MINOR: Build test artifacts once in CI

.github/workflows/rc.yml

@@ -162,7 +162,6 @@ jobs:
       fail-fast: false
       matrix:
         platform:
-          - { runs_on: macos-15-intel, arch: "x86_64"}
           - { runs_on: macos-14, arch: "aarch_64" }
     env:
       MACOSX_DEPLOYMENT_TARGET: "14.0"
@@ -211,46 +210,19 @@ jobs:
           # llvm@14 because llvm is newer than llvm@14.
           brew uninstall llvm || :
 
-          # We can remove this when we drop support for
-          # macos-15-intel. because macos-14 or later with arm64 uses /opt/homebrew/
-          # not /usr/local/.
-          #
-          # Ensure updating python@XXX with the "--overwrite" option.
-          # If python@XXX is updated without "--overwrite", it causes
-          # a conflict error. Because Python 3 installed not by
-          # Homebrew exists in /usr/local on GitHub Actions. If
-          # Homebrew's python@XXX is updated without "--overwrite", it
-          # tries to replace /usr/local/bin/2to3 and so on and causes
-          # a conflict error.
           brew update
-          for python_package in $(brew list | grep python@ | sort -r); do
-            brew install --overwrite ${python_package}
-          done
-          brew install --overwrite python3
 
-          if [ "$(uname -m)" = "arm64" ]; then
-            # pkg-config formula is deprecated but it's still installed
-            # in GitHub Actions runner now. We can remove this once
-            # pkg-config formula is removed from GitHub Actions runner.
-            brew uninstall pkg-config || :
-            brew uninstall pkg-config@0.29.2 || :
-          fi
+          # pkg-config formula is deprecated but it's still installed
+          # in GitHub Actions runner now. We can remove this once
+          # pkg-config formula is removed from GitHub Actions runner.
+          brew uninstall pkg-config || :
+          brew uninstall pkg-config@0.29.2 || :
 
           # We don't use Homebrew's aws-sdk-cpp and gRPC. See the
           # "brew uninstall" calls below for details. So we don't install
           # them instead of installing and uninstalling them.
           #
-          # This is also needed because Homebrew doesn't provide bottles
-          # for them on x86_64 macOS. Homebrew treats x86_64 macOS as a
-          # tier 3 configuration and rarely builds bottles for it:
-          #
-          #   https://docs.brew.sh/Support-Tiers#tier-3
-          #
-          # "brew bundle" fails with "no bottle available!" without this
-          # because it doesn't build them from source.
-          #
-          # We don't use Homebrew's Node.js too. Homebrew doesn't provide
-          # a bottle for it on x86_64 macOS for the same reason.
+          # We don't need Homebrew's Node.js for the JNI build either.
           HOMEBREW_BUNDLE_BREW_SKIP="aws-sdk-cpp grpc node" \
             brew bundle --file=arrow/cpp/Brewfile
           # We want to link aws-sdk-cpp statically but Homebrew's
@@ -388,7 +360,6 @@ jobs:
           tar -xf apache-arrow-java-*.tar.gz --strip-components=1
           tar -xvzf jni-linux-x86_64.tar.gz
           tar -xvzf jni-linux-aarch_64.tar.gz
-          tar -xvzf jni-macos-x86_64.tar.gz
           tar -xvzf jni-macos-aarch_64.tar.gz
           tar -xvzf jni-windows-x86_64.tar.gz
       - name: Test that shared libraries exist
@@ -405,11 +376,6 @@ jobs:
           test -f jni/arrow_orc_jni/aarch_64/libarrow_orc_jni.so
           test -f jni/gandiva_jni/aarch_64/libgandiva_jni.so
 
-          test -f jni/arrow_cdata_jni/x86_64/libarrow_cdata_jni.dylib
-          test -f jni/arrow_dataset_jni/x86_64/libarrow_dataset_jni.dylib
-          test -f jni/arrow_orc_jni/x86_64/libarrow_orc_jni.dylib
-          test -f jni/gandiva_jni/x86_64/libgandiva_jni.dylib
-
           test -f jni/arrow_cdata_jni/aarch_64/libarrow_cdata_jni.dylib
           test -f jni/arrow_dataset_jni/aarch_64/libarrow_dataset_jni.dylib
           test -f jni/arrow_orc_jni/aarch_64/libarrow_orc_jni.dylib

.github/workflows/test.yml

@@ -34,28 +34,16 @@ permissions:
   contents: read
 
 env:
+  BUILD_JDK: "17"
   DOCKER_VOLUME_PREFIX: ".docker/"
+  MAVEN: 3.9.16
 
 jobs:
-  ubuntu:
-    name: AMD64 ${{ matrix.name }} JDK ${{ matrix.jdk }} Maven ${{ matrix.maven }}
+  build-java:
+    name: Build Java artifacts
     runs-on: ubuntu-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        jdk: [17, 21, 25]
-        maven: [3.9.16]
-        image: [ubuntu, conda-jni-cdata]
-        include:
-          - image: ubuntu
-            name: "Ubuntu"
-          - image: conda-jni-cdata
-            name: "Conda JNI"
-    env:
-      JDK: ${{ matrix.jdk }}
-      MAVEN: ${{ matrix.maven }}
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@v7
@@ -65,85 +53,197 @@ jobs:
       - name: Cache Docker Volumes
         uses: actions/cache@v6
         with:
-          path: .docker
-          key: maven-${{ matrix.jdk }}-${{ matrix.maven }}-${{ hashFiles('compose.yaml', '**/pom.xml') }}
-          restore-keys: maven-${{ matrix.jdk }}-${{ matrix.maven }}-
-      - name: Execute Docker Build
+          path: .docker/maven-cache
+          key: java-build-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-${{ hashFiles('compose.yaml', '**/pom.xml') }}
+          restore-keys: java-build-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-
+      - name: Build without tests
         env:
-          # Enables build caching, but not strictly required
           DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
+          JDK: ${{ env.BUILD_JDK }}
         run: |
           docker compose run \
+            --rm \
             -e CI=true \
             -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
-            ${{ matrix.image }}
+            ubuntu-artifacts
+          sudo chown -R "$(id -u):$(id -g)" .docker
+      - name: Pack reusable artifacts
+        run: |
+          tar -czf java-build.tgz \
+            .docker/java-build \
+            .docker/maven-cache/repository/org/apache/arrow
+      - name: Upload reusable artifacts
+        uses: actions/upload-artifact@v5
+        with:
+          name: java-build
+          path: java-build.tgz
+          retention-days: 1
+      - name: Exclude reactor artifacts from Maven dependency cache
+        run: rm -rf .docker/maven-cache/repository/org/apache/arrow
 
-  macos:
-    name: ${{ matrix.arch }} macOS ${{ matrix.macos }} Java JDK ${{ matrix.jdk }}
-    runs-on: macos-${{ matrix.macos }}
+  test-java:
+    name: ${{ matrix.name || format('AMD64 Ubuntu JDK {0} Maven 3.9.16', matrix.jdk) }}
+    needs: build-java
+    runs-on: ${{ matrix.os }}
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 30
     strategy:
       fail-fast: false
       matrix:
+        jdk: [17, 21, 25]
+        os: [ubuntu-latest]
         include:
-          - arch: AMD64
-            jdk: 17
-            macos: 15-intel
           - arch: AArch64
             jdk: 17
-            macos: latest
+          - name: AMD64 Windows Server 2022 Java JDK 17
+            os: windows-latest
+            jdk: 17
+    env:
+      JDK: ${{ matrix.jdk }}
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@v7
         with:
-          fetch-depth: 0
           submodules: recursive
       - name: Set up Java
+        if: ${{ !matrix.compose_service }}
         uses: actions/setup-java@v6
         with:
           distribution: 'temurin'
           java-version: ${{ matrix.jdk }}
           cache: 'maven'
-      - name: Build
+      - name: Cache Docker Volumes
+        if: ${{ matrix.compose_service }}
+        uses: actions/cache@v6
+        with:
+          path: .docker/maven-cache
+          key: java-build-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-${{ hashFiles('compose.yaml', '**/pom.xml') }}
+          restore-keys: java-build-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-
+      - name: Download reusable artifacts
+        uses: actions/download-artifact@v6
+        with:
+          name: java-build
+      - name: Restore reusable artifacts
+        shell: bash
+        run: |
+          rm -rf \
+            .docker/java-build \
+            .docker/maven-cache/repository/org/apache/arrow
+          tar -xzf java-build.tgz
+      - name: Restore reusable artifacts for hosted runner
+        if: ${{ !matrix.compose_service }}
+        shell: bash
+        run: |
+          cp -a .docker/java-build/build build
+          rm -rf "${HOME}/.m2/repository/org/apache/arrow"
+          mkdir -p "${HOME}/.m2/repository/org/apache"
+          cp -a .docker/maven-cache/repository/org/apache/arrow "${HOME}/.m2/repository/org/apache/"
+      - name: Test prebuilt artifacts on macOS/Windows
+        if: ${{ !matrix.compose_service }}
         shell: bash
         env:
+          ARROW_JAVA_TEST_PREBUILT: "ON"
           DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
-        run: ci/scripts/build.sh . build jni
-      - name: Test
+        run: ci/scripts/test.sh . build jni
+      - name: Test prebuilt artifacts on Ubuntu Docker
+        if: ${{ matrix.compose_service }}
         shell: bash
         env:
           DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
-        run: ci/scripts/test.sh . build jni
+        run: |
+          docker compose run \
+            --rm \
+            -e CI=true \
+            -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
+            ${{ matrix.compose_service }}
+      - name: Exclude reactor artifacts from hosted Maven dependency cache
+        if: ${{ !matrix.compose_service && always() }}
+        shell: bash
+        run: rm -rf "${HOME}/.m2/repository/org/apache/arrow"
 
-  windows:
-    name: AMD64 Windows Server 2022 Java JDK ${{ matrix.jdk }}
-    runs-on: windows-latest
+  build-cdata:
+    name: Build C Data artifacts
+    runs-on: ubuntu-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        jdk: [17]
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@v7
         with:
           fetch-depth: 0
           submodules: recursive
-      - name: Set up Java
-        uses: actions/setup-java@v6
+      - name: Cache Docker Volumes
+        uses: actions/cache@v6
         with:
-          java-version: ${{ matrix.jdk }}
-          distribution: 'temurin'
-          cache: 'maven'
-      - name: Build
-        shell: bash
+          path: .docker/maven-cache
+          key: cdata-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-${{ hashFiles('compose.yaml', '**/pom.xml') }}
+          restore-keys: cdata-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-
+      - name: Build C Data without tests
         env:
           DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
-        run: ci/scripts/build.sh . build jni
-      - name: Test
-        shell: bash
+          JDK: ${{ env.BUILD_JDK }}
+        run: |
+          docker compose run \
+            --rm \
+            -e CI=true \
+            -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
+            cdata-artifacts
+          sudo chown -R "$(id -u):$(id -g)" .docker
+      - name: Pack reusable C Data artifacts
+        run: |
+          tar -czf cdata-build.tgz \
+            .docker/cdata-build \
+            .docker/cdata-jni-dist \
+            .docker/maven-cache/repository/org/apache/arrow
+      - name: Upload reusable C Data artifacts
+        uses: actions/upload-artifact@v5
+        with:
+          name: cdata-build
+          path: cdata-build.tgz
+          retention-days: 1
+      - name: Exclude reactor artifacts from Maven dependency cache
+        run: rm -rf .docker/maven-cache/repository/org/apache/arrow
+
+  test-cdata:
+    name: AMD64 Conda JNI JDK ${{ matrix.jdk }} Maven 3.9.16
+    needs: build-cdata
+    runs-on: ubuntu-latest
+    if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        jdk: [17, 21, 25]
+    env:
+      JDK: ${{ matrix.jdk }}
+    steps:
+      - name: Checkout Arrow
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+      - name: Cache Docker Volumes
+        uses: actions/cache@v6
+        with:
+          path: .docker/maven-cache
+          key: cdata-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-${{ hashFiles('compose.yaml', '**/pom.xml') }}
+          restore-keys: cdata-${{ env.BUILD_JDK }}-${{ env.MAVEN }}-
+      - name: Download reusable C Data artifacts
+        uses: actions/download-artifact@v6
+        with:
+          name: cdata-build
+      - name: Restore reusable C Data artifacts
+        run: |
+          rm -rf \
+            .docker/cdata-build \
+            .docker/cdata-jni-dist \
+            .docker/maven-cache/repository/org/apache/arrow
+          tar -xzf cdata-build.tgz
+      - name: Test C Data without compiler lifecycle
         env:
           DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
-        run: ci/scripts/test.sh . build jni
+        run: |
+          docker compose run \
+            --rm \
+            -e CI=true \
+            -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
+            cdata-test-prebuilt

c/src/main/java/org/apache/arrow/c/Format.java

@@ -63,10 +63,10 @@ static String asString(ArrowType arrowType) {
         {
           ArrowType.Decimal type = (ArrowType.Decimal) arrowType;
           if (type.getBitWidth() == 128) {
-            return String.format("d:%d,%d", type.getPrecision(), type.getScale());
+            return String.format(Locale.ROOT, "d:%d,%d", type.getPrecision(), type.getScale());
           }
           return String.format(
-              "d:%d,%d,%d", type.getPrecision(), type.getScale(), type.getBitWidth());
+              Locale.ROOT, "d:%d,%d,%d", type.getPrecision(), type.getScale(), type.getBitWidth());
         }
       case Duration:
         {
@@ -88,12 +88,12 @@ static String asString(ArrowType arrowType) {
       case FixedSizeBinary:
         {
           ArrowType.FixedSizeBinary type = (ArrowType.FixedSizeBinary) arrowType;
-          return String.format("w:%d", type.getByteWidth());
+          return String.format(Locale.ROOT, "w:%d", type.getByteWidth());
         }
       case FixedSizeList:
         {
           ArrowType.FixedSizeList type = (ArrowType.FixedSizeList) arrowType;
-          return String.format("+w:%d", type.getListSize());
+          return String.format(Locale.ROOT, "+w:%d", type.getListSize());
         }
       case FloatingPoint:
         {