace=True) + fact_payment = fact_payment.astype({"currency_id": "int", "payment_id": "int"}) + return fact_payment + + +# test passed + + +def create_dim_transaction(dict_of_df): + dim_transaction = dict_of_df["transaction"].loc[ + :, ["transaction_id", "transaction_type", "sales_order_id", "purchase_order_id"] + ] + # dim_transaction = dim_transaction.astype({"sales_order_id":"Int64","purchase_order_id":"Int64"}) + return dim_transaction + + +# test passed + + +def create_dim_location(dict_of_df): + dim_location = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + ) + return dim_location + + +def create_dim_counterparty(dict_of_df): + df_prefixed_address = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"phone": "phone_number"}) + .add_prefix("counterparty_legal_", axis=1) + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="counterparty_legal_address_id", + how="inner", + ) # .dropna(inplace=True) + dim_counterparty = df_cp.drop( + labels=[ + "legal_address_id", + "counterparty_legal_address_id", + "created_at", + "last_updated", + "commercial_contact", + "delivery_contact", + ], + axis=1, + ) + return dim_counterparty + + +# test passed + + +def create_dim_date(dict_of_df): + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] + list_of_date_columns = [] + for df in fact_dfs: + date_col_names = [ + col_name for col_name in list(df.columns) if "_date" in col_name + ] + for col in date_col_names: + list_of_date_columns.append(df[col]) + sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]") + df_date = pd.DataFrame(data=sr_date, columns=["date_id"]) + df_date.drop_duplicates(inplace=True) + # df_date.dropna(inplace=True) + df_date["year"] = df_date["date_id"].dt.year + df_date["month"] = df_date["date_id"].dt.month + df_date["day"] = df_date["date_id"].dt.day + df_date["day_of_week"] = df_date["date_id"].dt.dayofweek + df_date["day_name"] = df_date["date_id"].dt.day_name() + df_date["month_name"] = df_date["date_id"].dt.month_name() + df_date["quarter"] = df_date["date_id"].dt.quarter + return df_date + + +# tests passed + + +def scrape_currency_names(): + response = requests.get("https://www.xe.com/currency/").content + soup = BeautifulSoup(response, "html.parser") + currency = [ + item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"}) + ] + sr = pd.Series(currency) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) + return df_cur + + +# tests passed + + +def create_dim_currency(dict_of_df, names=scrape_currency_names()): + df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1) + dim_currency = pd.merge( + df_cur, names, left_on="currency_code", right_on="currency_code", how="left" + ) + dim_currency.drop_duplicates(inplace=True) + dim_currency.astype({"currency_name": "string", "currency_code": "string"}) + print(dim_currency.dtypes, "<<<<<<<<<Dtype") + return dim_currency + + +# tests passed + + +def create_dim_payment_type(dict_of_df): + df_payment_type = dict_of_df["payment_type"] + dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_payment_type + + +# tests passed + + +def create_dim_design(dict_of_df): + df_design = dict_of_df["design"] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] + return dim_design + + +# tests passed + + +def create_dim_staff(dict_of_df): + staff_department = pd.merge( + dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" + ) + dim_staff = staff_department.loc[ + :, + [ + "staff_id", + "first_name", + "last_name", + "department_name", + "location", + "email_address", + ], + ] + return dim_staff diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py new file mode 100644 index 0000000..f782922 --- /dev/null +++ b/src/transform_lambda/transform_lambda.py @@ -0,0 +1,223 @@ +import json +import boto3 +import re +import logging +import pandas as pd +import pyarrow as pa +import pyarrow.parquet as pq +from src.transform_lambda.dataframes import * +from botocore.exceptions import ClientError +from pg8000.native import Connection, InterfaceError +from datetime import datetime + + +class DBConnectionException(Exception): + """Wraps pg8000.native Error or DatabaseError.""" + + def __init__(self, e): + """Initialise with provided error message.""" + self.message = str(e) + super().__init__(self.message) + + +logger = logging.getLogger(__name__) + +logging.basicConfig( + format="{asctime} - {levelname} - {message}", + style="{", + datefmt="%Y-%m-%d %H:%M", + level=logging.DEBUG, +) + +logging.getLogger("botocore").setLevel(logging.WARNING) + +TABLES = [ + "sales_order", + "transaction", + "payment", + "counterparty", + "address", + "staff", + "purchase_order", + "department", + "currency", + "design", + "payment_type", +] + + +def lambda_handler(event, context): + db = None + + try: + db = connect_to_database() + bucket = bucket_name("transform") + + existing_s3_files = list_existing_s3_files(bucket) + + dict_of_df = read_from_s3_subfolder_to_df( + TABLES, bucket_name("extract"), client=boto3.client("s3") + ) + + immutable_df_dict = { + "dim_counterparty": create_dim_counterparty(dict_of_df), + "dim_date": create_dim_date(dict_of_df), + "dim_location": create_dim_location(dict_of_df), + "dim_staff": create_dim_staff(dict_of_df), + "dim_design": create_dim_design(dict_of_df), + "dim_transaction": create_dim_transaction(dict_of_df), + "dim_payment_type": create_dim_payment_type(dict_of_df), + } + + mutable_df_dict = { + "fact_sales_order": create_fact_sales_order(dict_of_df), + "fact_purchase_order": create_fact_purchase_orders(dict_of_df), + "fact_payment": create_fact_payment(dict_of_df), + "dim_currency": create_dim_currency(dict_of_df), + } + print(immutable_df_dict.values()) + print(mutable_df_dict.values()) + status = process_to_parquet_and_upload_to_s3( + existing_s3_files, immutable_df_dict, mutable_df_dict, bucket + ) + + if not status["uploaded"]: + logger.info("No dataframes written to the bucket.") + return { + "statusCode": 204, + "body": json.dumps("No files where uploaded."), + } + + return { + "statusCode": 200, + "body": json.dumps( + f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{ + 'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}""" + ), + } + + except Exception as e: + logger.error(f"Error: {e}", exc_info=True) + return {"statusCode": 500, "body": json.dumps("Internal server error.")} + finally: + if db: + db.close() + + +def process_to_parquet_and_upload_to_s3( + existing_s3_files, + immutable_df_dict, + mutable_df_dict, + bucket, + client=boto3.client("s3"), +): + status = {"uploaded": [], "not_uploaded": []} + + for table_name, df in immutable_df_dict.items(): + if table_name in existing_s3_files: + status["not_uploaded"].append(table_name) + else: + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + # changed parquet_file variable to the file name + client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet") + status["uploaded"].append(table_name) + + for table_name, df in mutable_df_dict.items(): + s3_key = datetime.strftime( + datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet" + ) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + client.upload_file(f"{table_name}.parquet", bucket, s3_key) + status["uploaded"].append(table_name) + + return status + + +def retrieve_secrets(): + secret_name = "bentley-secrets" + region_name = "eu-west-2" + + # Create a Secrets Manager client + session = boto3.session.Session() + client = session.client(service_name="secretsmanager", region_name=region_name) + + try: + get_secret_value_response = client.get_secret_value(SecretId=secret_name) + except ClientError as e: + logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}") + raise e + except KeyError: + logger.error(f"Secret {secret_name} does not contain a SecretString") + raise ValueError(f"Secret {secret_name} does not contain a SecretString") + + return get_secret_value_response["SecretString"] + + +def connect_to_database() -> Connection: + try: + secrets = json.loads(retrieve_secrets()) + host = secrets["host"] + port = secrets["port"] + user = secrets["user"] + password = secrets["password"] + database = secrets["database"] + + return Connection( + database=database, user=user, password=password, host=host, port=port + ) + except InterfaceError as i: + logger.error(f"Interface error: {i}") + raise DBConnectionException("Failed to connect to database") + + +def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): + table_dfs = {} + for table in tables: + response = client.list_objects_v2(Bucket=bucket, Prefix=table) + list_of_keys = [ + "s3://" + bucket + "/" + object["Key"] for object in response["Contents"] + ] + list_of_df = [pd.read_csv(key) for key in list_of_keys] + table_dfs[table] = pd.concat(list_of_df) + return table_dfs + + +def bucket_name(bucket_prefix, client=boto3.client("s3")): + response = client.list_buckets() + bucket_filter = [ + bucket["Name"] + for bucket in response["Buckets"] + if bucket_prefix in bucket["Name"] + ] + + if not bucket_filter: + raise ValueError(f"No bucket found with prefix: {bucket_prefix}") + + return bucket_filter[0] + + +def list_existing_s3_files(bucket_name, client=boto3.client("s3")): + logging.info("Listing existing S3 files") + + try: + response = client.list_objects_v2(Bucket=bucket_name) + + if "Contents" in response: + existing_files = [obj["Key"] for obj in response["Contents"]] + else: + logger.error("The bucket is empty") + return [] # changed from None to [] so it is an iterable + + except ClientError as e: + logger.error(f"Error listing S3 objects: {e}") + raise e + + return existing_files + + +if __name__ == "__main__": + lambda_handler({}, "") |