ref: Remove message similarity calculation

getsentry · Sep 19, 2024 · cbe15d8 · cbe15d8
1 parent 54117ec
commit cbe15d8
Showing 1 changed file with 2 additions and 9 deletions.
diff --git a/src/seer/grouping/grouping.py b/src/seer/grouping/grouping.py
@@ -1,4 +1,3 @@
-import difflib
 import gc
 import logging
 from functools import wraps
@@ -367,9 +366,6 @@ def get_nearest_neighbors(self, issue: GroupingRequest) -> SimilarityResponse:
 
  similarity_response = SimilarityResponse(responses=[])
  for record, distance in results:
- message_similarity_score = difflib.SequenceMatcher(
- None, issue.message, record.message
- ).ratio()
  should_group = distance <= issue.threshold
 
  if should_group:
@@ -387,7 +383,7 @@ def get_nearest_neighbors(self, issue: GroupingRequest) -> SimilarityResponse:
  GroupingResponse(
  parent_hash=record.hash,
  stacktrace_distance=distance,
- message_distance=1.0 - message_similarity_score,
+ message_distance=0.0,
  should_group=should_group,
  )
  )
@@ -443,13 +439,10 @@ def insert_batch_grouping_records(
 
  if nearest_neighbor:
  neighbor, distance = nearest_neighbor[0][0], nearest_neighbor[0][1]
- message_similarity_score = difflib.SequenceMatcher(
- None, entry.message, neighbor.message
- ).ratio()
  response = GroupingResponse(
  parent_hash=neighbor.hash,
  stacktrace_distance=distance,
- message_distance=1.0 - message_similarity_score,
+ message_distance=0.0,
  should_group=True,
  )
  groups_with_neighbor[str(entry.group_id)] = response