⚡️ Speed up method CodeCommitProvider._get_language_percentages by 68%

pr_agent/git_providers/codecommit_provider.py

@@ -1,6 +1,5 @@
 import os
 import re
-from collections import Counter
 from typing import List, Optional, Tuple
 from urllib.parse import urlparse
 
@@ -76,7 +75,7 @@ def is_supported(self, capability: str) -> bool:
             "create_inline_comment",
             "publish_inline_comments",
             "get_labels",
-            "gfm_markdown"
+            "gfm_markdown",
         ]:
             return False
         return True
@@ -91,13 +90,19 @@ def get_files(self) -> list[CodeCommitFile]:
             return self.git_files
 
         self.git_files = []
-        differences = self.codecommit_client.get_differences(self.repo_name, self.pr.destination_commit, self.pr.source_commit)
+        differences = self.codecommit_client.get_differences(
+            self.repo_name, self.pr.destination_commit, self.pr.source_commit
+        )
         for item in differences:
-            self.git_files.append(CodeCommitFile(item.before_blob_path,
-                                                 item.before_blob_id,
-                                                 item.after_blob_path,
-                                                 item.after_blob_id,
-                                                 CodeCommitProvider._get_edit_type(item.change_type)))
+            self.git_files.append(
+                CodeCommitFile(
+                    item.before_blob_path,
+                    item.before_blob_id,
+                    item.after_blob_path,
+                    item.after_blob_id,
+                    CodeCommitProvider._get_edit_type(item.change_type),
+                )
+            )
         return self.git_files
 
     def get_diff_files(self) -> list[FilePatchInfo]:
@@ -121,15 +126,18 @@ def get_diff_files(self) -> list[FilePatchInfo]:
             if diff_item.a_blob_id is not None:
                 patch_filename = diff_item.a_path
                 original_file_content_str = self.codecommit_client.get_file(
-                    self.repo_name, diff_item.a_path, self.pr.destination_commit)
+                    self.repo_name, diff_item.a_path, self.pr.destination_commit
+                )
                 if isinstance(original_file_content_str, (bytes, bytearray)):
                     original_file_content_str = original_file_content_str.decode("utf-8")
             else:
                 original_file_content_str = ""
 
             if diff_item.b_blob_id is not None:
                 patch_filename = diff_item.b_path
-                new_file_content_str = self.codecommit_client.get_file(self.repo_name, diff_item.b_path, self.pr.source_commit)
+                new_file_content_str = self.codecommit_client.get_file(
+                    self.repo_name, diff_item.b_path, self.pr.source_commit
+                )
                 if isinstance(new_file_content_str, (bytes, bytearray)):
                     new_file_content_str = new_file_content_str.decode("utf-8")
             else:
@@ -144,9 +152,7 @@ def get_diff_files(self) -> list[FilePatchInfo]:
                 patch,
                 diff_item.b_path,
                 edit_type=diff_item.edit_type,
-                old_filename=None
-                if diff_item.a_path == diff_item.b_path
-                else diff_item.a_path,
+                old_filename=None if diff_item.a_path == diff_item.b_path else diff_item.a_path,
             )
             # Only add valid files to the diff list
             # "bad extensions" are set in the language_extensions.toml file
@@ -190,12 +196,16 @@ def publish_code_suggestions(self, code_suggestions: list) -> bool:
         for suggestion in code_suggestions:
             # Verify that each suggestion has the required keys
             if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
-                get_logger().warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
+                get_logger().warning(
+                    f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys"
+                )
                 continue
 
             # Publish the code suggestion to CodeCommit
             try:
-                get_logger().debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
+                get_logger().debug(
+                    f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}"
+                )
                 self.codecommit_client.publish_comment(
                     repo_name=self.repo_name,
                     pr_number=self.pr_num,
@@ -227,7 +237,9 @@ def remove_initial_comment(self):
     def remove_comment(self, comment):
         return ""  # not implemented yet
 
-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
+    def publish_inline_comment(
+        self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None
+    ):
         # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
         raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
 
@@ -257,7 +269,7 @@ def get_languages(self):
         - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
         """
         commit_files = self.get_files()
-        filenames = [ item.filename for item in commit_files ]
+        filenames = [item.filename for item in commit_files]
         extensions = CodeCommitProvider._get_file_extensions(filenames)
 
         # Calculate the percentage of each file extension in the PR
@@ -402,7 +414,7 @@ def _add_additional_newlines(body: str) -> str:
         Returns:
         - str: the PR body with the double newlines added
         """
-        return re.sub(r'(?<!\n)\n(?!\n)', '\n\n', body)
+        return re.sub(r"(?<!\n)\n(?!\n)", "\n\n", body)
 
     @staticmethod
     def _remove_markdown_html(comment: str) -> str:
@@ -488,10 +500,18 @@ def _get_language_percentages(extensions):
         if total_files == 0:
             return {}
 
-        # Identify language by file extension and count
-        lang_count = Counter(extensions)
-        # Convert counts to percentages
-        lang_percentage = {
-            lang: round(count / total_files * 100) for lang, count in lang_count.items()
-        }
+        # Optimization: Avoid Counter and one-pass dict accumulation,
+        # minimize rounding and float operations by deferring calculation
+        counts = {}
+        for ext in extensions:
+            counts[ext] = counts.get(ext, 0) + 1
+
+        inv_total = 100 / total_files  # hoist division for repeated use
+
+        lang_percentage = {}
+        for lang, count in counts.items():
+            # Use integer arithmetics as much as possible for speed
+            percent = round(count * inv_total)
+            lang_percentage[lang] = percent
+
         return lang_percentage