Delete some unused methods, test top-level methods

Author: jeromekelleher

bio2zarr/vcf.py

@@ -118,9 +118,6 @@ def update(self, other):
         self.min_value = min(self.min_value, other.min_value)
         self.max_value = max(self.max_value, other.max_value)
 
-    def asdict(self):
-        return dataclasses.asdict(self)
-
 
 @dataclasses.dataclass
 class VcfField:
@@ -206,18 +203,6 @@ class VcfMetadata:
     contig_lengths: list = None
     partitions: list = None
 
-    @property
-    def fixed_fields(self):
-        return [field for field in self.fields if field.category == "fixed"]
-
-    @property
-    def info_fields(self):
-        return [field for field in self.fields if field.category == "INFO"]
-
-    @property
-    def format_fields(self):
-        return [field for field in self.fields if field.category == "FORMAT"]
-
     @staticmethod
     def fromdict(d):
         fields = [VcfField.fromdict(fd) for fd in d["fields"]]
@@ -445,10 +430,6 @@ def num_chunks(self, partition_index):
             self.partition_num_chunks[partition_index] = n
         return self.partition_num_chunks[partition_index]
 
-    def __repr__(self):
-        # TODO add class name
-        return repr({"path": str(self.path), **self.vcf_field.summary.asdict()})
-
     def chunk_path(self, partition_index, chunk_index):
         return self.path / f"p{partition_index}" / f"c{chunk_index}"
 
@@ -1299,7 +1280,7 @@ def to_zarr(
         zarr_path,
         conversion_spec=spec,
         worker_processes=worker_processes,
-        show_progress=True,
+        show_progress=show_progress,
     )
 
 

tests/test_vcf.py

@@ -284,6 +284,20 @@ def test_worker_processes(self, ds, tmp_path, worker_processes):
         ds2 = sg.load_dataset(out)
         xt.assert_equal(ds, ds2)
 
+    @pytest.mark.parametrize("worker_processes", [0, 1, 2])
+    def test_full_pipeline(self, ds, tmp_path, worker_processes):
+        exploded = tmp_path / "example.exploded"
+        vcf.explode(
+            [self.data_path], exploded, worker_processes=worker_processes,
+        )
+        schema = tmp_path / "schema.json"
+        with open(schema, "w") as f:
+            vcf.generate_spec(exploded, f)
+        out = tmp_path / "example.zarr"
+        vcf.to_zarr(exploded, out, schema, worker_processes=worker_processes)
+        ds2 = sg.load_dataset(out)
+        xt.assert_equal(ds, ds2)
+
 
 @pytest.mark.parametrize(
     "name",