build: lint as a separate step

.github/actions/java-test/action.yaml

@@ -59,7 +59,7 @@ runs:
       #  temporarily work around https://github.com/actions/runner-images/issues/13341
       #  by disabling caching for macOS
       if: ${{ runner.os != 'macOS' }}
-      uses: actions/cache@v4
+      uses: actions/cache@v5
       with:
         path: |
           ~/.m2/repository
@@ -68,36 +68,6 @@ runs:
         restore-keys: |
           ${{ runner.os }}-java-maven-
 
-    - name: Run Maven compile
-      shell: bash
-      run: |
-        ./mvnw -B package -DskipTests scalafix:scalafix -Dscalafix.mode=CHECK -Psemanticdb ${{ inputs.maven_opts }}
-
-    - name: Setup Node.js
-      uses: actions/setup-node@v6
-      with:
-        node-version: '24'
-
-    - name: Install prettier
-      shell: bash
-      run: |
-        npm install -g prettier
-
-    - name: Run prettier
-      shell: bash
-      run: |
-        npx prettier "**/*.md" --write
-
-    - name: Mark workspace as safe for git
-      shell: bash
-      run: |
-        git config --global --add safe.directory "$GITHUB_WORKSPACE"
-
-    - name: Check for any local git changes (such as generated docs)
-      shell: bash
-      run: |
-        ./dev/ci/check-working-tree-clean.sh
-
     - name: Run all tests
       shell: bash
       if: ${{ inputs.suites == '' }}
@@ -106,7 +76,7 @@ runs:
         SPARK_LOCAL_HOSTNAME: "localhost"
         SPARK_LOCAL_IP: "127.0.0.1"
       run: |
-        MAVEN_OPTS="-Xmx4G -Xms2G -XX:+UnlockDiagnosticVMOptions -XX:+ShowMessageBoxOnError -XX:+HeapDumpOnOutOfMemoryError -XX:ErrorFile=./hs_err_pid%p.log" SPARK_HOME=`pwd` ./mvnw -B -Prelease clean install ${{ inputs.maven_opts }}
+        MAVEN_OPTS="-Xmx4G -Xms2G -XX:+UnlockDiagnosticVMOptions -XX:+ShowMessageBoxOnError -XX:+HeapDumpOnOutOfMemoryError -XX:ErrorFile=./hs_err_pid%p.log" SPARK_HOME=`pwd` ./mvnw -B -Prelease install ${{ inputs.maven_opts }}
     - name: Run specified tests
       shell: bash
       if: ${{ inputs.suites != '' }}
@@ -117,7 +87,7 @@ runs:
       run: |
         MAVEN_SUITES="$(echo "${{ inputs.suites }}" | paste -sd, -)"
         echo "Running with MAVEN_SUITES=$MAVEN_SUITES"
-        MAVEN_OPTS="-Xmx4G -Xms2G -DwildcardSuites=$MAVEN_SUITES -XX:+UnlockDiagnosticVMOptions -XX:+ShowMessageBoxOnError -XX:+HeapDumpOnOutOfMemoryError -XX:ErrorFile=./hs_err_pid%p.log" SPARK_HOME=`pwd` ./mvnw -B -Prelease clean install ${{ inputs.maven_opts }}
+        MAVEN_OPTS="-Xmx4G -Xms2G -DwildcardSuites=$MAVEN_SUITES -XX:+UnlockDiagnosticVMOptions -XX:+ShowMessageBoxOnError -XX:+HeapDumpOnOutOfMemoryError -XX:ErrorFile=./hs_err_pid%p.log" SPARK_HOME=`pwd` ./mvnw -B -Prelease install ${{ inputs.maven_opts }}
     - name: Upload crash logs
       if: failure()
       uses: actions/upload-artifact@v6

.github/workflows/pr_build_linux.yml

@@ -66,8 +66,74 @@
           rustup component add rustfmt
           cd native && cargo fmt --all -- --check
 
+  lint-java:
+    needs: lint
+    name: Lint Java (${{ matrix.profile.name }})
+    runs-on: ubuntu-latest
+    container:
+      image: amd64/rust
+      env:
+        JAVA_TOOL_OPTIONS: ${{ matrix.profile.java_version == '17' && '--add-exports=java.base/sun.nio.ch=ALL-UNNAMED --add-exports=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED' || '' }}
+    strategy:
+      matrix:
+        profile:
+          - name: "Spark 3.4, JDK 11, Scala 2.12"
+            java_version: "11"
+            maven_opts: "-Pspark-3.4 -Pscala-2.12"
+          - name: "Spark 3.5, JDK 17, Scala 2.12"
+            java_version: "17"
+            maven_opts: "-Pspark-3.5 -Pscala-2.12"
+          - name: "Spark 4.0, JDK 17"
+            java_version: "17"
+            maven_opts: "-Pspark-4.0"
+      fail-fast: false
+    steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+      - uses: actions/checkout@v6
+
+      - name: Setup Rust & Java toolchain
+        uses: ./.github/actions/setup-builder
+        with:
+          rust-version: ${{ env.RUST_VERSION }}
+          jdk-version: ${{ matrix.profile.java_version }}
+
+      - name: Cache Maven dependencies
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.m2/repository
+            /root/.m2/repository
+          key: ${{ runner.os }}-java-maven-${{ hashFiles('**/pom.xml') }}-lint
+          restore-keys: |
+            ${{ runner.os }}-java-maven-
+
+      - name: Run scalafix check
+        run: |
+          ./mvnw -B package -DskipTests scalafix:scalafix -Dscalafix.mode=CHECK -Psemanticdb ${{ matrix.profile.maven_opts }}
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: '24'
+
+      - name: Install prettier
+        run: |
+          npm install -g prettier
+
+      - name: Run prettier
+        run: |
+          npx prettier "**/*.md" --write
+
+      - name: Mark workspace as safe for git
+        run: |
+          git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
+      - name: Check for any local git changes (such as generated docs)
+        run: |
+          ./dev/ci/check-working-tree-clean.sh
+
   # Build native library once and share with all test jobs
   build-native:
     needs: lint
     name: Build Native Library
     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-comet', github.run_id) || 'ubuntu-latest' }}