Make chunks have the same number of dimensions as shape

sgkit-dev · Jul 8, 2024 · ada71fa · ada71fa
1 parent 69ee0e8
commit ada71fa
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 5 deletions.
diff --git a/bio2zarr/vcf2zarr/vcz.py b/bio2zarr/vcf2zarr/vcz.py
@@ -98,6 +98,7 @@ def from_field(
         # TODO make an option to add in the empty extra dimension
         if vcf_field.summary.max_number > 1:
             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
             # are actually correct.
             if vcf_field.vcf_number == "R":
@@ -251,7 +252,12 @@ def spec_from_field(field, array_name=None):
             )
 
         def fixed_field_spec(
-            name, dtype, vcf_field=None, shape=(m,), dimensions=("variants",)
+            name,
+            dtype,
+            vcf_field=None,
+            shape=(m,),
+            dimensions=("variants",),
+            chunks=None,
         ):
             return ZarrArraySpec.new(
                 vcf_field=vcf_field,
@@ -260,7 +266,7 @@ def fixed_field_spec(
                 shape=shape,
                 description="",
                 dimensions=dimensions,
-                chunks=[variants_chunk_size],
+                chunks=chunks or [variants_chunk_size],
             )
 
         alt_field = icf.fields["ALT"]
@@ -276,12 +282,14 @@ def fixed_field_spec(
                 dtype="bool",
                 shape=(m, icf.metadata.num_filters),
                 dimensions=["variants", "filters"],
+                chunks=(variants_chunk_size, icf.metadata.num_filters),
             ),
             fixed_field_spec(
                 name="variant_allele",
                 dtype="O",
                 shape=(m, max_alleles),
                 dimensions=["variants", "alleles"],
+                chunks=(variants_chunk_size, max_alleles),
             ),
             fixed_field_spec(
                 name="variant_id",
@@ -329,6 +337,7 @@ def fixed_field_spec(
                 )
             )
             shape += [ploidy]
+            chunks += [ploidy]
             dimensions += ["ploidy"]
             array_specs.append(
                 ZarrArraySpec.new(

diff --git a/tests/test_vcz.py b/tests/test_vcz.py
@@ -313,7 +313,7 @@ def test_call_genotype(self, schema):
             "name": "call_genotype",
             "dtype": "i1",
             "shape": (9, 3, 2),
-            "chunks": (10000, 1000),
+            "chunks": (10000, 1000, 2),
             "dimensions": ("variants", "samples", "ploidy"),
             "description": "",
             "vcf_field": None,
@@ -332,7 +332,7 @@ def test_call_genotype_mask(self, schema):
             "name": "call_genotype_mask",
             "dtype": "bool",
             "shape": (9, 3, 2),
-            "chunks": (10000, 1000),
+            "chunks": (10000, 1000, 2),
             "dimensions": ("variants", "samples", "ploidy"),
             "description": "",
             "vcf_field": None,
@@ -351,7 +351,7 @@ def test_call_genotype_phased(self, schema):
             "name": "call_genotype_mask",
             "dtype": "bool",
             "shape": (9, 3, 2),
-            "chunks": (10000, 1000),
+            "chunks": (10000, 1000, 2),
             "dimensions": ("variants", "samples", "ploidy"),
             "description": "",
             "vcf_field": None,