chore: add analyze_docs.py script for docs analysis

EdwardAngert · claude · EdwardAngert · commit 13d9d7d73837 · 2025-04-07T15:25:33.000-04:00
- Add external Python script for document structure analysis - Improves maintainability by separating Python code from YAML - Handles document heading counts and title extraction - Includes error handling for corrupted files 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
diff --git a/.github/actions/docs-analysis/analyze_docs.py b/.github/actions/docs-analysis/analyze_docs.py
@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+import sys
+import json
+import os
+import re
+
+files_to_analyze = sys.stdin.read().strip().split('\n')
+doc_structure = {}
+
+for file_path in files_to_analyze:
+    if not file_path or not file_path.endswith('.md') or not os.path.isfile(file_path):
+        continue
+        
+    try:
+        with open(file_path, 'r', encoding='utf-8') as f:
+            content = f.read()
+            
+        # Extract title (first h1)
+        title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
+        title = title_match.group(1) if title_match else 'Untitled'
+        
+        # Count headings
+        h1_count = len(re.findall(r'^# ', content, re.MULTILINE))
+        h2_count = len(re.findall(r'^## ', content, re.MULTILINE))
+        h3_count = len(re.findall(r'^### ', content, re.MULTILINE))
+        
+        doc_structure[file_path] = {
+            'title': title,
+            'headings': {
+                'h1': h1_count,
+                'h2': h2_count,
+                'h3': h3_count
+            }
+        }
+        
+        print(f'Analyzed {file_path}: H1={h1_count}, H2={h2_count}, H3={h3_count}, Title="{title}"', file=sys.stderr)
+    except Exception as e:
+        print(f'Error analyzing {file_path}: {str(e)}', file=sys.stderr)
+
+# Write JSON output
+with open('.github/temp/doc_structure.json', 'w', encoding='utf-8') as f:
+    json.dump(doc_structure, f, indent=2)
+
+print(json.dumps(doc_structure))
