【OCR Issue No.12】Modify the setuptools configuration from SETUP.py into PYPROJECT.toml (#12013)

Modify the setuptools configuration from SETUP.py into PYPROJECT.toml

.github/workflows/python-publish.yml

@@ -33,7 +33,7 @@ jobs:
         pip install setuptools
         pip install wheel
     - name: Build package
-      run: python setup.py bdist_wheel
+      run: python -m build
     - name: Publish package
       uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
       with:

VERSION_NUMBER

@@ -0,0 +1 @@
+2.8.0

__init__.py

@@ -12,8 +12,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from .paddleocr import *
+import importlib.metadata as importlib_metadata
 
-__version__ = paddleocr.VERSION
+try:
+    __version__ = importlib_metadata.version(__package__ or __name__)
+except importlib_metadata.PackageNotFoundError:
+    __version__ = "0.0.0"
 __all__ = [
     "PaddleOCR",
     "PPStructure",

paddleocr.py

@@ -78,7 +78,6 @@ __all__ = [
 ]
 
 SUPPORT_DET_MODEL = ["DB"]
-VERSION = "2.8.0"
 SUPPORT_REC_MODEL = ["CRNN", "SVTR_LCNet"]
 BASE_DIR = os.path.expanduser("~/.paddleocr/")
 

pyproject.toml

@@ -0,0 +1,70 @@
+[build-system]
+requires = ["setuptools", "setuptools-scm", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "paddleocr"
+# After each version release, the version number needs to be incremented
+dynamic = ["version"]
+description = "Awesome OCR toolkits based on PaddlePaddle(8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embedded and IoT devices)"
+authors = [
+    {name = "PaddlePaddle", email = "Paddle-better@baidu.com"},
+]
+maintainers = [
+    {name = "PaddlePaddle", email = "Paddle-better@baidu.com"},
+]
+readme = "README.md"
+requires-python = ">=3.8"
+keywords = [
+    "ocr",
+    "textdetection",
+    "textrecognition",
+    "paddleocr",
+    "crnn",
+    "east",
+    "star-net",
+    "rosetta",
+    "ocrlite",
+    "db",
+    "chineseocr",
+    "chinesetextdetection",
+    "chinesetextrecognition",
+]
+license = {text = "Apache License 2.0"}
+classifiers = [
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Natural Language :: Chinese (Simplified)",
+    "Programming Language :: Python :: 3",
+    "Topic :: Utilities",
+]
+dependencies = [
+    "shapely",
+    "scikit-image",
+    "imgaug",
+    "pyclipper",
+    "lmdb",
+    "tqdm",
+    "numpy",
+    "rapidfuzz",
+    "opencv-python<=4.6.0.66",
+    "opencv-contrib-python<=4.6.0.66",
+    "cython",
+    "Pillow>=10.0.0",
+    "pyyaml",
+    "python-docx",
+    "beautifulsoup4",
+    "fonttools>=4.24.0",
+    "fire>=0.3.0",
+]
+
+[project.scripts]
+paddleocr = "paddleocr.paddleocr:main"
+
+[tool.setuptools]
+packages = ["paddleocr"]
+package-dir = { "paddleocr" = "" }
+include-package-data = true
+
+[tool.setuptools.dynamic]
+version = {file = "VERSION_NUMBER"}

setup.py

@@ -13,68 +13,6 @@
 # limitations under the License.
 
 from setuptools import setup
-from io import open
-import subprocess
-
-# get version by matchiing, so will not need to setup complex env in github aciton
-p = subprocess.Popen(
-    "grep ^VERSION ./paddleocr.py | awk '{print $3}' | tr -d '\"'",
-    stdout=subprocess.PIPE,
-    stderr=subprocess.PIPE,
-    shell=True,
-)
-raw_VERSION, _ = p.communicate()
-VERSION = raw_VERSION.decode().strip()
 
 
-def load_requirements(file_list=None):
+setup()
-    if file_list is None:
-        file_list = ["requirements.txt"]
-    if isinstance(file_list, str):
-        file_list = [file_list]
-    requirements = []
-    for file in file_list:
-        with open(file, encoding="utf-8-sig") as f:
-            requirements.extend(f.readlines())
-    return requirements
-
-
-def readme():
-    with open("doc/doc_en/whl_en.md", encoding="utf-8-sig") as f:
-        README = f.read()
-    return README
-
-
-setup(
-    name="paddleocr",
-    packages=["paddleocr"],
-    package_dir={"paddleocr": ""},
-    include_package_data=True,
-    entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version=VERSION,
-    install_requires=load_requirements(
-        ["requirements.txt", "ppstructure/recovery/requirements.txt"]
-    ),
-    license="Apache License 2.0",
-    description="Awesome OCR toolkits based on PaddlePaddle(8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embedded and IoT devices)",
-    long_description=readme(),
-    long_description_content_type="text/markdown",
-    url="https://github.com/PaddlePaddle/PaddleOCR",
-    download_url="https://github.com/PaddlePaddle/PaddleOCR.git",
-    keywords=[
-        "ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition"
-    ],
-    classifiers=[
-        "Intended Audience :: Developers",
-        "Operating System :: OS Independent",
-        "Natural Language :: Chinese (Simplified)",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.2",
-        "Programming Language :: Python :: 3.3",
-        "Programming Language :: Python :: 3.4",
-        "Programming Language :: Python :: 3.5",
-        "Programming Language :: Python :: 3.6",
-        "Programming Language :: Python :: 3.7",
-        "Topic :: Utilities",
-    ],
-)