Use str dtype

Author: tomwhite

bio2zarr/vcf2zarr/icf.py

@@ -99,7 +99,7 @@ def smallest_dtype(self):
             ret = "U1"
         else:
             assert self.vcf_type == "String"
-            ret = "O"
+            ret = "str"
         return ret
 
 

bio2zarr/vcf2zarr/vcz.py

@@ -288,14 +288,14 @@ def fixed_field_spec(
             ),
             fixed_field_spec(
                 name="variant_allele",
-                dtype="O",
+                dtype="str",
                 shape=(m, max_alleles),
                 dimensions=["variants", "alleles"],
                 chunks=(variants_chunk_size, max_alleles),
             ),
             fixed_field_spec(
                 name="variant_id",
-                dtype="O",
+                dtype="str",
             ),
             fixed_field_spec(
                 name="variant_id_mask",
@@ -399,9 +399,11 @@ def summary_table(self):
                 "avg_chunk_stored": core.display_size(int(stored / array.nchunks)),
                 "shape": str(array.shape),
                 "chunk_shape": str(array.chunks),
-                "compressor": str(array.compressor),
-                "filters": str(array.filters),
             }
+            if hasattr(array, "compressor"):
+                d["compressor"] = array.compressor
+            if hasattr(array, "filters"):
+                d["filters"] = array.filters
             data.append(d)
         return data