Merge remote-tracking branch 'upstream/main' into gh-39555-build-numpy-2

apache · Jan 30, 2024 · 88daada · 88daada
2 parents fa80565 + b778ace
commit 88daada
Show file tree

Hide file tree

Showing 955 changed files with 7,300 additions and 4,500 deletions.
diff --git a/.asf.yaml b/.asf.yaml
@@ -19,13 +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:
+    - amoeba
     - anjakefala
     - benibus
     - danepitkin
     - davisusanibar
-    - felipecrv
     - js8544
-    - amoeba
+    - vibhatha
 
 notifications:
   commits:      commits@arrow.apache.org

diff --git a/.github/workflows/cpp.yml b/.github/workflows/cpp.yml
@@ -101,7 +101,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: ${{ matrix.image }}-${{ hashFiles('cpp/**') }}
@@ -214,7 +214,7 @@ jobs:
         run: |
           echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.ccache-info.outputs.cache-dir }}
           key: cpp-ccache-macos-${{ hashFiles('cpp/**') }}
@@ -310,7 +310,7 @@ jobs:
         run: |
           echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.ccache-info.outputs.cache-dir }}
           key: cpp-ccache-windows-${{ env.CACHE_VERSION }}-${{ hashFiles('cpp/**') }}
@@ -402,7 +402,7 @@ jobs:
         shell: msys2 {0}
         run: ci/scripts/msys2_setup.sh cpp
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ccache
           key: cpp-ccache-${{ matrix.msystem_lower}}-${{ hashFiles('cpp/**') }}

diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -45,7 +45,7 @@ jobs:
         run: |
           ci/scripts/util_free_space.sh
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: ubuntu-docs-${{ hashFiles('cpp/**') }}

diff --git a/.github/workflows/docs_light.yml b/.github/workflows/docs_light.yml
@@ -51,7 +51,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: conda-docs-${{ hashFiles('cpp/**') }}

diff --git a/.github/workflows/integration.yml b/.github/workflows/integration.yml
@@ -75,7 +75,7 @@ jobs:
         run: |
           ci/scripts/util_free_space.sh
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: conda-${{ hashFiles('cpp/**') }}

diff --git a/.github/workflows/java.yml b/.github/workflows/java.yml
@@ -69,7 +69,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: maven-${{ hashFiles('java/**') }}

diff --git a/.github/workflows/java_jni.yml b/.github/workflows/java_jni.yml
@@ -63,7 +63,7 @@ jobs:
         run: |
           ci/scripts/util_free_space.sh
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: java-jni-manylinux-2014-${{ hashFiles('cpp/**', 'java/**') }}
@@ -103,7 +103,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: maven-${{ hashFiles('java/**') }}

diff --git a/.github/workflows/js.yml b/.github/workflows/js.yml
@@ -91,7 +91,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Jest Cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: js/.jest-cache
           key: js-jest-cache-${{ runner.os }}-${{ hashFiles('js/src/**/*.ts', 'js/test/**/*.ts', 'js/yarn.lock') }}
@@ -121,7 +121,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Jest Cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: js/.jest-cache
           key: js-jest-cache-${{ runner.os }}-${{ hashFiles('js/src/**/*.ts', 'js/test/**/*.ts', 'js/yarn.lock') }}

diff --git a/.github/workflows/matlab.yml b/.github/workflows/matlab.yml
@@ -65,7 +65,7 @@ jobs:
         shell: bash
         run: echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.ccache-info.outputs.cache-dir }}
           key: matlab-ccache-ubuntu-${{ hashFiles('cpp/**', 'matlab/**') }}
@@ -113,7 +113,7 @@ jobs:
         shell: bash
         run: echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.ccache-info.outputs.cache-dir }}
           key: matlab-ccache-macos-${{ hashFiles('cpp/**', 'matlab/**') }}
@@ -155,7 +155,7 @@ jobs:
         shell: bash
         run: echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ${{ steps.ccache-info.outputs.cache-dir }}

diff --git a/.github/workflows/python.yml b/.github/workflows/python.yml
@@ -94,7 +94,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: ${{ matrix.cache }}-${{ hashFiles('cpp/**') }}

diff --git a/.github/workflows/r.yml b/.github/workflows/r.yml
@@ -73,7 +73,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           # As this key is identical on both matrix builds only one will be able to successfully cache,
@@ -206,7 +206,7 @@ jobs:
           ci/scripts/ccache_setup.sh
           echo "CCACHE_DIR=$(cygpath --absolute --windows ccache)" >> $GITHUB_ENV
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ccache
           key: r-${{ matrix.config.rtools }}-ccache-mingw-${{ matrix.config.arch }}-${{ hashFiles('cpp/src/**/*.cc','cpp/src/**/*.h)') }}-${{ github.run_id }}

diff --git a/.github/workflows/r_nightly.yml b/.github/workflows/r_nightly.yml
@@ -86,7 +86,7 @@ jobs:
             exit 1
           fi
       - name: Cache Repo
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: repo
           key: r-nightly-${{ github.run_id }}

diff --git a/.github/workflows/ruby.yml b/.github/workflows/ruby.yml
@@ -76,7 +76,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Cache Docker Volumes
-        uses: actions/cache@88522ab9f39a2ea568f7027eddc7d8d8bc9d59c8 # v3.3.1
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:
           path: .docker
           key: ubuntu-${{ matrix.ubuntu }}-ruby-${{ hashFiles('cpp/**') }}
@@ -167,7 +167,7 @@ jobs:
         run: |
           echo "cache-dir=$(ccache --get-config cache_dir)" >> $GITHUB_OUTPUT
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.ccache-info.outputs.cache-dir }}
           key: ruby-ccache-macos-${{ hashFiles('cpp/**') }}
@@ -252,7 +252,7 @@ jobs:
         run: |
           ridk exec bash ci\scripts\msys2_setup.sh ruby
       - name: Cache ccache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ccache
           key: ruby-ccache-ucrt${{ matrix.mingw-n-bits }}-${{ hashFiles('cpp/**') }}
@@ -277,7 +277,7 @@ jobs:
           Write-Output "gem-dir=$(ridk exec gem env gemdir)" | `
             Out-File -FilePath $env:GITHUB_OUTPUT -Encoding utf8 -Append
       - name: Cache RubyGems
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ${{ steps.rubygems-info.outputs.gem-dir }}
           key: ruby-rubygems-ucrt${{ matrix.mingw-n-bits }}-${{ hashFiles('**/Gemfile', 'ruby/*/*.gemspec') }}

diff --git a/c_glib/README.md b/c_glib/README.md
@@ -142,6 +142,17 @@ $ meson compile -C c_glib.build
 $ sudo meson install -C c_glib.build
 ```
 
+> [!WARNING]
+>
+> When building Arrow GLib, it typically uses the Arrow C++ installed via Homebrew. However, this can lead to build failures
+> if there are mismatches between the changes in Arrow's GLib and C++ libraries. To resolve this, you may need to
+> reference the Arrow C++ library built locally. In such cases, use the `--cmake-prefix-path` option with the `meson setup` 
+> command to explicitly specify the library path.
+>
+> ```console
+> $ meson setup c_glib.build c_glib --cmake-prefix-path=${arrow_cpp_install_prefix} -Dgtk_doc=true
+> ```
+
 Others:
 
 ```console
@@ -231,9 +242,18 @@ Now, you can run unit tests by the followings:
 
 ```console
 $ cd c_glib.build
-$ bundle exec ../c_glib/test/run-test.sh
+$ BUNDLE_GEMFILE=../c_glib/Gemfile bundle exec ../c_glib/test/run-test.sh
 ```
 
+
+> [!NOTE]
+>
+> If debugging is necessary, you can proceed using the `DEBUGGER` option as follows:
+>
+> ```console
+> $ DEBUGGER=lldb BUNDLE_GEMFILE=../c_glib/Gemfile bundle exec ../c_glib/test/run-test.sh
+> ```
+
 ## Common build problems
 
 ### build failed - /usr/bin/ld: cannot find -larrow