Support -R/--regions-file and -T/--targets-file

tests/data/txt/regions-3col.tsv

@@ -0,0 +1,2 @@
+20	1230237	1235237
+X	10	10

tests/test_bcftools_validation.py

@@ -105,6 +105,26 @@ def run_vcztools(args: str, expect_error=False) -> tuple[str, str]:
             "view --no-version -r '20:1230236-' -i 'FMT/DP>3' -s 'NA00002,NA00003'",
             "sample.vcf.gz"
         ),
+        (
+            "view --no-version -R tests/data/txt/regions-3col.tsv -i 'FMT/DP>3' -s 'NA00002,NA00003'",  # noqa: E501
+            "sample.vcf.gz"
+        ),
+        (
+            "view --no-version -t '20:1230236-' -i 'FMT/DP>3' -s 'NA00002,NA00003'",
+            "sample.vcf.gz"
+        ),
+        (
+            "view --no-version -t '^20:1230236-' -i 'FMT/DP>3' -s 'NA00002,NA00003'",
+            "sample.vcf.gz"
+        ),
+        (
+            "view --no-version -T tests/data/txt/regions-3col.tsv -i 'FMT/DP>3' -s 'NA00002,NA00003'",  # noqa: E501
+            "sample.vcf.gz"
+        ),
+        (
+            "view --no-version -T ^tests/data/txt/regions-3col.tsv -i 'FMT/DP>3' -s 'NA00002,NA00003'",  # noqa: E501
+            "sample.vcf.gz"
+        ),
         (
             "view --no-version -i 'FILTER=\"VQSRTrancheSNP99.80to100.00\"'",
             "1kg_2020_chrM.vcf.gz"
@@ -239,6 +259,14 @@ def test_vcf_output_with_output_option(tmp_path, args, vcf_file):
             r"query -f '[%CHROM %POS %SAMPLE %GT %DP %GQ\n]' -r '20:1230236-' -i 'FMT/DP>3' -S tests/data/txt/samples.txt",  # noqa: E501
             "sample.vcf.gz",
         ),
+        (
+            r"query -f '[%CHROM %POS %SAMPLE %GT %DP %GQ\n]' -R tests/data/txt/regions-3col.tsv -i 'FMT/DP>3' -s 'NA00002,NA00003'",  # noqa: E501
+            "sample.vcf.gz",
+        ),
+        (
+            r"query -f '[%CHROM %POS %SAMPLE %GT %DP %GQ\n]' -T ^tests/data/txt/regions-3col.tsv -i 'FMT/DP>3' -s 'NA00002,NA00003'",  # noqa: E501
+            "sample.vcf.gz",
+        ),
     ],
 )
 def test_output(tmp_path, args, vcf_name):

tests/test_regions.py

@@ -1,6 +1,7 @@
 import pytest
+from numpy.testing import assert_array_equal
 
-from vcztools.regions import parse_region_string
+from vcztools.regions import parse_region_string, parse_regions, parse_targets
 
 
 @pytest.mark.parametrize(
@@ -16,3 +17,28 @@ def test_parse_region_string(
     targets: str, expected: tuple[str, int | None, int | None]
 ):
     assert parse_region_string(targets) == expected
+
+
+def test_parse_regions_file():
+    all_contigs = ["19", "20", "X"]
+    genomic_ranges = parse_regions(
+        regions=None,
+        all_contigs=all_contigs,
+        regions_file="tests/data/txt/regions-3col.tsv",
+    )
+    assert_array_equal(genomic_ranges.contigs, [1, 2])
+    assert_array_equal(genomic_ranges.starts, [1230236, 9])
+    assert_array_equal(genomic_ranges.ends, [1235237, 10])
+
+
+def test_parse_targets_file():
+    all_contigs = ["19", "20", "X"]
+    genomic_ranges = parse_targets(
+        targets=None,
+        all_contigs=all_contigs,
+        targets_file="^tests/data/txt/regions-3col.tsv",
+    )
+    assert_array_equal(genomic_ranges.contigs, [1, 2])
+    assert_array_equal(genomic_ranges.starts, [1230236, 9])
+    assert_array_equal(genomic_ranges.ends, [1235237, 10])
+    assert genomic_ranges.complement

vcztools/cli.py

@@ -69,6 +69,13 @@ def wrapper(*args, **kwargs):
     default=None,
     help="Regions to include.",
 )
+regions_file = click.option(
+    "-R",
+    "--regions-file",
+    type=str,
+    default=None,
+    help="File of regions to include.",
+)
 samples = click.option(
     "-s",
     "--samples",
@@ -90,6 +97,13 @@ def wrapper(*args, **kwargs):
     default=None,
     help="Target regions to include.",
 )
+targets_file = click.option(
+    "-T",
+    "--targets-file",
+    type=str,
+    default=None,
+    help="File of target regions to include.",
+)
 version = click.version_option(version=f"{provenance.__version__}")
 zarr_backend_storage = click.option(
     "--zarr-backend-storage",
@@ -159,10 +173,12 @@ def index(path, nrecords, stats, zarr_backend_storage):
     default=None,
 )
 @regions
+@regions_file
 @force_samples
 @samples
 @samples_file
 @targets
+@targets_file
 @include
 @exclude
 @click.option(
@@ -180,7 +196,9 @@ def query(
     list_samples,
     format,
     regions,
+    regions_file,
     targets,
+    targets_file,
     force_samples,
     samples,
     samples_file,
@@ -216,7 +234,9 @@ def query(
             output,
             query_format=format,
             regions=regions,
+            regions_file=regions_file,
             targets=targets,
+            targets_file=targets_file,
             samples=samples,
             samples_file=samples_file,
             force_samples=force_samples,
@@ -248,6 +268,7 @@ def query(
     help="Do not append version and command line information to the output VCF header.",
 )
 @regions
+@regions_file
 @force_samples
 @click.option(
     "-I",
@@ -264,6 +285,7 @@ def query(
     help="Drop genotypes.",
 )
 @targets
+@targets_file
 @include
 @exclude
 @zarr_backend_storage
@@ -275,7 +297,9 @@ def view(
     no_header,
     no_version,
     regions,
+    regions_file,
     targets,
+    targets_file,
     force_samples,
     no_update,
     samples,
@@ -310,7 +334,9 @@ def view(
             no_header=no_header,
             no_version=no_version,
             regions=regions,
+            regions_file=regions_file,
             targets=targets,
+            targets_file=targets_file,
             no_update=no_update,
             samples=samples,
             samples_file=samples_file,

vcztools/query.py

@@ -7,8 +7,14 @@
 import pyparsing as pp
 
 from vcztools import constants, retrieval
+from vcztools.regions import parse_regions, parse_targets
 from vcztools.samples import parse_samples
-from vcztools.utils import missing, open_zarr, vcf_name_to_vcz_names
+from vcztools.utils import (
+    _as_fixed_length_unicode,
+    missing,
+    open_zarr,
+    vcf_name_to_vcz_names,
+)
 
 
 def list_samples(vcz_path, output, zarr_backend_storage=None):
@@ -299,7 +305,9 @@ def write_query(
     *,
     query_format: str,
     regions=None,
+    regions_file=None,
     targets=None,
+    targets_file=None,
     samples=None,
     samples_file=None,
     force_samples: bool = False,
@@ -320,6 +328,10 @@ def write_query(
     contigs = root["contig_id"][:]
     filters = root["filter_id"][:]
 
+    contigs_u = _as_fixed_length_unicode(root["contig_id"][:]).tolist()
+    regions = parse_regions(regions, contigs_u, regions_file=regions_file)
+    targets = parse_targets(targets, contigs_u, targets_file=targets_file)
+
     if "\\n" not in query_format and not disable_automatic_newline:
         query_format = query_format + "\\n"