WIP: [R] Verify CRAN release 23.0.1

compose.yaml

@@ -441,7 +441,9 @@ services:
       ARROW_HOME: /arrow
       ARROW_DEPENDENCY_SOURCE: BUNDLED
       LIBARROW_MINIMAL: "false"
-      ARROW_MIMALLOC: "ON"
+      # explicitly enable GCS when we build libarrow so that binary libarrow
+      # users get more fully-featured builds
+      ARROW_GCS: "ON"
     volumes: *ubuntu-volumes
     command: &cpp-static-command
       /bin/bash -c "

cpp/src/arrow/compute/kernels/hash_aggregate.cc

@@ -277,8 +277,16 @@ template <typename T>
 concept CBooleanConcept = std::same_as<T, bool>;
 
 // XXX: Ideally we want to have std::floating_point<Float16> = true.
+// Some older standard library implementations (e.g., macOS 11.x libc++) have partial
+// C++20 concepts support with std::same_as but lack std::floating_point.
+#if defined(__cpp_lib_concepts) && __cpp_lib_concepts >= 202002L
 template <typename T>
 concept CFloatingPointConcept = std::floating_point<T> || std::same_as<T, util::Float16>;
+#else
+template <typename T>
+concept CFloatingPointConcept =
+    std::is_floating_point_v<T> || std::same_as<T, util::Float16>;
+#endif
 
 template <typename T>
 concept CDecimalConcept = std::same_as<T, Decimal32> || std::same_as<T, Decimal64> ||

dev/tasks/r/github.macos.cran.yml

@@ -21,10 +21,12 @@
 
 jobs:
   macos-cran:
-    name: "macOS similar to CRAN"
+    name: "macOS {{ '${{ matrix.config }}' }}"
     runs-on: macOS-latest
     strategy:
       fail-fast: false
+      matrix:
+        config: ["cran-m1", "cran-release"]
 
     steps:
       {{ macros.github_checkout_arrow()|indent }}
@@ -58,7 +60,35 @@ jobs:
           extra-packages: |
             any::rcmdcheck
             any::sys
-      - name: Install
+      - name: Install MacOSX 11.3 SDK
+        if: matrix.config == 'cran-release'
+        env:
+          SDK_TOKEN: {{ '${{ secrets.JONKEANE_MACOS_11_SDK_DOWNLOAD_TOKEN }}' }}
+        run: |
+          # Download, Confirm integrity, expand. This will fail if the hash does not match.
+          curl -fsSL -H "Authorization: Bearer $SDK_TOKEN" \
+            -H "Accept: application/vnd.github+json" \
+            https://api.github.com/repos/jonkeane/crossbow_11_sdk/tarball/v0.0.1 \
+            -o /tmp/MacOSX11.3.sdk.tar.gz
+          echo "493570e56d6c6af26128e9096de738822589cc3cdb1b29aa5854f3f4c99756ac  /tmp/MacOSX11.3.sdk.tar.gz" | shasum -a 256 -c -
+          sudo tar -xzf /tmp/MacOSX11.3.sdk.tar.gz -C /Library/Developer/CommandLineTools/SDKs/
+          # Move SDK from extracted folder (GitHub archives as {owner}-{repo}-{sha}/)
+          sudo mv /Library/Developer/CommandLineTools/SDKs/jonkeane-crossbow_11_sdk-*/MacOSX11.3.sdk \
+            /Library/Developer/CommandLineTools/SDKs/MacOSX11.3.sdk
+          sudo rm -rf /Library/Developer/CommandLineTools/SDKs/jonkeane-crossbow_11_sdk-*
+          ls -la /Library/Developer/CommandLineTools/SDKs/
+      - name: Install (cran-release)
+        if: matrix.config == 'cran-release'
+        env:
+          _R_CHECK_CRAN_INCOMING_: false
+          SDKROOT: '/Library/Developer/CommandLineTools/SDKs/MacOSX11.3.sdk'
+          NOT_CRAN: false
+        run: |
+          sccache --start-server || echo 'sccache not found'
+          cd arrow/r
+          R CMD INSTALL . --install-tests
+      - name: Install (cran-m1)
+        if: matrix.config == 'cran-m1'
         env:
           _R_CHECK_CRAN_INCOMING_: false
           CXX: "clang++ -mmacos-version-min=14.6"
@@ -77,6 +107,6 @@ jobs:
       - name: Save the test output
         uses: actions/upload-artifact@v4
         with:
-          name: test-output
+          name: test-output-{{ '${{ matrix.config }}' }}
           path: arrow-tests/testthat.Rout*
         if: always()

dev/tasks/r/github.packages.yml

@@ -81,7 +81,6 @@ jobs:
         env:
         {{ macros.github_set_sccache_envvars()|indent(8) }}
           MACOSX_DEPLOYMENT_TARGET: "11.6"
-          ARROW_S3: ON
           ARROW_GCS: ON
           ARROW_DEPENDENCY_SOURCE: BUNDLED
           CMAKE_GENERATOR: Ninja

r/NEWS.md

@@ -18,6 +18,29 @@
 -->
 
 # arrow 23.0.1
+
+## Minor improvements and fixes
+
+- Fix C++20 compatibility issue on macOS (#49221).
+- Turn off GCS support by default on macOS; see `vignette("install", package = "arrow")` for details on enabling it (#49068, #48995).
+
+# arrow 23.0.0
+
+## New features
+
+- `nchar()` now supports `keepNA = FALSE` (@HyukjinKwon, #48665).
+- `stringr::str_ilike()` binding for case-insensitive pattern matching (#48262).
+
+## Minor improvements and fixes
+
+- Fix slow performance reading files with large number of columns (#48104).
+- Fix segfault when calling `concat_tables()` on a `RecordBatch` (#47885).
+- Writing partitioned datasets on S3 no longer requires `ListBucket` permissions (@HaochengLIU, #47599).
+
+## Installation
+
+- As of version 23.0.0, `arrow` requires C++20 to build from source. This means that you may need a newer compiler than the default on some older systems. See `vignette("install", package = "arrow")` for guidance.
+
 # arrow 22.0.0.1
 
 ## Minor improvements and fixes

r/README.md

@@ -1,13 +1,5 @@
 # arrow <img src="https://arrow.apache.org/img/arrow-logo_hex_black-txt_white-bg.png" align="right" alt="" width="120" />
 
-<!-- badges: start -->
-
-[![cran](https://www.r-pkg.org/badges/version-last-release/arrow)](https://cran.r-project.org/package=arrow)
-[![CI](https://github.com/apache/arrow/actions/workflows/r.yml/badge.svg?branch=main&event=push)](https://github.com/apache/arrow/actions/workflows/r.yml?query=branch%3Amain+event%3Apush)
-[![R-universe status badge](https://apache.r-universe.dev/badges/arrow)](https://apache.r-universe.dev)
-[![conda-forge](https://img.shields.io/conda/vn/conda-forge/r-arrow.svg)](https://anaconda.org/conda-forge/r-arrow)
-
-<!-- badges: end -->
 
 ## Overview
 
@@ -64,7 +56,7 @@ It allows users to read and write data in a variety of formats:
 
 It provides access to remote filesystems and servers:
 
-- Read and write files in Amazon S3 and Google Cloud Storage buckets
+- Read and write files in Amazon S3 and Google Cloud Storage buckets (note: CRAN builds include S3 support but not GCS which require an alternative installation method; see the [cloud storage article](https://arrow.apache.org/docs/r/articles/fs.html) for details)
 - Connect to Arrow Flight servers to transport large datasets over networks
 
 Additional features include:

r/inst/NOTICE.txt

@@ -1,5 +1,5 @@
 Apache Arrow
-Copyright 2016-2024 The Apache Software Foundation
+Copyright 2016-2026 The Apache Software Foundation
 
 This product includes software developed at
 The Apache Software Foundation (http://www.apache.org/).
@@ -17,9 +17,6 @@ https://github.com/libdynd
 This product includes software from the LLVM project
  * distributed under the University of Illinois Open Source
 
-This product includes software from the google-lint project
- * Copyright (c) 2009 Google Inc. All rights reserved.
-
 This product includes software from the mman-win32 project
  * Copyright https://code.google.com/p/mman-win32/
  * Licensed under the MIT License;

r/tools/checksums/r-libarrow-darwin-arm64-23.0.1.zip.sha512

@@ -0,0 +1 @@
+3d1156bac8ed2939f3541cbfdb6da0d2a33aa1cc9d8c54f4046532fe5bb5d436ff67d2ab8f47ca6efd2169efad9de6f9451745913eca952239265c11c1e046b4  r-libarrow-darwin-arm64-23.0.1.zip

r/tools/checksums/r-libarrow-darwin-x86_64-23.0.1.zip.sha512

@@ -0,0 +1 @@
+d4daf5ea72c0abcee74b8726c7a96450025f7a6662e4ba302e74c00c0bf1d547ce7cd97a2708f3a577396cb3127533bbbd986dfaa572696dd360ba031e4602f9  r-libarrow-darwin-x86_64-23.0.1.zip

r/tools/checksums/r-libarrow-linux-x86_64-23.0.1.zip.sha512

@@ -0,0 +1 @@
+3b39b288d9e280d2fa4dce1bd36d46f7981004448bcb7c4d16002bb25cecc2a31bf334383159364687a66379468c8bc81982a6e087593fd3d2daf0651d7657e8  r-libarrow-linux-x86_64-23.0.1.zip

r/tools/checksums/r-libarrow-windows-x86_64-23.0.1.zip.sha512

@@ -0,0 +1 @@
+4af0fd6f280f4271131ce700a6edb52651cb5dbcfe740ecbc47fa851bfdcc779c834a049305b33521f6144952680141118a7f387b941c2c4590c46ce86909cb1  r-libarrow-windows-x86_64-23.0.1.zip

r/tools/nixlibs.R

@@ -597,7 +597,7 @@ build_libarrow <- function(src_dir, dst_dir) {
     env_var_list <- c(
       env_var_list,
       ARROW_S3 = Sys.getenv("ARROW_S3", "ON"),
-      ARROW_GCS = Sys.getenv("ARROW_GCS", "ON"),
+      # ARROW_GCS = Sys.getenv("ARROW_GCS", "ON"),
       ARROW_WITH_ZSTD = Sys.getenv("ARROW_WITH_ZSTD", "ON")
     )
   }