modernize packaging and add release automation

.github/workflows/check-build.yml

@@ -54,4 +54,6 @@ jobs:
         shell: bash
         run: ./test.sh
       - name: Build
-        run: python setup.py sdist bdist_wheel
+        run: |
+          pip install build
+          python -m build .

.github/workflows/python-publish.yml

@@ -0,0 +1,38 @@
+# This workflows will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  - push
+
+jobs:
+  build-n-publish:
+    name: Build and publish Python distributions to PyPI
+    if: ${{ github.repository_owner == 'mjpost' }}
+
+    runs-on: ubuntu-latest
+    environment: release
+
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
+
+    steps:
+    - uses: actions/checkout@v4
+      # with:
+      #   fetch-depth: 0
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[build]
+    - name: Build sdist and wheel
+      run: |
+        python -m build
+    - name: Publish distribution to PyPI
+      if: startsWith(github.ref, 'refs/tags')
+      uses: pypa/gh-action-pypi-publish@release/v1

.gitignore

@@ -8,3 +8,4 @@ sacrebleu.egg-info
 *~
 .DS_Store
 .idea/
+sacrebleu/version.py

Makefile

@@ -5,7 +5,7 @@ test:
 	bash test.sh
 
 pip:
-	python3 setup.py sdist bdist_wheel
+	python3 -m build .
 
 publish: pip
 	twine upload dist/*

pyproject.toml

@@ -0,0 +1,80 @@
+[build-system]
+requires = ["setuptools>=64", "setuptools_scm>=8"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sacrebleu"
+dynamic = ["version"]
+authors = [{ name = "Matt Post", email = "post@cs.jhu.edu" }]
+maintainers = [{ name = "Matt Post", email = "post@cs.jhu.edu" }]
+description = "Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores"
+readme = "README.md"
+license = { file = "LICENSE.txt" }
+classifiers = [
+    # How mature is this project? Common values are
+    #   3 - Alpha
+    #   4 - Beta
+    #   5 - Production/Stable
+    "Development Status :: 5 - Production/Stable",
+
+    # Indicate who your project is intended for
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Text Processing",
+
+    # Pick your license as you wish (should match "license" above)
+    "License :: OSI Approved :: Apache Software License",
+
+    # List operating systems
+    "Operating System :: POSIX",
+    "Operating System :: MacOS :: MacOS X",
+    "Operating System :: Microsoft :: Windows",
+
+    # Specify the Python versions you support here. In particular, ensure
+    # that you indicate whether you support Python 2, Python 3 or both.
+    "Programming Language :: Python :: 3 :: Only",
+
+    # Indicate that type hints are provided
+    "Typing :: Typed",
+]
+
+requires-python = ">=3.8"
+
+keywords = [
+    "machine translation",
+    "evaluation",
+    "NLP",
+    "natural language processing",
+    "computational linguistics",
+]
+
+dependencies = [
+    "portalocker",
+    "regex",
+    "tabulate>=0.8.9",
+    "numpy>=1.17",
+    "colorama",
+    "lxml",
+]
+
+[project.optional-dependencies]
+dev = ["wheel", "pytest", "mypy", "types-tabulate", "lxml-stubs", "setuptools"]
+ja = ["mecab-python3>=1.0.9,<2.0.0", "ipadic>=1.0,<2.0"]
+ko = ["mecab-ko>=1.0.0,<=1.0.1", "mecab-ko-dic>=1.0,<2.0"]
+
+[project.scripts]
+sacrebleu = "sacrebleu.sacrebleu:main"
+
+[project.urls]
+Repository = "https://github.com/mjpost/sacrebleu"
+
+[tool.setuptools.packages.find]
+include = ["sacrebleu*"]
+
+[tool.setuptools.package-data]
+sacrebleu = ["py.typed"]
+
+[tool.setuptools_scm]
+version_file = "sacrebleu/version.py"

sacrebleu/__init__.py

@@ -14,30 +14,53 @@
 # express or implied. See the License for the specific language governing
 # permissions and limitations under the License.
 
-__version__ = '2.4.1'
-__description__ = 'Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores'
+__description__ = "Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores"
 
 
-from .utils import smart_open, SACREBLEU_DIR, download_test_set
-from .utils import get_source_file, get_reference_files
-from .utils import get_available_testsets, get_langpairs_for_testset
-from .metrics.helpers import extract_word_ngrams, extract_char_ngrams
+# Backward compatibility functions for old style API access (<= 1.4.10)
+from .compat import (
+    corpus_bleu,
+    corpus_chrf,
+    corpus_ter,
+    raw_corpus_bleu,
+    sentence_bleu,
+    sentence_chrf,
+    sentence_ter,
+)
 from .dataset import DATASETS
 from .metrics import BLEU, CHRF, TER
-
-# Backward compatibility functions for old style API access (<= 1.4.10)
-from .compat import corpus_bleu, raw_corpus_bleu, sentence_bleu
-from .compat import corpus_chrf, sentence_chrf
-from .compat import corpus_ter, sentence_ter
+from .metrics.helpers import extract_char_ngrams, extract_word_ngrams
+from .utils import (
+    SACREBLEU_DIR,
+    download_test_set,
+    get_available_testsets,
+    get_langpairs_for_testset,
+    get_reference_files,
+    get_source_file,
+    smart_open,
+)
+from .version import __version__
 
 __all__ = [
-    'smart_open', 'SACREBLEU_DIR', 'download_test_set',
-    'get_source_file', 'get_reference_files',
-    'get_available_testsets', 'get_langpairs_for_testset',
-    'extract_word_ngrams', 'extract_char_ngrams',
-    'DATASETS',
-    'BLEU', 'CHRF', 'TER',
-    'corpus_bleu', 'raw_corpus_bleu', 'sentence_bleu',
-    'corpus_chrf', 'sentence_chrf',
-    'corpus_ter', 'sentence_ter'
+    "smart_open",
+    "SACREBLEU_DIR",
+    "download_test_set",
+    "get_source_file",
+    "get_reference_files",
+    "get_available_testsets",
+    "get_langpairs_for_testset",
+    "extract_word_ngrams",
+    "extract_char_ngrams",
+    "DATASETS",
+    "BLEU",
+    "CHRF",
+    "TER",
+    "corpus_bleu",
+    "raw_corpus_bleu",
+    "sentence_bleu",
+    "corpus_chrf",
+    "sentence_chrf",
+    "corpus_ter",
+    "sentence_ter",
+    "__version__",
 ]