delete blank lines in v2 mapping; fix a bug in merging protein field …

…in v2 parser
biothings · Nov 3, 2023 · aee64e5 · aee64e5
1 parent 191878e
commit aee64e5
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 3 deletions.
diff --git a/src/hub/dataload/sources/dbnsfp/dbnsfp_mapping_44a_v2.py b/src/hub/dataload/sources/dbnsfp/dbnsfp_mapping_44a_v2.py
@@ -266,8 +266,6 @@
                     },
                 }
             },
-
-
             "cds_strand": {
                 "type": "keyword",
                 "normalizer": "keyword_lowercase_normalizer"

diff --git a/src/hub/dataload/sources/dbnsfp/dbnsfp_parser_44a_v2.py b/src/hub/dataload/sources/dbnsfp/dbnsfp_parser_44a_v2.py
@@ -874,7 +874,7 @@ def load_file(path: str, assembly: str):
                 # We guarantee that the protein field is always a list at this moment. See prune_protein()
                 # if not isinstance(last_protein_field, list):
                 #     last_protein_field = [last_protein_field]
-                last_protein_field.append(curr_protein_field)
+                last_protein_field.extend(curr_protein_field)
 
                 last_doc["dbnsfp"]["protein"] = last_protein_field
                 continue
-Original file line number
+Diff line change
@@ Expand Up / @@ -266,8 +266,6 @@ @@
                         },
                     }
                 },
                 "cds_strand": {
                     "type": "keyword",
                     "normalizer": "keyword_lowercase_normalizer"
@@ Expand Down @@