Handle case where GT is defined in header, but not used in FORMAT

sgkit-dev · Jul 8, 2024 · 399cdc6 · 399cdc6
1 parent ada71fa
commit 399cdc6
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 4 deletions.
diff --git a/bio2zarr/vcf2zarr/icf.py b/bio2zarr/vcf2zarr/icf.py
@@ -1079,7 +1079,11 @@ def process_partition(self, partition_index):
                     for field in info_fields:
                         tcw.append(field.full_name, variant.INFO.get(field.name, None))
                     if has_gt:
-                        tcw.append("FORMAT/GT", variant.genotype.array())
+                        if variant.genotype is None:
+                            val = None
+                        else:
+                            val = variant.genotype.array()
+                        tcw.append("FORMAT/GT", val)
                     for field in format_fields:
                         val = variant.format(field.name)
                         tcw.append(field.full_name, val)

diff --git a/bio2zarr/vcf2zarr/vcz.py b/bio2zarr/vcf2zarr/vcz.py
@@ -321,7 +321,7 @@ def fixed_field_spec(
             array_specs.append(spec_from_field(field))
 
         if gt_field is not None:
-            ploidy = gt_field.summary.max_number - 1
+            ploidy = max(gt_field.summary.max_number - 1, 1)
             shape = [m, n]
             chunks = [variants_chunk_size, samples_chunk_size]
             dimensions = ["variants", "samples"]
@@ -728,9 +728,13 @@ def encode_genotypes_partition(self, partition_index):
         source_field = self.icf.fields["FORMAT/GT"]
         for value in source_field.iter_values(partition.start, partition.stop):
             j = gt.next_buffer_row()
-            icf.sanitise_value_int_2d(gt.buff, j, value[:, :-1])
+            icf.sanitise_value_int_2d(
+                gt.buff, j, value[:, :-1] if value is not None else None
+            )
             j = gt_phased.next_buffer_row()
-            icf.sanitise_value_int_1d(gt_phased.buff, j, value[:, -1])
+            icf.sanitise_value_int_1d(
+                gt_phased.buff, j, value[:, -1] if value is not None else None
+            )
             # TODO check is this the correct semantics when we are padding
             # with mixed ploidies?
             j = gt_mask.next_buffer_row()