Merge branch 'apache:main' into dataset_max_rows_queued

Author: gitmodimo

.asf.yaml

@@ -18,6 +18,19 @@
 github:
   description: "Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics"
   homepage: https://arrow.apache.org/
+  labels:
+    - arrow
+    - parquet
+
+  features:
+    issues: true
+    projects: true
+    discussions: true
+
+  protected_branches:
+    # protect main against force push
+    main: {}
+
   collaborators:
     - anjakefala
     - hiroyuki-sato
@@ -31,4 +44,5 @@ notifications:
   issues_status: [email protected]
   issues:       [email protected]
   pullrequests: [email protected]
+  discussions: [email protected]
   jira_options: link label worklog

.clang-tidy

@@ -27,7 +27,6 @@ Checks: |
 # produce HeaderFilterRegex from cpp/build-support/lint_exclusions.txt with:
 # echo -n '^('; sed -e 's/*/\.*/g' cpp/build-support/lint_exclusions.txt | tr '\n' '|'; echo ')$'
 HeaderFilterRegex: '^(.*codegen.*|.*_generated.*|.*windows_compatibility.h|.*pyarrow_api.h|.*pyarrow_lib.h|.*python/config.h|.*python/platform.h|.*thirdparty/ae/.*|.*vendored/.*|.*RcppExports.cpp.*|)$'
-AnalyzeTemporaryDtors: true
 CheckOptions:
   - key:             google-readability-braces-around-statements.ShortStatementLines
     value:           '1'

.editorconfig

@@ -50,15 +50,6 @@ indent_style = space
 indent_size = 2
 indent_style = space
 
-[*.go]
-indent_size = 8
-indent_style = tab
-tab_width = 8
-
-[*.{js,ts}]
-indent_size = 4
-indent_style = space
-
 [*.{py,pyx,pxd,pxi}]
 indent_size = 4
 indent_style = space

.env

@@ -47,15 +47,15 @@ ULIMIT_CORE=-1
 
 # Default versions for platforms
 ALMALINUX=8
-ALPINE_LINUX=3.18
+ALPINE_LINUX=3.22
 DEBIAN=12
-FEDORA=39
+FEDORA=42
 UBUNTU=22.04
 
 # Default versions for various dependencies
 CLANG_TOOLS=14
-CMAKE=3.25.0
-CUDA=11.2.2
+CMAKE=3.26.0
+CUDA=11.7.1
 DASK=latest
 DOTNET=8.0
 GCC=
@@ -65,14 +65,15 @@ KARTOTHEK=latest
 # LLVM 12 and GCC 11 reports -Wmismatched-new-delete.
 LLVM=18
 MAVEN=3.8.7
-NODE=18
+NODE=20
 NUMBA=latest
+NUMBA_CUDA=latest
 NUMPY=latest
 PANDAS=latest
 PYTHON=3.9
 PYTHON_IMAGE_TAG=3.9
 PYTHON_ABI_TAG=cp39
-R=4.4
+R=4.5
 SPARK=master
 TURBODBC=latest
 

.gitattributes

@@ -1,4 +1,5 @@
 cpp/src/arrow/util/bpacking_*_generated.h linguist-generated=true
+cpp/src/parquet/chunker_*_generated.h linguist-generated=true
 cpp/src/generated/*.cpp linguist-generated=true
 cpp/src/generated/*.h linguist-generated=true
 go/**/*.s linguist-generated=true

.github/CODEOWNERS

@@ -34,15 +34,12 @@
 /cpp/src/arrow/flight/ @lidavidm
 /cpp/src/parquet @wgtmac
 /csharp/ @curthagenlocher
-/go/ @zeroshade
-/java/ @lidavidm
-/js/ @domoritz @trxcllnt
 /matlab/ @kevingurney @kou @sgilmore10
+/python/ @AlenkaF @raulcd @rok 
 /python/pyarrow/_flight.pyx @lidavidm
 /python/pyarrow/**/*gandiva* @wjones127
 /r/ @jonkeane @thisisnic
 /ruby/ @kou
-/swift/ @kou
 
 # Docs
 # /docs/

.github/ISSUE_TEMPLATE/usage_question.yaml

@@ -23,12 +23,14 @@ body:
   - type: markdown
     attributes:
       value: >
-        While we enable issues as a mechanism for new contributors and
+        While we enable Issues as a mechanism for new contributors and
         passers-by who are unfamiliar with Apache Software Foundation projects
         to ask questions and interact with the project, we encourage users to
-        ask such questions on the [public mailing
-        lists](https://arrow.apache.org/community/) as these provide higher
-        visibility than GitHub issues:
+        ask such questions using either [GitHub
+        Discussions](https://github.com/apache/arrow/discussions) or the mailing
+        lists.
+
+        If you prefer to use the mailing lists,
 
         * For usage questions, please email [email protected] (first
         subscribe by sending an e-mail to [email protected]).
@@ -41,7 +43,8 @@ body:
         page](https://arrow.apache.org/community/) for more information on the
         mailing lists as well as for a link to the searchable archives.
 
-        Do not be surprised by responses to issues raised here directing you to those
+        Do not be surprised by responses to Issues raised here directing you to
+        [Discussions](https://github.com/apache/arrow/discussions) or the
         mailing lists, or to report a bug or feature request here.
 
         Thank you!

.github/dependabot.yml

@@ -24,12 +24,19 @@ updates:
     commit-message:
       prefix: "MINOR: [CI] "
     open-pull-requests-limit: 10
-  - package-ecosystem: "npm"
-    directory: "/js/"
+  - package-ecosystem: "gomod"
+    directory: "/swift/CDataWGo/"
     schedule:
-      interval: "monthly"
+      interval: "weekly"
+    commit-message:
+      prefix: "MINOR: [Swift] "
+    open-pull-requests-limit: 10
+  - package-ecosystem: "gomod"
+    directory: "/swift/data-generator/swift-datagen/"
+    schedule:
+      interval: "weekly"
     commit-message:
-      prefix: "MINOR: [JS] "
+      prefix: "MINOR: [Swift] "
     open-pull-requests-limit: 10
   - package-ecosystem: "nuget"
     directory: "/csharp/"

.github/workflows/archery.yml

@@ -58,14 +58,14 @@ jobs:
     timeout-minutes: 15
     steps:
       - name: Checkout Arrow
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
       - name: Git Fixup
         shell: bash
         run: git branch $ARCHERY_DEFAULT_BRANCH origin/$ARCHERY_DEFAULT_BRANCH || true
       - name: Setup Python
-        uses: actions/setup-python@v5.4.0
+        uses: actions/setup-python@v5.6.0
         with:
           python-version: '3.9'
       - name: Install pygit2 binary wheel

.github/workflows/comment_bot.yml

@@ -36,20 +36,20 @@ jobs:
       pull-requests: write
     steps:
       - name: Checkout Arrow
-        uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           path: arrow
           # fetch the tags for version number generation
           fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: 3.12
       - name: Install Archery and Crossbow dependencies
         run: pip install -e arrow/dev/archery[bot]
       - name: Handle GitHub comment event
         env:
-          ARROW_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           CROSSBOW_GITHUB_TOKEN: ${{ secrets.CROSSBOW_GITHUB_TOKEN }}
         run: |
           archery --debug trigger-bot \