Revert "Drop 3.9" #95

.github/workflows/ci.yml

@@ -27,7 +27,7 @@ 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: ["3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
         exclude:
           # Just run macos tests on one Python version
           - os: macos-13
@@ -36,6 +36,8 @@ 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

pyproject.toml

@@ -17,7 +17,7 @@ dependencies = [
   "pyranges",
   "pyparsing>=3"
 ]
-requires-python = ">=3.10"
+requires-python = ">=3.9"
 classifiers = [
   "Development Status :: 4 - Beta",
   "License :: OSI Approved :: Apache Software License",
@@ -28,6 +28,7 @@ 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",
@@ -61,8 +62,8 @@ addopts = "--cov=vcztools --cov-report=term-missing"
 write_to = "vcztools/_version.py"
 
 [tool.ruff]
-# Assume Python 3.10
-target-version = "py310"
+# Assume Python 3.9
+target-version = "py39"
 
 # Same as Black.
 line-length = 88

tests/test_regions.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 import pytest
 
 from vcztools.regions import parse_region_string
@@ -13,6 +15,6 @@
     ],
 )
 def test_parse_region_string(
-    targets: str, expected: tuple[str, int | None, int | None]
+    targets: str, expected: tuple[str, Optional[int], Optional[int]]
 ):
     assert parse_region_string(targets) == expected

tests/test_vcf_writer.py

@@ -85,7 +85,7 @@ def test_write_vcf__filtering(tmp_path, include, exclude, expected_chrom_pos):
     assert len(variants) == len(expected_chrom_pos)
     assert v.samples == ["NA00001", "NA00002", "NA00003"]
 
-    for variant, chrom_pos in zip(variants, expected_chrom_pos, strict=True):
+    for variant, chrom_pos in zip(variants, expected_chrom_pos):
         chrom, pos = chrom_pos
         assert variant.CHROM == chrom
         assert variant.POS == pos
@@ -141,7 +141,7 @@ def test_write_vcf__regions(tmp_path, regions, targets,
 
     assert v.samples == ["NA00001", "NA00002", "NA00003"]
 
-    for variant, chrom_pos in zip(variants, expected_chrom_pos, strict=True):
+    for variant, chrom_pos in zip(variants, expected_chrom_pos):
         chrom, pos = chrom_pos
         assert variant.CHROM == chrom
         assert variant.POS == pos
@@ -230,7 +230,7 @@ def test_write_vcf__regions_samples_filtering(
     assert len(variants) == len(expected_chrom_pos)
     assert v.samples == ["NA00001"]
 
-    for variant, chrom_pos in zip(variants, expected_chrom_pos, strict=True):
+    for variant, chrom_pos in zip(variants, expected_chrom_pos):
         chrom, pos = chrom_pos
         assert variant.CHROM == chrom
         assert variant.POS == pos

vcztools/filter.py

@@ -1,6 +1,6 @@
 import functools
 import operator
-from collections.abc import Callable
+from typing import Callable
 
 import numpy as np
 import pyparsing as pp

vcztools/query.py

@@ -1,7 +1,7 @@
 import functools
 import itertools
 import math
-from collections.abc import Callable
+from typing import Callable, Optional, Union
 
 import numpy as np
 import pyparsing as pp
@@ -62,10 +62,10 @@ def __call__(self, *args, **kwargs):
 class QueryFormatGenerator:
     def __init__(
         self,
-        query_format: str | pp.ParseResults,
+        query_format: Union[str, pp.ParseResults],
         *,
-        include: str | None = None,
-        exclude: str | None = None,
+        include: Optional[str] = None,
+        exclude: Optional[str] = None,
     ):
         if isinstance(query_format, str):
             parser = QueryFormatParser()
@@ -99,7 +99,7 @@ def generate(root):
                     end = start + v_chunk_size
 
                     for gt_row, phase in zip(
-                        gt_zarray[start:end], phase_zarray[start:end], strict=True
+                        gt_zarray[start:end], phase_zarray[start:end]
                     ):
 
                         def stringify(gt_and_phase: tuple):
@@ -113,7 +113,7 @@ def stringify(gt_and_phase: tuple):
                             return separator.join(gt)
 
                         gt_row = gt_row.tolist()
-                        yield map(stringify, zip(gt_row, phase, strict=True))
+                        yield map(stringify, zip(gt_row, phase))
             else:
                 # TODO: Support datasets without the phasing data
                 raise NotImplementedError
@@ -230,8 +230,8 @@ def _compose_sample_loop_generator(
 
         def generate(root):
             iterables = (generator(root) for generator in generators)
-            zipped = zip(*iterables, strict=True)
-            zipped_zipped = (zip(*element, strict=True) for element in zipped)
+            zipped = zip(*iterables)
+            zipped_zipped = (zip(*element) for element in zipped)
             flattened_zipped_zipped = (
                 (
                     subsubelement
@@ -245,7 +245,7 @@ def generate(root):
         return generate
 
     def _compose_element_generator(
-        self, element: str | pp.ParseResults, *, sample_loop=False
+        self, element: Union[str, pp.ParseResults], *, sample_loop=False
     ) -> Callable:
         if isinstance(element, pp.ParseResults):
             if element.get_name() == "subfield":
@@ -272,7 +272,7 @@ def generate(root):
             return generate
 
     def _compose_filter_generator(
-        self, *, include: str | None = None, exclude: str | None = None
+        self, *, include: Optional[str] = None, exclude: Optional[str] = None
     ) -> Callable:
         assert not (include and exclude)
 
@@ -305,8 +305,8 @@ def _compose_generator(
         self,
         parse_results: pp.ParseResults,
         *,
-        include: str | None = None,
-        exclude: str | None = None,
+        include: Optional[str] = None,
+        exclude: Optional[str] = None,
     ) -> Callable:
         generators = (
             self._compose_element_generator(element) for element in parse_results
@@ -318,10 +318,7 @@ def _compose_generator(
         def generate(root) -> str:
             iterables = (generator(root) for generator in generators)
             filter_iterable = filter_generator(root)
-
-            for results, filter_indicator in zip(
-                zip(*iterables, strict=True), filter_iterable, strict=True
-            ):
+            for results, filter_indicator in zip(zip(*iterables), filter_iterable):
                 if filter_indicator:
                     results = map(str, results)
                     yield "".join(results)
@@ -334,8 +331,8 @@ def write_query(
     output=None,
     *,
     query_format: str,
-    include: str | None = None,
-    exclude: str | None = None,
+    include: Optional[str] = None,
+    exclude: Optional[str] = None,
 ):
     if include and exclude:
         raise ValueError(

vcztools/regions.py

@@ -1,12 +1,12 @@
 import re
-from typing import Any
+from typing import Any, Optional
 
 import numpy as np
 import pandas as pd
 from pyranges import PyRanges
 
 
-def parse_region_string(region: str) -> tuple[str, int | None, int | None]:
+def parse_region_string(region: str) -> tuple[str, Optional[int], Optional[int]]:
     """Return the contig, start position and end position from a region string."""
     if re.search(r":\d+-\d*$", region):
         contig, start_end = region.rsplit(":", 1)
@@ -21,7 +21,7 @@ def parse_region_string(region: str) -> tuple[str, int | None, int | None]:
 
 
 def regions_to_pyranges(
-    regions: list[tuple[str, int | None, int | None]], all_contigs: list[str]
+    regions: list[tuple[str, Optional[int], Optional[int]]], all_contigs: list[str]
 ) -> PyRanges:
     """Convert region tuples to a PyRanges object."""
 
@@ -44,7 +44,7 @@ def regions_to_pyranges(
     return PyRanges(chromosomes=chromosomes, starts=starts, ends=ends)
 
 
-def parse_regions(regions: str | None, all_contigs: list[str]) -> PyRanges | None:
+def parse_regions(regions: Optional[str], all_contigs: list[str]) -> Optional[PyRanges]:
     """Return a PyRanges object from a comma-separated set of region strings."""
     if regions is None:
         return None
@@ -54,21 +54,22 @@ def parse_regions(regions: str | None, all_contigs: list[str]) -> PyRanges | Non
 
 
 def parse_targets(
-    targets: str | None, all_contigs: list[str]
-) -> tuple[PyRanges | None, bool]:
+    targets: Optional[str], all_contigs: list[str]
+) -> tuple[Optional[PyRanges], bool]:
     """Return a PyRanges object from a comma-separated set of region strings,
     optionally preceeded by a ^ character to indicate complement."""
     if targets is None:
         return None, False
     complement = targets.startswith("^")
-    return parse_regions(
-        targets[1:] if complement else targets, all_contigs
-    ), complement
+    return (
+        parse_regions(targets[1:] if complement else targets, all_contigs),
+        complement,
+    )
 
 
 def regions_to_chunk_indexes(
-    regions: PyRanges | None,
-    targets: PyRanges | None,
+    regions: Optional[PyRanges],
+    targets: Optional[PyRanges],
     complement: bool,
     regions_index: Any,
 ):
@@ -112,8 +113,8 @@ def regions_to_chunk_indexes(
 
 
 def regions_to_selection(
-    regions: PyRanges | None,
-    targets: PyRanges | None,
+    regions: Optional[PyRanges],
+    targets: Optional[PyRanges],
     complement: bool,
     variant_contig: Any,
     variant_position: Any,

vcztools/stats.py

@@ -38,7 +38,7 @@ def stats(vcz, output):
         ).astype(np.int64)
 
         for contig, contig_length, nr in zip(
-            contigs, contig_lengths, num_records_per_contig, strict=True
+            contigs, contig_lengths, num_records_per_contig
         ):
             if nr > 0:
                 print(f"{contig}\t{contig_length}\t{nr}", file=output)

vcztools/utils.py

@@ -18,7 +18,7 @@ def open_file_like(file):
     """A context manager for opening a file path or string (and closing on exit),
     or passing a file-like object through."""
     with ExitStack() as stack:
-        if isinstance(file, str | Path):
+        if isinstance(file, (str, Path)):
             file = stack.enter_context(open(file, mode="w"))
         yield file
 

vcztools/vcf_writer.py

@@ -4,6 +4,7 @@
 import re
 import sys
 from datetime import datetime
+from typing import Optional
 
 import numpy as np
 import zarr
@@ -89,8 +90,8 @@ def write_vcf(
     no_update=None,
     samples=None,
     drop_genotypes: bool = False,
-    include: str | None = None,
-    exclude: str | None = None,
+    include: Optional[str] = None,
+    exclude: Optional[str] = None,
 ) -> None:
     """Convert a dataset to a VCF file.
 
@@ -307,7 +308,7 @@ def c_chunk_to_vcf(
     *,
     drop_genotypes,
     no_update,
-    preceding_future: concurrent.futures.Future | None = None,
+    preceding_future=None,
 ):
     chrom = contigs[get_vchunk_array(root["variant_contig"], v_chunk, v_mask_chunk)]
     # TODO check we don't truncate silently by doing this