WIP: Dummy PR to check maint-20.0.0 status

.github/workflows/ruby.yml

@@ -79,7 +79,7 @@ jobs:
       UBUNTU: ${{ matrix.ubuntu }}
     steps:
       - name: Checkout Arrow
-        uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # v4.0.0
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
           submodules: recursive
@@ -148,7 +148,7 @@ jobs:
       ARROW_WITH_ZSTD: ON
     steps:
       - name: Checkout Arrow
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
           submodules: recursive
@@ -248,7 +248,7 @@ jobs:
             /d 1 `
             /f
       - name: Checkout Arrow
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
           submodules: recursive
@@ -366,7 +366,7 @@ jobs:
             /d 1 `
             /f
       - name: Checkout Arrow
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
           submodules: recursive
@@ -395,6 +395,20 @@ jobs:
         env:
           # We can invalidate the current cache by updating this.
           CACHE_VERSION: "2024-05-09"
+      - name: Checkout vcpkg
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+          path: vcpkg
+          repository: microsoft/vcpkg
+      - name: Bootstrap vcpkg
+        run: |
+          vcpkg\bootstrap-vcpkg.bat
+          $VCPKG_ROOT = $(Resolve-Path -LiteralPath "vcpkg").ToString()
+          Write-Output ${VCPKG_ROOT} | `
+            Out-File -FilePath ${Env:GITHUB_PATH} -Encoding utf8 -Append
+          Write-Output "VCPKG_ROOT=${VCPKG_ROOT}" | `
+            Out-File -FilePath ${Env:GITHUB_ENV} -Encoding utf8 -Append
       - name: Setup NuGet credentials for vcpkg caching
         shell: bash
         run: |
@@ -411,10 +425,14 @@ jobs:
       - name: Build C++
         shell: cmd
         run: |
+          set VCPKG_ROOT_KEEP=%VCPKG_ROOT%
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
+          set VCPKG_ROOT=%VCPKG_ROOT_KEEP%
           bash -c "ci/scripts/cpp_build.sh $(pwd) $(pwd)/build"
       - name: Build GLib
         shell: cmd
         run: |
+          set VCPKG_ROOT_KEEP=%VCPKG_ROOT%
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
+          set VCPKG_ROOT=%VCPKG_ROOT_KEEP%
           bash -c "ci/scripts/c_glib_build.sh $(pwd) $(pwd)/build"

.github/workflows/verify_rc.yml

@@ -21,13 +21,24 @@ on:
   push:
     tags:
       - "*-rc*"
+  pull_request:
+    paths:
+      - ".github/workflows/verify_rc.yml"
+  workflow_dispatch:
+    inputs:
+      rc_tag:
+        description: "Tag of the rc to verify"
+        type: string
+        required: true
+
 
 permissions:
   contents: read
 
 env:
   TEST_DEFAULT: "0"
   VERBOSE: "1"
+  RC_TAG: "${{ inputs.rc_tag || github.event_name == 'pull_request' && 'apache-arrow-20.0.0-rc0' || github.ref_name }}"
 
 jobs:
   apt:
@@ -46,9 +57,9 @@ jobs:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Run
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           version=${package_id#apache-arrow-}
-          rc=${GITHUB_REF_NAME#*-rc}
+          rc=${RC_TAG#*-rc}
           dev/release/verify-release-candidate.sh ${version} ${rc}
 
   binary:
@@ -61,9 +72,9 @@ jobs:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Run
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           version=${package_id#apache-arrow-}
-          rc=${GITHUB_REF_NAME#*-rc}
+          rc=${RC_TAG#*-rc}
           dev/release/verify-release-candidate.sh ${version} ${rc}
 
   wheels-linux:
@@ -89,9 +100,9 @@ jobs:
         run: python -m pip install -e dev/archery[docker]
       - name: Prepare
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           echo "VERSION=${package_id#apache-arrow-}" >> ${GITHUB_ENV}
-          echo "RC=${GITHUB_REF_NAME#*-rc}" >> ${GITHUB_ENV}
+          echo "RC=${RC_TAG#*-rc}" >> ${GITHUB_ENV}
           distro=${{ matrix.distro }}
           if [ "${distro}" = "conda" ]; then
             echo "SERVICE=${distro}-verify-rc" >> ${GITHUB_ENV}
@@ -102,13 +113,16 @@ jobs:
             echo "$(echo ${os} | tr a-z A-Z)=${version}" >> ${GITHUB_ENV}
           fi
       - name: Run
+        env:
+          GH_TOKEN: ${{ github.token }}
         run: |
           archery docker run \
             -e TEST_DEFAULT="${TEST_DEFAULT}" \
             -e TEST_WHEELS="${TEST_WHEELS}" \
             -e VERBOSE="${VERBOSE}" \
             -e VERIFY_RC="${RC}" \
             -e VERIFY_VERSION="${VERSION}" \
+            -e GH_TOKEN="$GH_TOKEN" \
             ${SERVICE}
 
   wheels-macos:
@@ -126,10 +140,12 @@ jobs:
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Run
+        env:
+          GH_TOKEN: ${{ github.token }}
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           version=${package_id#apache-arrow-}
-          rc=${GITHUB_REF_NAME#*-rc}
+          rc=${RC_TAG#*-rc}
           dev/release/verify-release-candidate.sh ${version} ${rc}
 
   wheels-windows:
@@ -141,12 +157,14 @@ jobs:
       TEST_WHEELS: "1"
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          submodules: recursive
       - name: Prepare
         shell: bash
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           echo "VERSION=${package_id#apache-arrow-}" >> ${GITHUB_ENV}
-          echo "RC=${GITHUB_REF_NAME#*-rc}" >> ${GITHUB_ENV}
+          echo "RC=${RC_TAG#*-rc}" >> ${GITHUB_ENV}
       - uses: conda-incubator/setup-miniconda@505e6394dae86d6a5c7fbb6e3fb8938e3e863830 # v3.1.1
       - name: Install System Dependencies
         run: |
@@ -156,6 +174,8 @@ jobs:
         shell: bash
         run: ci/scripts/download_tz_database.sh
       - name: Run verification
+        env:
+          GH_TOKEN: ${{ github.token }}
         shell: cmd
         run: |
           dev/release/verify-release-candidate-wheels.bat %VERSION% %RC%
@@ -176,7 +196,7 @@ jobs:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Run
         run: |
-          package_id=${GITHUB_REF_NAME%-rc*}
+          package_id=${RC_TAG%-rc*}
           version=${package_id#apache-arrow-}
-          rc=${GITHUB_REF_NAME#*-rc}
+          rc=${RC_TAG#*-rc}
           dev/release/verify-release-candidate.sh ${version} ${rc}

c_glib/meson.build

@@ -48,6 +48,7 @@ endif
 version_major = version_numbers[0].to_int()
 version_minor = version_numbers[1].to_int()
 version_micro = version_numbers[2].to_int()
+version_no_snapshot = '.'.join(version_numbers)
 
 api_version = '1.0'
 so_version = version_major * 100 + version_minor
@@ -81,7 +82,7 @@ endif
 generate_vapi = have_gi and get_option('vapi')
 if generate_vapi
     pkgconfig_variables += ['vapidir=@0@'.format(vapi_dir)]
-    add_languages('vala')
+    add_languages('vala', native: false)
 endif
 
 arrow_cpp_build_dir = get_option('arrow_cpp_build_dir')
@@ -97,47 +98,96 @@ else
 endif
 
 if arrow_cpp_build_lib_dir == ''
-    arrow = dependency('arrow', version: ['>=' + version])
+    common_args = {'version': [f'>=@version_no_snapshot@']}
+    arrow = dependency(
+        'arrow',
+        'Arrow',
+        kwargs: common_args,
+        modules: ['Arrow::arrow_shared'],
+    )
     # They are just for checking required modules are enabled. They are built into
     # libarrow.so. So we don't need additional build flags for them.
-    dependency('arrow-compute', version: ['>=' + version])
-    dependency('arrow-csv', version: ['>=' + version])
-    dependency('arrow-filesystem', version: ['>=' + version])
-    dependency('arrow-json', version: ['>=' + version])
+    if arrow.type_name() == 'cmake'
+        assert(
+            arrow.get_variable('ARROW_COMPUTE', default_value: 'OFF') == 'ON',
+            'compute module must be enabled',
+        )
+        assert(
+            arrow.get_variable('ARROW_CSV', default_value: 'OFF') == 'ON',
+            'CSV module must be enabled',
+        )
+        assert(
+            arrow.get_variable('ARROW_FILESYSTEM', default_value: 'OFF') == 'ON',
+            'filesystem module must be enabled',
+        )
+        assert(
+            arrow.get_variable('ARROW_JSON', default_value: 'OFF') == 'ON',
+            'JSON module must be enabled',
+        )
+    else
+        dependency('arrow-compute', kwargs: common_args)
+        dependency('arrow-csv', kwargs: common_args)
+        dependency('arrow-filesystem', kwargs: common_args)
+        dependency('arrow-json', kwargs: common_args)
+    endif
 
-    have_arrow_orc = dependency(
-        'arrow-orc',
-        required: false,
-        version: ['>=' + version],
-    ).found()
+    if arrow.type_name() == 'cmake'
+        have_arrow_orc = (arrow.get_variable('ARROW_ORC', default_value: 'OFF') == 'ON')
+    else
+        have_arrow_orc = dependency(
+            'arrow-orc',
+            kwargs: common_args,
+            required: false,
+        ).found()
+    endif
     arrow_cuda = dependency(
         'arrow-cuda',
+        'ArrowCUDA',
+        kwargs: common_args,
+        modules: ['ArrowCUDA::arrow_cuda_shared'],
         required: false,
-        version: ['>=' + version],
     )
-    # we do not support compiling glib without acero engine
+    # we do not support compiling GLib without Acero engine
     arrow_acero = dependency(
         'arrow-acero',
-        required: true,
-        version: ['>=' + version],
+        'ArrowAcero',
+        kwargs: common_args,
+        modules: ['ArrowAcero::arrow_acero_shared'],
     )
     arrow_dataset = dependency(
         'arrow-dataset',
+        'ArrowDataset',
+        kwargs: common_args,
+        modules: ['ArrowDataset::arrow_dataset_shared'],
         required: false,
-        version: ['>=' + version],
     )
     arrow_flight = dependency(
         'arrow-flight',
+        'ArrowFlight',
+        kwargs: common_args,
+        modules: ['ArrowFlight::arrow_flight_shared'],
         required: false,
-        version: ['>=' + version],
     )
     arrow_flight_sql = dependency(
         'arrow-flight-sql',
+        'ArrowFlightSql',
+        kwargs: common_args,
+        modules: ['ArrowFlightSql::arrow_flight_sql_shared'],
+        required: false,
+    )
+    gandiva = dependency(
+        'gandiva',
+        'Gandiva',
+        kwargs: common_args,
+        modules: ['Gandiva::gandiva_shared'],
         required: false,
-        version: ['>=' + version],
     )
-    gandiva = dependency('gandiva', required: false, version: ['>=' + version])
-    parquet = dependency('parquet', required: false, version: ['>=' + version])
+    parquet = dependency(
+        'parquet',
+        'Parquet',
+        kwargs: common_args,
+        modules: ['Parquet::parquet_shared'],
+    )
 else
     base_include_directories += [
         include_directories(join_paths(arrow_cpp_build_dir, 'src')),

c_glib/vcpkg.json

@@ -1,23 +1,11 @@
 {
   "name": "arrow-glib",
   "version-string": "20.0.0-SNAPSHOT",
+  "$comment:dependencies": "We can enable gobject-introspection again once it's updated",
   "dependencies": [
     "glib",
-    "gobject-introspection",
     "pkgconf"
   ],
-  "$comment": "2025.02.14",
-  "builtin-baseline": "d5ec528843d29e3a52d745a64b469f810b2cedbf",
-  "overrides": [
-    {
-      "$comment":
-        "We need gobject-introspection 1.80.0 or later for GLib 2.80.0 but vcpkg doesn't provide it yet.",
-      "name": "glib",
-      "version": "2.78.4"
-    },
-    {
-      "name": "vcpkg-tool-meson",
-      "version": "1.3.2"
-    }
-  ]
+  "$comment": "We can update builtin-baseline by 'vcpkg x-update-baseline'",
+  "builtin-baseline": "09f6a4ef2f08252f7f4d924fd9c2d42165fb21c9"
 }

ci/docker/python-free-threaded-wheel-windows-test-vs2022.dockerfile

@@ -38,12 +38,15 @@ SHELL ["cmd", "/S", "/C"]
 RUN %PYTHON_CMD% -m pip install -U pip setuptools
 
 COPY python/requirements-wheel-test.txt C:/arrow/python/
+# Temporarily remove pandas from the requirements, see https://github.com/apache/arrow/issues/46041
+RUN findstr /V "pandas" C:\arrow\python\requirements-wheel-test.txt > C:\arrow\python\filtered-requirements-wheel-test.txt
 # Cython and Pandas wheels for 3.13 free-threaded are not released yet
+# hadolint ignore=DL3059
 RUN %PYTHON_CMD% -m pip install \
     --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple \
     --pre \
     --prefer-binary \
-    -r C:/arrow/python/requirements-wheel-test.txt
+    -r C:/arrow/python/filtered-requirements-wheel-test.txt
 # cffi-based tests would crash when importing cffi.
 # hadolint ignore=DL3059
 RUN %PYTHON_CMD% -m pip uninstall -y cffi