s

pr_agent/git_providers/git_provider.py

@@ -1,5 +1,6 @@
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
+from pr_agent.algo.language_handler import language_extension_map
 
 # enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
 from enum import Enum
@@ -173,26 +174,39 @@ def get_main_pr_language(languages, files) -> str:
             extension_list.append(file.filename.rsplit('.')[-1])
 
         # get the most common extension
-        most_common_extension = max(set(extension_list), key=extension_list.count)
+        most_common_extension = '.' + max(set(extension_list), key=extension_list.count)
-
+        try:
-        # look for a match. TBD: add more languages, do this systematically
+            if top_language in language_extension_map and most_common_extension in language_extension_map[top_language]:
-        if most_common_extension == 'py' and top_language == 'python' or \
-                most_common_extension == 'js' and top_language == 'javascript' or \
-                most_common_extension == 'ts' and top_language == 'typescript' or \
-                most_common_extension == 'go' and top_language == 'go' or \
-                most_common_extension == 'java' and top_language == 'java' or \
-                most_common_extension == 'c' and top_language == 'c' or \
-                most_common_extension == 'cpp' and top_language == 'c++' or \
-                most_common_extension == 'cs' and top_language == 'c#' or \
-                most_common_extension == 'swift' and top_language == 'swift' or \
-                most_common_extension == 'php' and top_language == 'php' or \
-                most_common_extension == 'rb' and top_language == 'ruby' or \
-                most_common_extension == 'rs' and top_language == 'rust' or \
-                most_common_extension == 'scala' and top_language == 'scala' or \
-                most_common_extension == 'kt' and top_language == 'kotlin' or \
-                most_common_extension == 'pl' and top_language == 'perl' or \
-                most_common_extension == top_language:
                 main_language_str = top_language
+            else:
+                for language, extensions in language_extension_map.items():
+                    if most_common_extension in extensions:
+                        main_language_str = language
+                        break
+        except Exception as e:
+            get_logger().exception(f"Failed to get main language: {e}")
+            pass
+
+        ## old approach:
+        # most_common_extension = max(set(extension_list), key=extension_list.count)
+        # if most_common_extension == 'py' and top_language == 'python' or \
+        #         most_common_extension == 'js' and top_language == 'javascript' or \
+        #         most_common_extension == 'ts' and top_language == 'typescript' or \
+        #         most_common_extension == 'tsx' and top_language == 'typescript' or \
+        #         most_common_extension == 'go' and top_language == 'go' or \
+        #         most_common_extension == 'java' and top_language == 'java' or \
+        #         most_common_extension == 'c' and top_language == 'c' or \
+        #         most_common_extension == 'cpp' and top_language == 'c++' or \
+        #         most_common_extension == 'cs' and top_language == 'c#' or \
+        #         most_common_extension == 'swift' and top_language == 'swift' or \
+        #         most_common_extension == 'php' and top_language == 'php' or \
+        #         most_common_extension == 'rb' and top_language == 'ruby' or \
+        #         most_common_extension == 'rs' and top_language == 'rust' or \
+        #         most_common_extension == 'scala' and top_language == 'scala' or \
+        #         most_common_extension == 'kt' and top_language == 'kotlin' or \
+        #         most_common_extension == 'pl' and top_language == 'perl' or \
+        #         most_common_extension == top_language:
+        #     main_language_str = top_language
 
     except Exception as e:
         get_logger().exception(e)

pr_agent/settings/pr_add_docs.toml

@@ -103,7 +103,7 @@ Description: '{{description}}'
 
 {%- if language %}
 
-Main language: {{language}}
+Main PR language: '{{language}}'
 {%- endif %}
 
 

pr_agent/settings/pr_description_prompts.toml

@@ -2,8 +2,8 @@
 system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
 Your task is to provide full description of a Pull Request (PR) content.
 - Make sure to focus on the new PR code (the '+' lines).
-- Notice that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or not up-to-date. Hence, compare them to the PR diff code, and use them only as a reference.
+- Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
-- Emphasize first the most important changes, and then the less important ones.
+- Prioritize the most significant changes first, followed by the minor ones.
 - If needed, each YAML output should be in block scalar format ('|-')
 {%- if extra_instructions %}
 
@@ -68,12 +68,15 @@ Answer should be a valid YAML, and nothing else. Each YAML output MUST be after
 """
 
 user="""PR Info:
+
 Previous title: '{{title}}'
+
 Previous description: '{{description}}'
+
 Branch: '{{branch}}'
 {%- if language %}
 
-Main language: {{language}}
+Main PR language: '{{ language }}'
 {%- endif %}
 {%- if commit_messages_str %}