Merge branch 'main' into getdummies-default-dtype

Author: kianelbo

.circleci/config.yml

@@ -4,7 +4,7 @@ jobs:
   test-arm:
     machine:
       image: ubuntu-2004:202101-01
-    resource_class: arm.medium
+    resource_class: arm.large
     environment:
       ENV_FILE: ci/deps/circle-38-arm64.yaml
       PYTEST_WORKERS: auto

.circleci/setup_env.sh

@@ -1,47 +1,16 @@
 #!/bin/bash -e
 
-# edit the locale file if needed
-if [[ "$(uname)" == "Linux" && -n "$LC_ALL" ]]; then
-    echo "Adding locale to the first line of pandas/__init__.py"
-    rm -f pandas/__init__.pyc
-    SEDC="3iimport locale\nlocale.setlocale(locale.LC_ALL, '$LC_ALL')\n"
-    sed -i "$SEDC" pandas/__init__.py
-
-    echo "[head -4 pandas/__init__.py]"
-    head -4 pandas/__init__.py
-    echo
-fi
+echo "Install Mambaforge"
+MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/4.14.0-0/Mambaforge-4.14.0-0-Linux-aarch64.sh"
+echo "Downloading $MAMBA_URL"
+wget -q $MAMBA_URL -O minimamba.sh
+chmod +x minimamba.sh
 
+MAMBA_DIR="$HOME/miniconda3"
+rm -rf $MAMBA_DIR
+./minimamba.sh -b -p $MAMBA_DIR
 
-MINICONDA_DIR=/usr/local/miniconda
-if [ -e $MINICONDA_DIR ] && [ "$BITS32" != yes ]; then
-    echo "Found Miniconda installation at $MINICONDA_DIR"
-else
-    echo "Install Miniconda"
-    DEFAULT_CONDA_URL="https://repo.continuum.io/miniconda/Miniconda3-latest"
-    if [[ "$(uname -m)" == 'aarch64' ]]; then
-        CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.10.1-4/Miniforge3-4.10.1-4-Linux-aarch64.sh"
-    elif [[ "$(uname)" == 'Linux' ]]; then
-        if [[ "$BITS32" == "yes" ]]; then
-            CONDA_URL="$DEFAULT_CONDA_URL-Linux-x86.sh"
-        else
-            CONDA_URL="$DEFAULT_CONDA_URL-Linux-x86_64.sh"
-        fi
-    elif [[ "$(uname)" == 'Darwin' ]]; then
-        CONDA_URL="$DEFAULT_CONDA_URL-MacOSX-x86_64.sh"
-    else
-      echo "OS $(uname) not supported"
-      exit 1
-    fi
-    echo "Downloading $CONDA_URL"
-    wget -q $CONDA_URL -O miniconda.sh
-    chmod +x miniconda.sh
-
-    MINICONDA_DIR="$HOME/miniconda3"
-    rm -rf $MINICONDA_DIR
-    ./miniconda.sh -b -p $MINICONDA_DIR
-fi
-export PATH=$MINICONDA_DIR/bin:$PATH
+export PATH=$MAMBA_DIR/bin:$PATH
 
 echo
 echo "which conda"
@@ -51,7 +20,7 @@ echo
 echo "update conda"
 conda config --set ssl_verify false
 conda config --set quiet true --set always_yes true --set changeps1 false
-conda install -y -c conda-forge -n base 'mamba>=0.21.2' pip setuptools
+mamba install -y -c conda-forge -n base pip setuptools
 
 echo "conda info -a"
 conda info -a
@@ -70,11 +39,6 @@ time mamba env update -n pandas-dev --file="${ENV_FILE}"
 echo "conda list -n pandas-dev"
 conda list -n pandas-dev
 
-if [[ "$BITS32" == "yes" ]]; then
-    # activate 32-bit compiler
-    export CONDA_BUILD=1
-fi
-
 echo "activate pandas-dev"
 source activate pandas-dev
 
@@ -90,15 +54,9 @@ if pip list | grep -q ^pandas; then
     pip uninstall -y pandas || true
 fi
 
-if [ "$(conda list -f qt --json)" != [] ]; then
-    echo
-    echo "remove qt"
-    echo "causes problems with the clipboard, we use xsel for that"
-    conda remove qt -y --force || true
-fi
-
 echo "Build extensions"
-python setup.py build_ext -q -j3
+# GH 47305: Parallel build can causes flaky ImportError from pandas/_libs/tslibs
+python setup.py build_ext -q -j1
 
 echo "Install pandas"
 python -m pip install --no-build-isolation --no-use-pep517 -e .

.github/workflows/32-bit-linux.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
     paths-ignore:
       - "doc/**"

.github/workflows/code-checks.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
 
 env:
@@ -151,6 +153,9 @@ jobs:
       - name: Build image
         run: docker build --pull --no-cache --tag pandas-dev-env .
 
+      - name: Show environment
+        run: docker run -w /home/pandas pandas-dev-env mamba run -n pandas-dev python -c "import pandas as pd; print(pd.show_versions())"
+
   requirements-dev-text-installable:
     name: Test install requirements-dev.txt
     runs-on: ubuntu-latest

.github/workflows/docbuild-and-upload.yml

@@ -4,10 +4,14 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
+    tags:
+      - '*'
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
 
 env:
@@ -49,6 +53,9 @@ jobs:
     - name: Build documentation
       run: doc/make.py --warnings-are-errors
 
+    - name: Build documentation zip
+      run: doc/make.py zip_html
+
     - name: Build the interactive terminal
       run: |
         cd web/interactive_terminal
@@ -60,7 +67,7 @@ jobs:
         echo "${{ secrets.server_ssh_key }}" > ~/.ssh/id_rsa
         chmod 600 ~/.ssh/id_rsa
         echo "${{ secrets.server_ip }} ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBE1Kkopomm7FHG5enATf7SgnpICZ4W2bw+Ho+afqin+w7sMcrsa0je7sbztFAV8YchDkiBKnWTG4cRT+KZgZCaY=" > ~/.ssh/known_hosts
-      if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+      if: github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/'))
 
     - name: Copy cheatsheets into site directory
       run: cp doc/cheatsheet/Pandas_Cheat_Sheet* web/build/
@@ -73,6 +80,10 @@ jobs:
       run: rsync -az --delete doc/build/html/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas/pandas-docs/dev
       if: github.event_name == 'push' && github.ref == 'refs/heads/main'
 
+    - name: Upload prod docs
+      run: rsync -az --delete doc/build/html/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas/pandas-docs/version/${GITHUB_REF_NAME:1}
+      if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+
     - name: Move docs into site directory
       run: mv doc/build/html web/build/docs
 

.github/workflows/macos-windows.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
     paths-ignore:
       - "doc/**"
@@ -26,7 +28,7 @@ jobs:
     defaults:
       run:
         shell: bash -el {0}
-    timeout-minutes: 120
+    timeout-minutes: 180
     strategy:
       matrix:
         os: [macos-latest, windows-latest]

.github/workflows/python-dev.yml

@@ -24,10 +24,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
     paths-ignore:
       - "doc/**"
@@ -78,9 +80,10 @@ jobs:
         python -m pip install python-dateutil pytz cython hypothesis==6.52.1 pytest>=6.2.5 pytest-xdist pytest-cov pytest-asyncio>=0.17
         python -m pip list
 
+    # GH 47305: Parallel build can cause flaky ImportError from pandas/_libs/tslibs
     - name: Build Pandas
       run: |
-        python setup.py build_ext -q -j2
+        python setup.py build_ext -q -j1
         python -m pip install -e . --no-build-isolation --no-use-pep517
 
     - name: Build Version

.github/workflows/scorecards.yml

@@ -0,0 +1,54 @@
+name: Scorecards supply-chain security
+on:
+  # Only the default branch is supported.
+  branch_protection_rule:
+  schedule:
+    - cron: '27 19 * * 4'
+  push:
+    branches: [ "main" ]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecards analysis
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Used to receive a badge.
+      id-token: write
+
+    if: github.repository == 'pandas-dev/pandas'  # don't run on forks
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/[email protected]
+        with:
+          results_file: results.sarif
+          results_format: sarif
+
+          # Publish the results for public repositories to enable scorecard badges. For more details, see
+          # https://github.com/ossf/scorecard-action#publishing-results.
+          publish_results: true
+
+      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
+      # format to the repository Actions tab.
+      - name: "Upload artifact"
+        uses: actions/upload-artifact@v3
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      # Upload the results to GitHub's code scanning dashboard.
+      - name: "Upload to code-scanning"
+        uses: github/codeql-action/upload-sarif@v1
+        with:
+          sarif_file: results.sarif

.github/workflows/sdist.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
     types: [labeled, opened, synchronize, reopened]
     paths-ignore:

.github/workflows/ubuntu.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
   pull_request:
     branches:
       - main
+      - 1.5.x
       - 1.4.x
     paths-ignore:
       - "doc/**"
@@ -24,7 +26,7 @@ jobs:
     defaults:
       run:
         shell: bash -el {0}
-    timeout-minutes: 120
+    timeout-minutes: 180
     strategy:
       matrix:
         env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
@@ -40,18 +42,26 @@ jobs:
           - name: "Minimum Versions"
             env_file: actions-38-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
-          - name: "Locale: it_IT.utf8"
+          - name: "Locale: it_IT"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
             extra_apt: "language-pack-it"
+            # Use the utf8 version as the default, it has no bad side-effect.
             lang: "it_IT.utf8"
             lc_all: "it_IT.utf8"
-          - name: "Locale: zh_CN.utf8"
+            # 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"
+          - name: "Locale: zh_CN"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
             extra_apt: "language-pack-zh-hans"
+            # Use the utf8 version as the default, it has no bad side-effect.
             lang: "zh_CN.utf8"
             lc_all: "zh_CN.utf8"
+            # 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"
           - name: "Copy-on-Write"
             env_file: actions-310.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -146,6 +156,12 @@ jobs:
       # xsel for clipboard tests
       run: sudo apt-get update && sudo apt-get install -y xsel ${{ env.EXTRA_APT }}
 
+    - name: Generate extra locales
+      # These extra locales will be available for locale.setlocale() calls in tests
+      run: |
+        sudo locale-gen ${{ matrix.extra_loc }}
+      if: ${{ matrix.extra_loc }}
+
     - name: Set up Conda
       uses: ./.github/actions/setup-conda
       with: