Retrieve 'ProbeSet' trait name

Issue:
https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi

* gn3/db/traits.py: new function (retrieve_probeset_trait_name)
* tests/unit/db/test_traits.py: test(s) for new function

  Add a function to retrieve the name of a 'ProbeSet' trait in a manner
  similar to genenetwork1's retrieval of the same, as implemented here
  https://github.com/genenetwork/genenetwork1/blob/master/web/webqtl/base/webqtlDataset.py#L140-154

  Unlike in genenetwork1, we do not mutate an object, instead, we return the
  values as retrieved from the database, and the caller will deal with the
  returned values as appropriate.

2 files changed, 40 insertions, 0 deletions

diff --git a/gn3/db/traits.py b/gn3/db/traits.py
index 4860a07..37b111e 100644
--- a/gn3/db/traits.py
+++ b/gn3/db/traits.py
@@ -90,3 +90,21 @@ def insert_publication(pubmed_id: int, publication: Optional[Dict],
                          ", ".join(['%s'] * len(publication))))
         with conn.cursor() as cursor:
             cursor.execute(insert_query, tuple(publication.values()))
+
+def retrieve_probeset_trait_name(threshold, name, connection):
+    """
+    Retrieve the name for a Probeset trait
+
+    This is extracted from the `webqtlDataset.retrieveName` function,
+    specifically the section dealing with 'ProbeSet' type traits
+    https://github.com/genenetwork/genenetwork1/blob/master/web/webqtl/base/webqtlDataset.py#L140-154"""
+    query = (
+        'SELECT Id, Name, FullName, ShortName, DataScale '
+        'FROM ProbeSetFreeze '
+        'WHERE '
+        'public > %(threshold)s '
+        'AND '
+        '(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)')
+    with connection.cursor() as cursor:
+        cursor.execute(query, {"threshold": threshold, "name": name})
+        return cursor.fetchone()
diff --git a/tests/unit/db/test_traits.py b/tests/unit/db/test_traits.py
new file mode 100644
index 0000000..6d2ba4d
--- /dev/null
+++ b/tests/unit/db/test_traits.py
@@ -0,0 +1,22 @@
+"""Tests for gn3/db/traits.py"""
+from unittest import mock, TestCase
+from gn3.db.traits import retrieve_probeset_trait_name
+
+class TestTraitsDBFunctions(TestCase):
+    "Test cases for traits functions"
+
+    def test_retrieve_probeset_trait_name(self):
+        """Test that the function is called correctly."""
+        db_mock = mock.MagicMock()
+        with db_mock.cursor() as cursor:
+            cursor.fetchone.return_value = (
+                "testName", "testNameFull", "testNameShort", "dataScale")
+            self.assertEqual(
+                retrieve_probeset_trait_name(9, "testName", db_mock),
+                ("testName", "testNameFull", "testNameShort", "dataScale"))
+            cursor.execute.assert_called_once_with(
+                "SELECT Id, Name, FullName, ShortName, DataScale "
+                "FROM ProbeSetFreeze "
+                "WHERE public > %(threshold)s AND "
+                "(Name = %(name)s OR FullName = %(name)s OR ShortName = %(name)s)",
+                {"threshold": 9, "name": "testName"})