Feat/find by germplasm and trait names (#62)

* Add generation of germplasm names list for studies

* Add traitNames field in datadiscovery

config/transform-elasticsearch/documents/datadiscovery_study.json

@@ -58,6 +58,10 @@
       "{flatten_distinct}": [
         "{.germplasmURIs => .accessionNumber}"
       ]
+    },"germplasmNames": {
+      "{flatten_distinct}": [
+        "{.germplasmURIs => .germplasmName}"
+      ]
     },
     "@id": "{.studyPUI}",
     "identifier": "{.studyDbId}",
@@ -183,6 +187,15 @@
         ]
       }
     },
+    "traitNames": {
+      "{list}": [
+            "{.observationVariableURIs => .observationVariableName + .name + .trait.name}"
+      ],
+      "{transform}": [
+        "flatten",
+        "distinct"
+      ]
+    },
     "node": "{.source}",
     "databaseName": {
       "{join}": [

config/transform-uri.json

@@ -1,7 +1,6 @@
 {
   "ignore-links": [
     "observation",
-    "observationVariable",
     "trait",
     "breedingMethod",
     "method",

tests/transform/integration/test_es_integration.py

@@ -118,3 +118,20 @@ def test_all_contacts_generated(self):
             expected_vib = json.load(expected_vib_f)
 
         self.assertEqual(DeepDiff(actual_vib, expected_vib), {})
+
+    def test_germplasNames_generated(self):
+        with gzip.open(self._actual_data_dir+"VIB/datadiscovery-1.json.gz") as actual_vib_f:
+            actual_vib = json.load(actual_vib_f)
+        for document_i in actual_vib:
+            if "studyType" in document_i:
+                self.assertTrue("germplasmNames" in document_i)
+
+    def test_traitNames_generated(self):
+        with gzip.open(self._actual_data_dir+"VIB/datadiscovery-1.json.gz") as actual_vib_f:
+            actual_vib = json.load(actual_vib_f)
+        for document_i in actual_vib:
+            if "studyType" in document_i:
+                self.assertTrue("traitNames" in document_i)
+                self.assertFalse(document_i["observationVariableDbIds"][0] in document_i["traitNames"])
+
+