Created
July 15, 2023 21:49
-
-
Save ondrejsojka/61abd5edd8999f45c5cc87cc5a07a7e6 to your computer and use it in GitHub Desktop.
This script concats all of a git repository into one .txt file, perfect for supplying as context to Claude or for integration with other LLMs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import sys | |
import pathspec | |
def load_gitignore(root_dir): | |
gitignore = os.path.join(root_dir, '.gitignore') | |
if os.path.exists(gitignore): | |
with open(gitignore, 'r') as file: | |
spec = pathspec.PathSpec.from_lines('gitwildmatch', file) | |
else: | |
spec = pathspec.PathSpec.from_lines('gitwildmatch', []) | |
return spec | |
def concatenate_files(root_dir, output_file_path): | |
ignore_spec = load_gitignore(root_dir) | |
with open(output_file_path, 'w') as output_file: | |
for root, dirs, files in os.walk(root_dir): | |
dirs[:] = [d for d in dirs if not d.startswith('.git')] | |
for file in files: | |
file_path = os.path.join(root, file) | |
if ignore_spec.match_file(file_path): | |
continue | |
relative_path = os.path.relpath(file_path, root_dir) | |
output_file.write(f'---\n{relative_path}\n') | |
with open(file_path, 'r', errors='ignore') as input_file: | |
output_file.write(input_file.read()) | |
output_file.write('\n') | |
root_dir = sys.argv[1] | |
output_file_path = sys.argv[2] | |
concatenate_files(root_dir, output_file_path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment