From 67de54d70ee918bbaf537cb2c119990c4a70c9a7 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Thu, 22 Aug 2024 16:55:48 +0100
Subject: add convert parquet to df function

---
 src/load_lambda.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 48 insertions(+), 2 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index c6a8e60..2f0c33a 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -1,2 +1,48 @@
-def lambda_handler():
-    pass
+import boto3
+from botocore.exceptions import ClientError
+from pg8000.native import Connection, InterfaceError, identifier
+import pandas as pd
+import pyarrow.parquet as pq
+from io import BytesIO
+
+from botocore.exceptions import ClientError
+import logging
+
+
+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)
+    
+def convert_parquet_files_to_dfs(bucket_name=None, client=None):
+    try:
+        if client is None:
+            client = boto3.client("s3")
+        if bucket_name is None:
+            bucket_name = "transform_bucket"
+        files = client.list_objects_v2(Bucket=bucket_name)
+
+        dfs = []
+        for file in files:
+            file_key = file['Key']
+            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()
+                dfs.append(df)
+            except ClientError as e:
+                logger.error(f"Unable to retrieve S3 object {file_key}: {e}")
+    except ValueError as value_error:
+        logger.error(f"Unable to list objects: {value_error}")
+        raise
+    except ClientError as client_error:
+        logger.error(f"Unable to list objects: {client_error}")
+
+    return dfs 
+ 
\ No newline at end of file
-- 
cgit v1.2.3


From 6bf831c5387408e92a63cb5667aab8f415b536e4 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 09:40:08 +0100
Subject: add improved convert parquet files to df function

---
 src/load_lambda.py | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 2f0c33a..1813db4 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -1,11 +1,8 @@
 import boto3
 from botocore.exceptions import ClientError
-from pg8000.native import Connection, InterfaceError, identifier
 import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
-
-from botocore.exceptions import ClientError
 import logging
 
 
@@ -19,7 +16,9 @@ logging.basicConfig(
 )
 
 logging.getLogger("botocore").setLevel(logging.WARNING)
-    
+
+# list and then retrieve parquet files from S3 bucket
+# convert parquet files into dataframes and return a list of dataframes  
 def convert_parquet_files_to_dfs(bucket_name=None, client=None):
     try:
         if client is None:
@@ -29,20 +28,26 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
         files = client.list_objects_v2(Bucket=bucket_name)
 
         dfs = []
-        for file in files:
-            file_key = file['Key']
-            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()
-                dfs.append(df)
-            except ClientError as e:
-                logger.error(f"Unable to retrieve S3 object {file_key}: {e}")
+        if "Contents" in files:
+            for file in files["Contents"]:
+                file_key = file['Key']
+                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()
+                    dfs.append(df)
+                except ClientError as e:
+                    logger.error(f"Unable to retrieve S3 object {file_key}: {e}")
+                except Exception as e:
+                    logger.error(f"Unable to process file {file_key}: {e}")
+        else:
+            logger.error(f"No files found in {bucket_name}.")
+            return []
     except ValueError as value_error:
         logger.error(f"Unable to list objects: {value_error}")
         raise
     except ClientError as client_error:
         logger.error(f"Unable to list objects: {client_error}")
+        raise
 
     return dfs 
- 
\ No newline at end of file
-- 
cgit v1.2.3


From 265d61c34c3a56b7e74333911e65d3148b2945b4 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 09:47:52 +0100
Subject: add get transform bucket function

---
 src/load_lambda.py | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 1813db4..a3fd996 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -17,6 +17,20 @@ logging.basicConfig(
 
 logging.getLogger("botocore").setLevel(logging.WARNING)
 
+# get transform bucket
+def transform_bucket(client=None):
+    if client is None:
+        client = boto3.client("s3")
+    response = client.list_buckets()
+    transform_bucket_filter = [
+        bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"]
+    ]
+
+    if not transform_bucket_filter:
+        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 and return a list of dataframes  
 def convert_parquet_files_to_dfs(bucket_name=None, client=None):
@@ -24,7 +38,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
         if client is None:
             client = boto3.client("s3")
         if bucket_name is None:
-            bucket_name = "transform_bucket"
+            bucket_name = transform_bucket(client)
         files = client.list_objects_v2(Bucket=bucket_name)
 
         dfs = []
-- 
cgit v1.2.3


From 09c8191ce983e4335cfb131d21ddb5413b849cfb Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 11:18:24 +0100
Subject: add tests

---
 src/load_lambda.py        | 61 ++++++++++++++++++++++++++++++++++++++++++++---
 tests/test_load_lambda.py |  3 +--
 2 files changed, 59 insertions(+), 5 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index a3fd996..d95c27a 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -4,6 +4,9 @@ import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
 import logging
+import json
+from src.extract_lambda import retrieve_secrets, connect_to_database
+from sqlalchemy import create_engine
 
 
 logger = logging.getLogger(__name__)
@@ -17,6 +20,43 @@ logging.basicConfig(
 
 logging.getLogger("botocore").setLevel(logging.WARNING)
 
+def lambda_handler(event, context):
+    db = None
+    try:
+        uploaded_tables = upload_dfs_to_database()
+        if uploaded_tables == []:
+            return {
+                "statusCode": 200,
+                "body": json.dumps("No datframes were uploaded."),
+            }
+        return {
+            "statusCode": 200,
+            "body": json.dumps(
+                f"""The following dataframes were uploaded successfully: 
+                {', '.join(upload_dfs_to_database['updated'])}."""
+            ),
+        }
+    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()
+
+# connect to database, slightly different way of doing it, to allow manipulation through pandas
+def connect_to_db_and_return_engine():
+    secrets = json.loads(retrieve_secrets("bentley-RDS-credentials"))  #need to amend retrieve secrets function
+    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}'
+    engine = create_engine(conn_str) #interface between python (pandas) and SQL
+    return engine
+
+
+
 # get transform bucket
 def transform_bucket(client=None):
     if client is None:
@@ -41,7 +81,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
             bucket_name = transform_bucket(client)
         files = client.list_objects_v2(Bucket=bucket_name)
 
-        dfs = []
+        dfs = {}
         if "Contents" in files:
             for file in files["Contents"]:
                 file_key = file['Key']
@@ -49,7 +89,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
                     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()
-                    dfs.append(df)
+                    dfs[file_key] = df
                 except ClientError as e:
                     logger.error(f"Unable to retrieve S3 object {file_key}: {e}")
                 except Exception as e:
@@ -64,4 +104,19 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
         logger.error(f"Unable to list objects: {client_error}")
         raise
 
-    return dfs 
+    return dfs
+
+def upload_dfs_to_database():
+    uploaded = []
+    dict_of_dfs = convert_parquet_files_to_dfs()
+    db_engine = connect_to_db_and_return_engine()
+    try:
+        for table_name, df in dict_of_dfs:
+            df.to_sql(table_name, con=db_engine, ifexists="replace", index=False)
+            uploaded.append(table_name)
+    except Exception as e:
+        logger.error(f"Error uploading dataframes: {e}")
+    db_engine.dispose()
+    return uploaded
+
+    # aiming to return a list of uploaded tables
\ No newline at end of file
diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py
index 0572340..d9ea918 100644
--- a/tests/test_load_lambda.py
+++ b/tests/test_load_lambda.py
@@ -1,8 +1,7 @@
-import boto3
 import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
-from src.load_lambda import convert_parquet_files_to_dataframes
+from src.load_lambda import convert_parquet_files_to_dfs
 
 class TestConvertParquetToDFs:
     def test_convert_parquet_to_dfs_returns_df():
-- 
cgit v1.2.3


From 65289cdd17359c6a29560339e134e0ddf9461ce0 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 12:08:09 +0100
Subject: add amendments to load lambda

---
 src/load_lambda.py | 66 ++++++++++++++++++++++++++++++------------------------
 1 file changed, 37 insertions(+), 29 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index d95c27a..f92bb45 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -1,11 +1,11 @@
 import boto3
-from botocore.exceptions import ClientError
+from botocore.exceptions import ClientError, InterfaceError
 import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
 import logging
 import json
-from src.extract_lambda import retrieve_secrets, connect_to_database
+from src.extract_lambda import retrieve_secrets
 from sqlalchemy import create_engine
 
 
@@ -18,67 +18,74 @@ logging.basicConfig(
     level=logging.DEBUG,
 )
 
-logging.getLogger("botocore").setLevel(logging.WARNING)
+logging.getLogger("botocore").setLevel(logging.INFO)
+
 
 def lambda_handler(event, context):
-    db = None
     try:
         uploaded_tables = upload_dfs_to_database()
-        if uploaded_tables == []:
+        if not uploaded_tables:
             return {
                 "statusCode": 200,
-                "body": json.dumps("No datframes were uploaded."),
+                "body": json.dumps("No dataframes were uploaded."),
             }
         return {
             "statusCode": 200,
             "body": json.dumps(
                 f"""The following dataframes were uploaded successfully: 
-                {', '.join(upload_dfs_to_database['updated'])}."""
+                {', '.join(uploaded_tables)} ."""
             ),
         }
     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()
 
 # connect to database, slightly different way of doing it, to allow manipulation through pandas
 def connect_to_db_and_return_engine():
-    secrets = json.loads(retrieve_secrets("bentley-RDS-credentials"))  #need to amend retrieve secrets function
-    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}'
-    engine = create_engine(conn_str) #interface between python (pandas) and SQL
-    return engine
-
-
+    try:
+        secrets = json.loads(retrieve_secrets("bentley-RDS-credentials"))  #need to amend retrieve secrets function
+        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}'
+        engine = create_engine(conn_str) #interface between python (pandas) and SQL
+        return engine
+    except Exception as e:
+        logger.error(f"Interface error: {e}")
+        raise RuntimeError("Failed to create database engine")
+    
 
 # get transform bucket
-def transform_bucket(client=None):
+def get_transform_bucket(client=None):
     if client is None:
         client = boto3.client("s3")
-    response = client.list_buckets()
+    try:
+        response = client.list_buckets()
+    except ClientError as e:
+        logger.error(f"Error listing S3 buckets: {e}")
+        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:
-        raise ValueError("No transform_bucket found")
+        logger.error("No transform bucket found")
+        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 and return a list of dataframes  
+# convert parquet files into dataframes
+# return a dictionary of dataframes with name as key, and dataframe object as value 
 def convert_parquet_files_to_dfs(bucket_name=None, client=None):
     try:
         if client is None:
             client = boto3.client("s3")
         if bucket_name is None:
-            bucket_name = transform_bucket(client)
+            bucket_name = get_transform_bucket()
         files = client.list_objects_v2(Bucket=bucket_name)
 
         dfs = {}
@@ -96,7 +103,7 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
                     logger.error(f"Unable to process file {file_key}: {e}")
         else:
             logger.error(f"No files found in {bucket_name}.")
-            return []
+            return {}
     except ValueError as value_error:
         logger.error(f"Unable to list objects: {value_error}")
         raise
@@ -111,11 +118,12 @@ def upload_dfs_to_database():
     dict_of_dfs = convert_parquet_files_to_dfs()
     db_engine = connect_to_db_and_return_engine()
     try:
-        for table_name, df in dict_of_dfs:
-            df.to_sql(table_name, con=db_engine, ifexists="replace", index=False)
+        for table_name, df in dict_of_dfs.items():
+            df.to_sql(table_name, con=db_engine, if_exists="replace", index=False)
             uploaded.append(table_name)
     except Exception as e:
         logger.error(f"Error uploading dataframes: {e}")
+        raise
     db_engine.dispose()
     return uploaded
 
-- 
cgit v1.2.3


From f3bb705a31ab9d94dc856c2de0da4b7b73a57fae Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 12:38:25 +0100
Subject: add get transform bucket test

---
 src/load_lambda.py        |  2 +-
 tests/test_load_lambda.py | 48 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 45 insertions(+), 5 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index f92bb45..a9d5ac5 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -1,5 +1,5 @@
 import boto3
-from botocore.exceptions import ClientError, InterfaceError
+from botocore.exceptions import ClientError
 import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py
index d9ea918..2392f10 100644
--- a/tests/test_load_lambda.py
+++ b/tests/test_load_lambda.py
@@ -1,8 +1,48 @@
 import pandas as pd
 import pyarrow.parquet as pq
 from io import BytesIO
-from src.load_lambda import convert_parquet_files_to_dfs
+from moto import mock_aws
+import boto3
+import os
+import pytest
+from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database
 
-class TestConvertParquetToDFs:
-    def test_convert_parquet_to_dfs_returns_df():
-        
\ No newline at end of file
+@pytest.fixture(scope="class")
+def aws_credentials():
+    os.environ["AWS_ACCESS_KEY_ID"] = "testing"
+    os.environ["AWS_SECRET_ACCESS_KEY"] = "testing"
+    os.environ["AWS_SECURIT_TOKEN"] = "testing"
+    os.environ["AWS_SESSION_TOKEN"] = "testing"
+    os.environ["AWS_DEFAULT_REGION"] = "eu-west-2"
+
+
+@pytest.fixture(scope="class")
+def s3_client(aws_credentials):
+    with mock_aws():
+        yield boto3.client("s3")
+
+@pytest.fixture(scope="function")
+def s3_mock_bucket(s3_client):
+    bucket = s3_client.create_bucket(
+        Bucket="transform_bucket",
+        CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+    )
+    return bucket
+
+
+class TestLambdaHandler:
+    pass
+
+class TestConnectToDBAndReturnEngine:
+    pass
+
+class TestGetTransformBucket:
+    def test_get_transform_bucket_returns_string(self, s3_client, s3_mock_bucket):
+        result = get_transform_bucket(s3_client)
+        assert result == "transform_bucket"
+
+class TestConvertParquetToDfs:
+        pass
+
+class TestUploadDfsToDatabase:
+    pass
\ No newline at end of file
-- 
cgit v1.2.3


From 0f8f376fe806ea72f056356cc043213f61159697 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 14:35:36 +0100
Subject: add retrieve secrets function

---
 src/load_lambda.py | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index a9d5ac5..2dc90ba 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -40,10 +40,29 @@ def lambda_handler(event, context):
         logger.error(f"Error: {e}", exc_info=True)
         return {"statusCode": 500, "body": json.dumps("Internal server error.")}
 
+def retrieve_secrets():
+    secret_name = "bentley-RDS-credentials"
+    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"]
+
 # connect to database, slightly different way of doing it, to allow manipulation through pandas
 def connect_to_db_and_return_engine():
     try:
-        secrets = json.loads(retrieve_secrets("bentley-RDS-credentials"))  #need to amend retrieve secrets function
+        secrets = json.loads(retrieve_secrets())
         host = secrets["host"]
         port = secrets["port"]
         user = secrets["user"]
-- 
cgit v1.2.3


From 500ebf24c746ec87c9c846f5a82d638cc23983b9 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Fri, 23 Aug 2024 17:04:08 +0100
Subject: add amendendments for upload_dfs_to_db

---
 src/load_lambda.py | 47 ++++++++++++++++++++++++++++++++++-------------
 1 file changed, 34 insertions(+), 13 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 2dc90ba..8eaea32 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -24,7 +24,7 @@ logging.getLogger("botocore").setLevel(logging.INFO)
 def lambda_handler(event, context):
     try:
         uploaded_tables = upload_dfs_to_database()
-        if not uploaded_tables:
+        if not uploaded_tables["uploaded"]:
             return {
                 "statusCode": 200,
                 "body": json.dumps("No dataframes were uploaded."),
@@ -33,7 +33,7 @@ def lambda_handler(event, context):
             "statusCode": 200,
             "body": json.dumps(
                 f"""The following dataframes were uploaded successfully: 
-                {', '.join(uploaded_tables)} ."""
+                {uploaded_tables["uploaded"]} ."""
             ),
         }
     except Exception as e:
@@ -133,17 +133,38 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
     return dfs
 
 def upload_dfs_to_database():
-    uploaded = []
+    upload_status = {"uploaded": [], "not_uploaded": []}
     dict_of_dfs = convert_parquet_files_to_dfs()
     db_engine = connect_to_db_and_return_engine()
-    try:
-        for table_name, df in dict_of_dfs.items():
-            df.to_sql(table_name, con=db_engine, if_exists="replace", index=False)
-            uploaded.append(table_name)
-    except Exception as e:
-        logger.error(f"Error uploading dataframes: {e}")
-        raise
+    immutable_df_dict = ["dim_counterparty.parquet", 
+                         "dim_date.parquet", #this needs to be mutable
+                         "dim_location.parquet", 
+                         "dim_staff.parquet", 
+                         "dim_design.parquet"]
+    mutable_df_dict = ["fact_sales_order", 
+                       "fact_purchase_order",  
+                       "fact_payment", 
+                       "dim_currency"]
+    
+    for file_name, df in dict_of_dfs.items():
+        if file_name in immutable_df_dict:
+            table_name = file_name.split(".")[0]
+            try:
+                df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False)
+                upload_status["uploaded"].append(table_name)
+            except Exception as e:
+                logger.error(f"Error uploading dataframe {file_name} to database: {e}")
+                raise
+        elif file_name.rsplit('_', 1)[0] in mutable_df_dict:
+            table_name = file_name.rsplit('_', 1)[0]
+            try:
+                    df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False)
+                    upload_status["uploaded"].append(table_name)
+            except Exception as e:
+                logger.error(f"Error uploading dataframe {file_name} to database: {e}")
+                raise
+        else:
+            upload_status["not_uploaded"].append(file_name)
+            logger.error(f"{file_name} does not correspond with table in database")
     db_engine.dispose()
-    return uploaded
-
-    # aiming to return a list of uploaded tables
\ No newline at end of file
+    return upload_status
\ No newline at end of file
-- 
cgit v1.2.3


From 69edb14dad584d45fa6a83a90c08292b84795507 Mon Sep 17 00:00:00 2001
From: "deepsource-autofix[bot]"
 <62050782+deepsource-autofix[bot]@users.noreply.github.com>
Date: Fri, 23 Aug 2024 16:11:45 +0000
Subject: style: format code with Autopep8, Black and Ruff Formatter

This commit fixes the style issues introduced in 0ff2956 according to the output
from Autopep8, Black and Ruff Formatter.

Details: https://github.com/ajschofield/de-project-bentley/pull/95
---
 src/load_lambda.py        | 75 ++++++++++++++++++++++++++++++++---------------
 tests/test_load_lambda.py | 44 +++++++++++++++++----------
 2 files changed, 80 insertions(+), 39 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 8eaea32..6e6bc80 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -40,6 +40,7 @@ def lambda_handler(event, context):
         logger.error(f"Error: {e}", exc_info=True)
         return {"statusCode": 500, "body": json.dumps("Internal server error.")}
 
+
 def retrieve_secrets():
     secret_name = "bentley-RDS-credentials"
     region_name = "eu-west-2"
@@ -59,7 +60,10 @@ def retrieve_secrets():
 
     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():
     try:
         secrets = json.loads(retrieve_secrets())
@@ -68,13 +72,14 @@ def connect_to_db_and_return_engine():
         user = secrets["user"]
         password = secrets["password"]
         database = secrets["database"]
-        conn_str = f'postgresql+pg8000://{user}:{password}@{host}:{port}/{database}'
-        engine = create_engine(conn_str) #interface between python (pandas) and SQL
+        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}")
         raise RuntimeError("Failed to create database engine")
-    
+
 
 # get transform bucket
 def get_transform_bucket(client=None):
@@ -85,9 +90,11 @@ def get_transform_bucket(client=None):
     except ClientError as e:
         logger.error(f"Error listing S3 buckets: {e}")
         raise RuntimeError("Error listing S3 buckets")
-    
+
     transform_bucket_filter = [
-        bucket["Name"] for bucket in response["Buckets"] if "transform" in bucket["Name"]
+        bucket["Name"]
+        for bucket in response["Buckets"]
+        if "transform" in bucket["Name"]
     ]
 
     if not transform_bucket_filter:
@@ -96,9 +103,12 @@ def get_transform_bucket(client=None):
 
     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 
+# return a dictionary of dataframes with name as key, and dataframe object as value
+
+
 def convert_parquet_files_to_dfs(bucket_name=None, client=None):
     try:
         if client is None:
@@ -110,10 +120,10 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
         dfs = {}
         if "Contents" in files:
             for file in files["Contents"]:
-                file_key = file['Key']
+                file_key = file["Key"]
                 try:
                     file_obj = client.get_object(Bucket=bucket_name, Key=file_key)
-                    parquet_file = pq.ParquetFile(BytesIO(file_obj['Body'].read()))
+                    parquet_file = pq.ParquetFile(BytesIO(file_obj["Body"].read()))
                     df = parquet_file.read().to_pandas()
                     dfs[file_key] = df
                 except ClientError as e:
@@ -132,34 +142,51 @@ def convert_parquet_files_to_dfs(bucket_name=None, client=None):
 
     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"]
-    mutable_df_dict = ["fact_sales_order", 
-                       "fact_purchase_order",  
-                       "fact_payment", 
-                       "dim_currency"]
-    
+    immutable_df_dict = [
+        "dim_counterparty.parquet",
+        "dim_date.parquet",  # this needs to be mutable
+        "dim_location.parquet",
+        "dim_staff.parquet",
+        "dim_design.parquet",
+    ]
+    mutable_df_dict = [
+        "fact_sales_order",
+        "fact_purchase_order",
+        "fact_payment",
+        "dim_currency",
+    ]
+
     for file_name, df in dict_of_dfs.items():
         if file_name in immutable_df_dict:
             table_name = file_name.split(".")[0]
             try:
-                df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False)
+                df.to_sql(
+                    table_name,
+                    con=db_engine,
+                    schema="project_team_2",
+                    if_exists="overwrite",
+                    index=False,
+                )
                 upload_status["uploaded"].append(table_name)
             except Exception as e:
                 logger.error(f"Error uploading dataframe {file_name} to database: {e}")
                 raise
-        elif file_name.rsplit('_', 1)[0] in mutable_df_dict:
-            table_name = file_name.rsplit('_', 1)[0]
+        elif file_name.rsplit("_", 1)[0] in mutable_df_dict:
+            table_name = file_name.rsplit("_", 1)[0]
             try:
-                    df.to_sql(table_name, con=db_engine, schema="project_team_2", if_exists="overwrite", index=False)
-                    upload_status["uploaded"].append(table_name)
+                df.to_sql(
+                    table_name,
+                    con=db_engine,
+                    schema="project_team_2",
+                    if_exists="overwrite",
+                    index=False,
+                )
+                upload_status["uploaded"].append(table_name)
             except Exception as e:
                 logger.error(f"Error uploading dataframe {file_name} to database: {e}")
                 raise
@@ -167,4 +194,4 @@ def upload_dfs_to_database():
             upload_status["not_uploaded"].append(file_name)
             logger.error(f"{file_name} does not correspond with table in database")
     db_engine.dispose()
-    return upload_status
\ No newline at end of file
+    return upload_status
diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py
index e04ccec..88c71e4 100644
--- a/tests/test_load_lambda.py
+++ b/tests/test_load_lambda.py
@@ -5,7 +5,14 @@ from moto import mock_aws
 import boto3
 import os
 import pytest
-from src.load_lambda import lambda_handler, connect_to_db_and_return_engine, get_transform_bucket, convert_parquet_files_to_dfs, upload_dfs_to_database
+from src.load_lambda import (
+    lambda_handler,
+    connect_to_db_and_return_engine,
+    get_transform_bucket,
+    convert_parquet_files_to_dfs,
+    upload_dfs_to_database,
+)
+
 
 @pytest.fixture(scope="class")
 def aws_credentials():
@@ -25,12 +32,15 @@ def mock_s3_client(aws_credentials):
 class TestLambdaHandler:
     pass
 
+
 class TestRetrieveSecrets:
     pass
 
+
 class TestConnectToDBAndReturnEngine:
     pass
 
+
 class TestGetTransformBucket:
     def test_raises_value_error_if_no_buckets(self, mock_s3_client):
         with pytest.raises(ValueError, match="No transform bucket found"):
@@ -38,35 +48,38 @@ class TestGetTransformBucket:
 
     def test_raises_value_error_if_no_transform_bucket(self, mock_s3_client):
         mock_s3_client.create_bucket(
-        Bucket="extract_bucket",
-        CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
-    )
+            Bucket="extract_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
         with pytest.raises(ValueError, match="No transform bucket found"):
             get_transform_bucket(mock_s3_client)
 
     def test_returns_transform_bucket_if_one_bucket(self, mock_s3_client):
         mock_s3_client.create_bucket(
-        Bucket="transform_bucket",
-        CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
-    )
+            Bucket="transform_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
         result = get_transform_bucket(mock_s3_client)
         assert result == "transform_bucket"
 
     def test_only_returns_transform_bucket_if_several_buckets(self, mock_s3_client):
         mock_s3_client.create_bucket(
-        Bucket="another_test_bucket",
-        CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
-    )
+            Bucket="another_test_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
         result = get_transform_bucket(mock_s3_client)
         assert result == "transform_bucket"
 
+
 class TestConvertParquetToDfs:
     def test_function_returns_empty_dictionary_if_no_files(self, mock_s3_client):
         mock_s3_client.create_bucket(
-        Bucket="transform_bucket",
-        CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
-    )
-        result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client)
+            Bucket="transform_bucket",
+            CreateBucketConfiguration={"LocationConstraint": "eu-west-2"},
+        )
+        result = convert_parquet_files_to_dfs(
+            bucket_name="transform_bucket", client=mock_s3_client
+        )
         assert result == {}
 
     # def test_function_returns_dictionary_with_table_with_file_key():
@@ -74,5 +87,6 @@ class TestConvertParquetToDfs:
     #     result = convert_parquet_files_to_dfs(bucket_name="transform_bucket", client=mock_s3_client)
     #     assert "dim_staff" in result
 
+
 class TestUploadDfsToDatabase:
-    pass
\ No newline at end of file
+    pass
-- 
cgit v1.2.3


From 151429859bca904cbacf18f4b169f1f768fa212a Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Tue, 27 Aug 2024 12:01:53 +0100
Subject: remove import as not required

---
 src/load_lambda.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 6e6bc80..685c562 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -5,7 +5,6 @@ import pyarrow.parquet as pq
 from io import BytesIO
 import logging
 import json
-from src.extract_lambda import retrieve_secrets
 from sqlalchemy import create_engine
 
 
@@ -169,7 +168,7 @@ def upload_dfs_to_database():
                     table_name,
                     con=db_engine,
                     schema="project_team_2",
-                    if_exists="overwrite",
+                    if_exists="append",
                     index=False,
                 )
                 upload_status["uploaded"].append(table_name)
@@ -183,7 +182,7 @@ def upload_dfs_to_database():
                     table_name,
                     con=db_engine,
                     schema="project_team_2",
-                    if_exists="overwrite",
+                    if_exists="append",
                     index=False,
                 )
                 upload_status["uploaded"].append(table_name)
@@ -195,3 +194,6 @@ def upload_dfs_to_database():
             logger.error(f"{file_name} does not correspond with table in database")
     db_engine.dispose()
     return upload_status
+
+if __name__ == "__main__":
+    lambda_handler(None, None)
-- 
cgit v1.2.3


From 8cd9edde84f4ca706ad93b143c5ff7e3397ce981 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Tue, 27 Aug 2024 12:28:58 +0100
Subject: add json.loads to retrieve secrests function

---
 src/load_lambda.py | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 685c562..f08e335 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -40,16 +40,19 @@ def lambda_handler(event, context):
         return {"statusCode": 500, "body": json.dumps("Internal server error.")}
 
 
-def retrieve_secrets():
-    secret_name = "bentley-RDS-credentials"
+def retrieve_secrets(client=None, secret_name=None):
+    session = boto3.session.Session()
     region_name = "eu-west-2"
 
-    # Create a Secrets Manager client
-    session = boto3.session.Session()
-    client = session.client(service_name="secretsmanager", region_name=region_name)
+    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)
+        print(get_secret_value_response)
     except ClientError as e:
         logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}")
         raise e
@@ -57,7 +60,7 @@ def retrieve_secrets():
         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"]
+    return json.loads(get_secret_value_response["SecretString"])
 
 
 # connect to database, slightly different way of doing it, to allow manipulation through pandas
-- 
cgit v1.2.3


From d623c42a891f2fe8a26493354af0d9e299f3c526 Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 27 Aug 2024 15:19:14 +0100
Subject: refactor: add parameter for sm_secret

---
 src/load_lambda.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index f08e335..11d1d70 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -49,7 +49,6 @@ def retrieve_secrets(client=None, secret_name=None):
     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)
         print(get_secret_value_response)
@@ -66,9 +65,12 @@ def retrieve_secrets(client=None, secret_name=None):
 # connect to database, slightly different way of doing it, to allow manipulation through pandas
 
 
-def connect_to_db_and_return_engine():
+def connect_to_db_and_return_engine(sm_secret=None):
+    if sm_secret is None:
+        sm_secret = retrieve_secrets()
+
     try:
-        secrets = json.loads(retrieve_secrets())
+        secrets = json.loads(sm_secret)
         host = secrets["host"]
         port = secrets["port"]
         user = secrets["user"]
@@ -198,5 +200,6 @@ def upload_dfs_to_database():
     db_engine.dispose()
     return upload_status
 
+
 if __name__ == "__main__":
     lambda_handler(None, None)
-- 
cgit v1.2.3


From cbfc98a9f43b5a0dae95337057c18c9dc2a298e3 Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 27 Aug 2024 16:00:29 +0100
Subject: wip: update TestLambdaHandler & lambda_handler function

---
 src/load_lambda.py        | 19 +++++++++++--------
 tests/test_load_lambda.py | 12 +++++++++---
 2 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 11d1d70..39fa27d 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -23,18 +23,21 @@ logging.getLogger("botocore").setLevel(logging.INFO)
 def lambda_handler(event, context):
     try:
         uploaded_tables = upload_dfs_to_database()
-        if not uploaded_tables["uploaded"]:
+        if uploaded_tables["not_uploaded"]:
             return {
                 "statusCode": 200,
                 "body": json.dumps("No dataframes were uploaded."),
             }
-        return {
-            "statusCode": 200,
-            "body": json.dumps(
-                f"""The following dataframes were uploaded successfully: 
-                {uploaded_tables["uploaded"]} ."""
-            ),
-        }
+
+        if uploaded_tables["uploaded"]:
+            return {
+                "statusCode": 200,
+                "body": json.dumps(
+                    f"""The following dataframes were uploaded successfully: 
+                    {uploaded_tables["uploaded"]} ."""
+                ),
+            }
+
     except Exception as e:
         logger.error(f"Error: {e}", exc_info=True)
         return {"statusCode": 500, "body": json.dumps("Internal server error.")}
diff --git a/tests/test_load_lambda.py b/tests/test_load_lambda.py
index a29b75a..9286e48 100644
--- a/tests/test_load_lambda.py
+++ b/tests/test_load_lambda.py
@@ -35,7 +35,7 @@ class TestLambdaHandler:
     def test_lambda_handler_returns_success(self, mocker):
         mocker.patch(
             "src.load_lambda.upload_dfs_to_database",
-            return_value={"uploaded": ["table_one", "table_two"]},
+            return_value={"uploaded": ["table_one", "table_two"], "not_uploaded": []},
         )
         result = lambda_handler(None, None)
         assert result["statusCode"] == 200
@@ -45,14 +45,20 @@ class TestLambdaHandler:
     def test_lambda_handler_does_not_upload_anything(self, mocker):
         mocker.patch(
             "src.load_lambda.upload_dfs_to_database",
-            return_value={"uploaded": []},
+            return_value={"uploaded": [], "not_uploaded": []},
         )
         result = lambda_handler(None, None)
         assert result["statusCode"] == 200
         assert "No dataframes were uploaded" in result["body"]
 
     def test_lambda_handler_returns_exception(self, mocker):
-        pass
+        mocker.patch(
+            "src.load_lambda.upload_dfs_to_database",
+            return_value={"test": []},
+        )
+
+        with pytest.raises(Exception):
+            lambda_handler(None, None)
 
 
 class TestRetrieveSecrets:
-- 
cgit v1.2.3


From 27f89b78775f9b6fd8d3d560689c53db2beb1b64 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Tue, 27 Aug 2024 16:39:38 +0100
Subject: add logger error to lambda handler

---
 src/load_lambda.py | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 39fa27d..9e15af3 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -5,6 +5,7 @@ import pyarrow.parquet as pq
 from io import BytesIO
 import logging
 import json
+import traceback
 from sqlalchemy import create_engine
 
 
@@ -28,8 +29,7 @@ def lambda_handler(event, context):
                 "statusCode": 200,
                 "body": json.dumps("No dataframes were uploaded."),
             }
-
-        if uploaded_tables["uploaded"]:
+        elif uploaded_tables["uploaded"]:
             return {
                 "statusCode": 200,
                 "body": json.dumps(
@@ -37,10 +37,12 @@ def lambda_handler(event, context):
                     {uploaded_tables["uploaded"]} ."""
                 ),
             }
-
+        else:
+            logger.error(f"error")
+            return {"error"}
     except Exception as e:
-        logger.error(f"Error: {e}", exc_info=True)
-        return {"statusCode": 500, "body": json.dumps("Internal server error.")}
+        logger.error({e})
+        return {"statusCode": 500, "body": {e}}
 
 
 def retrieve_secrets(client=None, secret_name=None):
-- 
cgit v1.2.3


From 0915d4fe4e151d6b593467129b51a1322398fc04 Mon Sep 17 00:00:00 2001
From: Ellie <ecsymonds@gmail.com>
Date: Tue, 27 Aug 2024 17:27:21 +0100
Subject: add json.loads

---
 src/load_lambda.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'src/load_lambda.py')

diff --git a/src/load_lambda.py b/src/load_lambda.py
index 9e15af3..7339ab9 100644
--- a/src/load_lambda.py
+++ b/src/load_lambda.py
@@ -64,7 +64,7 @@ def retrieve_secrets(client=None, secret_name=None):
         logger.error(f"Secret {secret_name} does not contain a SecretString")
         raise ValueError(f"Secret {secret_name} does not contain a SecretString")
 
-    return json.loads(get_secret_value_response["SecretString"])
+    return get_secret_value_response["SecretString"]
 
 
 # connect to database, slightly different way of doing it, to allow manipulation through pandas
@@ -72,10 +72,10 @@ def retrieve_secrets(client=None, secret_name=None):
 
 def connect_to_db_and_return_engine(sm_secret=None):
     if sm_secret is None:
-        sm_secret = retrieve_secrets()
+        sm_secret = json.loads(retrieve_secrets())
 
     try:
-        secrets = json.loads(sm_secret)
+        secrets = sm_secret
         host = secrets["host"]
         port = secrets["port"]
         user = secrets["user"]
@@ -171,13 +171,14 @@ def upload_dfs_to_database():
     ]
 
     for file_name, df in dict_of_dfs.items():
+        print(df)
         if file_name in immutable_df_dict:
             table_name = file_name.split(".")[0]
+            print(table_name, "<<<<<")
             try:
                 df.to_sql(
                     table_name,
                     con=db_engine,
-                    schema="project_team_2",
                     if_exists="append",
                     index=False,
                 )
-- 
cgit v1.2.3