Merge branch 'development' into feature/load-lambda

5 files changed, 733 insertions, 13 deletions

diff --git a/requirements.txt b/requirements.txt
index 614a0ab..763b95a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -31,4 +31,5 @@ xmltodict==0.13.0
 s3fs 
 pandas
 pyarrow
-SQLAlchemy
\ No newline at end of file
+SQLAlchemy
+bs4
diff --git a/src/dataframes.py b/src/dataframes.py
new file mode 100644
index 0000000..ab53063
--- /dev/null
+++ b/src/dataframes.py
@@ -0,0 +1,229 @@
+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
+
+
+def create_fact_sales_order(dict_of_df):
+    df_sales = dict_of_df["sales_order"]
+    df_sales.index.name = "sales_record_id"
+    df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date
+    df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time
+    df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date
+    df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time
+    fact_sales_order = df_sales.loc[
+        :,
+        [
+            "sales_record_id",
+            "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",
+        ],
+    ]
+    return fact_sales_order
+
+
+# fact_purchase_order from purchase_order
+
+
+def create_fact_purchase_orders(dict_of_df):
+    df_po = dict_of_df["purchase_order"]
+    df_po.index.name = "purchase_record_id"
+    df_po["created_date"] = df_po["created_at"].date()
+    df_po["created_time"] = df_po["created_at"].dt.time
+    df_po["last_updated_date"] = df_po["last_updated_at"].date()
+    df_po["last_updated_time"] = df_po["last_updated_at"].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"
+    )
+    df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True)
+    return df_po
+
+
+def create_fact_payment(dict_of_df):
+    df_payment = dict_of_df["payment"]
+    df_payment.index.name = "payment_record_id"
+    df_payment["created_date"] = df_payment["created_at"].date()
+    df_payment["created_time"] = df_payment["created_at"].time
+    df_payment["last_updated_date"] = df_payment["last_updated"].date()
+    df_payment["last_updated_time"] = df_payment["last_updated"].time
+    df_payment["payment_date"] = pd.to_datetime(
+        df_payment["payment_date"], format="%Y-%m-%d"
+    )
+    fact_payment = df_payment.loc[
+        :,
+        [
+            "payment_record_id",
+            "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",
+        ],
+    ]
+    return fact_payment
+
+
+# test passed
+
+
+def create_dim_transaction(dict_of_df):
+    df_transaction = dict_of_df["transaction"].drop(
+        labels=["created_at", "last_updated"], axis=1
+    )
+    return df_transaction
+
+
+# test passed
+def create_dim_location(dict_of_df):
+    df_loc = (
+        dict_of_df["address"]
+        .drop(labels=["created_at", "last_updated"], axis=1)
+        .rename(columns={"address_id": "location_id"})
+    )
+    return df_loc
+
+
+def create_dim_counterparty(dict_of_df):
+    df_prefixed_address = dict_of_df["address"].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="outer",
+    )
+    df_cp.drop(
+        columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True
+    )
+    return df_cp
+
+
+# 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),
+    ]
+    date_col_names = [
+        col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name
+    ]
+    list_of_date_columns = []
+    for df in fact_dfs:
+        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["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_cur = pd.merge(
+        df_cur, names, left_on="currency_code", right_on="currency_code", how="inner"
+    )
+    return dim_cur
+
+
+# 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.py b/src/transform_lambda.py
index 9238180..2cd9272 100644
--- a/src/transform_lambda.py
+++ b/src/transform_lambda.py
@@ -1,16 +1,37 @@
 import json
 import boto3
 import re
-import io
-from io import StringIO
+import logging
 import pandas as pd
+import pyarrow as pa
+import pyarrow.parquet as pq
+from dataframes import *
+from botocore.exceptions import ClientError
+from pg8000.native import Connection, InterfaceError
+from datetime import datetime
 
 
-def lambda_handler(event, context):
-    pass
+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__)
 
-tables = [
+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",
@@ -25,6 +46,130 @@ tables = [
 ]
 
 
+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),
+        }
+
+        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),
+        }
+
+        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
+            client.upload_file(parquet_file, 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(parquet_file, 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:
@@ -35,3 +180,37 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")):
         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"]
+    ]
+
+    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 None
+
+    except ClientError as e:
+        logger.error(f"Error listing S3 objects: {e}")
+        raise e
+
+    return existing_files
+
+
+if __name__ == "__main__":
+    lambda_handler({}, "")
diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py
new file mode 100644
index 0000000..a245379
--- /dev/null
+++ b/tests/test_fact_sales_order.py
@@ -0,0 +1,246 @@
+from src.dataframes import *
+import pandas as pd
+from unittest.mock import patch
+from datetime import datetime as dt
+
+
+class TestCreateDimDesign:
+    def test_dim_design_returns_dataframe(self):
+        d = {
+            "test": ["Hello", "Bye"],
+            "design_id": ["Hello", "Bye"],
+            "design_name": ["Hello", "Bye"],
+            "file_name": ["Hello", "Bye"],
+            "file_location": ["Hello", "Bye"],
+            "Hello": ["Hello", "Bye"],
+        }
+        test_df = {"design": pd.DataFrame(data=d)}
+        result = create_dim_design(test_df)
+        assert isinstance(result, pd.DataFrame)
+
+    def test_dim_design_returns_correct_columns_and_values(self):
+        d = {
+            "test": ["Hello", "Bye"],
+            "design_id": ["Hello", "Bye"],
+            "design_name": ["Hello", "Bye"],
+            "file_name": ["Hello", "Bye"],
+            "file_location": ["Hello", "Bye"],
+            "Hello": ["Hello", "Bye"],
+        }
+        test_df = {"design": pd.DataFrame(data=d)}
+        result = create_dim_design(test_df)
+        d2 = {
+            "design_id": ["Hello", "Bye"],
+            "design_name": ["Hello", "Bye"],
+            "file_name": ["Hello", "Bye"],
+            "file_location": ["Hello", "Bye"],
+        }
+        expected_df = pd.DataFrame(data=d2)
+        expected_result = expected_df.copy()
+        assert result.equals(expected_result)
+
+
+class TestCreateDimStaff:
+    def test_dim_staff_returns_dataframe(self):
+        d = {
+            "staff_id": ["Hello", "Bye"],
+            "first_name": ["Hello", "Bye"],
+            "last_name": ["Hello", "Bye"],
+            "department_id": ["Hello", "Bye"],
+        }
+        d2 = {
+            "department_name": ["Hello", "Bye"],
+            "location": ["Hello", "Bye"],
+            "email_address": ["Hello", "Bye"],
+            "department_id": ["Hello", "Bye"],
+        }
+        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
+        result = create_dim_staff(test_df)
+        assert isinstance(result, pd.DataFrame)
+
+    def test_dim_staff_returns_correct_columns_and_values(self):
+        d = {
+            "staff_id": ["Hello", "Bye"],
+            "first_name": ["Hello", "Bye"],
+            "last_name": ["Hello", "Bye"],
+            "department_id": ["Hello", "Bye"],
+        }
+        d2 = {
+            "department_name": ["Hello", "Bye"],
+            "location": ["Hello", "Bye"],
+            "email_address": ["Hello", "Bye"],
+            "department_id": ["Hello", "Bye"],
+        }
+        test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)}
+        result = create_dim_staff(test_df)
+        expected_d = {
+            "staff_id": ["Hello", "Bye"],
+            "first_name": ["Hello", "Bye"],
+            "last_name": ["Hello", "Bye"],
+            "department_name": ["Hello", "Bye"],
+            "location": ["Hello", "Bye"],
+            "email_address": ["Hello", "Bye"],
+        }
+        expected_df = pd.DataFrame(data=expected_d)
+        expected_result = expected_df.copy()
+        assert result.equals(expected_result)
+
+
+class TestCreatePaymentType:
+    def test_create_dim_payment_type_returns_correct_columns_and_values(self):
+        d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]}
+        test_df = {"payment_type": pd.DataFrame(data=d)}
+        result = create_dim_payment_type(test_df)
+        expected_columns = ["payment_type_id", "payment_type_name"]
+        expected_d = {
+            "payment_type_id": ["Hello", "Bye"],
+            "payment_type_name": ["Hello", "Bye"],
+        }
+        expected_df = pd.DataFrame(data=expected_d)
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+        assert result.equals(expected_df)
+
+
+class TestCreateDimCounterparty:
+    def test_create_dim_counterparty_type_returns_correct_columns_and_object(self):
+        data_l = pd.DataFrame(
+            data={
+                "counterparty_id": ["Hello", "Bye"],
+                "counterparty_legal_name": ["Hello", "Bye"],
+                "commercial_contact": ["Hello", "Bye"],
+                "legal_address_id": ["bond street", "regent street"],
+            }
+        )
+        data_a = pd.DataFrame(
+            data={
+                "address_id": ["bond street", "regent street"],
+                "postcode": [98365, 93753],
+            }
+        )
+        test_df = {"address": data_a, "counterparty": data_l}
+        result = create_dim_counterparty(test_df)
+
+        expected_columns = [
+            "counterparty_id",
+            "counterparty_legal_name",
+            "commercial_contact",
+            "counterparty_legal_postcode",
+        ]
+        print(data_l)
+        print(data_a)
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == expected_columns
+
+
+class TestCreateDimCurrency:
+    def test_dim_currency_returns_columns_and_values(self):
+        nones = [None, None, None]
+        d = {
+            "currency_id": [1, 2, 3],
+            "currency_code": ["USD", "EUR", "GBP"],
+            "created_at": nones,
+            "last_updated": nones,
+        }
+        test_df = {"currency": pd.DataFrame(data=d)}
+        scraper_output = pd.DataFrame(
+            {
+                "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"],
+                "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"],
+            }
+        )
+        result = create_dim_currency(test_df, names=scraper_output).sort_values(
+            by="currency_code", axis=0
+        )
+        expected_d = {
+            "currency_id": [1, 2, 3],
+            "currency_code": ["USD", "EUR", "GBP"],
+            "currency_name": ["US Dollar", "Euro", "Pound"],
+        }
+        expected_df = pd.DataFrame(data=expected_d).sort_values(
+            by="currency_code", axis=0
+        )
+        assert isinstance(result, pd.DataFrame)
+        assert result.equals(expected_df)
+
+    def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self):
+        result = scrape_currency_names()
+        assert isinstance(result, pd.DataFrame)
+        assert list(result.columns) == ["currency_code", "currency_name"]
+
+
+class TestCreateDimDate:
+    def test_returns_required_columns(self):
+        df_one = pd.DataFrame(
+            data={
+                "updated_date": dt(2020, 5, 17),
+                "created_date": dt(2021, 5, 13),
+                "not_dat": None,
+            },
+            index=[0],
+        )
+        df_two = pd.DataFrame(
+            data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)},
+            index=[0],
+        )
+        df_three = pd.DataFrame(
+            data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)},
+            index=[0],
+        )
+        expected_df = pd.DataFrame(
+            data=[
+                [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2],
+                [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2],
+                [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3],
+                [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2],
+                [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2],
+            ],
+            columns=[
+                "date_id",
+                "year",
+                "month",
+                "day",
+                "day_of_week",
+                "day_name",
+                "month_name",
+                "quarter",
+            ],
+        )
+        with patch("src.dataframes.create_fact_payment") as mock_fp:
+            with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo:
+                with patch("src.dataframes.create_fact_sales_order") as mock_fso:
+                    mock_fp.return_value = df_one
+                    mock_fpo.return_value = df_two
+                    mock_fso.return_value = df_three
+                    result = create_dim_date({"dum": 0})
+                    result.reset_index(inplace=True, drop=True)
+                    assert result.eq(expected_df, axis="columns").all(axis=None)
+
+
+class TestCreateDimLocation:
+    def test_returns_correct_columns_lo(self):
+        dict_df = {
+            "address": pd.DataFrame(
+                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
+                columns=["created_at", "last_updated", "address_id", "postal_code"],
+            )
+        }
+        result = create_dim_location(dict_df)
+        assert list(result.columns) == ["location_id", "postal_code"]
+
+
+class TestCreateDimTransaction:
+    def test_returns_correct_columns_tr(self):
+        dict_df = {
+            "transaction": pd.DataFrame(
+                data=[["some_time", "some_other_time", 1, "SE18 9QO"]],
+                columns=[
+                    "created_at",
+                    "last_updated",
+                    "transaction_id",
+                    "some_other_id",
+                ],
+            )
+        }
+        result = create_dim_transaction(dict_df)
+        assert list(result.columns) == ["transaction_id", "some_other_id"]
diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py
index 4c689f7..5ed743e 100644
--- a/tests/test_transform_lambda.py
+++ b/tests/test_transform_lambda.py
@@ -1,11 +1,23 @@
-from src.transform_lambda import read_from_s3_subfolder_to_df
+from src.transform_lambda import (
+    read_from_s3_subfolder_to_df,
+    list_existing_s3_files,
+    bucket_name,
+)
 from moto import mock_aws
 import pytest
 import pandas as pd
 import os
 import boto3
+from botocore.exceptions import ClientError
 import numpy as np
 
+# import caplog
+import logging
+
+
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+
 
 @pytest.fixture(scope="class")
 def aws_credentials():
@@ -23,7 +35,7 @@ def s3_client(aws_credentials):
 
 
 class TestReadFromS3:
-    @pytest.mark.skip(reason="The test is broken!")
+    # @pytest.mark.skip(reason="The test is broken!")
     def test_returns_dictionary_with_correct_value_pair(self, s3_client):
         s3_client.create_bucket(
             Bucket="dummy_buc",
@@ -40,15 +52,20 @@ class TestReadFromS3:
         )
         print(result)
         expected_df = pd.DataFrame(
-            np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]),
-            columns=["Food_type", "Flavour", "Colour"],
+            np.array(
+                [
+                    ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"],
+                    ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"],
+                ]
+            ),
+            columns=["Food_type", "Flavour", "Colour", "last_updated"],
         )
         assert isinstance(result, dict)
         assert list(result.keys())[0] == "Foods"
         assert isinstance(result["Foods"], pd.DataFrame)
         assert result["Foods"].eq(expected_df, axis="columns").all(axis=None)
 
-    @pytest.mark.skip(reason="The test is broken!")
+    # @pytest.mark.skip(reason="The test is broken!")
     def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client):
         s3_client.upload_file(
             "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv"
@@ -58,8 +75,13 @@ class TestReadFromS3:
             tables, bucket="dummy_buc", client=s3_client
         )
         expected_foods_df = pd.DataFrame(
-            np.array([["Vegetable", "Sour", "Green"], ["Berry", "Sweet", "Red"]]),
-            columns=["Food_type", "Flavour", "Colour"],
+            np.array(
+                [
+                    ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"],
+                    ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"],
+                ]
+            ),
+            columns=["Food_type", "Flavour", "Colour", "last_updated"],
         )
         expected_cars_df = pd.DataFrame(
             np.array(
@@ -74,3 +96,46 @@ class TestReadFromS3:
         assert list(result.keys()) == tables
         assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None)
         assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None)
+
+
+class TestListExistingFiles:
+    def test_functions_receives_error_if_no_bucket(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        with pytest.raises(ClientError):
+            list_existing_s3_files("rando_bucket", client=s3_client)
+
+        assert (
+            "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist"
+            in caplog.text
+        )
+
+    def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        s3_client.create_bucket(
+            Bucket="mock_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
+        response = list_existing_s3_files("mock_bucket", client=s3_client)
+        assert "The bucket is empty" in caplog.text
+
+    def test_retrieves_existing_files(self, s3_client, caplog):
+        caplog.set_level(logging.INFO)
+
+        s3_client.upload_file("tests/dummy.txt", "mock_bucket", "dummy.txt")
+        result = list_existing_s3_files("mock_bucket", client=s3_client)
+        assert result == ["dummy.txt"]
+
+
+class TestBucketName:
+    def test_functions_retrieves_bucket(self, s3_client):
+        s3_client.create_bucket(
+            Bucket="mock_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
+
+        bucket = bucket_name("mock_bucket", s3_client)
+        assert bucket == "mock_bucket"
+
+    # def test_