Moved by tag from the fuzzy match group to exact match (#4481)

* Moved by tag from the regex group to exact matchch

* Added the test for frisby

* Run linter

catalog/dags/common/storage/media.py

@@ -16,13 +16,13 @@
     "no person",
     "squareformat",
     "undefined",
+    "by",
 }
 
 # Filter out tags that contain the following terms. All entrées should be lowercase.
 TAG_CONTAINS_DENYLIST = {
     ":",
     "=",
-    "by",
     "by-nc",
     "by-nc-nd",
     "by-nc-sa",

catalog/tests/dags/common/storage/test_media.py

@@ -565,8 +565,11 @@ def test_MediaStore_validates_filetype(filetype, url, expected_filetype):
             id="sort and enriches multiple tags",
         ),
         pytest.param(
-            ["cc0", "valid", "garbage:=metacrap", "uploaded:by=flickrmobile"],
-            [{"name": "valid", "provider": "test_provider"}],
+            ["cc0", "valid", "garbage:=metacrap", "uploaded:by=flickrmobile", "frisby"],
+            [
+                {"name": "frisby", "provider": "test_provider"},
+                {"name": "valid", "provider": "test_provider"},
+            ],
             id="exclude tags by the denylist",
         ),
         pytest.param("notalist", None, id="nonlist tags should be None"),

ingestion_server/ingestion_server/cleanup.py

@@ -29,6 +29,7 @@
     "uploaded:by=flickrmobile",
     "uploaded:by=instagram",
     "flickriosapp:filter=flamingo",
+    "by",
 }
 
 # Filter out tags that contain the following terms. All entrees should be
@@ -39,7 +40,6 @@
     ":",
     "=",
     "cc0",
-    "by",
     "by-nc",
     "by-nd",
     "by-sa",