Merge branch 'main' into handle-num-nulls-correctly

mapleFU · Sep 5, 2024 · c92d31f · c92d31f
2 parents 0060abf + 50219ef
commit c92d31f
Show file tree

Hide file tree

Showing 321 changed files with 7,942 additions and 3,287 deletions.
diff --git a/.env b/.env
@@ -58,8 +58,8 @@ CUDA=11.2.2
 DASK=latest
 DOTNET=8.0
 GCC_VERSION=""
-GO=1.21.8
-STATICCHECK=v0.4.7
+GO=1.22.6
+STATICCHECK=v0.5.1
 HDFS=3.2.1
 JDK=11
 KARTOTHEK=latest
@@ -71,6 +71,7 @@ NUMBA=latest
 NUMPY=latest
 PANDAS=latest
 PYTHON=3.8
+PYTHON_IMAGE_TAG=3.8
 R=4.4
 SPARK=master
 TURBODBC=latest
@@ -95,7 +96,7 @@ VCPKG="943c5ef1c8f6b5e6ced092b242c8299caae2ff01"    # 2024.04.26 Release
 # ci/docker/python-wheel-windows-vs2019.dockerfile.
 # This is a workaround for our CI problem that "archery docker build" doesn't
 # use pulled built images in dev/tasks/python-wheels/github.windows.yml.
-PYTHON_WHEEL_WINDOWS_IMAGE_REVISION=2024-06-18
+PYTHON_WHEEL_WINDOWS_IMAGE_REVISION=2024-08-06
 
 # Use conanio/${CONAN_BASE}:{CONAN_VERSION} for "docker-compose run --rm conan".
 # See https://github.com/conan-io/conan-docker-tools#readme and

diff --git a/.github/workflows/archery.yml b/.github/workflows/archery.yml
@@ -58,7 +58,7 @@ jobs:
         shell: bash
         run: git branch $ARCHERY_DEFAULT_BRANCH origin/$ARCHERY_DEFAULT_BRANCH || true
       - name: Setup Python
-        uses: actions/setup-python@v5.1.1
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: '3.9'
       - name: Install pygit2 binary wheel

diff --git a/.github/workflows/comment_bot.yml b/.github/workflows/comment_bot.yml
@@ -41,7 +41,7 @@ jobs:
           # fetch the tags for version number generation
           fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Install Archery and Crossbow dependencies

diff --git a/.github/workflows/cpp.yml b/.github/workflows/cpp.yml
@@ -99,7 +99,6 @@ jobs:
             cat <<JSON >> "$GITHUB_OUTPUT"
           {
             "arch": "arm64v8",
-            "archery-use-legacy-docker-compose": "1",
             "clang-tools": "10",
             "image": "ubuntu-cpp",
             "llvm": "10",
@@ -124,9 +123,6 @@ jobs:
         include: ${{ fromJson(needs.docker-targets.outputs.targets) }}
     env:
       ARCH: ${{ matrix.arch }}
-      # By default, use `docker compose` because docker-compose v1 is obsolete,
-      # except where the Docker client version is too old.
-      ARCHERY_USE_LEGACY_DOCKER_COMPOSE: ${{ matrix.archery-use-legacy-docker-compose || '0' }}
       ARROW_SIMD_LEVEL: ${{ matrix.simd-level }}
       CLANG_TOOLS: ${{ matrix.clang-tools }}
       LLVM: ${{ matrix.llvm }}
@@ -147,6 +143,7 @@ jobs:
         run: |
           sudo apt update
           sudo apt install -y --no-install-recommends python3 python3-dev python3-pip
+          python3 -m pip install -U pip
       - name: Setup Archery
         run: python3 -m pip install -e dev/archery[docker]
       - name: Execute Docker Build
@@ -246,7 +243,7 @@ jobs:
           $(brew --prefix bash)/bin/bash \
             ci/scripts/install_minio.sh latest ${ARROW_HOME}
       - name: Set up Python
-        uses: actions/setup-python@v5.1.1
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: 3.12
       - name: Install Google Cloud Storage Testbench
@@ -412,12 +409,10 @@ jobs:
       ARROW_WITH_SNAPPY: ON
       ARROW_WITH_ZLIB: ON
       ARROW_WITH_ZSTD: ON
-      # Don't use preinstalled Boost by empty BOOST_ROOT and
-      # -DBoost_NO_BOOST_CMAKE=ON
+      # Don't use preinstalled Boost by empty BOOST_ROOT
       BOOST_ROOT: ""
       ARROW_CMAKE_ARGS: >-
         -DARROW_PACKAGE_PREFIX=/${{ matrix.msystem_lower}}
-        -DBoost_NO_BOOST_CMAKE=ON
         -DCMAKE_FIND_PACKAGE_PREFER_CONFIG=ON
       # We can't use unity build because we don't have enough memory on
       # GitHub Actions.
@@ -467,16 +462,18 @@ jobs:
             https://dl.min.io/server/minio/release/windows-amd64/archive/minio.RELEASE.2022-05-26T05-48-41Z
           chmod +x /usr/local/bin/minio.exe
       - name: Set up Python
-        uses: actions/[email protected]
+        uses: actions/[email protected]
+        id: python-install
         with:
           python-version: 3.9
       - name: Install Google Cloud Storage Testbench
-        shell: bash
+        shell: msys2 {0}
+        env:
+          PIPX_BIN_DIR: /usr/local/bin
+          PIPX_BASE_PYTHON: ${{ steps.python-install.outputs.python-path }}
         run: |
           ci/scripts/install_gcs_testbench.sh default
-          echo "PYTHON_BIN_DIR=$(cygpath --windows $(dirname $(which python3.exe)))" >> $GITHUB_ENV
       - name: Test
         shell: msys2 {0}
         run: |
-          PATH="$(cygpath --unix ${PYTHON_BIN_DIR}):${PATH}"
           ci/scripts/cpp_test.sh "$(pwd)" "$(pwd)/build"
diff --git a/.github/workflows/csharp.yml b/.github/workflows/csharp.yml
@@ -108,7 +108,7 @@ jobs:
         with:
           dotnet-version: ${{ matrix.dotnet }}
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Checkout Arrow

diff --git a/.github/workflows/dev.yml b/.github/workflows/dev.yml
@@ -45,7 +45,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Install pre-commit
@@ -104,7 +104,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Install Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: '3.12'
       - name: Install Ruby

diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -52,7 +52,7 @@ jobs:
           key: debian-docs-${{ hashFiles('cpp/**') }}
           restore-keys: debian-docs-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Setup Archery

diff --git a/.github/workflows/docs_light.yml b/.github/workflows/docs_light.yml
@@ -58,7 +58,7 @@ jobs:
           key: conda-docs-${{ hashFiles('cpp/**') }}
           restore-keys: conda-docs-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Setup Archery

diff --git a/.github/workflows/go.yml b/.github/workflows/go.yml
@@ -62,13 +62,13 @@ jobs:
           {
             "arch-label": "AMD64",
             "arch": "amd64",
-            "go": "1.21",
+            "go": "1.22",
             "runs-on": "ubuntu-latest"
           },
           {
             "arch-label": "AMD64",
             "arch": "amd64",
-            "go": "1.22",
+            "go": "1.23",
             "runs-on": "ubuntu-latest"
           }
           JSON
@@ -78,15 +78,13 @@ jobs:
           {
             "arch-label": "ARM64",
             "arch": "arm64v8",
-            "archery-use-legacy-docker-compose": "1",
-            "go": "1.21",
+            "go": "1.22",
             "runs-on": ["self-hosted", "arm", "linux"]
           },
           {
             "arch-label": "ARM64",
             "arch": "arm64v8",
-            "archery-use-legacy-docker-compose": "1",
-            "go": "1.22",
+            "go": "1.23",
             "runs-on": ["self-hosted", "arm", "linux"]
           }
           JSON
@@ -106,9 +104,6 @@ jobs:
         include: ${{ fromJson(needs.docker-targets.outputs.targets) }}
     env:
       ARCH: ${{ matrix.arch }}
-      # By default, use Docker CLI because docker-compose v1 is obsolete,
-      # except where the Docker client version is too old.
-      ARCHERY_USE_LEGACY_DOCKER_COMPOSE: ${{ matrix.archery-use-legacy-docker-compose || '0' }}
       GO: ${{ matrix.go }}
     steps:
       - name: Checkout Arrow
@@ -202,7 +197,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: ['1.21', '1.22']
+        go: ['1.22', '1.23']
     env:
       GO: ${{ matrix.go }}
     steps:
@@ -212,7 +207,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -243,7 +238,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: ['1.21', '1.22']
+        go: ['1.22', '1.23']
     env:
       GO: ${{ matrix.go }}
     steps:
@@ -252,7 +247,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -282,7 +277,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: ['1.21', '1.22']
+        go: ['1.22', '1.23']
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
@@ -315,7 +310,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: ['1.21', '1.22']
+        go: ['1.22', '1.23']
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
@@ -328,7 +323,7 @@ jobs:
           go-version: ${{ matrix.go }}
           cache: true
           cache-dependency-path: go/go.sum
-      - name: Install staticcheck      
+      - name: Install staticcheck
         run: |
           . .env
           go install honnef.co/go/tools/cmd/staticcheck@${STATICCHECK}
@@ -344,7 +339,7 @@ jobs:
           github.event_name == 'push' &&
           github.repository == 'apache/arrow' &&
           github.ref_name == 'main'
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: '3.10'
       - name: Run Benchmarks
@@ -373,7 +368,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: ['1.21', '1.22']
+        go: ['1.22', '1.23']
     env:
       ARROW_GO_TESTCGO: "1"
     steps:
@@ -444,7 +439,7 @@ jobs:
           ci/scripts/msys2_setup.sh cgo
       - name: Get required Go version
         run: |
-          (. .env && echo "GO_VERSION=${GO}") >> $GITHUB_ENV  
+          (. .env && echo "GO_VERSION=${GO}") >> $GITHUB_ENV
       - name: Update CGO Env vars
         shell: msys2 {0}
         run: |

diff --git a/.github/workflows/integration.yml b/.github/workflows/integration.yml
@@ -89,7 +89,7 @@ jobs:
           key: conda-${{ hashFiles('cpp/**') }}
           restore-keys: conda-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/java.yml b/.github/workflows/java.yml
@@ -76,7 +76,7 @@ jobs:
           key: maven-${{ hashFiles('java/**') }}
           restore-keys: maven-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/java_jni.yml b/.github/workflows/java_jni.yml
@@ -70,7 +70,7 @@ jobs:
           key: java-jni-manylinux-2014-${{ hashFiles('cpp/**', 'java/**') }}
           restore-keys: java-jni-manylinux-2014-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -110,7 +110,7 @@ jobs:
           key: maven-${{ hashFiles('java/**') }}
           restore-keys: maven-
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/java_nightly.yml b/.github/workflows/java_nightly.yml
@@ -58,7 +58,7 @@ jobs:
           repository: ursacomputing/crossbow
           ref: main
       - name: Set up Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           cache: 'pip'
           python-version: 3.12

diff --git a/.github/workflows/js.yml b/.github/workflows/js.yml
@@ -54,7 +54,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/pr_bot.yml b/.github/workflows/pr_bot.yml
@@ -82,7 +82,7 @@ jobs:
           # fetch the tags for version number generation
           fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
           python-version: 3.12
       - name: Install Archery and Crossbow dependencies