Add filter_description field

Author: tomwhite

bio2zarr/vcz.py

@@ -520,7 +520,7 @@ def init(
         # Doing this synchronously - this is fine surely
         self.encode_samples(root)
         if self.source.filters is not None:
-            self.encode_filter_id(root)
+            self.encode_filters(root)
         if self.source.contigs is not None:
             self.encode_contigs(root)
 
@@ -581,9 +581,7 @@ def encode_contigs(self, root):
             )
             array.attrs["_ARRAY_DIMENSIONS"] = ["contigs"]
 
-    def encode_filter_id(self, root):
-        # TODO need a way to store description also
-        # https://github.com/sgkit-dev/vcf-zarr-spec/issues/19
+    def encode_filters(self, root):
         filters = self.source.filters
         array = root.array(
             "filter_id",
@@ -593,6 +591,14 @@ def encode_filter_id(self, root):
             compressor=DEFAULT_ZARR_COMPRESSOR,
         )
         array.attrs["_ARRAY_DIMENSIONS"] = ["filters"]
+        array = root.array(
+            "filter_description",
+            data=[filt.description for filt in filters],
+            shape=len(filters),
+            dtype="str",
+            compressor=DEFAULT_ZARR_COMPRESSOR,
+        )
+        array.attrs["_ARRAY_DIMENSIONS"] = ["filters"]
 
     def init_array(self, root, array_spec, variants_dim_size):
         kwargs = dict(zarr_utils.ZARR_FORMAT_KWARGS)

tests/test_vcf_examples.py

@@ -30,6 +30,14 @@ def ds(self, tmp_path_factory):
 
     def test_filters(self, ds):
         nt.assert_array_equal(ds["filter_id"], ["PASS", "s50", "q10"])
+        nt.assert_array_equal(
+            ds["filter_description"],
+            [
+                "All filters passed",
+                "Less than 50% of samples have data",
+                "Quality below 10",
+            ],
+        )
         nt.assert_array_equal(
             ds["variant_filter"],
             [
@@ -957,6 +965,7 @@ def test_info_fields(self, ds):
             "contig_id",
             "contig_length",
             "filter_id",
+            "filter_description",
             "region_index",
             "sample_id",
         ]

tests/test_vcz.py

@@ -740,6 +740,7 @@ def test_vcz(self, zarr_path):
             "/sample_id",
             "/variant_id_mask",
             "/filter_id",
+            "/filter_description",
             "/contig_id",
         ]
         nt.assert_array_equal(sorted(df["name"]), sorted(fields))