Merge branch 'main' into experiment_roaring_bitmap_for_int32_anti_semi_joins

Author: coderfender

.asf.yaml

@@ -60,6 +60,29 @@ github:
           - "Spell Check with Typos"
           - "Circular Dependency Check"
           - "Detect Unused Dependencies"
+          - "linux build test"
+          - "cargo check datafusion-common features"
+          - "cargo check datafusion-substrait features"
+          - "cargo check datafusion-proto features"
+          - "cargo check datafusion features"
+          - "cargo check datafusion-functions features"
+          - "cargo test (amd64)"
+          - "cargo test datafusion-cli (amd64)"
+          - "cargo examples (amd64)"
+          - "cargo test doc (amd64)"
+          - "cargo doc"
+          - "build and run with wasm-pack"
+          - "verify benchmark results (amd64)"
+          - "Run sqllogictest with Postgres runner"
+          - "Run sqllogictest in Substrait round-trip mode"
+          - "cargo test (macos-aarch64)"
+          - "Verify Vendored Code"
+          - "Check cargo fmt"
+          - "clippy"
+          - "check Cargo.toml formatting"
+          - "check configs.md and ***_functions.md is up-to-date"
+          - "check example README is up-to-date"
+          - "Verify MSRV (Min Supported Rust Version)"
     # needs to be updated as part of the release process
     # .asf.yaml doesn't support wildcard branch protection rules, only exact branch names
     # https://github.com/apache/infrastructure-asfyaml?tab=readme-ov-file#branch-protection
@@ -74,6 +97,12 @@ github:
     branch-52:
       required_pull_request_reviews:
         required_approving_review_count: 1
+    branch-53:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
+    branch-54:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
   pull_requests:
     # enable updating head branches of pull requests
     allow_update_branch: true

.github/workflows/audit.yml

@@ -45,7 +45,7 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
       - name: Install cargo-audit
-        uses: taiki-e/install-action@481c34c1cf3a84c68b5e46f4eccfc82af798415a  # v2.75.23
+        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
         with:
           tool: cargo-audit
       - name: Run audit check

.github/workflows/breaking_changes_detector.yml

@@ -89,7 +89,7 @@ jobs:
 
       - name: Install cargo-semver-checks
         if: steps.changed_crates.outputs.packages != ''
-        uses: taiki-e/install-action@94cb46f8d6e437890146ffbd78a778b78e623fb2  # v2.74.0
+        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
         with:
           tool: cargo-semver-checks
 

.github/workflows/codeql.yml

@@ -45,11 +45,11 @@ jobs:
         persist-credentials: false
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4
+      uses: github/codeql-action/init@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
       with:
         languages: actions
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4
+      uses: github/codeql-action/analyze@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
       with:
         category: "/language:actions"

.github/workflows/dev.yml

@@ -64,7 +64,7 @@ jobs:
           source ci/scripts/utils/tool_versions.sh
           echo "LYCHEE_VERSION=${LYCHEE_VERSION}" >> "$GITHUB_ENV"
       - name: Install lychee
-        uses: taiki-e/install-action@481c34c1cf3a84c68b5e46f4eccfc82af798415a  # v2.75.23
+        uses: taiki-e/install-action@213ccc1a076163c093f914550b94feb90fab916d  # v2.79.2
         with:
           tool: lychee@${{ env.LYCHEE_VERSION }}
       - name: Run markdown link check

.github/workflows/extended.yml

@@ -57,41 +57,13 @@ permissions:
   checks: write
 
 jobs:
-
-  # Check crate compiles and base cargo check passes
-  linux-build-lib:
-    name: linux build test
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=8,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
-    # note: do not use amd/rust container to preserve disk space
-    steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
-        with:
-          ref: ${{ github.event.inputs.pr_head_sha }} # will be empty if triggered by push
-          submodules: true
-          fetch-depth: 1
-      - name: Install Rust
-        run: |
-          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-          source $HOME/.cargo/env
-          rustup toolchain install
-      - name: Install Protobuf Compiler
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y protobuf-compiler
-      - name: Prepare cargo build
-        run: |
-          cargo check --profile ci --all-targets
-          cargo clean
-
   # Run extended tests (with feature 'extended_tests')
   linux-test-extended:
     name: cargo test 'extended_tests' (amd64)
-    needs: [linux-build-lib]
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=32,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ${{ vars.USE_RUNS_ON == 'true' && format('runs-on={0},family=m8a+m7a+c8a,cpu=32,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
     # note: do not use amd/rust container to preserve disk space
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
+      - uses: runs-on/action@d141ef83eb66d096ce8afc767e09115a65c63b60  # v2.1.2
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           ref: ${{ github.event.inputs.pr_head_sha }} # will be empty if triggered by push
@@ -134,11 +106,11 @@ jobs:
   # Check answers are correct when hash values collide
   hash-collisions:
     name: cargo test hash collisions (amd64)
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ${{ vars.USE_RUNS_ON == 'true' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
+      - uses: runs-on/action@d141ef83eb66d096ce8afc767e09115a65c63b60  # v2.1.2
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           ref: ${{ github.event.inputs.pr_head_sha }} # will be empty if triggered by push
@@ -156,11 +128,11 @@ jobs:
 
   sqllogictest-sqlite:
     name: "Run sqllogictests with the sqlite test suite"
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=32,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ${{ vars.USE_RUNS_ON == 'true' && format('runs-on={0},family=m8a+m7a+c8a,cpu=32,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
+      - uses: runs-on/action@d141ef83eb66d096ce8afc767e09115a65c63b60  # v2.1.2
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           ref: ${{ github.event.inputs.pr_head_sha }} # will be empty if triggered by push

.github/workflows/labeler.yml

@@ -44,7 +44,7 @@ jobs:
           github.event_name == 'pull_request_target' &&
             (github.event.action == 'opened' ||
              github.event.action == 'synchronize')
-        uses: actions/labeler@634933edcd8ababfe52f92936142cc22ac488b1b  # v6.0.1
+        uses: actions/labeler@f27b608878404679385c85cfa523b85ccb86e213  # v6.1.0
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           configuration-path: .github/workflows/labeler/labeler-config.yml