Force haploids to always be phased

Closes #399

Author: jeromekelleher

bio2zarr/vcf.py

@@ -1051,6 +1051,10 @@ def iter_genotypes(self, shape, start, stop):
             phased = value[:, -1] if value is not None else None
             sanitised_genotypes = sanitise_value_int_2d(shape, genotypes)
             sanitised_phased = sanitise_value_int_1d(shape[:-1], phased)
+            # Force haploids to always be phased
+            # https://github.com/sgkit-dev/bio2zarr/issues/399
+            if sanitised_genotypes.shape[1] == 1:
+                sanitised_phased[:] = True
             yield sanitised_genotypes, sanitised_phased
 
     def iter_alleles_and_genotypes(self, start, stop, shape, num_alleles):

tests/test_simulated_data.py

@@ -3,6 +3,7 @@
 import pysam
 import pytest
 import sgkit as sg
+import numpy as np
 
 from bio2zarr import vcf as vcf_mod
 
@@ -32,6 +33,9 @@ def assert_ts_ds_equal(ts, ds, ploidy=1):
         ts.genotype_matrix().reshape((ts.num_sites, ts.num_individuals, ploidy)),
         ds.call_genotype.values,
     )
+    nt.assert_array_equal(
+        ds.call_genotype_phased.values,
+        np.ones((ts.num_sites, ts.num_individuals), dtype=bool))
     nt.assert_equal(ds.variant_allele[:, 0].values, "A")
     nt.assert_equal(ds.variant_allele[:, 1].values, "T")
     nt.assert_equal(ds.variant_position, ts.sites_position)