Merge remote-tracking branch 'upstream/main' into pandas-metadata-fie…

…ld-name

.github/workflows/dev_pr/issue_check.js

@@ -78,7 +78,7 @@ module.exports = async ({github, context}) => {
     const pullRequestNumber = context.payload.number;
     const title = context.payload.pull_request.title;
     const issue = helpers.detectIssue(title)
-    if (issue){
+    if (issue && issue.kind === "github") {
         await verifyGitHubIssue(github, context, pullRequestNumber, issue.id);
     }
 };

.github/workflows/dev_pr/link.js

@@ -77,7 +77,7 @@ module.exports = async ({github, context}) => {
   const pullRequestNumber = context.payload.number;
   const title = context.payload.pull_request.title;
   const issue = helpers.detectIssue(title);
-  if (issue){
+  if (issue && issue.kind === "github") {
     await commentGitHubURL(github, context, pullRequestNumber, issue.id);
   }
 };

ci/docker/debian-12-cpp.dockerfile

@@ -108,6 +108,11 @@ RUN /arrow/ci/scripts/install_azurite.sh
 COPY ci/scripts/install_sccache.sh /arrow/ci/scripts/
 RUN /arrow/ci/scripts/install_sccache.sh unknown-linux-musl /usr/local/bin
 
+# Prioritize system packages and local installation.
+#
+# The following dependencies will be downloaded due to missing/invalid packages
+# provided by the distribution:
+# - opentelemetry-cpp-dev is not packaged
 ENV ARROW_ACERO=ON \
     ARROW_AZURE=ON \
     ARROW_BUILD_TESTS=ON \
@@ -134,6 +139,7 @@ ENV ARROW_ACERO=ON \
     AWSSDK_SOURCE=BUNDLED \
     Azure_SOURCE=BUNDLED \
     google_cloud_cpp_storage_SOURCE=BUNDLED \
+    opentelemetry_cpp_SOURCE=BUNDLED \
     ORC_SOURCE=BUNDLED \
     PATH=/usr/lib/ccache/:$PATH \
     PYTHON=python3 \

ci/docker/fedora-39-cpp.dockerfile

@@ -103,6 +103,7 @@ ENV ARROW_ACERO=ON \
     CC=gcc \
     CXX=g++ \
     google_cloud_cpp_storage_SOURCE=BUNDLED \
+    opentelemetry_cpp_SOURCE=BUNDLED \
     PARQUET_BUILD_EXAMPLES=ON \
     PARQUET_BUILD_EXECUTABLES=ON \
     PATH=/usr/lib/ccache/:$PATH \

ci/docker/ubuntu-20.04-cpp.dockerfile

@@ -135,16 +135,19 @@ RUN /arrow/ci/scripts/install_ceph.sh
 COPY ci/scripts/install_sccache.sh /arrow/ci/scripts/
 RUN /arrow/ci/scripts/install_sccache.sh unknown-linux-musl /usr/local/bin
 
-# Prioritize system packages and local installation
+# Prioritize system packages and local installation.
+#
 # The following dependencies will be downloaded due to missing/invalid packages
 # provided by the distribution:
 # - Abseil is not packaged
 # - libc-ares-dev does not install CMake config files
 # - flatbuffer is not packaged
 # - libgtest-dev only provide sources
 # - libprotobuf-dev only provide sources
+# - opentelemetry-cpp-dev is not packaged
+#
 # ARROW-17051: this build uses static Protobuf, so we must also use
-# static Arrow to run Flight/Flight SQL tests
+# static Arrow to run Flight/Flight SQL tests.
 ENV absl_SOURCE=BUNDLED \
     ARROW_ACERO=ON \
     ARROW_AZURE=OFF \
@@ -179,6 +182,7 @@ ENV absl_SOURCE=BUNDLED \
     google_cloud_cpp_storage_SOURCE=BUNDLED \
     gRPC_SOURCE=BUNDLED \
     GTest_SOURCE=BUNDLED \
+    opentelemetry_cpp_SOURCE=BUNDLED \
     ORC_SOURCE=BUNDLED \
     PARQUET_BUILD_EXAMPLES=ON \
     PARQUET_BUILD_EXECUTABLES=ON \

ci/docker/ubuntu-22.04-cpp.dockerfile

@@ -184,11 +184,13 @@ RUN /arrow/ci/scripts/install_azurite.sh
 COPY ci/scripts/install_sccache.sh /arrow/ci/scripts/
 RUN /arrow/ci/scripts/install_sccache.sh unknown-linux-musl /usr/local/bin
 
-# Prioritize system packages and local installation
+# Prioritize system packages and local installation.
+#
 # The following dependencies will be downloaded due to missing/invalid packages
 # provided by the distribution:
 # - Abseil is old
 # - libc-ares-dev does not install CMake config files
+# - opentelemetry-cpp-dev is not packaged
 ENV absl_SOURCE=BUNDLED \
     ARROW_ACERO=ON \
     ARROW_AZURE=ON \
@@ -222,6 +224,7 @@ ENV absl_SOURCE=BUNDLED \
     AWSSDK_SOURCE=BUNDLED \
     Azure_SOURCE=BUNDLED \
     google_cloud_cpp_storage_SOURCE=BUNDLED \
+    opentelemetry_cpp_SOURCE=BUNDLED \
     ORC_SOURCE=BUNDLED \
     PARQUET_BUILD_EXAMPLES=ON \
     PARQUET_BUILD_EXECUTABLES=ON \

ci/docker/ubuntu-24.04-cpp.dockerfile

@@ -172,7 +172,11 @@ RUN /arrow/ci/scripts/install_azurite.sh
 COPY ci/scripts/install_sccache.sh /arrow/ci/scripts/
 RUN /arrow/ci/scripts/install_sccache.sh unknown-linux-musl /usr/local/bin
 
-# Prioritize system packages and local installation
+# Prioritize system packages and local installation.
+#
+# The following dependencies will be downloaded due to missing/invalid packages
+# provided by the distribution:
+# - opentelemetry-cpp-dev is not packaged
 ENV ARROW_ACERO=ON \
     ARROW_AZURE=ON \
     ARROW_BUILD_STATIC=ON \
@@ -205,6 +209,7 @@ ENV ARROW_ACERO=ON \
     AWSSDK_SOURCE=BUNDLED \
     Azure_SOURCE=BUNDLED \
     google_cloud_cpp_storage_SOURCE=BUNDLED \
+    opentelemetry_cpp_SOURCE=BUNDLED \
     ORC_SOURCE=BUNDLED \
     PARQUET_BUILD_EXAMPLES=ON \
     PARQUET_BUILD_EXECUTABLES=ON \

ci/scripts/cpp_build.sh

@@ -225,6 +225,7 @@ else
     -DgRPC_SOURCE=${gRPC_SOURCE:-} \
     -DGTest_SOURCE=${GTest_SOURCE:-} \
     -Dlz4_SOURCE=${lz4_SOURCE:-} \
+    -Dopentelemetry-cpp_SOURCE=${opentelemetry_cpp_SOURCE:-} \
     -DORC_SOURCE=${ORC_SOURCE:-} \
     -DPARQUET_BUILD_EXAMPLES=${PARQUET_BUILD_EXAMPLES:-OFF} \
     -DPARQUET_BUILD_EXECUTABLES=${PARQUET_BUILD_EXECUTABLES:-OFF} \

cpp/CMakePresets.json

@@ -78,6 +78,7 @@
       "name": "features-minimal",
       "hidden": true,
       "cacheVariables": {
+        "ARROW_MIMALLOC": "OFF",
         "ARROW_WITH_RE2": "OFF",
         "ARROW_WITH_UTF8PROC": "OFF"
       }
@@ -91,7 +92,8 @@
         "ARROW_CSV": "ON",
         "ARROW_DATASET": "ON",
         "ARROW_FILESYSTEM": "ON",
-        "ARROW_JSON": "ON"
+        "ARROW_JSON": "ON",
+        "ARROW_MIMALLOC": "ON"
       }
     },
     {

cpp/cmake_modules/DefineOptions.cmake

@@ -362,29 +362,11 @@ takes precedence over ccache if a storage backend is configured" ON)
 
   define_option(ARROW_IPC "Build the Arrow IPC extensions" ON)
 
-  set(ARROW_JEMALLOC_DESCRIPTION "Build the Arrow jemalloc-based allocator")
-  if(WIN32
-     OR CMAKE_SYSTEM_NAME STREQUAL "FreeBSD"
-     OR CMAKE_SYSTEM_PROCESSOR MATCHES "aarch|ARM|arm"
-     OR NOT ARROW_ENABLE_THREADING)
-    # jemalloc is not supported on Windows.
-    #
-    # jemalloc is the default malloc implementation on FreeBSD and can't
-    # be built with --disable-libdl on FreeBSD. Because lazy-lock feature
-    # is required on FreeBSD. Lazy-lock feature requires libdl.
-    #
-    # jemalloc may have a problem on ARM.
-    # See also: https://github.com/apache/arrow/issues/44342
-    #
-    # jemalloc requires thread.
-    define_option(ARROW_JEMALLOC ${ARROW_JEMALLOC_DESCRIPTION} OFF)
-  else()
-    define_option(ARROW_JEMALLOC ${ARROW_JEMALLOC_DESCRIPTION} ON)
-  endif()
+  define_option(ARROW_JEMALLOC "Build the Arrow jemalloc-based allocator" OFF)
 
   define_option(ARROW_JSON "Build Arrow with JSON support (requires RapidJSON)" OFF)
 
-  define_option(ARROW_MIMALLOC "Build the Arrow mimalloc-based allocator" OFF)
+  define_option(ARROW_MIMALLOC "Build the Arrow mimalloc-based allocator" ON)
 
   define_option(ARROW_PARQUET
                 "Build the Parquet libraries"

cpp/cmake_modules/ThirdpartyToolchain.cmake

@@ -738,9 +738,8 @@ if(DEFINED ENV{ARROW_ORC_URL})
   set(ORC_SOURCE_URL "$ENV{ARROW_ORC_URL}")
 else()
   set_urls(ORC_SOURCE_URL
-           "https://www.apache.org/dyn/closer.cgi?action=download&filename=/orc/orc-${ARROW_ORC_BUILD_VERSION}/orc-${ARROW_ORC_BUILD_VERSION}.tar.gz"
-           "https://downloads.apache.org/orc/orc-${ARROW_ORC_BUILD_VERSION}/orc-${ARROW_ORC_BUILD_VERSION}.tar.gz"
-           "https://github.com/apache/orc/archive/rel/release-${ARROW_ORC_BUILD_VERSION}.tar.gz"
+           "https://www.apache.org/dyn/closer.lua/orc/orc-${ARROW_ORC_BUILD_VERSION}/orc-${ARROW_ORC_BUILD_VERSION}.tar.gz?action=download"
+           "https://dlcdn.apache.org/orc/orc-${ARROW_ORC_BUILD_VERSION}/orc-${ARROW_ORC_BUILD_VERSION}.tar.gz"
   )
 endif()
 
@@ -817,6 +816,7 @@ if(DEFINED ENV{ARROW_THRIFT_URL})
   set(THRIFT_SOURCE_URL "$ENV{ARROW_THRIFT_URL}")
 else()
   set(THRIFT_SOURCE_URL
+      "https://www.apache.org/dyn/closer.lua/thrift/${ARROW_THRIFT_BUILD_VERSION}/thrift-${ARROW_THRIFT_BUILD_VERSION}.tar.gz?action=download"
       "https://dlcdn.apache.org/thrift/${ARROW_THRIFT_BUILD_VERSION}/thrift-${ARROW_THRIFT_BUILD_VERSION}.tar.gz"
   )
 endif()
@@ -4971,7 +4971,6 @@ if(ARROW_WITH_OPENTELEMETRY)
   # cURL is required whether we build from source or use an existing installation
   # (OTel's cmake files do not call find_curl for you)
   find_curl()
-  set(opentelemetry-cpp_SOURCE "AUTO")
   resolve_dependency(opentelemetry-cpp)
   set(ARROW_OPENTELEMETRY_LIBS
       opentelemetry-cpp::trace

cpp/src/arrow/CMakeLists.txt

@@ -166,8 +166,7 @@ if(WIN32)
   list(APPEND ARROW_SYSTEM_LINK_LIBS "ws2_32")
 endif()
 
-if(NOT WIN32 AND NOT APPLE)
-  # Pass -lrt on Linux only
+if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
   list(APPEND ARROW_SYSTEM_LINK_LIBS rt)
 endif()
 
@@ -674,6 +673,7 @@ set(ARROW_TESTING_SRCS
     testing/fixed_width_test_util.cc
     testing/generator.cc
     testing/gtest_util.cc
+    testing/math.cc
     testing/process.cc
     testing/random.cc
     testing/util.cc)
@@ -726,9 +726,6 @@ set(ARROW_COMPUTE_SRCS
     compute/function.cc
     compute/function_internal.cc
     compute/kernel.cc
-    compute/key_hash_internal.cc
-    compute/key_map_internal.cc
-    compute/light_array_internal.cc
     compute/ordering.cc
     compute/registry.cc
     compute/kernels/chunked_internal.cc
@@ -747,20 +744,7 @@ set(ARROW_COMPUTE_SRCS
     compute/kernels/vector_selection.cc
     compute/kernels/vector_selection_filter_internal.cc
     compute/kernels/vector_selection_internal.cc
-    compute/kernels/vector_selection_take_internal.cc
-    compute/row/encode_internal.cc
-    compute/row/compare_internal.cc
-    compute/row/grouper.cc
-    compute/row/row_encoder_internal.cc
-    compute/row/row_internal.cc
-    compute/util.cc
-    compute/util_internal.cc)
-
-append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/key_hash_internal_avx2.cc)
-append_runtime_avx2_bmi2_src(ARROW_COMPUTE_SRCS compute/key_map_internal_avx2.cc)
-append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/row/compare_internal_avx2.cc)
-append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/row/encode_internal_avx2.cc)
-append_runtime_avx2_bmi2_src(ARROW_COMPUTE_SRCS compute/util_avx2.cc)
+    compute/kernels/vector_selection_take_internal.cc)
 
 if(ARROW_COMPUTE)
   # Include the remaining kernels
@@ -793,10 +777,25 @@ if(ARROW_COMPUTE)
        compute/kernels/vector_replace.cc
        compute/kernels/vector_run_end_encode.cc
        compute/kernels/vector_select_k.cc
-       compute/kernels/vector_sort.cc)
+       compute/kernels/vector_sort.cc
+       compute/key_hash_internal.cc
+       compute/key_map_internal.cc
+       compute/light_array_internal.cc
+       compute/row/encode_internal.cc
+       compute/row/compare_internal.cc
+       compute/row/grouper.cc
+       compute/row/row_encoder_internal.cc
+       compute/row/row_internal.cc
+       compute/util.cc
+       compute/util_internal.cc)
 
   append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/kernels/aggregate_basic_avx2.cc)
   append_runtime_avx512_src(ARROW_COMPUTE_SRCS compute/kernels/aggregate_basic_avx512.cc)
+  append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/key_hash_internal_avx2.cc)
+  append_runtime_avx2_bmi2_src(ARROW_COMPUTE_SRCS compute/key_map_internal_avx2.cc)
+  append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/row/compare_internal_avx2.cc)
+  append_runtime_avx2_src(ARROW_COMPUTE_SRCS compute/row/encode_internal_avx2.cc)
+  append_runtime_avx2_bmi2_src(ARROW_COMPUTE_SRCS compute/util_avx2.cc)
 endif()
 
 arrow_add_object_library(ARROW_COMPUTE ${ARROW_COMPUTE_SRCS})

cpp/src/arrow/compute/CMakeLists.txt

@@ -87,16 +87,18 @@ add_arrow_test(internals_test
                function_test.cc
                exec_test.cc
                kernel_test.cc
-               light_array_test.cc
-               registry_test.cc
-               key_hash_test.cc
-               row/compare_test.cc
-               row/grouper_test.cc
-               row/row_encoder_internal_test.cc
-               row/row_test.cc
-               util_internal_test.cc)
+               registry_test.cc)
 
 add_arrow_compute_test(expression_test SOURCES expression_test.cc)
+add_arrow_compute_test(row_test
+                       SOURCES
+                       key_hash_test.cc
+                       light_array_test.cc
+                       row/compare_test.cc
+                       row/grouper_test.cc
+                       row/row_encoder_internal_test.cc
+                       row/row_test.cc
+                       util_internal_test.cc)
 
 add_arrow_benchmark(function_benchmark PREFIX "arrow-compute")
 

cpp/src/arrow/compute/api_scalar.cc

@@ -732,20 +732,26 @@ void RegisterScalarOptions(FunctionRegistry* registry) {
 
 SCALAR_ARITHMETIC_UNARY(AbsoluteValue, "abs", "abs_checked")
 SCALAR_ARITHMETIC_UNARY(Acos, "acos", "acos_checked")
+SCALAR_ARITHMETIC_UNARY(Acosh, "acosh", "acosh_checked")
 SCALAR_ARITHMETIC_UNARY(Asin, "asin", "asin_checked")
+SCALAR_ARITHMETIC_UNARY(Atanh, "atanh", "atanh_checked")
 SCALAR_ARITHMETIC_UNARY(Cos, "cos", "cos_checked")
 SCALAR_ARITHMETIC_UNARY(Ln, "ln", "ln_checked")
 SCALAR_ARITHMETIC_UNARY(Log10, "log10", "log10_checked")
 SCALAR_ARITHMETIC_UNARY(Log1p, "log1p", "log1p_checked")
 SCALAR_ARITHMETIC_UNARY(Log2, "log2", "log2_checked")
-SCALAR_ARITHMETIC_UNARY(Sqrt, "sqrt", "sqrt_checked")
 SCALAR_ARITHMETIC_UNARY(Negate, "negate", "negate_checked")
 SCALAR_ARITHMETIC_UNARY(Sin, "sin", "sin_checked")
+SCALAR_ARITHMETIC_UNARY(Sqrt, "sqrt", "sqrt_checked")
 SCALAR_ARITHMETIC_UNARY(Tan, "tan", "tan_checked")
+SCALAR_EAGER_UNARY(Asinh, "asinh")
 SCALAR_EAGER_UNARY(Atan, "atan")
+SCALAR_EAGER_UNARY(Cosh, "cosh")
 SCALAR_EAGER_UNARY(Exp, "exp")
 SCALAR_EAGER_UNARY(Expm1, "expm1")
 SCALAR_EAGER_UNARY(Sign, "sign")
+SCALAR_EAGER_UNARY(Sinh, "sinh")
+SCALAR_EAGER_UNARY(Tanh, "tanh")
 
 Result<Datum> Round(const Datum& arg, RoundOptions options, ExecContext* ctx) {
   return CallFunction("round", {arg}, &options, ctx);

cpp/src/arrow/compute/api_scalar.h

@@ -784,6 +784,52 @@ Result<Datum> Atan(const Datum& arg, ExecContext* ctx = NULLPTR);
 ARROW_EXPORT
 Result<Datum> Atan2(const Datum& y, const Datum& x, ExecContext* ctx = NULLPTR);
 
+/// \brief Compute the hyperbolic sine of the array values.
+/// \param[in] arg The values to compute the hyperbolic sine for.
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise hyperbolic sine of the values
+ARROW_EXPORT
+Result<Datum> Sinh(const Datum& arg, ExecContext* ctx = NULLPTR);
+
+/// \brief Compute the hyperbolic cosine of the array values.
+/// \param[in] arg The values to compute the hyperbolic cosine for.
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise hyperbolic cosine of the values
+ARROW_EXPORT
+Result<Datum> Cosh(const Datum& arg, ExecContext* ctx = NULLPTR);
+
+/// \brief Compute the hyperbolic tangent of the array values.
+/// \param[in] arg The values to compute the hyperbolic tangent for.
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise hyperbolic tangent of the values
+ARROW_EXPORT
+Result<Datum> Tanh(const Datum& arg, ExecContext* ctx = NULLPTR);
+
+/// \brief Compute the inverse hyperbolic sine of the array values.
+/// \param[in] arg The values to compute the inverse hyperbolic sine for.
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise inverse hyperbolic sine of the values
+ARROW_EXPORT
+Result<Datum> Asinh(const Datum& arg, ExecContext* ctx = NULLPTR);
+
+/// \brief Compute the inverse hyperbolic cosine of the array values.
+/// \param[in] arg The values to compute the inverse hyperbolic cosine for.
+/// \param[in] options arithmetic options (enable/disable overflow checking), optional
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise inverse hyperbolic cosine of the values
+ARROW_EXPORT
+Result<Datum> Acosh(const Datum& arg, ArithmeticOptions options = ArithmeticOptions(),
+                    ExecContext* ctx = NULLPTR);
+
+/// \brief Compute the inverse hyperbolic tangent of the array values.
+/// \param[in] arg The values to compute the inverse hyperbolic tangent for.
+/// \param[in] options arithmetic options (enable/disable overflow checking), optional
+/// \param[in] ctx the function execution context, optional
+/// \return the elementwise inverse hyperbolic tangent of the values
+ARROW_EXPORT
+Result<Datum> Atanh(const Datum& arg, ArithmeticOptions options = ArithmeticOptions(),
+                    ExecContext* ctx = NULLPTR);
+
 /// \brief Get the natural log of a value.
 ///
 /// If argument is null the result will be null.