Adding git workflows with test matrix and common workflows

.github/stale.yml

@@ -0,0 +1,21 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 30
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 5
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - locked
+  - must
+  - roadmap
+  - should
+  - keep
+# Label to use when marking an issue as stale
+staleLabel: stale
+markComment: >
+  We're closing this issue because it hasn't been updated in a while.
+  This isn't a judgement on the merit of the issue in any way.
+  It's just a way of keeping the issues clean.
+  This issue is stale because it has been open 30 days with no activity.
+  Remove stale label or comment or this will be closed in 5 days
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: true

.github/workflows/build_test.yml

@@ -0,0 +1,88 @@
+name: BuildAndTest
+
+on:
+  push:
+    branches:
+      - master
+      - '!release*'
+  pull_request:
+    branches:
+      - master
+      - '!release*'
+jobs:
+  build:
+    name: "Build Deequ with JDK ${{ matrix.java }}, Hadoop ${{ matrix.hadoop }}, Spark ${{ matrix.spark-version }}"
+    # os: [ubuntu-latest, macos-latest, windows-latest]
+    runs-on: ubuntu-20.04
+    strategy:
+      fail-fast: false
+      matrix:
+        hadoop: [2.7, 3.2]
+        java: [11]
+        spark-version: [2.4.7, 3.0.2]  # 3.1.1 - not supported yet
+        scala-version: [2.12]
+    env:
+      GITHUB_PREV_SHA: ${{ github.event.before }}
+      SPARK_VERSION: ${{ matrix.spark-version }}
+    timeout-minutes: 60
+    steps:
+      - name: Checkout Spark repository
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Set up JDK
+        uses: actions/setup-java@v2
+        with:
+          java-version: ${{ matrix.java }}
+          distribution: 'adopt'
+
+      # Install spark from apache-mirror: https://apachemirror.wuchna.com/spark/
+      - name: Run setup-spark ${{ matrix.spark-version }}
+        uses: vemonet/setup-spark@v1
+        with:
+          spark-version: ${{ matrix.spark-version }}
+          hadoop-version: ${{ matrix.hadoop }}
+
+      - name: Check Java
+        run: java -version
+
+      - name: Check Spark
+        run: spark-submit --version
+
+      - name: Check Disk Size before Cache
+        run: |
+          df -hm
+
+      - name: Cache Maven packages
+        uses: actions/cache@v2
+        with:
+          path: ~/.m2
+          key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
+          restore-keys: ${{ runner.os }}-m2
+
+      - name: Check Maven-com Cache
+        uses: actions/cache@v2
+        with:
+          path: ~/.m2/repository/com
+          key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-m2-
+
+      - name: Check Disk Size before Build
+        run: |
+          df -hm
+
+      - name: Build with Maven
+        run: mvn clean install
+
+      - name: Check Disk Size after Build
+        run: |
+          df -hm
+      #   run: mvn --batch-mode --update-snapshots verify
+
+      # - run: mkdir staging && cp target/*.jar staging
+      # - uses: actions/upload-artifact@v2
+      #   with:
+      #     name: Package
+      #     path: staging

.github/workflows/cancel_duplicate_workflow_runs.yml

@@ -0,0 +1,20 @@
+name: Cancelling Duplicates Workflows
+on:
+  workflow_run:
+    workflows:
+      - 'Build and test'
+    types: ['requested']
+
+jobs:
+  # Cancel duplicate workflow runs
+  cancel-duplicate-workflow-runs:
+    name: "Cancel duplicate workflow runs"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: potiuk/cancel-workflow-runs@8248bc1feff049e98c0e6a96889b147199c38203
+        name: "Cancel duplicate workflow runs"
+        with:
+          cancelMode: allDuplicates
+          token: ${{ secrets.GITHUB_TOKEN }}
+          sourceRunId: ${{ github.event.workflow_run.id }}
+          skipEventTypes: '["push", "schedule"]'

.github/workflows/close_stale.yml

@@ -0,0 +1,34 @@
+name: Mark and Close stale issues and pull requests
+
+on:
+  schedule:
+  - cron: "30 0 * * *"
+
+jobs:
+  # Mark and Close stale
+  stale:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+    - uses: actions/stale@v3
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-pr-message: >
+          We're closing this PR because it hasn't been updated in a while.
+          This isn't a judgement on the merit of the PR in any way. It's just
+          a way of keeping the PR queue manageable.
+          If you'd like to revive this PR, please reopen it and ask a
+          committer to remove the Stale tag!
+        stale-pr-label: 'no-pr-activity'
+        stale-issue-message: >
+          We're closing this issue because it hasn't been updated in a while.
+          This isn't a judgement on the merit of the issue in any way.
+          It's just a way of keeping the issues clean.
+          This issue is stale because it has been open 30 days with no activity.
+          Remove stale label or comment or this will be closed in 5 days
+        stale-issue-label: 'no-issue-activity'
+        exempt-issue-labels: 'blocked,must,should,keep'
+        days-before-stale: 30
+        days-before-close: 5

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,62 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches:
+      - master
+      - '!release*'
+  pull_request:
+    branches:
+      - master
+      - '!release*'
+  schedule:
+    - cron: '37 14 * * 3'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
+        # Learn more:
+        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # 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.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+    # - run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/delete_merged_branch.yaml

@@ -0,0 +1,17 @@
+# Reference: https://github.com/SvanBoxel/delete-merged-branch
+name: Delete Merged Branches
+# The event that triggers the workflow
+on:
+  pull_request:
+    types:
+      - closed
+jobs:
+  delete_branch:
+    # The machine each job should run
+    runs-on: ubuntu-latest
+    # The tasks each job should run
+    steps:
+      - name: delete branch
+        uses: SvanBoxel/delete-merged-branch@main
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/greetings.yml

@@ -0,0 +1,16 @@
+name: Greetings
+
+on: [pull_request, issues]
+
+jobs:
+  greeting:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+    - uses: actions/first-interaction@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        issue-message: 'Message that will be displayed on users first issue'
+        pr-message: 'Message that will be displayed on users first pull request'

.github/workflows/lint_commits.yml

@@ -0,0 +1,34 @@
+name: Lint Commits
+
+on:
+  pull_request_target:
+    types: ["opened", "reopened", "synchronize"]
+
+jobs:
+  # lint commits
+  lint_commits:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Lint commits
+        uses: actions-ecosystem/action-lint-commits@v1
+        id: lint-commits
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          regex: '.+' # ^\w+\(.+\): e.g.) "feat(api): Add /users/get" or `ci: Adds CI workflow`
+          format: markdown
+
+      - name: Post warning comment
+        uses: actions-ecosystem/action-create-comment@v1
+        if: ${{ steps.lint-commits.outputs.unmatched_commits != '' }}
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          body: |
+            The following commits needs their message changes:
+
+            ${{ steps.lint-commits.outputs.unmatched_commits }}
+
+            The format `<type>(<scope>): <subject>` (`'.+'`) is acceptable. e.g., `feat(api): Add /users/get` or `ci: Adds CI workflow`
+
+      - name: Soft exit (Fail) when commits don't pass lint
+        if: ${{ steps.lint-commits.outputs.unmatched_commits != '' }}
+        run: exit 0

.github/workflows/on_review_requested.yml

@@ -0,0 +1,18 @@
+name: Review requested
+on:
+  pull_request_target:
+    types: [review_requested]
+jobs:
+  review-label:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions-ecosystem/action-add-labels@v1
+      if: github.event.review.state == 'changes_requested'
+      with:
+        github_token: "${{ secrets.GITHUB_TOKEN }}"
+        labels: todo
+    - uses: actions-ecosystem/action-add-labels@v1
+      if: github.event.review.state == 'approved'
+      with:
+        github_token: "${{ secrets.GITHUB_TOKEN }}"
+        labels: approved