Merge branch 'master' into jdbc-double-buffer-result-set

.asf.yaml

@@ -19,11 +19,13 @@ github:
   description: "Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing"
   homepage: https://arrow.apache.org/
   collaborators:
+    - anjakefala
     - benibus
     - danepitkin
+    - davisusanibar
     - felipecrv
-    - milesgranger
-    - toddfarmer
+    - js8544
+    - mapleFU
 
 notifications:
   commits:      commits@arrow.apache.org

.clang-tidy

@@ -21,6 +21,7 @@ Checks: |
   -clang-analyzer-alpha*,
   google-*,
   modernize-*,
+  -modernize-avoid-c-arrays,
   -modernize-use-trailing-return-type,
   -modernize-use-nodiscard,
 # produce HeaderFilterRegex from cpp/build-support/lint_exclusions.txt with:

.env

@@ -66,7 +66,7 @@ KARTOTHEK=latest
 # LLVM 12 and GCC 11 reports -Wmismatched-new-delete.
 LLVM=14
 MAVEN=3.5.4
-NODE=16
+NODE=18
 NUMBA=latest
 NUMPY=latest
 PANDAS=latest

.github/CODEOWNERS

@@ -28,25 +28,26 @@
 ## Components
 /c_glib/ @kou
 # /cpp/
-/cpp/src/arrow/compute @westonpace
+/cpp/src/arrow/acero @westonpace
+/cpp/src/arrow/adapters/orc @wgtmac
 /cpp/src/arrow/dataset @westonpace
 /cpp/src/arrow/engine @westonpace
 /cpp/src/arrow/flight/ @lidavidm
 /cpp/src/arrow/util/async* @westonpace
 /cpp/src/arrow/util/future* @westonpace
 /cpp/src/arrow/util/thread* @westonpace
-/cpp/src/parquet @wjones127
+/cpp/src/parquet @wgtmac
 /cpp/src/skyhook @westonpace
 /csharp/ @westonpace
 /go/ @zeroshade
 /java/ @lidavidm
 /js/ @domoritz @trxcllnt
-/matlab/ @assignUser
-/python/ @AlenkaF
+/matlab/ @kevingurney @kou
 /python/pyarrow/_flight.pyx @lidavidm
 /python/pyarrow/**/*gandiva* @wjones127
 /r/ @paleolimbot @thisisnic
 /ruby/ @kou
+/swift/ @kou
 
 # Docs
 # /docs/

ci/docker/debian-10-go-cgo-python.dockerfile → .github/dependabot.yml

@@ -15,22 +15,27 @@
 # specific language governing permissions and limitations
 # under the License.
 
-ARG base
-FROM ${base}
-
-ENV DEBIAN_FRONTEND noninteractive
-
-# Install python3 and pip so we can install pyarrow to test the C data interface.
-RUN apt-get update -y -q && \
-    apt-get install -y -q --no-install-recommends \
-        python3 \
-        python3-pip && \
-    apt-get clean
-
-RUN ln -s /usr/bin/python3 /usr/local/bin/python && \
-    ln -s /usr/bin/pip3 /usr/local/bin/pip
-
-# Need a newer pip than Debian's to install manylinux201x wheels
-RUN pip install -U pip
-
-RUN pip install pyarrow cffi --only-binary pyarrow
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    commit-message:
+      prefix: "MINOR: [CI] "
+  - package-ecosystem: "nuget"
+    directory: "/csharp/"
+    schedule:
+      interval: "weekly"
+    commit-message:
+      prefix: "MINOR: [C#] "
+    ignore:
+      - dependency-name: "Microsoft.Extensions.*"
+        update-types:
+          - "version-update:semver-major"
+      - dependency-name: "Microsoft.Bcl.*"
+        update-types:
+          - "version-update:semver-major"
+      - dependency-name: "System.*"
+        update-types:
+          - "version-update:semver-major"

.github/workflows/comment_bot.yml

@@ -182,11 +182,11 @@ jobs:
     if: github.event.comment.body == 'take'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/github-script@v3
+      - uses: actions/github-script@v6
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
-            github.issues.addAssignees({
+            github.rest.issues.addAssignees({
                 owner: context.repo.owner,
                 repo: context.repo.repo,
                 issue_number: context.payload.issue.number,

.github/workflows/cpp.yml

@@ -67,7 +67,8 @@ jobs:
             image: conda-cpp
             llvm: "14"
             runs-on: ubuntu-latest
-            title: AMD64 Conda C++
+            simd-level: AVX2
+            title: AMD64 Conda C++ AVX2
             ubuntu: "22.04"
           - arch: amd64
             clang-tools: "14"
@@ -85,6 +86,7 @@ jobs:
             ubuntu: "20.04"
     env:
       ARCH: ${{ matrix.arch }}
+      ARROW_SIMD_LEVEL: ${{ matrix.simd-level }}
       CLANG_TOOLS: ${{ matrix.clang-tools }}
       LLVM: ${{ matrix.llvm }}
       UBUNTU: ${{ matrix.ubuntu }}
@@ -114,7 +116,11 @@ jobs:
           ulimit -c unlimited
           archery docker run ${{ matrix.image }}
       - name: Docker Push
-        if: success() && github.event_name == 'push' && github.repository == 'apache/arrow'
+        if: >-
+          success() &&
+          github.event_name == 'push' &&
+          github.repository == 'apache/arrow' &&
+          github.ref_name == 'main'
         env:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -147,6 +153,7 @@ jobs:
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 75
     env:
+      ARROW_AZURE: ON
       ARROW_BUILD_TESTS: ON
       ARROW_DATASET: ON
       ARROW_FLIGHT: ON
@@ -162,12 +169,18 @@ jobs:
       ARROW_WITH_BROTLI: ON
       ARROW_WITH_BZ2: ON
       ARROW_WITH_LZ4: ON
-      ARROW_WITH_OPENTELEMETRY: ON
+      # GH-36013 disabling opentelemetry here because we can't
+      # get the patched version from conda
+      # ARROW_WITH_OPENTELEMETRY: ON
       ARROW_WITH_SNAPPY: ON
       ARROW_WITH_ZLIB: ON
       ARROW_WITH_ZSTD: ON
       GTest_SOURCE: BUNDLED
     steps:
+      - name: CPU Info
+        run: |
+          sysctl -a | grep cpu
+          sysctl -a | grep "hw.optional"
       - name: Checkout Arrow
         uses: actions/checkout@v3
         with:
@@ -180,7 +193,7 @@ jobs:
           rm -f /usr/local/bin/pydoc3* || :
           rm -f /usr/local/bin/python3* || :
           rm -f /usr/local/bin/python3-config || :
-          brew update --preinstall
+          brew update --preinstall || :
           brew bundle --file=cpp/Brewfile
       - name: Install MinIO
         run: |
@@ -213,7 +226,7 @@ jobs:
           ci/scripts/cpp_test.sh $(pwd) $(pwd)/build
 
   windows:
-    name: AMD64 ${{ matrix.name }} C++17
+    name: ${{ matrix.title }}
     runs-on: ${{ matrix.os }}
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 60
@@ -224,7 +237,8 @@ jobs:
           - windows-2019
         include:
           - os: windows-2019
-            name: Windows 2019
+            simd-level: AVX2
+            title: AMD64 Windows 2019 C++17 AVX2
     env:
       ARROW_BOOST_USE_SHARED: OFF
       ARROW_BUILD_BENCHMARKS: ON
@@ -239,6 +253,7 @@ jobs:
       ARROW_MIMALLOC: ON
       ARROW_ORC: ON
       ARROW_PARQUET: ON
+      ARROW_SIMD_LEVEL: ${{ matrix.simd-level }}
       ARROW_USE_GLOG: OFF
       ARROW_VERBOSE_THIRDPARTY_BUILD: OFF
       ARROW_WITH_BROTLI: OFF
@@ -267,7 +282,7 @@ jobs:
             /d 1 `
             /f
       - name: Installed Packages
-        run: choco list -l
+        run: choco list
       - name: Install Dependencies
         run: choco install -y --no-progress openssl
       - name: Checkout Arrow
@@ -358,6 +373,7 @@ jobs:
       CMAKE_ARGS: >-
         -DARROW_PACKAGE_PREFIX=/${{ 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.
       # CMAKE_UNITY_BUILD: ON

.github/workflows/csharp.yml

@@ -49,7 +49,7 @@ jobs:
         dotnet: ['7.0.x']
     steps:
       - name: Install C#
-        uses: actions/setup-dotnet@v2
+        uses: actions/setup-dotnet@v3
         with:
           dotnet-version: ${{ matrix.dotnet }}
       - name: Checkout Arrow
@@ -77,7 +77,7 @@ jobs:
         dotnet: ['7.0.x']
     steps:
       - name: Install C#
-        uses: actions/setup-dotnet@v2
+        uses: actions/setup-dotnet@v3
         with:
           dotnet-version: ${{ matrix.dotnet }}
       - name: Checkout Arrow
@@ -104,7 +104,7 @@ jobs:
         dotnet: ['7.0.x']
     steps:
       - name: Install C#
-        uses: actions/setup-dotnet@v2
+        uses: actions/setup-dotnet@v3
         with:
           dotnet-version: ${{ matrix.dotnet }}
       - name: Checkout Arrow

.github/workflows/dev.yml

@@ -55,7 +55,11 @@ jobs:
           ulimit -c unlimited
           archery docker run -e GITHUB_ACTIONS=true ubuntu-lint
       - name: Docker Push
-        if: success() && github.event_name == 'push' && github.repository == 'apache/arrow'
+        if: >-
+          success() &&
+          github.event_name == 'push' &&
+          github.repository == 'apache/arrow' &&
+          github.ref_name == 'main'
         env:
           ARCHERY_DOCKER_USER: ${{ secrets.DOCKERHUB_USER }}
           ARCHERY_DOCKER_PASSWORD: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -92,14 +96,14 @@ jobs:
         with:
           ruby-version: '2.7'
       - name: Install .NET
-        uses: actions/setup-dotnet@v2
+        uses: actions/setup-dotnet@v3
         with:
           dotnet-version: '7.0.x'
       - name: Install Dependencies
         shell: bash
         run: |
           gem install test-unit
-          pip install cython setuptools six pytest jira
+          pip install "cython<3" setuptools six pytest jira
       - name: Run Release Test
         env:
           ARROW_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/dev_pr.yml

@@ -44,12 +44,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
+        with:
+          repository: apache/arrow
+          ref: main
+          persist-credentials: false
 
       - name: Comment JIRA link
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@v3
+        uses: actions/github-script@v6
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -60,7 +64,7 @@ jobs:
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@v3
+        uses: actions/github-script@v6
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -71,7 +75,7 @@ jobs:
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@v3
+        uses: actions/github-script@v6
         with:
           debug: true
           github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/dev_pr/helpers.js

@@ -75,7 +75,7 @@ async function getJiraInfo(jiraID) {
  */
  async function getGitHubInfo(github, context, issueID, pullRequestNumber) {
     try {
-        const response = await github.issues.get({
+        const response = await github.rest.issues.get({
             issue_number: issueID,
             owner: context.repo.owner,
             repo: context.repo.repo,
@@ -91,4 +91,4 @@ module.exports = {
     detectIssue,
     getJiraInfo,
     getGitHubInfo
-};
+};