Fix named VCF Number dimensions of size 1

Author: tomwhite

bio2zarr/vcz.py

@@ -137,7 +137,9 @@ def from_field(
         if array_name is None:
             array_name = prefix + vcf_field.name
         # TODO make an option to add in the empty extra dimension
-        if vcf_field.summary.max_number > 1 or vcf_field.full_name == "FORMAT/LAA":
+        if (
+            vcf_field.summary.max_number > 0 and vcf_field.vcf_number in ("R", "A", "G")
+        ) or (vcf_field.summary.max_number > 1 or vcf_field.full_name == "FORMAT/LAA"):
             shape.append(vcf_field.summary.max_number)
             chunks.append(vcf_field.summary.max_number)
             # TODO we should really be checking this to see if the named dimensions

tests/test_vcf_examples.py

@@ -997,6 +997,11 @@ def test_variant_ANN(self, ds):
         ]
         nt.assert_array_equal(ds.variant_ANN.values, variant_ANN)
 
+    def test_variant_MLEAF(self, ds):
+        # fixes https://github.com/sgkit-dev/bio2zarr/issues/353
+        assert ds.variant_MLEAF.dims == ("variants", "alt_alleles")
+        assert ds.variant_MLEAF.shape == (21, 1)
+
 
 class TestGeneratedFieldsExample:
     data_path = "tests/data/vcf/field_type_combos.vcf.gz"