Merge remote-tracking branch 'upstream/main' into bug60343v1

Author: jorisvandenbossche

.circleci/config.yml

@@ -61,7 +61,6 @@ pandas/_version.py export-subst
 *.pxi export-ignore
 
 # Ignoring stuff from the top level
-.circleci export-ignore
 .github export-ignore
 asv_bench export-ignore
 ci export-ignore

.gitattributes

@@ -22,10 +22,11 @@ defaults:
 
 jobs:
   ubuntu:
-    runs-on: ubuntu-22.04
+    runs-on: ${{ matrix.platform }}
     timeout-minutes: 90
     strategy:
       matrix:
+        platform: [ubuntu-22.04, ubuntu-24.04-arm]
         env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
@@ -35,9 +36,11 @@ jobs:
             env_file: actions-311-downstream_compat.yaml
             pattern: "not slow and not network and not single_cpu"
             pytest_target: "pandas/tests/test_downstream.py"
+            platform: ubuntu-22.04
           - name: "Minimum Versions"
             env_file: actions-310-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
+            platform: ubuntu-22.04
           - name: "Locale: it_IT"
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -48,6 +51,7 @@ jobs:
             # Also install it_IT (its encoding is ISO8859-1) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "it_IT"
+            platform: ubuntu-22.04
           - name: "Locale: zh_CN"
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -58,25 +62,32 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
+            platform: ubuntu-22.04
           - name: "Future infer strings"
             env_file: actions-312.yaml
             pandas_future_infer_string: "1"
+            platform: ubuntu-22.04
           - name: "Future infer strings (without pyarrow)"
             env_file: actions-311.yaml
             pandas_future_infer_string: "1"
+            platform: ubuntu-22.04
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
+            platform: ubuntu-22.04
           - name: "Numpy Dev"
             env_file: actions-311-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "-W error::DeprecationWarning -W error::FutureWarning"
+            platform: ubuntu-22.04
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"
+            pandas_future_infer_string: "1"
+            platform: ubuntu-22.04
       fail-fast: false
-    name: ${{ matrix.name || format('ubuntu-latest {0}', matrix.env_file) }}
+    name: ${{ matrix.name || format('{0} {1}', matrix.platform, matrix.env_file) }}
     env:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
@@ -91,7 +102,7 @@ jobs:
       REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}-${{ matrix.platform }}
       cancel-in-progress: true
 
     services:
@@ -419,20 +430,20 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Set up Python for Pyodide
+      - name: Set up Python for pyodide-build
         id: setup-python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.11.3'
+          python-version: '3.12'
 
       - name: Set up Emscripten toolchain
         uses: mymindstorm/setup-emsdk@v14
         with:
-          version: '3.1.46'
+          version: '3.1.58'
           actions-cache-folder: emsdk-cache
 
       - name: Install pyodide-build
-        run: pip install "pyodide-build==0.25.1"
+        run: pip install "pyodide-build>=0.29.2"
 
       - name: Build pandas for Pyodide
         run: |
@@ -441,10 +452,13 @@ jobs:
       - name: Set up Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '18'
+          node-version: '20'
 
       - name: Set up Pyodide virtual environment
+        env:
+          pyodide-version: '0.27.1'
         run: |
+          pyodide xbuildenv install ${{ env.pyodide-version }}
           pyodide venv .venv-pyodide
           source .venv-pyodide/bin/activate
           pip install dist/*.whl

.github/workflows/unit-tests.yml

@@ -94,7 +94,8 @@ jobs:
         buildplat:
         - [ubuntu-22.04, manylinux_x86_64]
         - [ubuntu-22.04, musllinux_x86_64]
-        - [macos-12, macosx_x86_64]
+        - [ubuntu-24.04-arm, manylinux_aarch64]
+        - [macos-13, macosx_x86_64]
         # Note: M1 images on Github Actions start from macOS 14
         - [macos-14, macosx_arm64]
         - [windows-2022, win_amd64]

.github/workflows/wheels.yml

@@ -137,3 +137,7 @@ doc/source/savefig/
 # Interactive terminal generated files #
 ########################################
 .jupyterlite.doit.db
+
+# Pyodide/WASM related files #
+##############################
+/.pyodide-xbuildenv-*

.gitignore

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.1
+    rev: v0.8.6
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.13'
+    rev: 'v2.14'
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -74,7 +74,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.19.0
+    rev: v3.19.1
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -95,12 +95,17 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.4
+    rev: v19.1.6
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
+-   repo: https://github.com/trim21/pre-commit-mirror-meson
+    rev: v1.6.1
+    hooks:
+    - id: meson-fmt
+      args: ['--inplace']
 -   repo: local
     hooks:
     -   id: pyright

.pre-commit-config.yaml

@@ -594,7 +594,7 @@ def setup(self):
         self.StringIO_input = StringIO(data)
 
     def time_read_csv_index_col(self):
-        read_csv(self.StringIO_input, index_col="a")
+        read_csv(self.data(self.StringIO_input), index_col="a")
 
 
 class ReadCSVDatePyarrowEngine(StringIORewind):
@@ -605,7 +605,7 @@ def setup(self):
 
     def time_read_csv_index_col(self):
         read_csv(
-            self.StringIO_input,
+            self.data(self.StringIO_input),
             parse_dates=["a"],
             engine="pyarrow",
             dtype_backend="pyarrow",