Consolidate project config under pyproject

.gitignore

@@ -1,3 +1,6 @@
+# auto generated by setuptools_scm and configured in pyproject.toml
+bio2zarr/_version.py
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -152,9 +155,9 @@ dmypy.json
 # Cython debug symbols
 cython_debug/
 
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+# IDE
+.vscode
+.idea
+
+# Mac
+.DS_Store

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
       - id: check-case-conflict
       - id: check-yaml
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.7
+    rev: v0.4.2
     hooks:
       - id: ruff
         args: [ --fix ]

bio2zarr/vcf.py

@@ -12,7 +12,7 @@
 import shutil
 import sys
 import tempfile
-from typing import Any, List
+from typing import Any
 
 import cyvcf2
 import humanfriendly
@@ -746,9 +746,9 @@ class IcfFieldWriter:
     transformer: VcfValueTransformer
     compressor: Any
     max_buffered_bytes: int
-    buff: List[Any] = dataclasses.field(default_factory=list)
+    buff: list[Any] = dataclasses.field(default_factory=list)
     buffered_bytes: int = 0
-    chunk_index: List[int] = dataclasses.field(default_factory=lambda: [0])
+    chunk_index: list[int] = dataclasses.field(default_factory=lambda: [0])
     num_records: int = 0
 
     def append(self, val):

bio2zarr/vcf_utils.py

@@ -3,8 +3,9 @@
 import os
 import pathlib
 import struct
+from collections.abc import Sequence
 from dataclasses import dataclass
-from typing import IO, Any, Dict, Optional, Sequence, Union
+from typing import IO, Any, Optional, Union
 
 import cyvcf2
 import humanfriendly
@@ -183,7 +184,7 @@ def get_first_locus_in_bin(csi: CSIIndex, bin: int) -> int:
 
 
 def read_csi(
-    file: PathType, storage_options: Optional[Dict[str, str]] = None
+    file: PathType, storage_options: Optional[dict[str, str]] = None
 ) -> CSIIndex:
     """Parse a CSI file into a `CSIIndex` object.
 
@@ -297,7 +298,7 @@ def offsets(self) -> Any:
 
 
 def read_tabix(
-    file: PathType, storage_options: Optional[Dict[str, str]] = None
+    file: PathType, storage_options: Optional[dict[str, str]] = None
 ) -> TabixIndex:
     """Parse a tabix file into a `TabixIndex` object.
 

pyproject.toml

@@ -1,15 +1,85 @@
+[build-system]
+requires = ["setuptools >= 69", "setuptools_scm[toml] >= 8"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "bio2zarr"
+description = "Convert bioinformatics data to Zarr"
+readme = "README.md"
+license = {file = "LICENSE"}
+authors = [
+  {name = "sgkit Developers", email = "project@pystatgen.org"},
+]
+dependencies = [
+  "numpy",
+  "zarr >= 2.17",
+  "click",
+  "tabulate",
+  "tqdm",
+  "humanfriendly",
+  # cyvcf2 also pulls in coloredlogs and click",
+  # colouredlogs pulls in humanfriendly",
+  "cyvcf2",
+  "bed_reader",
+]
+requires-python = ">=3.9"
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "License :: OSI Approved :: Apache, Software License",
+  "Operating System :: OS Independent",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Topic :: Scientific/Engineering"
+]
+dynamic = ["version"]
+
+[project.urls]
+repository = "https://github.com/sgkit-dev/bio2zarr"
+documentation = "https://sgkit-dev.github.io/bio2zarr/intro.html"
+
+[project.scripts]
+vcf2zarr = "bio2zarr.cli:vcf2zarr"
+plink2zarr = "bio2zarr.cli:plink2zarr"
+vcf_partition = "bio2zarr.cli:vcf_partition"
+
+[tool.setuptools]
+packages = ["bio2zarr"]
+
+[tool.setuptools_scm]
+version_file = "bio2zarr/_version.py"
+
+[tool.pytest.ini_options]
+testpaths = "tests"
+addopts = "--cov=bio2zarr --cov-report term-missing"
+
 [tool.ruff]
+# Assume Python 3.9
+target-version = "py39"
+
 # Same as Black.
 line-length = 88
 indent-width = 4
 
-# Assume Python 3.8
-target-version = "py38"
-
 [tool.ruff.lint]
 select = ["E", "F", "B", "W", "I", "N", "UP", "A", "RUF", "PT"]
 #Allow uppercase names for e.g. call_AD
 ignore = ["N806", "N802", "A001", "A002"]
 
 fixable = ["ALL"]
-unfixable = []
+unfixable = []
+
+[tool.ruff.lint.isort]
+known-third-party = [
+  "hypothesis",
+  "msprime",
+  "numpy",
+  "pandas",
+  "pytest",
+  "setuptools",
+  "sgkit",
+  "zarr"
+]