Merge pull request #1133 from Codium-ai/tr/err_protections

Add error handling for empty diff files in utils.py and optimize file…
qodo-ai · Aug 13, 2024 · 672cdc0 · 672cdc0
2 parents 7ac9f27 + 86a9cfe
commit 672cdc0
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 6 deletions.
diff --git a/pr_agent/algo/utils.py b/pr_agent/algo/utils.py
@@ -781,6 +781,9 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
     re_hunk_header = re.compile(
         r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
 
+    if not diff_files:
+        return position, absolute_position
+
     for file in diff_files:
         if file.filename and (file.filename.strip() == relevant_file):
             patch = file.patch

diff --git a/pr_agent/git_providers/bitbucket_provider.py b/pr_agent/git_providers/bitbucket_provider.py
@@ -12,7 +12,7 @@
 from ..algo.utils import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
-from .git_provider import GitProvider
+from .git_provider import GitProvider, MAX_FILES_ALLOWED_FULL
 
 
 def _gef_filename(diff):
@@ -198,20 +198,30 @@ def get_diff_files(self) -> list[FilePatchInfo]:
 
         invalid_files_names = []
         diff_files = []
+        counter_valid = 0
         for index, diff in enumerate(diffs):
             file_path = _gef_filename(diff)
             if not is_valid_file(file_path):
                 invalid_files_names.append(file_path)
                 continue
 
             try:
-                if diff.old.get_data("links"):
-                    original_file_content_str = self._get_pr_file_content(diff.old.get_data("links")['self']['href'])
+                counter_valid += 1
+                if counter_valid < MAX_FILES_ALLOWED_FULL // 2:  # factor 2 because bitbucket has limited API calls
+                    if diff.old.get_data("links"):
+                        original_file_content_str = self._get_pr_file_content(
+                            diff.old.get_data("links")['self']['href'])
+                    else:
+                        original_file_content_str = ""
+                    if diff.new.get_data("links"):
+                        new_file_content_str = self._get_pr_file_content(diff.new.get_data("links")['self']['href'])
+                    else:
+                        new_file_content_str = ""
                 else:
+                    if counter_valid == MAX_FILES_ALLOWED_FULL // 2:
+                        get_logger().info(
+                            f"Bitbucket too many files in PR, will avoid loading full content for rest of files")
                     original_file_content_str = ""
-                if diff.new.get_data("links"):
-                    new_file_content_str = self._get_pr_file_content(diff.new.get_data("links")['self']['href'])
-                else:
                     new_file_content_str = ""
             except Exception as e:
                 get_logger().exception(f"Error - bitbucket failed to get file content, error: {e}")