add tests for 1.2 and 2.0

biolink · May 13, 2024 · 7631465 · 7631465
1 parent 7843455
commit 7631465
Show file tree

Hide file tree

Showing 2 changed files with 55 additions and 9 deletions.
diff --git a/ontobio/io/entitywriter.py b/ontobio/io/entitywriter.py
@@ -139,6 +139,7 @@ def write_entity(self, entity):
             10. Properties <-- entity.properties
 
         """
+        print(entity.get('taxon'))
 
         if self.version == "2.0":
             vals = [
@@ -147,21 +148,23 @@ def write_entity(self, entity):
                 entity.get('full_name'),  # DB_Object_Name
                 entity.get('synonyms'),  # DB_Object_Synonyms
                 entity.get('type'),  # DB_Object_Type
-                normalize_taxon(entity["NCBITaxon"]["id"]),  # DB_Object_Taxon
+                normalize_taxon(entity.get("taxon").get("id")),  # DB_Object_Taxon
                 "",  # Encoded_by
                 entity.get('parents'),  # Parent_Protein
                 "",  # Protein_Containing_Complex_Members
                 entity.get('xrefs'),  # DB_Xrefs
                 entity.get('properties')  # Gene_Product_Properties
             ]
         else:
+            prefix, local_id = self._split_prefix(entity)
             vals = [
-                entity.get('id').split(":")[0],  # DB
-                entity.get('label').split(":")[1],  # DB_Object_ID
+                prefix,  # DB
+                local_id,  # DB_Object_ID
+                entity.get('label'),  # DB_Object_Symbol
                 entity.get('full_name'),  # DB_Object_Symbol
                 entity.get('synonyms'),  # DB_Object_Name
                 entity.get('type'),  # DB_Object_Synonyms
-                normalize_taxon(entity["NCBITaxon"]["id"]),  # DB_Object_Type
+                normalize_taxon(entity.get("taxon").get("id")),  # taxon
                 entity.get('parents'),  # Parent_Object_ID
                 entity.get('xrefs'),  # DB_Xref(s)
                 entity.get('properties')  # Properties

diff --git a/tests/test_gpiwriter.py b/tests/test_gpiwriter.py
@@ -3,14 +3,14 @@
 from ontobio.io import entitywriter, gafgpibridge
 
 
-def test_header_newline():
+def test_gpi_2_0_writer():
     gpi_obj = {
         'id': "MGI:MGI:1918911",
         'label': "0610005C13Rik",  # db_object_symbol,
         'full_name': "RIKEN cDNA 0610005C13 gene",  # db_object_name,
         'synonyms': [],
         'type': ["SO:0000000"],  # db_object_type,
-        'taxon': "NCBITaxon:10090",
+        'taxon': {"id": "NCBITaxon:10090"},
         'encoded_by': "", # encoded_by
         'parents': "",
         'protein_containing_complex_members': "", # protein_containing_complex_members
@@ -22,13 +22,56 @@ def test_header_newline():
     entity = gafgpibridge.Entity(gpi_obj)
 
     out = io.StringIO()
-    gpiwriter = entitywriter.GpiWriter(file=out)
-    gpiwriter.write_entity(entity)
+    gpiwriter20 = entitywriter.GpiWriter(file=out, version="2.0")
+    gpiwriter20.write_entity(entity)
     outlines = out.getvalue().split("\n")
 
     expected_lines = [
         "!gpi-version: 2.0",
-        "MGI:1918911\t0610005C13Rik\tRIKEN cDNA 0610005C13 gene\t\tSO:0000000\tNCBITaxon:10090\t\t\t\t\t",
+        "MGI:MGI:1918911\t0610005C13Rik\tRIKEN cDNA 0610005C13 gene\t\tSO:0000000\ttaxon:10090\t\t\t\t\t",
+        ""
+    ]
+    assert expected_lines == outlines
+
+    out = io.StringIO()
+    gpiwriter12 = entitywriter.GpiWriter(file=out, version="1.2")
+    gpiwriter12.write_entity(entity)
+    outlines = out.getvalue().split("\n")
+
+    expected_lines = [
+        "!gpi-version: 1.2",
+        "MGI\tMGI:1918911\t0610005C13Rik\tRIKEN cDNA 0610005C13 gene\t\tSO:0000000\ttaxon:10090\t\t\t\t\t",
+        ""
+    ]
+    assert expected_lines == outlines
+
+
+def test_gpi_1_2_writer():
+    gpi_obj = {
+        'id': "MGI:MGI:1918911",
+        'label': "0610005C13Rik",  # db_object_symbol,
+        'full_name': "RIKEN cDNA 0610005C13 gene",  # db_object_name,
+        'synonyms': [],
+        'type': ["SO:0000000"],  # db_object_type,
+        'taxon': {"id": "NCBITaxon:10090"},
+        'encoded_by': "", # encoded_by
+        'parents': "",
+        'protein_containing_complex_members': "", # protein_containing_complex_members
+        'xrefs': "",
+        'properties': ""
+
+    }
+
+    entity = gafgpibridge.Entity(gpi_obj)
+
+    out = io.StringIO()
+    gpiwriter20 = entitywriter.GpiWriter(file=out, version="1.2")
+    gpiwriter20.write_entity(entity)
+    outlines = out.getvalue().split("\n")
+
+    expected_lines = [
+        "!gpi-version: 1.2",
+        "MGI\tMGI:1918911\t0610005C13Rik\tRIKEN cDNA 0610005C13 gene\t\tSO:0000000\ttaxon:10090\t\t\t",
         ""
     ]
     assert expected_lines == outlines