Added linting and pytests (#28)

.github/dependabot.yml

@@ -0,0 +1,15 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/codeql.yml

@@ -0,0 +1,92 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  schedule:
+    - cron: '16 17 * * 5'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: python
+          build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/coverage.yml

@@ -0,0 +1,31 @@
+name: Coverage
+
+on:
+  workflow_run:
+    workflows: ["Tests"]
+    types:
+      - completed
+
+jobs:
+  coverage:
+    name: Run tests & display coverage
+    runs-on: ubuntu-latest
+    if: github.event.workflow_run.event == 'pull_request' && github.event.workflow_run.conclusion == 'success'
+    permissions:
+      # Gives the action the necessary permissions for publishing new
+      # comments in pull requests.
+      pull-requests: write
+      # Gives the action the necessary permissions for editing existing
+      # comments (to avoid publishing multiple comments in the same PR)
+      contents: write
+      # Gives the action the necessary permissions for looking up the
+      # workflow that launched this workflow, and download the related
+      # artifact that contains the comment to be published
+      actions: read
+    steps:
+      - name: Post comment
+        uses: py-cov-action/python-coverage-comment-action@v3
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_PR_RUN_ID: ${{ github.event.workflow_run.id }}
+          verbose: true

.github/workflows/linters.yml

@@ -0,0 +1,43 @@
+name: Linters
+
+on:
+  pull_request:
+  push:
+    branches:
+      - "main"
+
+jobs:
+  black:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry config virtualenvs.create false
+          poetry install --only linters --no-root
+      - name: Run black
+        run: |
+          poetry run black --check .
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry config virtualenvs.create false
+          poetry install --only linters --no-root
+      - name: Run ruff
+        run: |
+          poetry run ruff check .

.github/workflows/tests.yml

@@ -0,0 +1,47 @@
+name: Tests
+
+on:
+  pull_request:
+  push:
+    branches:
+      - "main"
+
+jobs:
+  unit-tests:
+    runs-on: ubuntu-latest
+    permissions:
+      # Gives the action the necessary permissions for publishing new
+      # comments in pull requests.
+      pull-requests: write
+      # Gives the action the necessary permissions for pushing data to the
+      # python-coverage-comment-action branch, and for editing existing
+      # comments (to avoid publishing multiple comments in the same PR)
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry config virtualenvs.create false
+          poetry install --no-root
+      - name: Launch tests & generate report
+        run: poetry run pytest
+      - name: Coverage comment
+        id: coverage_comment
+        uses: py-cov-action/python-coverage-comment-action@v3
+        with:
+          GITHUB_TOKEN: ${{ github.token }}
+          verbose: true
+      - name: Store Pull Request comment to be posted
+        uses: actions/upload-artifact@v4
+        if: steps.coverage_comment.outputs.COMMENT_FILE_WRITTEN == 'true'
+        with:
+          # If you use a different name, update COMMENT_ARTIFACT_NAME accordingly
+          name: python-coverage-comment-action
+          # If you use a different name, update COMMENT_FILENAME accordingly
+          path: python-coverage-comment-action.txt

validation_aws/Job_Dockerfile → Job_Dockerfile

@@ -6,10 +6,10 @@ WORKDIR /usr/app
 
 COPY pyproject.toml .
 COPY poetry.lock .
-COPY src/ ./src/
+COPY src/sbl_validation_processor/*.py ./src/sbl_validation_processor/
 
 RUN poetry config virtualenvs.create false
-RUN poetry install --no-dev
+RUN poetry install --only main,processors
 
 ARG JOB_PATH=""
 ENV JOB_PATH=${JOB_PATH}

validation_aws/Lambda_Dockerfile → Lambda_Dockerfile

@@ -6,10 +6,10 @@ WORKDIR ${LAMBDA_TASK_ROOT}
 
 COPY ./pyproject.toml ${LAMBDA_TASK_ROOT}
 COPY ./poetry.lock ${LAMBDA_TASK_ROOT}
-COPY ./src ./src
+COPY src/sbl_validation_processor/*.py ./src/sbl_validation_processor/
 
 RUN poetry config virtualenvs.create false
-RUN poetry install --no-dev
+RUN poetry install --only main,processors
 
 ARG LAMBDA_PATH
 

validation_aws/Local_Dockerfile → Local_Dockerfile

@@ -9,7 +9,7 @@ COPY poetry.lock .
 COPY src/ ./src/
 
 RUN poetry config virtualenvs.create false
-RUN poetry install --no-dev
+RUN poetry install --no-dev --with local --with processors
 
 COPY local_watchdog/local_file_watcher.py .
 

validation_aws/SQS_Dockerfile → SQS_Dockerfile

@@ -6,10 +6,9 @@ WORKDIR /usr/app
 
 COPY pyproject.toml .
 COPY poetry.lock .
-COPY src/ ./src/
 
 RUN poetry config virtualenvs.create false
-RUN poetry install --no-dev
+RUN poetry install --only main,eks --no-root
 
 ARG SQS_PATH=""
 ENV SQS_PATH=${SQS_PATH}

validation_aws/do_sqs.sh → do_sqs.sh

@@ -9,23 +9,26 @@ then
     docker run -d --platform linux/amd64 --network sbl-project_default -v /tmp/filing_bucket/upload/:/tmp/filing_bucket/upload/ -e ENV=LOCAL -e DB_NAME=filing -e DB_USER=filing_user -e DB_PWD=filing_user -e DB_HOST=pg --name local_validation_run local_validation_run:latest
     docker container ls
 else
-    docker build --platform linux/amd64 -t sqs-parquet:latest -f SQS_Dockerfile --build-arg SQS_PATH=sqs_csv_to_parquet .
-    docker build --platform linux/amd64 -t sqs-validate:latest -f SQS_Dockerfile --build-arg SQS_PATH=sqs_parquet_validation .
-    docker build --platform linux/amd64 -t sqs-aggregator:latest -f SQS_Dockerfile --build-arg SQS_PATH=sqs_validation_aggregator .
-    docker build --platform linux/amd64 -t sqs-parquet-job:latest -f Job_Dockerfile --build-arg JOB_PATH=sqs_csv_to_parquet .
-    docker build --platform linux/amd64 -t sqs-validator-job:latest -f Job_Dockerfile --build-arg JOB_PATH=sqs_parquet_validation .
-    docker build --platform linux/amd64 -t sqs-aggregator-job:latest -f Job_Dockerfile --build-arg JOB_PATH=sqs_validation_aggregator .
-    docker tag sqs-parquet:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet:latest
-    docker tag sqs-parquet-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet-job:latest
-    docker tag sqs-validate:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validate:latest
-    docker tag sqs-validator-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validator-job:latest
-    docker tag sqs-aggregator:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator:latest
-    docker tag sqs-aggregator-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator-job:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet-job:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validate:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validator-job:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator:latest
-    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator-job:latest
+    docker build --platform linux/amd64 -t sqs-parquet:latest -f SQS_Dockerfile --build-arg SQS_PATH=src/sbl_validation_processor/sqs_csv_to_parquet .
+    docker build --platform linux/amd64 -t sqs-validate:latest -f SQS_Dockerfile --build-arg SQS_PATH=src/sbl_validation_processor/sqs_parquet_validation .
+    docker build --platform linux/amd64 -t sqs-aggregator:latest -f SQS_Dockerfile --build-arg SQS_PATH=src/sbl_validation_processor/sqs_validation_aggregator .
+    docker build --platform linux/amd64 -t sqs-parquet-job:latest -f Job_Dockerfile --build-arg JOB_PATH=src/sbl_validation_processor/sqs_csv_to_parquet .
+    docker build --platform linux/amd64 -t sqs-validator-job:latest -f Job_Dockerfile --build-arg JOB_PATH=src/sbl_validation_processor/sqs_parquet_validation .
+    docker build --platform linux/amd64 -t sqs-aggregator-job:latest -f Job_Dockerfile --build-arg JOB_PATH=src/sbl_validation_processor/sqs_validation_aggregator .
+    docker tag sqs-parquet:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet:latest.2
+    docker tag sqs-parquet-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet-job:latest.2
+    docker tag sqs-validate:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validate:latest.2
+    docker tag sqs-validator-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validator-job:latest.2
+    docker tag sqs-aggregator:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator:latest.2
+    docker tag sqs-aggregator-job:latest 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator-job:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-parquet-job:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validate:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-validator-job:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator:latest.2
+    docker push 099248080076.dkr.ecr.us-east-1.amazonaws.com/cfpb/regtech/sqs-aggregator-job:latest.2
+    kubectl rollout restart deployment -n regtech sqs-csv-poller
+    kubectl rollout restart deployment -n regtech sqs-pqs-poller
+    kubectl rollout restart deployment -n regtech sqs-res-poller
 fi