Add iter_filters

Author: benjeffery

bio2zarr/vcf2zarr/icf.py

@@ -927,6 +927,22 @@ def iter_id(self, start, stop):
             else:
                 yield None
 
+    def iter_filters(self, start, stop):
+        source_field = self.fields["FILTERS"]
+        lookup = {filt.id: index for index, filt in enumerate(self.metadata.filters)}
+
+        for filter_values in source_field.iter_values(start, stop):
+            filters = np.zeros(len(self.metadata.filters), dtype=bool)
+            if filter_values is not None:
+                for filter_id in filter_values:
+                    try:
+                        filters[lookup[filter_id]] = True
+                    except KeyError:
+                        raise ValueError(
+                            f"Filter '{filter_id}' was not defined in the header."
+                        ) from None
+            yield filters
+
     def iter_field(self, field_name, shape, start, stop):
         source_field = self.fields[field_name]
         sanitiser = source_field.sanitiser_factory(shape)

bio2zarr/writer.py

@@ -547,21 +547,12 @@ def encode_id_partition(self, partition_index):
         self.finalise_partition_array(partition_index, vid_mask)
 
     def encode_filters_partition(self, partition_index):
-        lookup = {filt.id: index for index, filt in enumerate(self.schema.filters)}
         var_filter = self.init_partition_array(partition_index, "variant_filter")
         partition = self.metadata.partitions[partition_index]
 
-        field = self.source.fields["FILTERS"]
-        for value in field.iter_values(partition.start, partition.stop):
+        for filter_values in self.source.iter_filters(partition.start, partition.stop):
             j = var_filter.next_buffer_row()
-            var_filter.buff[j] = False
-            for f in value:
-                try:
-                    var_filter.buff[j, lookup[f]] = True
-                except KeyError:
-                    raise ValueError(
-                        f"Filter '{f}' was not defined in the header."
-                    ) from None
+            var_filter.buff[j] = filter_values
 
         self.finalise_partition_array(partition_index, var_filter)