Fix similarity datasets message name (#2804)

* Fix similarity datasets message name Spark reader expects the names to start with similarity instead of similar. * Fix similarity datasets message name - 2 Spark reader expects the names to start with similarity instead of similar.
metabrainz · Mar 2, 2024 · c8b5abf · c8b5abf
1 parent fdd045d
commit c8b5abf
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/listenbrainz_spark/similarity/artist.py b/listenbrainz_spark/similarity/artist.py
@@ -143,21 +143,21 @@ def main(days, session, contribution, threshold, limit, skip, is_production_data
 
     if is_production_dataset:
         yield {
-            "type": "similar_recordings_start",
+            "type": "similarity_artist_start",
             "algorithm": algorithm
         }
 
     for entries in chunked(data, RECORDINGS_PER_MESSAGE):
         items = [row.asDict() for row in entries]
         yield {
-            "type": "similar_artists",
+            "type": "similarity_artist",
             "algorithm": algorithm,
             "data": items,
             "is_production_dataset": is_production_dataset
         }
 
     if is_production_dataset:
         yield {
-            "type": "similar_recordings_end",
+            "type": "similarity_artist_end",
             "algorithm": algorithm
         }
diff --git a/listenbrainz_spark/similarity/recording.py b/listenbrainz_spark/similarity/recording.py
@@ -127,21 +127,21 @@ def main(days, session, contribution, threshold, limit, skip, is_production_data
 
     if is_production_dataset:
         yield {
-            "type": "similar_recordings_start",
+            "type": "similarity_recording_start",
             "algorithm": algorithm
         }
 
     for entries in chunked(data, RECORDINGS_PER_MESSAGE):
         items = [row.asDict() for row in entries]
         yield {
-            "type": "similar_recordings",
+            "type": "similarity_recording",
             "algorithm": algorithm,
             "data": items,
             "is_production_dataset": is_production_dataset
         }
 
     if is_production_dataset:
         yield {
-            "type": "similar_recordings_end",
+            "type": "similarity_recording_end",
             "algorithm": algorithm
         }