Merge branch 'main' into try-fix-40431

ZhangHuiGui · Apr 2, 2024 · 0722f88 · 0722f88
2 parents 5180559 + 5ddef63
commit 0722f88
Show file tree

Hide file tree

Showing 154 changed files with 3,858 additions and 726 deletions.
diff --git a/.env b/.env
@@ -58,8 +58,8 @@ CUDA=11.2.2
 DASK=latest
 DOTNET=7.0
 GCC_VERSION=""
-GO=1.19.13
-STATICCHECK=v0.4.5
+GO=1.21.8
+STATICCHECK=v0.4.7
 HDFS=3.2.1
 JDK=8
 KARTOTHEK=latest

diff --git a/.github/workflows/archery.yml b/.github/workflows/archery.yml
@@ -57,7 +57,7 @@ jobs:
         shell: bash
         run: git branch $ARCHERY_DEFAULT_BRANCH origin/$ARCHERY_DEFAULT_BRANCH || true
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.1.0
         with:
           python-version: '3.12'
       - 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@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.12
       - name: Install Archery and Crossbow dependencies

diff --git a/.github/workflows/cpp.yml b/.github/workflows/cpp.yml
@@ -237,7 +237,7 @@ jobs:
           $(brew --prefix bash)/bin/bash \
             ci/scripts/install_minio.sh latest ${ARROW_HOME}
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.1.0
         with:
           python-version: 3.12
       - name: Install Google Cloud Storage Testbench
@@ -458,7 +458,7 @@ 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/setup-python@v5
+        uses: actions/setup-python@v5.1.0
         with:
           python-version: 3.9
       - name: Install Google Cloud Storage Testbench

diff --git a/.github/workflows/dev.yml b/.github/workflows/dev.yml
@@ -42,7 +42,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.12
       - name: Install pre-commit
@@ -101,7 +101,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Install Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: '3.12'
       - name: Install Ruby

diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -51,7 +51,7 @@ jobs:
           key: ubuntu-docs-${{ hashFiles('cpp/**') }}
           restore-keys: ubuntu-docs-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.12
       - name: Setup Archery

diff --git a/.github/workflows/docs_light.yml b/.github/workflows/docs_light.yml
@@ -57,7 +57,7 @@ jobs:
           key: conda-docs-${{ hashFiles('cpp/**') }}
           restore-keys: conda-docs-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.12
       - name: Setup Archery

diff --git a/.github/workflows/go.yml b/.github/workflows/go.yml
@@ -59,13 +59,13 @@ jobs:
           {
             "arch-label": "AMD64",
             "arch": "amd64",
-            "go": "1.19",
+            "go": "1.21",
             "runs-on": "ubuntu-latest"
           },
           {
             "arch-label": "AMD64",
             "arch": "amd64",
-            "go": "1.20",
+            "go": "1.22",
             "runs-on": "ubuntu-latest"
           }
           JSON
@@ -75,13 +75,13 @@ jobs:
           {
             "arch-label": "ARM64",
             "arch": "arm64v8",
-            "go": "1.19",
+            "go": "1.21",
             "runs-on": ["self-hosted", "arm", "linux"]
           },
           {
             "arch-label": "ARM64",
             "arch": "arm64v8",
-            "go": "1.20",
+            "go": "1.22",
             "runs-on": ["self-hosted", "arm", "linux"]
           }
           JSON
@@ -169,10 +169,13 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+      - name: Get required Go version
+        run: |
+          (. .env && echo "GO_VERSION=${GO}") >> $GITHUB_ENV
       - name: Install Go
         uses: actions/setup-go@v5
         with:
-          go-version: 1.19
+          go-version: "${{ env.GO_VERSION }}"
           cache: true
           cache-dependency-path: go/go.sum
       - name: Run build
@@ -188,7 +191,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: [1.19, '1.20']
+        go: ['1.21', '1.22']
     env:
       GO: ${{ matrix.go }}
     steps:
@@ -198,7 +201,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -229,7 +232,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: [1.19, '1.20']
+        go: ['1.21', '1.22']
     env:
       GO: ${{ matrix.go }}
     steps:
@@ -238,7 +241,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -268,7 +271,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: [1.19, '1.20']
+        go: ['1.21', '1.22']
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
@@ -301,7 +304,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: [1.19, '1.20']
+        go: ['1.21', '1.22']
     steps:
       - name: Checkout Arrow
         uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
@@ -330,7 +333,7 @@ jobs:
           github.event_name == 'push' &&
           github.repository == 'apache/arrow' &&
           github.ref_name == 'main'
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: '3.10'
       - name: Run Benchmarks
@@ -359,7 +362,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        go: [1.19, '1.20']
+        go: ['1.21', '1.22']
     env:
       ARROW_GO_TESTCGO: "1"
     steps:
@@ -428,6 +431,9 @@ jobs:
         shell: msys2 {0}
         run: |
           ci/scripts/msys2_setup.sh cgo
+      - name: Get required Go version
+        run: |
+          (. .env && echo "GO_VERSION=${GO}") >> $GITHUB_ENV  
       - name: Update CGO Env vars
         shell: msys2 {0}
         run: |
@@ -437,7 +443,7 @@ jobs:
       - name: Install go
         uses: actions/setup-go@v5
         with:
-          go-version: '1.19'
+          go-version: "${{ env.GO_VERSION }}"
           cache: true
           cache-dependency-path: go/go.sum
       - name: Install staticcheck

diff --git a/.github/workflows/integration.yml b/.github/workflows/integration.yml
@@ -81,7 +81,7 @@ jobs:
           key: conda-${{ hashFiles('cpp/**') }}
           restore-keys: conda-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/java.yml b/.github/workflows/java.yml
@@ -75,7 +75,7 @@ jobs:
           key: maven-${{ hashFiles('java/**') }}
           restore-keys: maven-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/java_jni.yml b/.github/workflows/java_jni.yml
@@ -69,7 +69,7 @@ jobs:
           key: java-jni-manylinux-2014-${{ hashFiles('cpp/**', 'java/**') }}
           restore-keys: java-jni-manylinux-2014-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -109,7 +109,7 @@ jobs:
           key: maven-${{ hashFiles('java/**') }}
           restore-keys: maven-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         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@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           cache: 'pip'
           python-version: 3.12

diff --git a/.github/workflows/js.yml b/.github/workflows/js.yml
@@ -51,7 +51,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/matlab.yml b/.github/workflows/matlab.yml
@@ -42,7 +42,23 @@ jobs:
 
   ubuntu:
     name: AMD64 Ubuntu 20.04 MATLAB
-    runs-on: ubuntu-latest
+    # Explicitly pin the Ubuntu version to 20.04 for the time being because:
+    #
+    #     1. The version of GLIBCXX shipped with Ubuntu 22.04 is not binary compatible
+    #        with the GLIBCXX bundled with MATLAB R2023a. This is a relatively common
+    #        issue.
+    #
+    #        For example, see:
+    #
+    #        https://www.mathworks.com/matlabcentral/answers/1907290-how-to-manually-select-the-libstdc-library-to-use-to-resolve-a-version-glibcxx_-not-found
+    #
+    #     2. The version of GLIBCXX shipped with Ubuntu 22.04 is not binary compatible with
+    #        the version of GLIBCXX shipped with Debian 11. Several of the Arrow community
+    #        members who work on the MATLAB bindings use Debian 11 locally for qualification.
+    #        Using Ubuntu 20.04 eases development workflows for these community members.
+    #
+    # In the future, we can investigate adding support for building against more Linux (e.g. `ubuntu-22.04`) and MATLAB versions (e.g. R2023b).
+    runs-on: ubuntu-20.04
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     steps:
       - name: Check out repository
@@ -74,22 +90,14 @@ jobs:
         run: ci/scripts/matlab_build.sh $(pwd)
       - name: Run MATLAB Tests
         env:
-          # libarrow.so requires a more recent version of libstdc++.so
-          # than is bundled with MATLAB under <matlabroot>/sys/os/glnxa64.
-          # Therefore, if a MEX function that depends on libarrow.so
-          # is executed within the MATLAB address space, runtime linking
-          # errors will occur. To work around this issue, we can explicitly
-          # force MATLAB to use the system libstdc++.so via LD_PRELOAD.
-          LD_PRELOAD: /usr/lib/x86_64-linux-gnu/libstdc++.so.6
-
           # Add the installation directory to the MATLAB Search Path by
           # setting the MATLABPATH environment variable.
           MATLABPATH: matlab/install/arrow_matlab
         uses: matlab-actions/run-tests@v2
         with:
           select-by-folder: matlab/test
   macos:
-    name: AMD64 macOS 11 MATLAB
+    name: AMD64 macOS 12 MATLAB
     runs-on: macos-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     steps:

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@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.12
       - name: Install Archery and Crossbow dependencies

diff --git a/.github/workflows/python.yml b/.github/workflows/python.yml
@@ -100,7 +100,7 @@ jobs:
           key: ${{ matrix.cache }}-${{ hashFiles('cpp/**') }}
           restore-keys: ${{ matrix.cache }}-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -162,7 +162,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.1.0
         with:
           python-version: '3.11'
       - name: Install Dependencies

diff --git a/.github/workflows/r.yml b/.github/workflows/r.yml
@@ -142,7 +142,7 @@ jobs:
             ubuntu-${{ matrix.ubuntu }}-r-${{ matrix.r }}-${{ hashFiles('cpp/src/**/*.cc','cpp/src/**/*.h)') }}-
             ubuntu-${{ matrix.ubuntu }}-r-${{ matrix.r }}-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery
@@ -203,7 +203,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery

diff --git a/.github/workflows/r_nightly.yml b/.github/workflows/r_nightly.yml
@@ -60,7 +60,7 @@ jobs:
           repository: ursacomputing/crossbow
           ref: main
       - name: Set up Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           cache: 'pip'
           python-version: 3.12

diff --git a/.github/workflows/ruby.yml b/.github/workflows/ruby.yml
@@ -82,7 +82,7 @@ jobs:
           key: ubuntu-${{ matrix.ubuntu }}-ruby-${{ hashFiles('cpp/**') }}
           restore-keys: ubuntu-${{ matrix.ubuntu }}-ruby-
       - name: Setup Python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
         with:
           python-version: 3.8
       - name: Setup Archery