Merge branch 'main' into remove-deprecated-append-rowgroup

.github/workflows/dev_pr/title_check.md

@@ -38,4 +38,4 @@ In the case of PARQUET issues on JIRA the title also supports:
 See also:
 
   * [Other pull requests](https://github.com/apache/arrow/pulls/)
-  * [Contribution Guidelines - How to contribute patches](https://arrow.apache.org/docs/developers/contributing.html#how-to-contribute-patches)
+  * [Contribution Guidelines - Contributing Overview](https://arrow.apache.org/docs/developers/overview.html)

.github/workflows/go.yml

@@ -106,7 +106,7 @@ jobs:
           github.event_name == 'push' &&
           github.repository == 'apache/arrow' &&
           github.ref_name == 'main'
-        uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe # v4.1.0
+        uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 # v5.0.0
         with:
           go-version: ${{ matrix.go }}
           cache: true
@@ -139,7 +139,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
           go-version: 1.19
           cache: true
@@ -245,7 +245,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Install go
-        uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe # v4.1.0
+        uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 # v5.0.0
         with:
           go-version: ${{ matrix.go }}
           cache: true
@@ -278,7 +278,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Install go
-        uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe # v4.1.0
+        uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 # v5.0.0
         with:
           go-version: ${{ matrix.go }}
           cache: true
@@ -338,7 +338,7 @@ jobs:
           fetch-depth: 0
           submodules: recursive
       - name: Install go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
           go-version: ${{ matrix.go }}
           cache: true
@@ -404,7 +404,7 @@ jobs:
           echo "CGO_LDFLAGS=-g -O2 -L$(cygpath --windows ${MINGW_PREFIX}/lib) -L$(cygpath --windows ${MINGW_PREFIX}/bin)" >> $GITHUB_ENV
           echo "MINGW_PREFIX=$(cygpath --windows ${MINGW_PREFIX})" >> $GITHUB_ENV
       - name: Install go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
           go-version: '1.19'
           cache: true

.github/workflows/ruby.yml

@@ -196,7 +196,9 @@ jobs:
         mingw-n-bits:
           - 64
         ruby-version:
-          - ruby
+          # TODO: Use the latest Ruby again when we fix GH-39130.
+          # - ruby
+          - "3.1"
     env:
       ARROW_BUILD_STATIC: OFF
       ARROW_BUILD_TESTS: OFF
@@ -246,13 +248,6 @@ jobs:
         uses: ruby/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby-version }}
-      - name: Upgrade MSYS2
-        run: |
-          ridk exec bash ci\scripts\msys2_system_upgrade.sh
-          taskkill /F /FI "MODULES eq msys-2.0.dll"
-      - name: Clean MSYS2
-        run: |
-          ridk exec bash ci\scripts\msys2_system_clean.sh
       - name: Setup MSYS2
         run: |
           ridk exec bash ci\scripts\msys2_setup.sh ruby

CONTRIBUTING.md

@@ -67,5 +67,5 @@ You can also ask on the mailing-list, see above.
 
 ## Further information
 
-Please read our [development documentation](https://arrow.apache.org/docs/developers/contributing.html)
+Please read our [development documentation](https://arrow.apache.org/docs/developers/index.html)
 or look through the [New Contributor's Guide](https://arrow.apache.org/docs/developers/guide/index.html).

ci/conan/all/conandata.yml

@@ -45,21 +45,21 @@ sources:
 patches:
   "8.0.1":
     - patch_file: "patches/8.0.0-0005-install-utils.patch"
-      patch_description: "enable utilis installation"
+      patch_description: "enable utils installation"
       patch_type: "conan"
     - patch_file: "patches/8.0.0-0006-fix-cmake.patch"
       patch_description: "use cci package"
       patch_type: "conan"
   "8.0.0":
     - patch_file: "patches/8.0.0-0005-install-utils.patch"
-      patch_description: "enable utilis installation"
+      patch_description: "enable utils installation"
       patch_type: "conan"
     - patch_file: "patches/8.0.0-0006-fix-cmake.patch"
       patch_description: "use cci package"
       patch_type: "conan"
   "7.0.0":
     - patch_file: "patches/7.0.0-0006-install-utils.patch"
-      patch_description: "enable utilis installation"
+      patch_description: "enable utils installation"
       patch_type: "conan"
     - patch_file: "patches/7.0.0-0007-fix-cmake.patch"
       patch_description: "use cci package"

ci/conan/all/conanfile.py

@@ -328,7 +328,7 @@ def _with_boost(self, required=False):
             return bool(self.options.with_boost)
 
     def _with_thrift(self, required=False):
-        # No self.options.with_thift exists
+        # No self.options.with_thrift exists
         return bool(required or self._parquet())
 
     def _with_utf8proc(self, required=False):

ci/conan/all/test_package/test_package.cpp

@@ -78,7 +78,7 @@ arrow::Status VectorToColumnarTable(const std::vector<struct data_row>& rows,
     // Indicate the start of a new list row. This will memorise the current
     // offset in the values builder.
     ARROW_RETURN_NOT_OK(components_builder.Append());
-    // Store the actual values. The final nullptr argument tells the underyling
+    // Store the actual values. The final nullptr argument tells the underlying
     // builder that all added values are valid, i.e. non-null.
     ARROW_RETURN_NOT_OK(cost_components_builder.AppendValues(row.cost_components.data(),
                                                              row.cost_components.size()));

ci/docker/conda-cpp.dockerfile

@@ -22,7 +22,7 @@ FROM ${repo}:${arch}-conda
 COPY ci/scripts/install_minio.sh /arrow/ci/scripts
 RUN /arrow/ci/scripts/install_minio.sh latest /opt/conda
 
-# Unless overriden use Python 3.10
+# Unless overridden use Python 3.10
 # Google GCS fails building with Python 3.11 at the moment.
 ARG python=3.10
 

ci/docker/java-jni-manylinux-201x.dockerfile

@@ -18,7 +18,7 @@
 ARG base
 FROM ${base}
 
-# Install the libaries required by the Gandiva to run
+# Install the libraries required by the Gandiva to run
 # Use enable llvm[enable-rtti] in the vcpkg.json to avoid link problems in Gandiva
 RUN vcpkg install \
         --clean-after-build \

ci/docker/python-wheel-manylinux.dockerfile

@@ -73,7 +73,7 @@ ENV CMAKE_BUILD_TYPE=${build_type} \
     VCPKG_FEATURE_FLAGS="manifests"
 COPY ci/vcpkg/vcpkg.json arrow/ci/vcpkg/
 # cannot use the S3 feature here because while aws-sdk-cpp=1.9.160 contains
-# ssl related fixies as well as we can patch the vcpkg portfile to support
+# ssl related fixes as well as we can patch the vcpkg portfile to support
 # arm machines it hits ARROW-15141 where we would need to fall back to 1.8.186
 # but we cannot patch those portfiles since vcpkg-tool handles the checkout of
 # previous versions => use bundled S3 build

ci/docker/python-wheel-windows-vs2017.dockerfile

@@ -55,7 +55,7 @@ ENV CMAKE_BUILD_TYPE=${build_type} \
     VCPKG_FEATURE_FLAGS="manifests"
 COPY ci/vcpkg/vcpkg.json arrow/ci/vcpkg/
 # cannot use the S3 feature here because while aws-sdk-cpp=1.9.160 contains
-# ssl related fixies as well as we can patch the vcpkg portfile to support
+# ssl related fixes as well as we can patch the vcpkg portfile to support
 # arm machines it hits ARROW-15141 where we would need to fall back to 1.8.186
 # but we cannot patch those portfiles since vcpkg-tool handles the checkout of
 # previous versions => use bundled S3 build
@@ -97,4 +97,4 @@ RUN python -m pip install -r arrow/python/requirements-wheel-build.txt
 
 # For debugging purposes
 # RUN wget --no-check-certificate https://github.com/lucasg/Dependencies/releases/download/v1.10/Dependencies_x64_Release.zip
-# RUN unzip Dependencies_x64_Release.zip -d Dependencies && setx path "%path%;C:\Depencencies"
+# RUN unzip Dependencies_x64_Release.zip -d Dependencies && setx path "%path%;C:\Dependencies"

ci/scripts/install_python.sh

@@ -21,7 +21,7 @@ set -eu
 
 declare -A platforms
 platforms=([windows]=Windows
-           [macos]=MacOSX
+           [macos]=macOS
            [linux]=Linux)
 
 declare -A versions
@@ -43,7 +43,7 @@ platform=${platforms[$1]}
 version=$2
 full_version=${versions[$2]}
 
-if [ $platform = "MacOSX" ]; then
+if [ $platform = "macOS" ]; then
     echo "Downloading Python installer..."
 
     if [ "$(uname -m)" = "arm64" ] || [ "$version" = "3.10" ] || [ "$version" = "3.11" ] || [ "$version" = "3.12" ]; then

ci/scripts/install_sccache.sh

@@ -56,7 +56,7 @@ if [ ! -d $PREFIX ]; then
     mkdir -p $PREFIX
 fi
 
-# Extract only the sccache binary into $PREFIX and ignore README and LCIENSE.
+# Extract only the sccache binary into $PREFIX and ignore README and LICENSE.
 # --wildcards doesn't work on busybox.
 tar -xzvf $SCCACHE_ARCHIVE --strip-component=1 --directory $PREFIX --exclude="sccache*/*E*E*"
 chmod u+x $PREFIX/sccache

ci/scripts/integration_spark.sh

@@ -27,7 +27,7 @@ test_pyarrow_only=${3:-false}
 # Spark branch to checkout
 spark_version=${SPARK_VERSION:-master}
 
-# Use old behavior that always dropped tiemzones.
+# Use old behavior that always dropped timezones.
 export PYARROW_IGNORE_TIMEZONE=1
 
 if [ "${SPARK_VERSION:1:2}" == "2." ]; then

ci/scripts/msys2_setup.sh

@@ -43,7 +43,6 @@ case "${target}" in
     packages+=(${MINGW_PACKAGE_PREFIX}-lz4)
     packages+=(${MINGW_PACKAGE_PREFIX}-ninja)
     packages+=(${MINGW_PACKAGE_PREFIX}-nlohmann-json)
-    packages+=(${MINGW_PACKAGE_PREFIX}-openssl)
     packages+=(${MINGW_PACKAGE_PREFIX}-protobuf)
     packages+=(${MINGW_PACKAGE_PREFIX}-rapidjson)
     packages+=(${MINGW_PACKAGE_PREFIX}-re2)
@@ -52,8 +51,17 @@ case "${target}" in
     packages+=(${MINGW_PACKAGE_PREFIX}-thrift)
     packages+=(${MINGW_PACKAGE_PREFIX}-xsimd)
     packages+=(${MINGW_PACKAGE_PREFIX}-uriparser)
-    packages+=(${MINGW_PACKAGE_PREFIX}-zlib)
     packages+=(${MINGW_PACKAGE_PREFIX}-zstd)
+
+    if [ "${target}" != "ruby" ]; then
+      # We don't update the exiting packages for Ruby because
+      # RubyInstaller for Windows bundles some DLLs such as libffi,
+      # OpenSSL and zlib separately. They should be ABI compatible
+      # with packages installed by MSYS2. If we specify packages
+      # explicitly here, the existing packages may be updated.
+      packages+=(${MINGW_PACKAGE_PREFIX}-openssl)
+      packages+=(${MINGW_PACKAGE_PREFIX}-zlib)
+    fi
   ;;
 esac
 
@@ -78,7 +86,6 @@ esac
 pacman \
   --needed \
   --noconfirm \
-  --refresh \
   --sync \
   "${packages[@]}"
 

ci/scripts/r_valgrind.sh

@@ -33,7 +33,7 @@ ${R_BIN} CMD INSTALL ${INSTALL_ARGS} arrow*.tar.gz
 pushd tests
 
 # to generate suppression files run:
-# ${R_BIN} --vanilla -d "valgrind --tool=memcheck --leak-check=full --track-origins=yes --gen-suppressions=all --log-file=memcheck.log" -f testtthat.supp
+# ${R_BIN} --vanilla -d "valgrind --tool=memcheck --leak-check=full --track-origins=yes --gen-suppressions=all --log-file=memcheck.log" -f testthat.supp
 ${R_BIN} --vanilla -d "valgrind --tool=memcheck --leak-check=full --track-origins=yes --suppressions=/${1}/ci/etc/valgrind-cran.supp" -f testthat.R |& tee testthat.out
 
 # valgrind --error-exitcode=1 should return an erroring exit code that we can catch,

cpp/CHANGELOG_PARQUET.md

@@ -4,7 +4,7 @@ Parquet C++ 1.5.0
     * [PARQUET-979] - [C++] Limit size of min, max or disable stats for long binary types
     * [PARQUET-1071] - [C++] parquet::arrow::FileWriter::Close is not idempotent
     * [PARQUET-1349] - [C++] PARQUET_RPATH_ORIGIN is not picked by the build
-    * [PARQUET-1334] - [C++] memory_map parameter seems missleading in parquet file opener
+    * [PARQUET-1334] - [C++] memory_map parameter seems misleading in parquet file opener
     * [PARQUET-1333] - [C++] Reading of files with dictionary size 0 fails on Windows with bad_alloc
     * [PARQUET-1283] - [C++] FormatStatValue appends trailing space to string and int96
     * [PARQUET-1270] - [C++] Executable tools do not get installed
@@ -13,7 +13,7 @@ Parquet C++ 1.5.0
     * [PARQUET-1255] - [C++] Exceptions thrown in some tests
     * [PARQUET-1358] - [C++] index_page_offset should be unset as it is not supported.
     * [PARQUET-1357] - [C++] FormatStatValue truncates binary statistics on zero character
-    * [PARQUET-1319] - [C++] Pass BISON_EXECUTABLE to Thrift EP for MacOS
+    * [PARQUET-1319] - [C++] Pass BISON_EXECUTABLE to Thrift EP for macOS
     * [PARQUET-1313] - [C++] Compilation failure with VS2017
     * [PARQUET-1315] - [C++] ColumnChunkMetaData.has_dictionary_page() should return bool, not int64_t
     * [PARQUET-1307] - [C++] memory-test fails with latest Arrow
@@ -28,7 +28,7 @@ Parquet C++ 1.5.0
     * [PARQUET-1346] - [C++] Protect against null values data in empty Arrow array
     * [PARQUET-1340] - [C++] Fix Travis Ci valgrind errors related to std::random_device
     * [PARQUET-1323] - [C++] Fix compiler warnings with clang-6.0
-    * [PARQUET-1279] - Use ASSERT_NO_FATAIL_FAILURE in C++ unit tests
+    * [PARQUET-1279] - Use ASSERT_NO_FATAL_FAILURE in C++ unit tests
     * [PARQUET-1262] - [C++] Use the same BOOST_ROOT and Boost_NAMESPACE for Thrift
     * [PARQUET-1267] - replace "unsafe" std::equal by std::memcmp
     * [PARQUET-1360] - [C++] Minor API + style changes follow up to PARQUET-1348
@@ -89,7 +89,7 @@ Parquet C++ 1.4.0
 
 ## New Feature
     * [PARQUET-1095] - [C++] Read and write Arrow decimal values
-    * [PARQUET-970] - Add Add Lz4 and Zstd compression codecs
+    * [PARQUET-970] - Add Lz4 and Zstd compression codecs
 
 ## Task
     * [PARQUET-1221] - [C++] Extend release README
@@ -233,10 +233,10 @@ Parquet C++ 1.1.0
     * [PARQUET-977] - Improve MSVC build
     * [PARQUET-957] - [C++] Add optional $PARQUET_BUILD_TOOLCHAIN environment variable option for configuring build environment
     * [PARQUET-961] - [C++] Strip debug symbols from libparquet libraries in release builds by default
-    * [PARQUET-954] - C++: Use Brolti 0.6 release
+    * [PARQUET-954] - C++: Use Brotli 0.6 release
     * [PARQUET-953] - [C++] Change arrow::FileWriter API to be initialized from a Schema, and provide for writing multiple tables
     * [PARQUET-941] - [C++] Stop needless Boost static library detection for CentOS 7 support
-    * [PARQUET-942] - [C++] Fix wrong variabe use in FindSnappy
+    * [PARQUET-942] - [C++] Fix wrong variable use in FindSnappy
     * [PARQUET-939] - [C++] Support Thrift_HOME CMake variable like FindSnappy does as Snappy_HOME
     * [PARQUET-940] - [C++] Fix Arrow library path detection
     * [PARQUET-937] - [C++] Support CMake < 3.4 again for Arrow detection
@@ -278,7 +278,7 @@ Parquet C++ 1.0.0
     * [PARQUET-614] - C++: Remove unneeded LZ4-related code
     * [PARQUET-604] - Install writer.h headers
     * [PARQUET-621] - C++: Uninitialised DecimalMetadata is read
-    * [PARQUET-620] - C++: Duplicate calls to ParquetFileWriter::Close cause duplicate metdata writes
+    * [PARQUET-620] - C++: Duplicate calls to ParquetFileWriter::Close cause duplicate metadata writes
     * [PARQUET-599] - ColumnWriter::RleEncodeLevels' size estimation might be wrong
     * [PARQUET-617] - C++: Enable conda build to work on systems with non-default C++ toolchains
     * [PARQUET-627] - Ensure that thrift headers are generated before source compilation
@@ -339,7 +339,7 @@ Parquet C++ 1.0.0
     * [PARQUET-626] - Fix builds due to unavailable llvm.org apt mirror
     * [PARQUET-629] - RowGroupSerializer should only close itself once
     * [PARQUET-472] - Clean up InputStream ownership semantics in ColumnReader
-    * [PARQUET-739] - Rle-decoding uses static buffer that is shared accross threads
+    * [PARQUET-739] - Rle-decoding uses static buffer that is shared across threads
     * [PARQUET-561] - ParquetFileReader::Contents PIMPL missing a virtual destructor
     * [PARQUET-892] - [C++] Clean up link library targets in CMake files
     * [PARQUET-454] - Address inconsistencies in boolean decoding
@@ -401,12 +401,12 @@ Parquet C++ 1.0.0
     * [PARQUET-653] - [C++] Re-enable -static-libstdc++ in dev artifact builds
     * [PARQUET-763] - C++: Expose ParquetFileReader through Arrow reader
     * [PARQUET-857] - [C++] Flatten parquet/encodings directory
-    * [PARQUET-862] - Provide defaut cache size values if CPU info probing is not available
+    * [PARQUET-862] - Provide default cache size values if CPU info probing is not available
     * [PARQUET-689] - C++: Compress DataPages eagerly
     * [PARQUET-874] - [C++] Use default memory allocator from Arrow
     * [PARQUET-267] - Detach thirdparty code from build configuration.
     * [PARQUET-418] - Add a utility to print contents of a Parquet file to stdout
-    * [PARQUET-519] - Disable compiler warning supressions and fix all DEBUG build warnings
+    * [PARQUET-519] - Disable compiler warning suppressions and fix all DEBUG build warnings
     * [PARQUET-447] - Add Debug and Release build types and associated compiler flags
     * [PARQUET-868] - C++: Build snappy with optimizations
     * [PARQUET-894] - Fix compilation warning

cpp/CMakeLists.txt

@@ -75,7 +75,7 @@ set(ARROW_VERSION "15.0.0-SNAPSHOT")
 
 string(REGEX MATCH "^[0-9]+\\.[0-9]+\\.[0-9]+" ARROW_BASE_VERSION "${ARROW_VERSION}")
 
-# if no build build type is specified, default to release builds
+# if no build type is specified, default to release builds
 if(NOT DEFINED CMAKE_BUILD_TYPE)
   set(CMAKE_BUILD_TYPE
       Release
@@ -873,9 +873,6 @@ add_dependencies(arrow_test_dependencies toolchain-tests)
 if(ARROW_STATIC_LINK_LIBS)
   add_dependencies(arrow_dependencies ${ARROW_STATIC_LINK_LIBS})
   if(ARROW_HDFS OR ARROW_ORC)
-    if(Protobuf_SOURCE STREQUAL "SYSTEM")
-      list(APPEND ARROW_STATIC_INSTALL_INTERFACE_LIBS ${ARROW_PROTOBUF_LIBPROTOBUF})
-    endif()
     if(NOT MSVC_TOOLCHAIN)
       list(APPEND ARROW_STATIC_LINK_LIBS ${CMAKE_DL_LIBS})
       list(APPEND ARROW_STATIC_INSTALL_INTERFACE_LIBS ${CMAKE_DL_LIBS})

cpp/CMakePresets.json

@@ -428,7 +428,7 @@
         "base-benchmarks",
         "features-maximal"
       ],
-      "displayName": "Benchmarking build with with everything enabled",
+      "displayName": "Benchmarking build with everything enabled",
       "cacheVariables": {}
     },
     {

cpp/apidoc/Doxyfile

@@ -239,7 +239,7 @@ QT_AUTOBRIEF           = NO
 # tag to YES if you prefer the old behavior instead.
 #
 # Note that setting this tag to YES also means that rational rose comments are
-# not recognized any more.
+# not recognized anymore.
 # The default value is: NO.
 
 MULTILINE_CPP_IS_BRIEF = NO
@@ -569,7 +569,7 @@ INTERNAL_DOCS          = NO
 # If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
 # names in lower-case letters. If set to YES, upper-case letters are also
 # allowed. This is useful if you have classes or files whose names only differ
-# in case and if your file system supports case sensitive file names. Windows
+# in case and if your file system supports case-sensitive file names. Windows
 # (including Cygwin) ands Mac users are advised to set this option to NO.
 # The default value is: system dependent.
 
@@ -734,7 +734,7 @@ SHOW_NAMESPACES        = YES
 # The FILE_VERSION_FILTER tag can be used to specify a program or script that
 # doxygen should invoke to get the current version for each file (typically from
 # the version control system). Doxygen will invoke the program by executing (via
-# popen()) the command command input-file, where command is the value of the
+# popen()) the command input-file, where command is the value of the
 # FILE_VERSION_FILTER tag, and input-file is the name of an input file provided
 # by doxygen. Whatever the program writes to standard output is used as the file
 # version. For an example see the documentation.