feat: Set up pre-commit hooks and collect documentation files

- Add GitHub Actions workflow for linting code
- Update .gitignore to exclude logs directory
- Configure pre-commit hooks for code formatting and linting
- Refactor main.py:
  - Extract codebase directory validation to separate function
  - Implement collect_documentation_files function to gather .md and .txt files
  - Skip files and directories specified in .gitignore
  - Add logging and setup logger
- Update main function to handle CLI arguments and call collect_documentation_files

.github/workflows/lint.yml

@@ -0,0 +1,20 @@
+---
+name: Lint code
+
+on: [push, pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    runs-on: ubuntu-20.04
+    timeout-minutes: 10
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Run pre-commit
+      uses: pre-commit/[email protected]

.gitignore

@@ -1,2 +1,3 @@
-.venv
-**/__pycache__
+/.venv
+**/__pycache__
+/logs

.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+    - id: check-yaml
+    - id: debug-statements
+    - id: end-of-file-fixer
+    - id: trailing-whitespace
+
+  - repo: https://github.com/psf/black
+    rev: 24.4.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort

main.py

@@ -1,46 +1,85 @@
-""" 1. The directory path of the codebase to be analyzed
-2. The output directory for the generated reports
-
-To implement this step, we'll break it down into smaller tasks:
-
-1. Create a command-line interface (CLI) for the program
-2. Prompt the user to enter the codebase directory path
-3. Validate the provided codebase directory path
-4. Prompt the user to enter the output directory path
-5. Validate the provided output directory path
-6. Store the user input for later use in the program """
-
 import argparse
 import os
 
+from codypy import log_message, setup_logger
+from pathspec import PathSpec
+
+
 def validate_codebase_dir(codebase_dir):
     if not os.path.exists(codebase_dir):
-        raise argparse.ArgumentTypeError(f"Codebase directory '{codebase_dir}' does not exist.")
-
-    git_dir = os.path.join(codebase_dir, '.git')
+        raise argparse.ArgumentTypeError(
+            f"Codebase directory '{codebase_dir}' does not exist."
+        )
+
+    git_dir = os.path.join(codebase_dir, ".git")
     if not os.path.isdir(git_dir):
-        raise argparse.ArgumentTypeError(f"Codebase directory '{codebase_dir}' is not a local GitHub repository.")
-
+        raise argparse.ArgumentTypeError(
+            f"Codebase directory '{codebase_dir}' is not a local GitHub repository."
+        )
+
     return codebase_dir
 
-def main():
-    # Create a command-line interface (CLI) for the program
-    parser = argparse.ArgumentParser(description='CodyArchitect')
-    parser.add_argument('codebase_dir', type=validate_codebase_dir, help='Path to the codebase directory')
-    parser.add_argument('--output_dir', '-o', help='Path to the output directory for generated reports')
-
-    # Prompt the user to enter the codebase directory path
-    args = parser.parse_args()
-
-    # Store the user input for later use in the program
-    codebase_dir = args.codebase_dir
-    output_dir = args.output_dir
-
+
+def collect_documentation_files(codebase_dir):
+    documentation_files = []
+    gitignore_path = os.path.join(codebase_dir, ".gitignore")
+    gitignore_spec = None
+
+    if os.path.exists(gitignore_path):
+        with open(gitignore_path, "r") as gitignore_file:
+            gitignore_spec = PathSpec.from_lines("gitwildmatch", gitignore_file)
+
+    for root, dirs, files in os.walk(codebase_dir):
+        if gitignore_spec:
+            dirs[:] = [
+                d for d in dirs if not gitignore_spec.match_file(os.path.join(root, d))
+            ]
+
+        for file in files:
+            file_path = os.path.join(root, file)
+            if gitignore_spec and gitignore_spec.match_file(file_path):
+                continue
+
+            if file.endswith(".md") or file.endswith(".txt"):
+                documentation_files.append(file_path)
+
+    return documentation_files
+
+
+def main(codebase_dir=None, output_dir=None):
+    if codebase_dir is None:
+        # Create a command-line interface (CLI) for the program
+        parser = argparse.ArgumentParser(description="CodyArchitect")
+        parser.add_argument(
+            "codebase_dir",
+            type=validate_codebase_dir,
+            help="Path to the codebase directory",
+        )
+        parser.add_argument(
+            "--output_dir",
+            "-o",
+            help="Path to the output directory for generated reports",
+        )
+
+        # Prompt the user to enter the codebase directory path
+        args = parser.parse_args()
+
+        # Store the user input for later use in the program
+        codebase_dir = args.codebase_dir
+        output_dir = args.output_dir
+
     # If the user did not provide an output directory path, create one in the codebase directory
     if not output_dir:
-        output_dir = os.path.join(codebase_dir, '.codyarchitect')
+        output_dir = os.path.join(codebase_dir, ".codyarchitect")
         if not os.path.exists(output_dir):
             os.makedirs(output_dir)
-
-if __name__ == '__main__':
-    main()
+
+    documentation_files = collect_documentation_files(codebase_dir)
+    log_message("Main: ", f"{documentation_files}")
+
+
+if __name__ == "__main__":
+
+    setup_logger("CodyArchitect", "logs")
+    codebase_dir = "."
+    main(codebase_dir)