aljaz/Tutorial-Codebase-Knowledge
1
0
Fork 0
mirror of https://github.com/aljazceru/Tutorial-Codebase-Knowledge.git synced 2025-12-18 23:14:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

Made the source argument mutually exclusive - you must specify either --repo or --dir

Browse Source 
Added a new crawl_local_files() function that mimics the interface of crawl_github_files()
Modified the FetchRepo node to handle both cases
Project name is now derived from either:
The repository name (from GitHub URL)
The directory name (from local path)
Or can be manually specified with -n/--name
The tool will use the same file pattern matching and size limits for both sources. All other functionality (generating abstractions, relationships, chapters, etc.) remains unchanged since they work with the same file list format.
This commit is contained in:
SpeedOfSpin
2025-04-08 18:27:32 +00:00
parent 60b5467f68
commit b6ab52aaa1
2 changed files with 114 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
main.py
View File

@@ -8,22 +8,27 @@ dotenv.load_dotenv()
# Default file patterns
DEFAULT_INCLUDE_PATTERNS = {
"*.py", "*.js", "*.ts", "*.go", "*.java", "*.pyi", "*.pyx",
"*.py", "*.js", "*.jsx", "*.ts", "*.tsx", "*.go", "*.java", "*.pyi", "*.pyx",
"*.c", "*.cc", "*.cpp", "*.h", "*.md", "*.rst", "Dockerfile",
"Makefile", "*.yaml", "*.yml"
"Makefile", "*.yaml", "*.yml",
}
DEFAULT_EXCLUDE_PATTERNS = {
"*test*", "tests/*", "docs/*", "examples/*", "v1/*",
"dist/*", "build/*", "experimental/*", "deprecated/*",
"legacy/*", ".git/*", ".github/*"
"legacy/*", ".git/*", ".github/*", ".next/*", ".vscode/*", "obj/*", "bin/*", "node_modules/*", "*.log"
}
# --- Main Function ---
def main():
parser = argparse.ArgumentParser(description="Generate a tutorial for a GitHub codebase.")
parser.add_argument("repo_url", help="URL of the public GitHub repository.")
parser.add_argument("-n", "--name", help="Project name (optional, derived from URL if omitted).")
parser = argparse.ArgumentParser(description="Generate a tutorial for a GitHub codebase or local directory.")
# Create mutually exclusive group for source
source_group = parser.add_mutually_exclusive_group(required=True)
source_group.add_argument("--repo", help="URL of the public GitHub repository.")
source_group.add_argument("--dir", help="Path to local directory.")
parser.add_argument("-n", "--name", help="Project name (optional, derived from repo/directory if omitted).")
parser.add_argument("-t", "--token", help="GitHub personal access token (optional, reads from GITHUB_TOKEN env var if not provided).")
parser.add_argument("-o", "--output", default="output", help="Base directory for output (default: ./output).")
parser.add_argument("-i", "--include", nargs="+", help="Include file patterns (e.g. '*.py' '*.js'). Defaults to common code files if not specified.")
@@ -32,14 +37,17 @@ def main():
args = parser.parse_args()
# Get GitHub token from argument or environment variable
github_token = args.token or os.environ.get('GITHUB_TOKEN')
if not github_token:
print("Warning: No GitHub token provided. You might hit rate limits for public repositories.")
# Get GitHub token from argument or environment variable if using repo
github_token = None
if args.repo:
github_token = args.token or os.environ.get('GITHUB_TOKEN')
if not github_token:
print("Warning: No GitHub token provided. You might hit rate limits for public repositories.")
# Initialize the shared dictionary with inputs
shared = {
"repo_url": args.repo_url,
"repo_url": args.repo,
"local_dir": args.dir,
"project_name": args.name, # Can be None, FetchRepo will derive it
"github_token": github_token,
"output_dir": args.output, # Base directory for CombineTutorial output
@@ -58,7 +66,7 @@ def main():
"final_output_dir": None
}
print(f"Starting tutorial generation for: {args.repo_url}")
print(f"Starting tutorial generation for: {args.repo or args.dir}")
# Create the flow instance
tutorial_flow = create_tutorial_flow()