Merge pull request #1349 from oraios/fix-duplicated-yaml-comments

Fix duplicated YAML comments

Author: opcode81

CHANGELOG.md

@@ -5,6 +5,7 @@ Status of the `main` branch. Changes prior to the next official version change w
 * General:
   - Support `serena --version` CLI command for displaying the current version #1347
   - Fix: Check for ignored path ignored `.git` folder only at the top level, not in every subdirectory (`Project._is_ignored_relative_path`) #1350
+  - Fix: Duplicate comments in re-saved YAML configuration files #1285
 
 # v1.1.2 (2026-04-14)
 

src/serena/config/serena_config.py

@@ -31,7 +31,7 @@
     SERENA_MANAGED_DIR_NAME,
 )
 from serena.util.inspection import determine_programming_language_composition
-from serena.util.yaml import YamlCommentNormalisation, load_yaml, normalise_yaml_comments, save_yaml, transfer_missing_yaml_comments
+from serena.util.yaml import YamlCommentNormalisation, load_yaml, normalise_yaml_comments, save_yaml, transfer_yaml_comments
 from solidlsp.ls_config import Language
 
 from ..analytics import RegisteredTokenCountEstimator
@@ -581,7 +581,7 @@ def save(self, project_yml_path: str, save_project_local_yml: bool = True) -> No
 
         # transfer missing comments from the template file
         template_config, _ = self._load_yaml_dict(PROJECT_TEMPLATE_FILE, self.YAML_COMMENT_NORMALISATION)
-        transfer_missing_yaml_comments(template_config, config_with_comments, self.YAML_COMMENT_NORMALISATION, force_update_all=True)
+        transfer_yaml_comments(template_config, config_with_comments, self.YAML_COMMENT_NORMALISATION, force_update_all=True)
 
         # save project.yml
         save_yaml(config_path, config_with_comments)
@@ -1063,7 +1063,7 @@ def save(self) -> None:
         # For some keys, we force updates, because old comments are problematic/misleading.
         normalise_yaml_comments(commented_yaml, YamlCommentNormalisation.LEADING_WITH_CONVERSION_FROM_TRAILING)
         template_yaml = load_yaml(SERENA_CONFIG_TEMPLATE_FILE, comment_normalisation=YamlCommentNormalisation.LEADING)
-        transfer_missing_yaml_comments(template_yaml, commented_yaml, YamlCommentNormalisation.LEADING, force_update_all=True)
+        transfer_yaml_comments(template_yaml, commented_yaml, YamlCommentNormalisation.LEADING, force_update_all=True)
 
         save_yaml(self.config_file_path, commented_yaml)
 

src/serena/util/yaml.py

@@ -4,7 +4,7 @@
 from enum import Enum
 from typing import Any
 
-from ruamel.yaml import YAML, CommentToken, StreamMark
+from ruamel.yaml import YAML, CommentedSeq, CommentToken, StreamMark
 from ruamel.yaml.comments import CommentedMap
 
 from serena.constants import SERENA_FILE_ENCODING
@@ -122,6 +122,20 @@ def trailing_to_leading(comment_entry: Any) -> Any:
                 first_token.value = first_token.value[1:]
         return token_list
 
+    def remove_nested_comments() -> None:
+        """
+        Removes nested comments, particularly of sequences, which incorrectly capture comments
+        that are actually intended for top-level keys.
+        """
+        for key in commented_map.keys():
+            entry = commented_map[key]
+            if isinstance(entry, CommentedSeq):
+                items = entry.ca.items
+                if isinstance(items, dict):
+                    items_keys = list(items.keys())
+                    for i in items_keys:
+                        items[i] = [None] * 4
+
     match comment_normalisation:
         case YamlCommentNormalisation.NONE:
             pass
@@ -176,6 +190,9 @@ def trailing_to_leading(comment_entry: Any) -> Any:
                                     preceding_comment[ITEM_COMMENT_INDEX_BEFORE] = token_list
                                     current_comment[ITEM_COMMENT_INDEX_BEFORE] = None
                     preceding_comment = current_comment
+
+            # remove nested comments, as we assume that only top-level keys are supposed to be commented
+            remove_nested_comments()
         case _:
             raise ValueError(f"Unhandled comment normalisation: {comment_normalisation}")
 
@@ -204,7 +221,7 @@ def yaml_comment_entry_is_empty(comment_entry: Any) -> bool:
         return False
 
 
-def transfer_missing_yaml_comments_by_index(
+def transfer_yaml_comments_by_index(
     source: CommentedMap, target: CommentedMap, indices: list[int], forced_update_keys: Sequence[str] = (), force_update_all: bool = False
 ) -> None:
     """
@@ -231,7 +248,7 @@ def transfer_missing_yaml_comments_by_index(
                     target_comment[index] = source_comment[index]
 
 
-def transfer_missing_yaml_comments(
+def transfer_yaml_comments(
     source: CommentedMap,
     target: CommentedMap,
     comment_normalisation: YamlCommentNormalisation,
@@ -251,7 +268,7 @@ def transfer_missing_yaml_comments(
         case YamlCommentNormalisation.NONE:
             pass
         case YamlCommentNormalisation.LEADING | YamlCommentNormalisation.LEADING_WITH_CONVERSION_FROM_TRAILING:
-            transfer_missing_yaml_comments_by_index(
+            transfer_yaml_comments_by_index(
                 source, target, [ITEM_COMMENT_INDEX_BEFORE], forced_update_keys=forced_update_keys, force_update_all=force_update_all
             )
         case _: