unittest.yml

# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
# SPDX-License-Identifier: Apache-2.0

name: Unit test

on:
  push:
    paths:
      - ".github/workflows/unittest.yml"
      - "bin/**"
      - "build_tools/**"
      - "pythainlp/**"
      - "tests/**"
      - "Makefile"
      - "MANIFEST.in"
      - "pyproject.toml"
  pull_request:
    branches:
      - dev
    paths:
      - ".github/workflows/unittest.yml"
      - "bin/**"
      - "build_tools/**"
      - "pythainlp/**"
      - "tests/**"
      - "Makefile"
      - "MANIFEST.in"
      - "pyproject.toml"

# Avoid duplicate runs for the same source branch and repository.
# For pull_request events, uses the source repo name from
# github.event.pull_request.head.repo.full_name; otherwise uses github.repository.
# For push events, uses the branch name from github.ref_name.
# For pull_request events, uses the source branch name from github.head_ref.
# This ensures events for the same repo and branch share the same group,
# and avoids cross-fork collisions when branch names are reused.
concurrency:
  group: >-
    ${{ github.workflow }}-${{
      github.event.pull_request.head.repo.full_name || github.repository
    }}-${{ github.head_ref || github.ref_name }}
  cancel-in-progress: true

jobs:
  unittest:
    strategy:
      fail-fast: false
      matrix:
        # To optimize CI/CD resource utilization and manage dependency overhead,
        # tests are categorized into four tiers based on their resource requirements
        # and dependency complexity: "core", "compact", "extra", and "noauto".
        # Test cases in "noauto" will not be included here.
        # See details of test matrix in:
        # https://github.com/PyThaiNLP/pythainlp/blob/dev/tests/README.md
        os: ["ubuntu-latest", "windows-latest", "macos-latest"]
        python-version: ["3.14", "3.9"] # Latest and earliest
        include:
          # Test the rest of Python versions only on Ubuntu
          - os: "ubuntu-latest"
            python-version: "3.13"
          - os: "ubuntu-latest"
            python-version: "3.12"
          - os: "ubuntu-latest"
            python-version: "3.11"
          - os: "ubuntu-latest"
            python-version: "3.10"

    runs-on: ${{ matrix.os }}
    env:
      PYICU_WIN_VER: 2.15 # 2.15 is the last version that supports Python 3.9
      INSTALL_FULL_DEPS: false
      PYTHON_VERSION_LATEST: "3.14"
      PYTHON_VERSION_LATEST_2: "3.13" # Second-latest supported version
      PYTHON_VERSION_EARLIEST: "3.9"

    steps:
      - name: Checkout
        uses: actions/checkout@v6

      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v6
        with:
          python-version: ${{ matrix.python-version }}
          cache: "pip"

      - name: Install build tools
        run: |
          pip install --upgrade "pip<24.1" "setuptools>=69.0.0,<=73.0.1"
          pip install coverage coveralls
        # pip<24.1 because https://github.com/omry/omegaconf/pull/1195
        # setuptools>=65.0.2 because https://github.com/pypa/setuptools/commit/d03da04e024ad4289342077eef6de40013630a44#diff-9ea6e1e3dde6d4a7e08c7c88eceed69ca745d0d2c779f8f85219b22266efff7fR1
        # setuptools<=73.0.1 because https://github.com/pypa/setuptools/issues/4620

      - name: Install ICU (macOS)
        if: startsWith(matrix.os, 'macos-')
        run: |
          brew install icu4c
          PKG_CONFIG_PATH=$(brew --prefix)/opt/icu4c/lib/pkgconfig
          echo "PKG_CONFIG_PATH=${PKG_CONFIG_PATH}" >> "${GITHUB_ENV}"
          ICU_VER=$(pkg-config --modversion icu-i18n)
          echo "ICU_VER=${ICU_VER}"
          echo "ICU_VER=${ICU_VER}" >> "${GITHUB_ENV}"

      - name: Install PyICU (Windows)
        if: startsWith(matrix.os, 'windows-') && (matrix.python-version == env.PYTHON_VERSION_LATEST_2 || matrix.python-version == env.PYTHON_VERSION_EARLIEST)
        shell: powershell
        # Get the wheel URL from https://github.com/cgohlke/pyicu-build/releases
        run: |
          $PYTHON_WIN_VER = "${{ matrix.python-version }}"
          $CP_VER = "cp" + $PYTHON_WIN_VER.Replace(".", "")
          $WHEEL_URL = "https://github.com/cgohlke/pyicu-build/releases/download/v${{ env.PYICU_WIN_VER }}/PyICU-${{ env.PYICU_WIN_VER }}-${CP_VER}-${CP_VER}-win_amd64.whl"
          pip install "$WHEEL_URL"

      - name: Install PyThaiNLP + full testing dependencies
        if: env.INSTALL_FULL_DEPS == 'true'
        env:
          SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL: True
        run: pip install ".[full]"

      - name: Test (core)
        if: ${{ (matrix.os == 'ubuntu-latest' && matrix.python-version != env.PYTHON_VERSION_LATEST_2 && matrix.python-version != env.PYTHON_VERSION_EARLIEST) || (matrix.os != 'ubuntu-latest' && matrix.python-version == env.PYTHON_VERSION_LATEST) }}
        env:
          PYTHONIOENCODING: utf-8
        run: |
          pip install .
          python -m unittest tests.core
        # Use 'unittest <test_module>' instead of 'unittest discover' to avoid
        # loading tests with dependencies more than expected.
        # Test cases loaded is defined in __init__.py in the tests directory.
        # See also tests/README.md

      - name: Test (compact + core)
        if: ${{ ((matrix.python-version == env.PYTHON_VERSION_LATEST_2) || (matrix.python-version == env.PYTHON_VERSION_EARLIEST)) && !(matrix.os == 'ubuntu-latest' && matrix.python-version == env.PYTHON_VERSION_LATEST_2) }}
        env:
          PYTHONIOENCODING: utf-8
        run: |
          pip install ".[compact]"
          python -m unittest tests.core tests.compact

      - name: Test (extra + compact + core)
        if: matrix.os == 'ubuntu-latest' && matrix.python-version == env.PYTHON_VERSION_LATEST_2
        env:
          PYTHONIOENCODING: utf-8
        run: |
          pip install ".[compact,extra]"
          coverage run -m unittest tests.core tests.compact tests.extra

      # Only submit a report from the "extra" run, to get maximum coverage
      - name: Coverage report
        if: matrix.os == 'ubuntu-latest' && matrix.python-version == env.PYTHON_VERSION_LATEST_2
        env:
          COVERALLS_SERVICE_NAME: github
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PYTHONIOENCODING: utf-8
        run: coveralls