import { TFile } from 'obsidian';
import { BaseExtractor } from './base';
import { ExtractedContent } from '../types';

export class MarkdownExtractor extends BaseExtractor {
  canHandle(file: TFile): boolean {
    return file.extension === 'md';
  }

  async extract(file: TFile): Promise<ExtractedContent> {
    const content = await this.getFileContent(file);
    const metadata = this.createBaseMetadata(file);
    
    // Extract frontmatter and body
    const { frontmatter, body } = this.extractFrontmatter(content);
    
    // Extract markdown elements
    const { headings, tags, links } = this.extractMarkdownElements(body);
    
    // Update metadata with extracted information
    metadata.h1 = headings.filter(h => h.length > 0);
    metadata.tags = [...new Set(tags)]; // Remove duplicates
    metadata.links = [...new Set(links)]; // Remove duplicates
    metadata.fm = frontmatter;
    
    // Extract aliases from frontmatter
    if (frontmatter.aliases) {
      metadata.aliases = Array.isArray(frontmatter.aliases) 
        ? frontmatter.aliases 
        : [frontmatter.aliases];
    }
    
    // Extract title from frontmatter if present
    if (frontmatter.title) {
      metadata.title = frontmatter.title;
    }

    return {
      text: body,
      metadata,
      pageNumbers: undefined // Markdown files don't have page numbers
    };
  }
}