Drop Python 3.9

Author: benjeffery

.github/workflows/cd.yml

@@ -19,7 +19,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: '3.10'
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip

.github/workflows/ci.yml

@@ -25,7 +25,7 @@ jobs:
         # Use macos-13 because pip binary packages for ARM aren't
         # available for many dependencies
         os: [macos-13, macos-14, ubuntu-latest]
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12"]
         exclude:
           # Just run macos tests on one Python version
           - os: macos-13
@@ -34,8 +34,6 @@ jobs:
             python-version: "3.11"
           - os: macos-13
             python-version: "3.12"
-          - os: macos-14
-            python-version: "3.9"
           - os: macos-14
             python-version: "3.10"
           - os: macos-14

bio2zarr/core.py

@@ -7,10 +7,8 @@
 import multiprocessing
 import os
 import os.path
-import sys
 import threading
 import time
-import warnings
 
 import humanfriendly
 import numcodecs
@@ -256,22 +254,6 @@ def setup_progress_counter(counter):
     _progress_counter = counter
 
 
-def warn_py39_mac():
-    if sys.platform == "darwin" and sys.version_info[:2] == (3, 9):
-        warnings.warn(
-            "There is a known issue with bio2zarr on MacOS Python 3.9 "
-            "in which OS-level named semaphores are leaked. "
-            "You will also probably see warnings like 'There appear to be N "
-            "leaked semaphore objects at shutdown'. "
-            "While this is likely harmless for a few runs, it could lead to "
-            "issues if you do a lot of conversion. To get prevent this issue "
-            "either: (1) use --worker-processes=0 or (2) upgrade to a newer "
-            "Python version. See https://github.com/sgkit-dev/bio2zarr/issues/209 "
-            "for more details.",
-            stacklevel=2,
-        )
-
-
 class ParallelWorkManager(contextlib.AbstractContextManager):
     def __init__(self, worker_processes=1, progress_config=None):
         # Need to specify this explicitly to suppport Macs and
@@ -284,7 +266,6 @@ def __init__(self, worker_processes=1, progress_config=None):
             # production. See note on the SynchronousExecutor class.
             self.executor = SynchronousExecutor()
         else:
-            warn_py39_mac()
             self.executor = cf.ProcessPoolExecutor(
                 max_workers=worker_processes,
                 mp_context=ctx,

bio2zarr/typing.py

@@ -1,4 +1,3 @@
 from pathlib import Path
-from typing import Union
 
-PathType = Union[str, Path]
+PathType = str | Path

bio2zarr/vcf.py

@@ -638,7 +638,8 @@ def chunks(self, partition_id, start_chunk=0):
         chunk_cumulative_records = self.chunk_record_index(partition_id)
         chunk_num_records = np.diff(chunk_cumulative_records)
         for count, cumulative in zip(
-            chunk_num_records[start_chunk:], chunk_cumulative_records[start_chunk + 1 :]
+            chunk_num_records[start_chunk:],
+            chunk_cumulative_records[start_chunk + 1 :],
         ):
             path = partition_path / f"{cumulative}"
             chunk = self.read_chunk(path)

bio2zarr/vcf_utils.py

@@ -7,7 +7,7 @@
 from collections.abc import Sequence
 from dataclasses import dataclass
 from enum import Enum
-from typing import IO, Any, Optional, Union
+from typing import IO, Any
 
 import cyvcf2
 import humanfriendly
@@ -33,7 +33,7 @@ def get_file_offset(vfp: int) -> int:
     return vfp >> 16 & address_mask
 
 
-def read_bytes_as_value(f: IO[Any], fmt: str, nodata: Optional[Any] = None) -> Any:
+def read_bytes_as_value(f: IO[Any], fmt: str, nodata: Any | None = None) -> Any:
     """Read bytes using a `struct` format string and return the unpacked data value.
 
     Parameters
@@ -85,8 +85,8 @@ class Region:
     """
 
     contig: str
-    start: Optional[int] = None
-    end: Optional[int] = None
+    start: int | None = None
+    end: int | None = None
 
     def __post_init__(self):
         assert self.contig is not None
@@ -197,9 +197,7 @@ def get_first_locus_in_bin(csi: CSIIndex, bin: int) -> int:
     return (bin - first_bin_on_level) * (max_span // level_size) + 1
 
 
-def read_csi(
-    file: PathType, storage_options: Optional[dict[str, str]] = None
-) -> CSIIndex:
+def read_csi(file: PathType, storage_options: dict[str, str] | None = None) -> CSIIndex:
     """Parse a CSI file into a `CSIIndex` object.
 
     Parameters
@@ -314,7 +312,7 @@ def offsets(self) -> Any:
 
 
 def read_tabix(
-    file: PathType, storage_options: Optional[dict[str, str]] = None
+    file: PathType, storage_options: dict[str, str] | None = None
 ) -> TabixIndex:
     """Parse a tabix file into a `TabixIndex` object.
 
@@ -512,8 +510,8 @@ def _filter_empty_and_refine(self, regions):
 
     def partition_into_regions(
         self,
-        num_parts: Optional[int] = None,
-        target_part_size: Union[None, int, str] = None,
+        num_parts: int | None = None,
+        target_part_size: None | int | str = None,
     ):
         if num_parts is None and target_part_size is None:
             raise ValueError("One of num_parts or target_part_size must be specified")

pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
   "cyvcf2",
   "bed_reader",
 ]
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 classifiers = [
   "Development Status :: 4 - Beta",
   "License :: OSI Approved :: Apache Software License",
@@ -37,7 +37,6 @@ classifiers = [
   "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",
   "Programming Language :: Python :: 3.12",
@@ -55,6 +54,7 @@ vcfpartition = "bio2zarr.cli:vcfpartition"
 
 [project.optional-dependencies]
 dev = [
+  "click>=8.2.0",
   "hypothesis-vcf",
   "msprime",
   "pysam",
@@ -76,8 +76,8 @@ testpaths = "tests"
 addopts = "--cov=bio2zarr --cov-report term-missing"
 
 [tool.ruff]
-# Assume Python 3.9
-target-version = "py39"
+# Assume Python 3.10
+target-version = "py310"
 
 # Same as Black.
 line-length = 88
@@ -86,7 +86,8 @@ indent-width = 4
 [tool.ruff.lint]
 select = ["E", "F", "B", "W", "I", "N", "UP", "A", "PT"]
 #Allow uppercase names for e.g. call_AD
-ignore = ["N806", "N802", "A001", "A002", "RUF"]
+#Don't add strict=False to zips (B905)
+ignore = ["N806", "N802", "A001", "A002", "B905", "RUF"]
 
 fixable = ["ALL"]
 unfixable = []