chore: init monorepo snapshot

2025-11-23 10:55:04 +08:00
commit c70ff52869
941 changed files with 246586 additions and 0 deletions
@@ -0,0 +1,153 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "mineru"
+dynamic = ["version"]
+license = { text = "AGPL-3.0" }
+description = "A practical tool for converting PDF to Markdown"
+readme = "README.md"
+requires-python = ">=3.10,<3.14"
+keywords = ["magic-pdf", "mineru", "MinerU", "convert", "pdf", "markdown"]
+classifiers = [
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+dependencies = [
+    "boto3>=1.28.43",
+    "click>=8.1.7",
+    "loguru>=0.7.2",
+    "numpy>=1.21.6",
+    "pdfminer.six==20250324",
+    "tqdm>=4.67.1",
+    "requests",
+    "httpx",
+    "pillow>=10.4.0",
+    "pypdfium2>=4.30.0",
+    "pypdf>=5.6.0",
+    "reportlab",
+    "modelscope>=1.26.0",
+    "huggingface-hub>=0.32.4",
+    "opencv-python>=4.11.0.86",
+    "openai>=1.70.0,<3",
+    "beautifulsoup4>=4.13.5,<5",
+    "magika>=0.6.2,<0.7.0",
+]
+
+[project.optional-dependencies]
+test = [
+    "mineru[core]",
+    "pytest",
+    "pytest-cov",
+    "coverage",
+    "fuzzywuzzy"
+]
+vlm = [
+    "torch>=2.6.0,<3",
+    "transformers>=4.51.1,<5.0.0",
+    "accelerate>=1.5.1",
+]
+vllm = [
+    "vllm>=0.10.1.1,<0.12",
+]
+mlx = [
+    "mlx-vlm>=0.3.3,<0.4",
+]
+pipeline = [
+    "matplotlib>=3.10,<4",
+    "ultralytics>=8.3.48,<9",
+    "doclayout_yolo==0.0.4",
+    "dill>=0.3.8,<1",
+    "PyYAML>=6.0.2,<7",
+    "ftfy>=6.3.1,<7",
+    "shapely>=2.0.7,<3",
+    "pyclipper>=1.3.0,<2",
+    "omegaconf>=2.3.0,<3",
+    "torch>=2.6.0,<3",
+    "torchvision",
+    "transformers>=4.49.0,!=4.51.0,<5.0.0",
+    "onnxruntime>1.17.0",
+]
+api = [
+    "fastapi",
+    "python-multipart",
+    "uvicorn",
+]
+gradio = [
+    "gradio>=5.34,<6",
+    "gradio-pdf>=0.0.22",
+]
+core = [
+    "mineru[vlm]",
+    "mineru[pipeline]",
+    "mineru[api]",
+    "mineru[gradio]",
+    "mineru[mlx] ; sys_platform == 'darwin'",
+]
+all = [
+    "mineru[core]",
+    "mineru[vllm]",
+]
+
+[project.urls]
+homepage = "https://mineru.net/"
+documentation = "https://opendatalab.github.io/MinerU/"
+repository = "https://github.com/opendatalab/MinerU"
+issues = "https://github.com/opendatalab/MinerU/issues"
+
+[project.scripts]
+mineru = "mineru.cli:client.main"
+mineru-vllm-server = "mineru.cli.vlm_vllm_server:main"
+mineru-models-download = "mineru.cli.models_download:download_models"
+mineru-api = "mineru.cli.fast_api:main"
+mineru-gradio = "mineru.cli.gradio_app:main"
+
+[tool.setuptools.dynamic]
+version = { attr = "mineru.version.__version__" }
+
+[tool.setuptools.packages.find]
+include = ["mineru*"]
+namespaces = false
+
+[tool.setuptools.package-data]
+"mineru" = ["resources/**"]
+"mineru.model.utils.pytorchocr.utils" = ["resources/**"]
+
+[tool.setuptools]
+include-package-data = true
+zip-safe = false
+
+[tool.pytest.ini_options]
+addopts = "-s --cov=mineru --cov-report html"
+
+[tool.coverage.run]
+command_line = "-m pytest tests/unittest/test_e2e.py"
+source = ["mineru/"]
+omit = [
+    "*/gradio_app.py",
+    "*/models_download.py",
+    "*/fast_api.py",
+    "*/cli/client.py",
+    "*/vlm_vllm_server.py",
+    "*/cli_parser.py",
+]
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.report]
+exclude_also = [
+    'def __repr__',
+    'if self.debug:',
+    'if settings.DEBUG',
+    'raise AssertionError',
+    'raise NotImplementedError',
+    'if 0:',
+    'if __name__ == .__main__.:',
+    'if TYPE_CHECKING:',
+    'class .*\bProtocol\):',
+    '@(abc\.)?abstractmethod',
+]