Merge branch 'main' into parquet/support-write-bloom-filter

.asf.yaml

@@ -21,10 +21,12 @@ github:
   collaborators:
     - anjakefala
     - benibus
-    - danepitkin
     - davisusanibar
+    - jbonofre
     - js8544
     - vibhatha
+    - zanmato1984
+    - ZhangHuiGui
 
 notifications:
   commits:      [email protected]

.env

@@ -56,7 +56,7 @@ UBUNTU=20.04
 CLANG_TOOLS=14
 CUDA=11.2.2
 DASK=latest
-DOTNET=7.0
+DOTNET=8.0
 GCC_VERSION=""
 GO=1.21.8
 STATICCHECK=v0.4.7
@@ -71,12 +71,12 @@ NUMBA=latest
 NUMPY=latest
 PANDAS=latest
 PYTHON=3.8
-R=4.2
+R=4.4
 SPARK=master
 TURBODBC=latest
 
-# These correspond to images on Docker Hub that contain R, e.g. rhub/ubuntu-gcc-release:latest
-R_IMAGE=ubuntu-gcc-release
+# These correspond to images on Docker Hub that contain R, e.g. rhub/ubuntu-release:latest
+R_IMAGE=ubuntu-release
 R_ORG=rhub
 R_TAG=latest
 
@@ -86,9 +86,6 @@ ARROW_R_DEV=TRUE
 R_PRUNE_DEPS=FALSE
 TZ=UTC
 
-# Any non-empty string will install devtoolset-${DEVTOOLSET_VERSION}
-DEVTOOLSET_VERSION=
-
 # Used through docker-compose.yml and serves as the default version for the
 # ci/scripts/install_vcpkg.sh script. Prefer to use short SHAs to keep the
 # docker tags more readable.

.github/dependabot.yml

@@ -23,30 +23,35 @@ updates:
       interval: "weekly"
     commit-message:
       prefix: "MINOR: [CI] "
+    open-pull-requests-limit: 10
   - package-ecosystem: "gomod"
     directory: "/go/"
     schedule:
       interval: "weekly"
     commit-message:
       prefix: "MINOR: [Go] "
+    open-pull-requests-limit: 10
   - package-ecosystem: "maven"
     directory: "/java/"
     schedule:
       interval: "weekly"
     commit-message:
       prefix: "MINOR: [Java] "
+    open-pull-requests-limit: 10
   - package-ecosystem: "npm"
     directory: "/js/"
     schedule:
       interval: "monthly"
     commit-message:
       prefix: "MINOR: [JS] "
+    open-pull-requests-limit: 10
   - package-ecosystem: "nuget"
     directory: "/csharp/"
     schedule:
       interval: "weekly"
     commit-message:
       prefix: "MINOR: [C#] "
+    open-pull-requests-limit: 10
     ignore:
       - dependency-name: "Microsoft.Extensions.*"
         update-types:

.github/workflows/cpp.yml

@@ -21,6 +21,7 @@ on:
   push:
     paths:
       - '.github/workflows/cpp.yml'
+      - 'ci/conda_env_*'
       - 'ci/docker/**'
       - 'ci/scripts/cpp_*'
       - 'ci/scripts/install_azurite.sh'
@@ -35,6 +36,7 @@ on:
   pull_request:
     paths:
       - '.github/workflows/cpp.yml'
+      - 'ci/conda_env_*'
       - 'ci/docker/**'
       - 'ci/scripts/cpp_*'
       - 'ci/scripts/install_azurite.sh'

.github/workflows/csharp.yml

@@ -46,7 +46,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        dotnet: ['7.0.x']
+        dotnet: ['8.0.x']
     steps:
       - name: Install C#
         uses: actions/setup-dotnet@v4
@@ -74,7 +74,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        dotnet: ['7.0.x']
+        dotnet: ['8.0.x']
     steps:
       - name: Install C#
         uses: actions/setup-dotnet@v4
@@ -94,19 +94,23 @@ jobs:
         run: ci/scripts/csharp_test.sh $(pwd)
 
   macos:
-    name: AMD64 macOS 11 C# ${{ matrix.dotnet }}
-    runs-on: macos-latest
+    name: AMD64 macOS 13 C# ${{ matrix.dotnet }}
+    runs-on: macos-13 # Pending https://github.com/pythonnet/pythonnet/issues/2396
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 15
     strategy:
       fail-fast: false
       matrix:
-        dotnet: ['7.0.x']
+        dotnet: ['8.0.x']
     steps:
       - name: Install C#
         uses: actions/setup-dotnet@v4
         with:
           dotnet-version: ${{ matrix.dotnet }}
+      - name: Setup Python
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
+        with:
+          python-version: 3.12
       - name: Checkout Arrow
         uses: actions/checkout@v4
         with:

.github/workflows/dev.yml

@@ -115,12 +115,12 @@ jobs:
       - name: Install .NET
         uses: actions/setup-dotnet@4d6c8fcf3c8f7a60068d26b594648e99df24cee3 # v4.0.0
         with:
-          dotnet-version: '7.0.x'
+          dotnet-version: '8.0.x'
       - name: Install Dependencies
         shell: bash
         run: |
           gem install test-unit
-          pip install "cython>=0.29.31" setuptools six pytest jira
+          pip install "cython>=0.29.31" setuptools six pytest jira setuptools-scm
       - name: Run Release Test
         env:
           ARROW_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs.yml

@@ -32,12 +32,12 @@ env:
 jobs:
 
   complete:
-    name: AMD64 Ubuntu 22.04 Complete Documentation
+    name: AMD64 Debian 12 Complete Documentation
     runs-on: ubuntu-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 150
     env:
-      UBUNTU: "22.04"
+      JDK: 17
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
@@ -50,8 +50,8 @@ jobs:
         uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
-          key: ubuntu-docs-${{ hashFiles('cpp/**') }}
-          restore-keys: ubuntu-docs-
+          key: debian-docs-${{ hashFiles('cpp/**') }}
+          restore-keys: debian-docs-
       - name: Setup Python
         uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
@@ -62,7 +62,8 @@ jobs:
         env:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
-        run: archery docker run ubuntu-docs
+          JDK: 17
+        run: archery docker run debian-docs
       - name: Docker Push
         if: >-
           success() &&
@@ -73,4 +74,4 @@ jobs:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
         continue-on-error: true
-        run: archery docker push ubuntu-docs
+        run: archery docker push debian-docs

.github/workflows/docs_light.yml

@@ -31,7 +31,7 @@ on:
 
 permissions:
   contents: read
-  
+
 env:
   ARCHERY_DEBUG: 1
   ARCHERY_USE_DOCKER_CLI: 1

.github/workflows/integration.yml

@@ -75,6 +75,11 @@ jobs:
         with:
           repository: apache/arrow-rs
           path: rust
+      - name: Checkout Arrow nanoarrow
+        uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
+        with:
+          repository: apache/arrow-nanoarrow
+          path: nanoarrow
       - name: Free up disk space
         run: |
           ci/scripts/util_free_space.sh
@@ -97,6 +102,7 @@ jobs:
         run: >
           archery docker run \
             -e ARCHERY_DEFAULT_BRANCH=${{ github.event.repository.default_branch }} \
+            -e ARCHERY_INTEGRATION_WITH_NANOARROW=1 \
             -e ARCHERY_INTEGRATION_WITH_RUST=1 \
             conda-integration
       - name: Docker Push

.github/workflows/issue_bot.yml

@@ -21,7 +21,6 @@ on:
   issues:
     types:
       - opened
-      - edited
 
 permissions:
   contents: read

.github/workflows/java.yml

@@ -86,11 +86,11 @@ jobs:
         env:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: |
           archery docker run \
             -e CI=true \
-            -e "GRADLE_ENTERPRISE_ACCESS_KEY=$GRADLE_ENTERPRISE_ACCESS_KEY" \
+            -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
             ${{ matrix.image }}
       - name: Docker Push
         if: >-
@@ -127,12 +127,12 @@ jobs:
       - name: Build
         shell: bash
         env:
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: ci/scripts/java_build.sh $(pwd) $(pwd)/build
       - name: Test
         shell: bash
         env:
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: ci/scripts/java_test.sh $(pwd) $(pwd)/build
 
   windows:
@@ -158,10 +158,10 @@ jobs:
       - name: Build
         shell: bash
         env:
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: ci/scripts/java_build.sh $(pwd) $(pwd)/build
       - name: Test
         shell: bash
         env:
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: ci/scripts/java_test.sh $(pwd) $(pwd)/build

.github/workflows/java_jni.yml

@@ -120,11 +120,11 @@ jobs:
         env:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
-          GRADLE_ENTERPRISE_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
+          DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }}
         run: |
           archery docker run \
             -e CI=true \
-            -e "GRADLE_ENTERPRISE_ACCESS_KEY=$GRADLE_ENTERPRISE_ACCESS_KEY" \
+            -e "DEVELOCITY_ACCESS_KEY=$DEVELOCITY_ACCESS_KEY" \
             conda-python-java-integration
       - name: Docker Push
         if: >-

.github/workflows/js.yml

@@ -106,10 +106,10 @@ jobs:
           node-version: ${{ matrix.node }}
       - name: Build
         shell: bash
-        run: ci/scripts/js_build.sh $(pwd)
+        run: ci/scripts/js_build.sh $(pwd) build
       - name: Test
         shell: bash
-        run: ci/scripts/js_test.sh $(pwd)
+        run: ci/scripts/js_test.sh $(pwd) build
 
   windows:
     name: AMD64 Windows NodeJS ${{ matrix.node }}
@@ -136,7 +136,7 @@ jobs:
           node-version: ${{ matrix.node }}
       - name: Build
         shell: bash
-        run: ci/scripts/js_build.sh $(pwd)
+        run: ci/scripts/js_build.sh $(pwd) build
       - name: Test
         shell: bash
-        run: ci/scripts/js_test.sh $(pwd)
+        run: ci/scripts/js_test.sh $(pwd) build

.github/workflows/matlab.yml

@@ -70,7 +70,7 @@ jobs:
       - name: Install MATLAB
         uses: matlab-actions/setup-matlab@v2
         with:
-          release: R2023a
+          release: R2024a
       - name: Install ccache
         run: sudo apt-get install ccache
       - name: Setup ccache
@@ -96,10 +96,18 @@ jobs:
         uses: matlab-actions/run-tests@v2
         with:
           select-by-folder: matlab/test
+          strict: true
   macos:
-    name: AMD64 macOS 12 MATLAB
-    runs-on: macos-12
+    name: ${{ matrix.architecture }} macOS ${{ matrix.macos-version }} MATLAB
+    runs-on: macos-${{ matrix.macos-version }}
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
+    strategy:
+      matrix:
+        include:
+            - architecture: AMD64
+              macos-version: "12"
+            - architecture: ARM64
+              macos-version: "14"
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
@@ -110,7 +118,7 @@ jobs:
       - name: Install MATLAB
         uses: matlab-actions/setup-matlab@v2
         with:
-          release: R2023a
+          release: R2024a
       - name: Install ccache
         run: brew install ccache
       - name: Setup ccache
@@ -135,7 +143,8 @@ jobs:
           MATLABPATH: matlab/install/arrow_matlab
         uses: matlab-actions/run-tests@v2
         with:
-          select-by-folder: matlab/test 
+          select-by-folder: matlab/test
+          strict: true
   windows:
     name: AMD64 Windows 2022 MATLAB
     runs-on: windows-2022
@@ -148,7 +157,7 @@ jobs:
       - name: Install MATLAB
         uses: matlab-actions/setup-matlab@v2
         with:
-          release: R2023a
+          release: R2024a
       - name: Download Timezone Database
         shell: bash
         run: ci/scripts/download_tz_database.sh
@@ -181,4 +190,5 @@ jobs:
           MATLABPATH: matlab/install/arrow_matlab
         uses: matlab-actions/run-tests@v2
         with:
-          select-by-folder: matlab/test 
+          select-by-folder: matlab/test
+          strict: true