From 1eebb7c99918406dbe6a5e18e8fcc63d340d8cea Mon Sep 17 00:00:00 2001
From: Marco Cano <artofmarco@gmail.com>
Date: Tue, 30 Apr 2024 09:54:52 -0700
Subject: [PATCH 1/2] script to fix niaid datasets

---
 scripts/fix_niaid_datasets.py | 42 +++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 scripts/fix_niaid_datasets.py

diff --git a/scripts/fix_niaid_datasets.py b/scripts/fix_niaid_datasets.py
new file mode 100644
index 00000000..534a25ad
--- /dev/null
+++ b/scripts/fix_niaid_datasets.py
@@ -0,0 +1,42 @@
+import logging
+
+from discovery.model.dataset import Dataset
+
+niaidContext = {
+"schema": "http://schema.org/",
+"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
+"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
+"bioschemas": "https://discovery.biothings.io/view/bioschemas/",
+"niaid": "https://discovery.biothings.io/view/niaid/",
+"nde": "https://discovery.biothings.io/view/nde/"
+}
+
+def updateContext():
+    """
+    Update datasets missing @context and update @types with outdated names
+    """
+    ids = []
+    needs_renaming =[]
+    docs = Dataset.search()
+    for doc in docs.scan():
+        d = doc.to_dict()
+        context = d.get("@context")
+        datasetID = getattr(getattr(doc, 'meta', None), 'id', None)
+        typ = getattr(doc, "@type", None)
+        if not context:
+            ids.append(datasetID)
+            # doc.update(**{"@context": niaidContext})
+        if 'niaid:Niaid' in typ:
+            needs_renaming.append(typ)
+            # doc.update(**{"@type": "niaid:Dataset"})
+
+    print(len(ids))
+    print(ids)
+    print("++++++++++++++++++")
+    print(len(needs_renaming))
+    print(needs_renaming)
+
+
+
+if __name__ == "__main__":
+    updateContext()

From 10590ce23fd25333d3356cf11339ba3f141081be Mon Sep 17 00:00:00 2001
From: Marco Cano <artofmarco@gmail.com>
Date: Thu, 2 May 2024 14:16:24 -0700
Subject: [PATCH 2/2] feat: :sparkles: add script to fix niaid datasets missing
 context

---
 scripts/fix_niaid_datasets.py | 46 +++++++++++++++++++----------------
 1 file changed, 25 insertions(+), 21 deletions(-)

diff --git a/scripts/fix_niaid_datasets.py b/scripts/fix_niaid_datasets.py
index 534a25ad..282328ed 100644
--- a/scripts/fix_niaid_datasets.py
+++ b/scripts/fix_niaid_datasets.py
@@ -1,40 +1,44 @@
-import logging
-
 from discovery.model.dataset import Dataset
 
 niaidContext = {
 "schema": "http://schema.org/",
 "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
 "rdfs": "http://www.w3.org/2000/01/rdf-schema#",
-"bioschemas": "https://discovery.biothings.io/view/bioschemas/",
-"niaid": "https://discovery.biothings.io/view/niaid/",
-"nde": "https://discovery.biothings.io/view/nde/"
+"bioschemas": "https://discovery.biothings.io/ns/bioschemas/",
+"niaid": "https://discovery.biothings.io/ns/niaid/",
 }
 
 def updateContext():
     """
     Update datasets missing @context and update @types with outdated names
     """
-    ids = []
-    needs_renaming =[]
+    # ids = []
+    # needs_renaming =[]
     docs = Dataset.search()
     for doc in docs.scan():
-        d = doc.to_dict()
-        context = d.get("@context")
-        datasetID = getattr(getattr(doc, 'meta', None), 'id', None)
-        typ = getattr(doc, "@type", None)
+        context = getattr(doc, '@context', None)
+        # dataset_id = getattr(getattr(doc, 'meta', None), 'id', None)
+        clss_type = getattr(doc, "@type", None)
         if not context:
-            ids.append(datasetID)
-            # doc.update(**{"@context": niaidContext})
-        if 'niaid:Niaid' in typ:
-            needs_renaming.append(typ)
-            # doc.update(**{"@type": "niaid:Dataset"})
+            if ":" not in clss_type:
+                # add context and fix class name
+                added_prefix = "niaid:" + clss_type
+                # ids.append(added_prefix)
+                doc.update(**{"@context": niaidContext, "@type": added_prefix})
+            else:
+                # add context
+                # ids.append('JUST CONTEXT')
+                doc.update(**{"@context": niaidContext})
+        if 'niaid:Niaid' in clss_type:
+            updated_name = clss_type.replace("niaid:Niaid", "niaid:")
+            # needs_renaming.append(clss_type + " >>> " + updated_name)
+            doc.update(**{"@type": updated_name})
 
-    print(len(ids))
-    print(ids)
-    print("++++++++++++++++++")
-    print(len(needs_renaming))
-    print(needs_renaming)
+    # print(len(ids))
+    # print(ids)
+    # print("++++++++++++++++++")
+    # print(len(needs_renaming))
+    # print(needs_renaming)