Merge branch 'datafusion-contrib:main' into gene.bordegaray/2025/11/add_broadcast_join_operator

Author: gene-bordegaray

.github/actions/setup/action.yml

@@ -12,6 +12,9 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: Free up disk space
+      shell: bash
+      run: ${{ github.action_path }}/free_disk_space.sh
     - shell: bash
       run: |
         echo $HOME
@@ -26,3 +29,4 @@ runs:
     - uses: Swatinem/rust-cache@v2
       with:
         key: ${{ runner.os }}-${{ inputs.targets }}-rust-cache
+        prefix-key: v1-rust

.github/actions/setup/free_disk_space.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# Script to free up disk space on CI systems
+# Source: https://github.com/apache/flink/blob/02d30ace69dc18555a5085eccf70ee884e73a16e/tools/azure-pipelines/free_disk_space.sh
+
+echo "Freeing up disk space on CI system"
+
+echo "Listing 100 largest packages"
+dpkg-query -Wf '${Installed-Size}\t${Package}\n' | sort -n | tail -n 100
+df -h
+
+echo "Removing large packages"
+sudo apt-get remove -y '^ghc-8.*'
+sudo apt-get remove -y '^dotnet-.*'
+sudo apt-get remove -y '^llvm-.*'
+sudo apt-get remove -y 'php.*'
+sudo apt-get remove -y azure-cli google-cloud-sdk hhvm google-chrome-stable firefox powershell mono-devel
+sudo apt-get autoremove -y
+sudo apt-get clean
+df -h
+
+echo "Removing large directories"
+rm -rf /usr/share/dotnet/
+df -h

.github/workflows/ci.yml

@@ -9,12 +9,20 @@ on:
 env:
   CARGO_TERM_COLOR: always
   RUST_BACKTRACE: 1
+  TPCDS_SCALE_FACTOR: 0.5 # 0.5 scale factor produces a data dir which is 124MB
 
 concurrency:
   group: ${{ github.ref }}
   cancel-in-progress: true
 
 jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/setup
+      - run: cargo build
+
   clippy:
     runs-on: ubuntu-latest
     steps:
@@ -38,7 +46,24 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: ./.github/actions/setup
-      - run: cargo test --features tpch --test tpch_validation_test
+      - run: cargo test --features tpch --test 'tpch_*'
+
+  tpcds-test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
+      - uses: ./.github/actions/setup
+      - name: Install DuckDB CLI
+        run: |
+          curl https://install.duckdb.org | sh
+          mkdir -p $HOME/.local/bin
+          mv /home/runner/.duckdb/cli/latest/duckdb $HOME/.local/bin/
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+      - name: Run TPC-DS test
+        id: test
+        run: cargo test --features tpcds --test tpcds_test
 
   format-check:
     runs-on: ubuntu-latest

.gitignore

@@ -1,4 +1,6 @@
 /.idea
 /target
 /benchmarks/data/
-testdata/tpch/data/
+testdata/tpch/*
+!testdata/tpch/queries
+testdata/tpcds/data/