import os
import json
from bs4 import BeautifulSoup

OUTPUT_DIR = os.path.normpath(os.environ.get("SITE_OUTPUT_DIR", "output"))

def strip_html_tags(html):
    soup = BeautifulSoup(html, "html.parser")
    for tag in soup(["script", "style"]):
        tag.decompose()

    text = soup.get_text(separator="\n")

    lines = [line.strip() for line in text.splitlines() if line.strip()]
    return "\n".join(lines)

def create_folder_structure_json(path):
    result = {
        'name': os.path.basename(path),
        'type': 'folder',
        'children': []
    }

    if not os.path.isdir(path):
        return result

    for entry in os.listdir(path):
        
        entry_path = os.path.join(path, entry)
        base_url = os.path.relpath(entry_path, OUTPUT_DIR)
        if os.path.isdir(entry_path):
            result['children'].append(
                create_folder_structure_json(entry_path)
            )
            
        elif entry.lower().endswith('.html'):
            file_entry = {
                'name': entry,
                'type': 'file',
                'url': base_url,
                'content': None
            }

            try:
                with open(entry_path, 'r', encoding='utf-8') as f:
                    html = f.read()
                    file_entry['content'] = strip_html_tags(html)

            except Exception as e:
                file_entry['content'] = f"<unreadable: {e}>"

            result['children'].append(file_entry)

    return result


folder_path = OUTPUT_DIR
folder_json = create_folder_structure_json(folder_path)

output_file = os.path.join(OUTPUT_DIR, 'search-index.json')
with open(output_file, 'w', encoding='utf-8') as f:
    json.dump(folder_json, f, indent=4, ensure_ascii=False)

print("JSON saved to", output_file)