import { JSDOM } from 'jsdom';
import TurndownService from 'turndown';
import { URL } from 'url';

interface HtmlProcessorOptions {
  baseUrl: string;
  includeImages?: boolean;
  stripTrackingParams?: boolean;
}

export class HtmlToMarkdownProcessor {
  private turndownService: TurndownService;
  private options: HtmlProcessorOptions;

  constructor(options: HtmlProcessorOptions) {
    this.options = options;
    this.turndownService = new TurndownService({
      headingStyle: 'atx',
      codeBlockStyle: 'fenced',
      hr: '---',
    });

    // Custom rules for turndown if needed, e.g., to handle specific elements
    // or to modify how links/images are rendered.
    this.turndownService.addRule('anchor', {
      filter: ['a'],
      replacement: (content, node) => {
        const anchor = node as HTMLAnchorElement;
        let href = anchor.href;
        if (href) {
          try {
            const resolvedUrl = new URL(href, this.options.baseUrl);
            if (this.options.stripTrackingParams) {
              // Simple stripping example
              resolvedUrl.searchParams.forEach((_value, key) => {
                if (key.startsWith('utm_') || key.startsWith('gclid')) {
                  resolvedUrl.searchParams.delete(key);
                }
              });
            }
            // Ensure absolute URL
            href = resolvedUrl.toString();
          } catch (e) {
            // Handle malformed URLs if necessary
          }
        }
        return `[${content}](${href || ''})`;
      }
    });

    if (!this.options.includeImages) {
      this.turndownService.remove('img');
    } else {
       this.turndownService.addRule('image', {
         filter: ['img'],
         replacement: (content, node) => {
           const img = node as HTMLImageElement;
           let src = img.src;
           if (src) {
             try {
               const resolvedUrl = new URL(src, this.options.baseUrl);
               src = resolvedUrl.toString();
             } catch (e) {
               // Handle malformed URLs
             }
           }
           return `![${img.alt || ''}](${src || ''})`;
         }
       });
    }
  }

  public process(html: string): string {
    const dom = new JSDOM(html);
    const document = dom.window.document;

    // A simplistic main content extraction for demonstration.
    // In a real library, this would involve sophisticated algorithms.
    let mainContentElement = document.querySelector('main') || document.body;

    // Remove common noisy elements from the main content (or entire document)
    ['nav', 'header', 'footer', 'aside', 'script', 'style', 'iframe'].forEach(tag => {
      document.querySelectorAll(tag).forEach(el => el.remove());
    });
    // Further heuristic-based removal could target ad divs, social buttons, etc.

    return this.turndownService.turndown(mainContentElement.innerHTML);
  }
}

// Example usage:
const htmlContent = `
  <!DOCTYPE html>
  <html>
  <head><title>Product Page</title></head>
  <body>
    <header><h1>Site Header</h1><nav>...</nav></header>
    <main>
      <article>
        <h2>Product Name</h2>
        <p>This is a great product. <a href="/details?id=123&utm_source=test">More info</a></p>
        <img src="/assets/product.jpg" alt="Product Image">
      </article>
      <aside>Related products...</aside>
    </main>
    <footer><p>Copyright</p></footer>
    <script>alert('hello');</script>
  </body>
  </html>
`;

const processor = new HtmlToMarkdownProcessor({
  baseUrl: 'https://example.com',
  includeImages: true,
  stripTrackingParams: true,
});
const markdown = processor.process(htmlContent);
console.log(markdown);
/* Expected output (simplified):
## Product Name

This is a great product. [More info](https://example.com/details?id=123)

![Product Image](https://example.com/assets/product.jpg)
*/