feat: Add new module 'deepbiop' and 'add' function

Cargo.toml

@@ -1,6 +1,7 @@
 [workspace]
 resolver = "2"
-members = ["crates/*"]
+members = ["crates/*", "py-deepbiop"]
+
 
 [workspace.package]
 version = "0.1.0"
@@ -61,6 +62,9 @@ flate2 = { version = "1.0.30", features = [
     "zlib-ng",
 ], default-features = false }
 
+
+deepbiop-fq = { version = "0.1.0", path = "crates/deepbiop-fq" }
+
 [profile.opt-dev]
 inherits = "dev"
 opt-level = 1

py-deepbiop/deepbiop/__init__.py

@@ -0,0 +1 @@
+from .deepbiop import *  # noqa: F403

py-deepbiop/pyproject.toml

@@ -0,0 +1,214 @@
+[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[tool.maturin]
+# "extension-module" tells pyo3 we want to build an extension module (skips linking against libpython.so)
+features = ["pyo3/extension-module"]
+
+[project]
+name = "deepbiop"
+description = "Deep Learning Preprocessing Library for Biological Data"
+readme = "README.md"
+requires-python = ">=3.9"
+keywords = ["deep learning", "bioinformatics", "biological data"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apach License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Rust",
+    "Topic :: Scientific/Engineering",
+]
+
+[project.urls]
+Homepage = ""
+
+
+[tool.mypy]
+files = ["polars", "tests"]
+strict = true
+enable_error_code = ["redundant-expr", "truthy-bool", "ignore-without-code"]
+disable_error_code = ["empty-body"]
+
+[[tool.mypy.overrides]]
+module = [
+    "IPython.*",
+    "adbc_driver_manager.*",
+    "adbc_driver_sqlite.*",
+    "arrow_odbc",
+    "backports",
+    "connectorx",
+    "deltalake.*",
+    "fsspec.*",
+    "gevent",
+    "great_tables",
+    "hvplot.*",
+    "jax.*",
+    "kuzu",
+    "matplotlib.*",
+    "moto.server",
+    "nest_asyncio",
+    "openpyxl",
+    "polars.polars",
+    "pyarrow.*",
+    "pydantic",
+    "pyiceberg.*",
+    "sqlalchemy.*",
+    "torch.*",
+    "xlsx2csv",
+    "xlsxwriter.*",
+    "zoneinfo",
+]
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = ["IPython.*", "matplotlib.*"]
+follow_imports = "skip"
+
+[[tool.mypy.overrides]]
+module = ["polars.*"]
+# We exclude the polars module from warn_return_any, because the PyO3 api does not have Python
+# type annotations. See https://github.com/PyO3/pyo3/issues/1112 for a discussion on adding
+# this capability. We could add a stub file for polars.polars (the PyO3 api), but that
+# amounts to duplicating almost all type annotations on our api, as the Python api itself is a
+# thin wrapper around the PyO3 api to start with.
+warn_return_any = false
+
+[tool.ruff]
+line-length = 88
+fix = true
+
+[tool.ruff.lint]
+select = [
+    "E",      # pycodestyle
+    "W",      # pycodestyle
+    "F",      # Pyflakes
+    "B",      # flake8-bugbear
+    "C4",     # flake8-comprehensions
+    "D",      # flake8-docstrings
+    "D213",   # Augment NumPy docstring convention: Multi-line docstring summary should start at the second line
+    "D417",   # Augment NumPy docstring convention: Missing argument descriptions
+    "I",      # isort
+    "SIM",    # flake8-simplify
+    "TCH",    # flake8-type-checking
+    "TID",    # flake8-tidy-imports
+    "UP",     # pyupgrade
+    "PT",     # flake8-pytest-style
+    "RUF",    # Ruff-specific rules
+    "PTH",    # flake8-use-pathlib
+    "FA",     # flake8-future-annotations
+    "PIE",    # flake8-pie
+    "TD",     # flake8-todos
+    "TRY",    # tryceratops
+    "EM",     # flake8-errmsg
+    "FBT001", # flake8-boolean-trap
+]
+
+ignore = [
+    # Line length regulated by formatter
+    "E501",
+    # pydocstyle: http://www.pydocstyle.org/en/stable/error_codes.html
+    "D401", # Relax NumPy docstring convention: First line should be in imperative mood
+    # flake8-pytest-style:
+    "PT011", # pytest.raises({exception}) is too broad, set the match parameter or use a more specific exception
+    # flake8-simplify
+    "SIM102", # Use a single `if` statement instead of nested `if` statements
+    "SIM108", # Use ternary operator
+    # ruff
+    "RUF005", # unpack-instead-of-concatenating-to-collection-literal
+    # pycodestyle
+    # TODO: Remove errors below to further improve docstring linting
+    # Ordered from most common to least common errors.
+    "D105", # Missing docstring in magic method
+    "D100", # Missing docstring in public module
+    "D104", # Missing docstring in public package
+    # flake8-todos
+    "TD002", # Missing author in TODO
+    "TD003", # Missing issue link on the line following this TODO
+    # tryceratops
+    "TRY003", # Avoid specifying long messages outside the exception class
+    # Lints below are turned off because of conflicts with the ruff formatter
+    "D206",
+    "W191",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = ["D100", "D102", "D103", "B018", "FBT001"]
+
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 88
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[tool.ruff.lint.flake8-type-checking]
+strict = true
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.pytest.ini_options]
+addopts = [
+    "--tb=short",
+    "--strict-config",
+    "--strict-markers",
+    "--import-mode=importlib",
+    # Default to running fast tests only. To run ALL tests, run: pytest -m ""
+    "-m not slow and not write_disk and not release and not docs and not hypothesis and not benchmark and not ci_only",
+]
+markers = [
+    "ci_only: Tests that should only run on CI by default.",
+    "debug: Tests that should be run on a Polars debug build.",
+    "docs: Documentation code snippets",
+    "release: Tests that should be run on a Polars release build.",
+    "slow: Tests with a longer than average runtime.",
+    "write_disk: Tests that write to disk",
+]
+filterwarnings = [
+    # Fail on warnings
+    "error",
+    # Allow debugging in an IPython console
+    "ignore:.*unrecognized arguments.*PyDevIPCompleter:DeprecationWarning",
+    # Ignore warnings issued by dependency internals
+    "ignore:.*is_sparse is deprecated.*:FutureWarning",
+    "ignore:FigureCanvasAgg is non-interactive:UserWarning",
+    "ignore:datetime.datetime.utcfromtimestamp\\(\\) is deprecated.*:DeprecationWarning",
+    "ignore:datetime.datetime.utcnow\\(\\) is deprecated.*:DeprecationWarning",
+    # Introspection under PyCharm IDE can generate this in Python 3.12
+    "ignore:.*co_lnotab is deprecated, use co_lines.*:DeprecationWarning",
+    # TODO: Excel tests lead to unclosed file warnings
+    # https://github.com/pola-rs/polars/issues/14466
+    "ignore:unclosed file.*:ResourceWarning",
+    # Ignore invalid warnings when running earlier versions of SQLAlchemy (we
+    # know they are invalid because our standard tests run the latest version)
+    "ignore:Deprecated API features detected.*:DeprecationWarning",
+]
+xfail_strict = true
+
+[tool.coverage.run]
+source = ["polars"]
+branch = true
+
+[tool.coverage.report]
+fail_under = 85
+skip_covered = true
+show_missing = true
+exclude_lines = [
+    "pragma: no cover",
+    "@overload",
+    "except ImportError",
+    "if TYPE_CHECKING:",
+    "from typing_extensions import ",
+]

py-deepbiop/src/lib.rs

@@ -0,0 +1,12 @@
+use pyo3::prelude::*;
+
+#[pyfunction]
+fn add(a: usize, b: usize) -> usize {
+    a + b
+}
+
+#[pymodule]
+fn deepbiop(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_function(wrap_pyfunction!(add, m)?)?;
+    Ok(())
+}