toPlainText static method

Implementation

static String toPlainText(String html) {
  // Remove script and style tags completely
  String cleaned = html.replaceAll(
      RegExp(r'<(script|style)[^>]*>.*?</\1>',
          caseSensitive: false, dotAll: true),
      '');

  // Convert common HTML elements to plain text equivalents
  cleaned = cleaned
      // Line breaks for block elements
      .replaceAll(
          RegExp(r'</(div|p|h[1-6]|li|br)>', caseSensitive: false), '\n')
      .replaceAll(RegExp(r'<br\s*/?>', caseSensitive: false), '\n')
      // Double line breaks for paragraphs and headers
      .replaceAll(RegExp(r'</(p|h[1-6])>', caseSensitive: false), '\n\n')
      // List items
      .replaceAll(RegExp(r'<li[^>]*>', caseSensitive: false), '• ')
      // Remove all remaining HTML tags
      .replaceAll(RegExp(r'<[^>]*>'), '');

  return _cleanText(cleaned);
}