#!/usr/bin/env python3
"""
Regenerates the notes index in notes.html based on files in notes/youtube/
Run after adding new notes.
"""

import os
import re
import json
from pathlib import Path

NOTES_DIR = Path(__file__).parent.parent / 'notes' / 'youtube'
NOTES_HTML = Path(__file__).parent.parent / 'kanban' / 'notes.html'

def extract_metadata(filepath):
    """Extract title, date, tags from markdown file."""
    with open(filepath, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Extract title (first # heading)
    title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
    title = title_match.group(1) if title_match else filepath.stem
    
    # Extract date from filename (YYYY-MM-DD_...)
    date_match = re.match(r'(\d{4}-\d{2}-\d{2})', filepath.name)
    date = date_match.group(1) if date_match else "Unknown"
    
    # Extract tags
    tags_match = re.search(r'\*\*Tags?:\*\*\s*(.+)$', content, re.MULTILINE)
    if tags_match:
        tags = [t.strip().replace('#', '') for t in tags_match.group(1).split(',')]
    else:
        # Try to find hashtags
        tags = re.findall(r'#(\w+)', content)[:5]
    
    return {
        'file': filepath.name,
        'title': title[:50],  # Truncate long titles
        'date': date,
        'tags': tags[:4]  # Max 4 tags
    }

def update_index():
    """Scan notes directory and update the HTML index."""
    if not NOTES_DIR.exists():
        print(f"Notes directory not found: {NOTES_DIR}")
        return
    
    # Get all markdown files
    notes = []
    for f in sorted(NOTES_DIR.glob('*.md'), reverse=True):  # Newest first
        notes.append(extract_metadata(f))
    
    # Read current HTML
    with open(NOTES_HTML, 'r', encoding='utf-8') as f:
        html = f.read()
    
    # Update the notesIndex
    index_json = json.dumps(notes, indent=12, ensure_ascii=False)
    
    # Replace the notesIndex in HTML
    pattern = r'const notesIndex = \[[\s\S]*?\];'
    replacement = f'const notesIndex = {index_json};'
    
    new_html = re.sub(pattern, replacement, html)
    
    with open(NOTES_HTML, 'w', encoding='utf-8') as f:
        f.write(new_html)
    
    print(f"Updated index with {len(notes)} notes:")
    for n in notes:
        print(f"  - {n['date']}: {n['title']}")

if __name__ == '__main__':
    update_index()