Add CI

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -47,7 +47,7 @@ body:
         - ParadeDB Docker Image
         - ParadeDB Helm Chart
         - ParadeDB pg_search Extension
-        - ParadeDB pg_lakehouse Extension
+        - ParadeDB pg_analytics Extension
     validations:
       required: true
 

.github/workflows/benchmark-pg_analytics.yml

@@ -0,0 +1,84 @@
+# workflows/benchmark-pg_analytics.yml
+#
+# Benchmark pg_analytics
+# Benchmark ParadeDB's pg_analytics performance on a nightly basis. This workflow can also be triggered
+# manually to benchmark other systems on one-off basis, to compare against ParadeDB.
+
+name: Benchmark pg_analytics
+
+on:
+  schedule:
+    - cron: "1 0 * * 1,2,3,4,5" # Run once per day on weekdays (days of the week 1-5) at 00:01 UTC
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    branches:
+      - dev
+      - main
+    paths:
+      - ".github/workflows/benchmark-pg_analytics.yml"
+      - "cargo-paradedb/**"
+      - "docker/Dockerfile"
+      - "pg_analytics/**"
+      - "!pg_analytics/README.md"
+      - "shared/Cargo.toml"
+  workflow_dispatch:
+
+concurrency:
+  group: benchmark-pg_analytics-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  benchmark-pg_analytics:
+    name: Benchmark pg_analytics on ${{ matrix.name }}
+    runs-on: depot-ubuntu-latest-8
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        include:
+          - name: ClickBench (Parquet, single)
+            flags: -w single
+            pg_version: 16
+          - name: ClickBench (Parquet, partitioned)
+            flags: -w partitioned
+            pg_version: 16
+
+    steps:
+      - name: Checkout Git Repository
+        uses: actions/checkout@v4
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Install & Configure Supported PostgreSQL Version
+        run: |
+          wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
+          sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt/ $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
+          sudo apt-get update && sudo apt-get install -y postgresql-${{ matrix.pg_version }} postgresql-server-dev-${{ matrix.pg_version }}
+          sudo chown -R $(whoami) /usr/share/postgresql/${{ matrix.pg_version }}/ /usr/lib/postgresql/${{ matrix.pg_version }}/ /var/lib/postgresql/${{ matrix.pg_version }}/
+          echo "/usr/lib/postgresql/${{ matrix.pg_version }}/bin" >> $GITHUB_PATH
+
+      - name: Install pgrx & pg_analytics
+        working-directory: pg_analytics/
+        run: |
+          cargo install -j $(nproc) --locked cargo-pgrx --version 0.11.3
+          cargo pgrx init --pg${{ matrix.pg_version }}=/usr/lib/postgresql/${{ matrix.pg_version }}/bin/pg_config
+          cargo pgrx install --pg-config="/usr/lib/postgresql/${{ matrix.pg_version }}/bin/pg_config" --release
+
+      - name: Add pg_analytics to shared_preload_libraries
+        working-directory: /home/runner/.pgrx/data-${{ matrix.pg_version }}/
+        run: sed -i "s/^#shared_preload_libraries = .*/shared_preload_libraries = 'pg_analytics'/" postgresql.conf
+
+      - name: Install the ParadeDB Benchmarking Tool
+        working-directory: cargo-paradedb/
+        run: cargo run install
+
+      - name: Run Official ${{ matrix.name }} Benchmark
+        working-directory: pg_analytics/
+        run: |
+          cargo pgrx start pg${{ matrix.pg_version }}
+          cargo paradedb bench hits run ${{ matrix.flags }} --url postgresql://localhost:288${{ matrix.pg_version }}/postgres
+
+      - name: Notify Slack on Failure
+        if: failure() && (github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main')
+        run: |
+          curl -X POST -H 'Content-type: application/json' --data '{"text":"Benchmark pg_analytics on ${{ matrix.name }} workflow failed in `paradedb/paradedb` -- investigate immediately!"}' ${{ secrets.SLACK_WEBHOOK_URL }}

.github/workflows/lint-bash.yml

@@ -0,0 +1,90 @@
+# workflows/lint-bash.yml
+#
+# Lint Bash
+# Lint and enforce good practices for Bash scripts.
+
+name: Lint Bash
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "**/*.sh"
+      - ".github/workflows/lint-bash.yml"
+  workflow_dispatch:
+
+concurrency:
+  group: lint-bash-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-bash:
+    name: Lint Bash Scripts
+    runs-on: depot-ubuntu-latest-2
+    if: github.event.pull_request.draft == false
+
+    steps:
+      - name: Checkout Git Repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python Environment
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install Beautysh
+        run: pip install beautysh
+
+      - name: Run Beautysh
+        run: |
+          shopt -s globstar nullglob
+          if compgen -G "**/*.sh" > /dev/null; then
+            beautysh **/*.sh --indent-size 2 --check
+          fi
+          shopt -u globstar nullglob
+
+      - name: Check Bash Scripts for "#!/bin/bash"
+        run: |
+          while read -r file
+          do
+            if [[ "$(head -c 11 "$file")" = "#!/bin/bash" ]]
+            then
+              echo "[#!/bin/bash -> Present] $file"
+            else
+              echo "[#!/bin/bash -> NOT FOUND] $file" && exit 1
+            fi
+          done < <(find . -name '*.sh')
+
+      - name: Check Bash Scripts for "set -Eeuo pipefail"
+        run: |
+          while read -r file
+          do
+            if grep -q \
+              -e "^set -Eeuo pipefail$" \
+              -e "^# @paradedb-skip-check-pipefail$" \
+              "$file"
+            then
+              echo "[set -Eeuo pipefail -> Present] $file"
+            else
+              echo "[set -Eeuo pipefail -> NOT FOUND] $file" && exit 1
+            fi
+          done < <(find . -name '*.sh')
+
+      - name: Run ShellCheck
+        shell: python {0}
+        run: |
+          import argparse
+          import glob
+          import subprocess
+          import sys
+
+          sh_files = set(glob.glob("**/*.sh", recursive=True))
+          for file in sh_files:
+            p = subprocess.run(
+                f"shellcheck {file}", shell=True, capture_output=True, check=False
+            )
+            print(p.stdout.decode())
+            if p.returncode != 0:
+                print(f"[Shellcheck did not pass] {file}")
+                sys.exit(1)
+          print(f"[Shellcheck passed] {file}")

.github/workflows/lint-docker.yml

@@ -0,0 +1,34 @@
+# workflows/lint-docker.yml
+#
+# Lint Docker
+# Lint Dockerfiles using Hadolint.
+
+name: Lint Docker
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - ".github/workflows/lint-docker.yml"
+      - "docker/**"
+  workflow_dispatch:
+
+concurrency:
+  group: lint-docker-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-docker:
+    name: Lint Dockerfiles
+    runs-on: depot-ubuntu-latest-2
+    if: github.event.pull_request.draft == false
+
+    steps:
+      - name: Checkout Git Repository
+        uses: actions/checkout@v4
+
+      - name: Run Hadolint
+        uses: jbergstroem/hadolint-gh-action@v1
+        with:
+          dockerfile: "**/Dockerfile*"
+          error_level: 2 # Treat INFO as error

.github/workflows/lint-format.yml

@@ -0,0 +1,64 @@
+# workflows/lint-format.yml
+#
+# Lint Format
+# Lint the project's file trailing spaces, line endings, and format.
+
+name: Lint Format
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+  workflow_dispatch:
+
+concurrency:
+  group: lint-format-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-format:
+    name: Lint File Endings & Trailing Whitespaces
+    runs-on: depot-ubuntu-latest-2
+    if: github.event.pull_request.draft == false
+
+    steps:
+      - name: Checkout Git Repository
+        uses: actions/checkout@v4
+
+      - name: Install fd Search Tool
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y fd-find
+          mkdir -p "$HOME/.local/bin"
+          sudo ln -s $(which fdfind) "$HOME/.local/bin/fd"
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Check for CRLF Files
+        run: |
+          FILES=$(git ls-files --eol | grep crlf || true)
+          if [[ ! -z "$FILES" ]]; then
+            echo "The following files have incorrect line endings:"
+            echo "$FILES"
+            false
+          fi
+
+      # We ignore .out and .sql files, which are used by pg_regress for testing
+      # and need a very specific format
+      - name: Check for Trailing Whitespaces
+        run: |
+          FILES=$(git grep -Ilr '[[:blank:]]$' -- ':(exclude)*.out' ':(exclude)*.sql' ':(exclude)*.rs' || true)
+          if [[ ! -z "$FILES" ]]; then
+            echo "The following files have trailing whitespaces:"
+            echo "$FILES"
+            exit 1
+          fi
+
+      - name: Print Modified Files
+        run: |
+          FILES=$(git ls-files --modified)
+          if [[ ! -z "$FILES" ]]; then
+            echo "The following files have incorrect trailing newlines:"
+            echo "$FILES"
+            echo "Please fix them using:"
+            echo -e 'if [[ -f "$1" ]]; then\n  echo -n "$1"\n  if (diff /dev/null "$1" || true) | tail -1 | grep -q "^\\ No newline"; then\n    echo >> "$1"\n    echo "...fixed"\n  else\n    echo ""\n  fi\nfi'
+            false
+          fi

.github/workflows/lint-markdown.yml

@@ -0,0 +1,41 @@
+# workflows/lint-markdown.yml
+#
+# Lint Markdown
+# Lint Markdown files using Prettier.
+
+name: Lint Markdown
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "**/*.md"
+      - "**/*.mdx"
+      - ".github/workflows/lint-markdown.yml"
+  workflow_dispatch:
+
+concurrency:
+  group: lint-markdown-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-markdown:
+    name: Lint Markdown Files
+    runs-on: depot-ubuntu-latest-2
+    if: github.event.pull_request.draft == false
+
+    steps:
+      - name: Checkout Git Repository
+        uses: actions/checkout@v4
+
+      - name: Set up NodeJS Environment
+        uses: actions/setup-node@v4
+
+      - name: Install Prettier
+        run: npm install -g prettier markdownlint-cli
+
+      - name: Run Markdown Lint
+        run: markdownlint '**/*.md'
+
+      - name: Run Prettier
+        run: prettier --check '{**/*.md,**/*.mdx}'

.github/workflows/lint-pr-title.yml

@@ -0,0 +1,29 @@
+# workflows/lint-pr-title.yml
+#
+# Lint PR Title
+# Lint and enforce proper PR title format.
+
+name: Lint PR Title
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+
+permissions:
+  pull-requests: read
+
+concurrency:
+  group: lint-pr-title-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-pr-title:
+    name: Validate PR Title
+    runs-on: depot-ubuntu-latest-2
+    if: github.event.pull_request.draft == false
+
+    steps:
+      - name: Checkout Git Repository
+        uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}