From b62ad8b4bc90e8f7a4782396768f6e1c29cadfc9 Mon Sep 17 00:00:00 2001
From: Pan <pany8@nih.gov>
Date: Thu, 11 Jul 2024 16:17:27 -0400
Subject: [PATCH] added script and workflow

---
 .github/workflows/lint.py            | 36 ++++++++++++++++++++++++
 .github/workflows/notebook-lint.yaml | 41 ++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)
 create mode 100644 .github/workflows/lint.py
 create mode 100644 .github/workflows/notebook-lint.yaml

diff --git a/.github/workflows/lint.py b/.github/workflows/lint.py
new file mode 100644
index 0000000..3f91768
--- /dev/null
+++ b/.github/workflows/lint.py
@@ -0,0 +1,36 @@
+import nbformat
+from nbformat.v4 import new_notebook
+
+def clean_notebook(file_path):
+    with open(file_path, 'r', encoding='utf-8') as f:
+        notebook = nbformat.read(f, as_version=4)
+
+    # Clean cells
+    for cell in notebook.cells:
+        if 'outputs' in cell:
+            cell['outputs'] = []
+        if 'execution_count' in cell:
+            cell['execution_count'] = None
+        if 'metadata' in cell:
+            cell['metadata'] = {}
+
+    # Clean notebook metadata
+    if 'metadata' in notebook:
+        notebook['metadata'] = {}
+
+    with open(file_path, 'w', encoding='utf-8') as f:
+        nbformat.write(notebook, f)
+
+
+if __name__ == "__main__":
+    import os
+
+    # Change this to the directory containing your notebooks
+    notebook_dir = '../../'
+
+    for root, dirs, files in os.walk(notebook_dir):
+        for file in files:
+            if file.endswith('.ipynb'):
+                file_path = os.path.join(root, file)
+                clean_notebook(file_path)
+                print(f'Cleaned {file_path}')
diff --git a/.github/workflows/notebook-lint.yaml b/.github/workflows/notebook-lint.yaml
new file mode 100644
index 0000000..634e0b3
--- /dev/null
+++ b/.github/workflows/notebook-lint.yaml
@@ -0,0 +1,41 @@
+name: 'Lint Notebook'
+on:
+  push:
+    branches:
+      - dev/lint
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  gather_stats:
+    name: 'Gather Stats'
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        working-directory: .github/workflows
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'pip'
+
+      - name: Install requirements.txt
+        run: |
+          python3 -m pip install --upgrade pip
+          pip3 install nbformat
+
+      - name: Generate reports
+        working-directory: .github/workflows
+        run: |
+          python3 lint.py
+
+      - name: Commit changes
+        uses: EndBug/add-and-commit@v9
+        with:
+          author_name: github-action
+          author_email: cbiit-github-action@github.com
+          message: 'Github Action: Refresh stats'