restructured directory, replaced Jenkins with Github Actions for CI a…

…nd added a tests package

.github/workflows/dev-test.yaml

@@ -0,0 +1,50 @@
+name: Pipeline Test in Dev and UAT
+
+on:
+  push:
+    branches: [ "dev" ]
+  pull_request:
+    branches: [ "uat" ]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python 3.11.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.11.10"
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+
+    - name: Create .env file
+      run: | 
+        echo ACCESS_SECRET=${{ secrets.ACCESS_SECRET }} >> .env 
+        echo ACCESS_KEY=${{ secrets.ACCESS_KEY }} >> .env
+
+    - name: Format Scripts in test and src
+      run: |
+        black src
+        black tests
+
+    - name: Lint with Ruff
+      run: |
+        python -m ruff check src/ tests/ 
+
+    - name: Run Sync ETL file
+      run: |
+        echo "running python src/etl.py"
+
+    - name: Test with pytest
+      run: |
+        echo "Starting tests..."

.gitignore

@@ -0,0 +1,177 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+src/.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# PyPI configuration file
+.pypirc
+
+#Test Files
+test.py
+
+# Ruff Formatter
+.ruff_cache

requirements.txt

@@ -1,7 +1,7 @@
-requests~=2.31.0
-pandas~=2.2.1
-yaml~=0.2.5
-pyyaml~=6.0.1
-boto3~=1.34.82
-python-dotenv~=1.0.1
-botocore~=1.34.82
+pandas==2.2.1
+boto3==1.35.57
+python-dotenv==1.0.1
+botocore==1.35.57
+aiohttp==3.11.10
+black==24.10.0
+pytest==7.4.4

src/__init__.py

@@ -0,0 +1 @@
+"""__init__.py file to make directory a python package."""

src/aws_tools/__init__.py

@@ -0,0 +1 @@
+"""__init__.py file to make directory a python package."""

aws_conn.py → src/aws_tools/s3.py

@@ -1,10 +1,7 @@
 import os
 from io import StringIO
 from dotenv import load_dotenv
-import logging
 import boto3
-from botocore.exceptions import ClientError
-import tempfile
 
 
 class S3Buckets:
@@ -37,11 +34,18 @@ def __init__(self, secret, access, region):
         :param region: specified region during instantiation of class
         """
         if region is None:
-            self.client = boto3.client('s3', aws_access_key_id=access, aws_secret_access_key=secret)
+            self.client = boto3.client(
+                "s3", aws_access_key_id=access, aws_secret_access_key=secret
+            )
             print(secret, access, region)
         else:
-            self.location = {'LocationConstraint': region}
-            self.client = boto3.client('s3', aws_access_key_id=access, aws_secret_access_key=secret, region_name=region)
+            self.location = {"LocationConstraint": region}
+            self.client = boto3.client(
+                "s3",
+                aws_access_key_id=access,
+                aws_secret_access_key=secret,
+                region_name=region,
+            )
 
     def list_buckets(self):
         """
@@ -68,10 +72,11 @@ def create_bucket(self, bucket_name):
             pass
         else:
             print("A new bucket will be created in your AWS account")
-            self.client.create_bucket(Bucket=bucket_name, CreateBucketConfiguration=self.location)
+            self.client.create_bucket(
+                Bucket=bucket_name, CreateBucketConfiguration=self.location
+            )
             print(f"The bucket {bucket_name} has been successfully created")
 
-
     def upload_dataframe_to_s3(self, df, bucket_name, object_name):
         """
         This method uploads a pandas dataframe to an S3 bucket in the user's AWS account
@@ -83,7 +88,9 @@ def upload_dataframe_to_s3(self, df, bucket_name, object_name):
         """
         csv_buffer = StringIO()
         df.to_csv(csv_buffer, header=True, index=False)
-        self.client.put_object(Bucket=bucket_name, Body=csv_buffer.getvalue(), Key = object_name)
+        self.client.put_object(
+            Bucket=bucket_name, Body=csv_buffer.getvalue(), Key=object_name
+        )
         print("Dataframe is saved as CSV in S3 bucket.")
 
     def read_file(self, bucket_name, object_name):
@@ -96,6 +103,5 @@ def read_file(self, bucket_name, object_name):
         :return: an object containing the file read from the S3 Bucket.
         """
         response = self.client.get_object(Bucket=bucket_name, Key=object_name)
-        file = StringIO(response['Body'].read().decode('utf-8'))
+        file = StringIO(response["Body"].read().decode("utf-8"))
         return file
-