Skip to content

Speed up directory tree generation #736

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
EdwardJXLi merged 2 commits into from
Mar 4, 2025
Merged

Speed up directory tree generation #736

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d75f441
Remove unnecessary graph pull for build directory tree
EdwardJXLi Mar 4, 2025
03f7fbe
Skip file read when parsing dir tree
EdwardJXLi Mar 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions src/codegen/git/repo_operator/repo_operator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -616,6 +616,7 @@ def iter_files(
subdirs: list[str] | None = None,
extensions: list[str] | None = None,
ignore_list: list[str] | None = None,
skip_content: bool = False,
) -> Generator[tuple[str, str]]:
"""Iterates over all files in the codebase, yielding the filepath and its content.

Expand All @@ -642,8 +643,11 @@ def iter_files(

if extensions is None or any(filepath.endswith(e) for e in extensions):
try:
content = self.get_file(filepath)
yield rel_filepath, content
if not skip_content:
content = self.get_file(filepath)
yield rel_filepath, content
else:
yield rel_filepath, ""
except Exception as e:
logger.warning(f"Error reading file {filepath}: {e}")

Expand Down
7 changes: 5 additions & 2 deletions src/codegen/sdk/codebase/codebase_context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,11 @@ def build_directory_tree(self) -> None:
# Reset and rebuild the directory tree
self.directories = dict()

for file_path, _ in self.projects[0].repo_operator.iter_files(subdirs=self.projects[0].subdirectories, ignore_list=GLOBAL_FILE_IGNORE_LIST):
for file_path, _ in self.projects[0].repo_operator.iter_files(
subdirs=self.projects[0].subdirectories,
ignore_list=GLOBAL_FILE_IGNORE_LIST,
skip_content=True,
):
file_path = Path(file_path)
directory = self.get_directory(file_path.parent, create_on_missing=True)
directory._add_file(file_path.name)
Expand Down Expand Up @@ -510,7 +514,6 @@ def _process_diff_files(self, files_to_sync: Mapping[SyncType, list[Path]], incr

# Step 6: Build directory tree
logger.info("> Building directory tree")
files = [f for f in sort_editables(self.get_nodes(NodeType.FILE), alphabetical=True, dedupe=False)]
self.build_directory_tree()

# Step 7: Build configs
Expand Down
Loading