LuHost/utils/contentdb-url.js

/**
 * ContentDB URL Parser and Validator
 * Handles parsing and validation of ContentDB package URLs
 */

class ContentDBUrlParser {
  /**
   * Parse a ContentDB URL to extract author and package name
   * @param {string} url - The URL to parse
   * @returns {Object} - {author, name, isValid, originalUrl}
   */
  static parseUrl(url) {
    if (!url || typeof url !== 'string') {
      return {
        author: null,
        name: null,
        isValid: false,
        originalUrl: url,
        error: 'URL is required'
      };
    }

    // Clean up the URL
    let cleanUrl = url.trim();
    
    // Remove protocol
    cleanUrl = cleanUrl.replace(/^https?:\/\//, '');
    
    // Remove trailing slash
    cleanUrl = cleanUrl.replace(/\/$/, '');
    
    // Define patterns to match
    const patterns = [
      // Full ContentDB URL: content.luanti.org/packages/author/name
      /^content\.luanti\.org\/packages\/([^\/\s]+)\/([^\/\s]+)$/,
      
      // Alternative domain patterns (if any)
      /^(?:www\.)?content\.luanti\.org\/packages\/([^\/\s]+)\/([^\/\s]+)$/,
      
      // Direct author/name format
      /^([^\/\s]+)\/([^\/\s]+)$/
    ];

    // Try each pattern
    for (const pattern of patterns) {
      const match = cleanUrl.match(pattern);
      if (match) {
        const author = match[1];
        const name = match[2];
        
        // Validate author and name format
        if (this.isValidIdentifier(author) && this.isValidIdentifier(name)) {
          return {
            author: author,
            name: name,
            isValid: true,
            originalUrl: url,
            cleanUrl: cleanUrl,
            fullUrl: `https://content.luanti.org/packages/${author}/${name}/`
          };
        } else {
          return {
            author: null,
            name: null,
            isValid: false,
            originalUrl: url,
            error: 'Invalid author or package name format'
          };
        }
      }
    }

    return {
      author: null,
      name: null,
      isValid: false,
      originalUrl: url,
      error: 'URL format not recognized'
    };
  }

  /**
   * Validate an identifier (author or package name)
   * @param {string} identifier - The identifier to validate
   * @returns {boolean} - Whether the identifier is valid
   */
  static isValidIdentifier(identifier) {
    if (!identifier || typeof identifier !== 'string') {
      return false;
    }

    // ContentDB identifiers should be alphanumeric with underscores and hyphens
    // Length should be reasonable (3-50 characters)
    return /^[a-zA-Z0-9_-]{3,50}$/.test(identifier);
  }

  /**
   * Generate various URL formats for a package
   * @param {string} author - Package author
   * @param {string} name - Package name
   * @returns {Object} - Object containing different URL formats
   */
  static generateUrls(author, name) {
    if (!this.isValidIdentifier(author) || !this.isValidIdentifier(name)) {
      throw new Error('Invalid author or package name');
    }

    return {
      web: `https://content.luanti.org/packages/${author}/${name}/`,
      api: `https://content.luanti.org/api/packages/${author}/${name}/`,
      releases: `https://content.luanti.org/api/packages/${author}/${name}/releases/`,
      direct: `${author}/${name}`
    };
  }

  /**
   * Validate multiple URL formats and suggest corrections
   * @param {string} url - The URL to validate
   * @returns {Object} - Validation result with suggestions
   */
  static validateWithSuggestions(url) {
    const result = this.parseUrl(url);
    
    if (result.isValid) {
      return {
        ...result,
        suggestions: []
      };
    }

    // Generate suggestions for common mistakes
    const suggestions = [];
    
    if (url.includes('minetest.') || url.includes('minetest/')) {
      suggestions.push('Did you mean content.luanti.org instead of minetest?');
    }
    
    if (url.includes('://content.luanti.org') && !url.includes('/packages/')) {
      suggestions.push('Make sure the URL includes /packages/author/name/');
    }
    
    if (url.includes(' ')) {
      suggestions.push('Remove spaces from the URL');
    }

    // Check if it looks like a partial URL
    if (url.includes('/') && !url.includes('content.luanti.org')) {
      suggestions.push('Try the full URL: https://content.luanti.org/packages/author/name/');
    }

    return {
      ...result,
      suggestions
    };
  }

  /**
   * Extract package information from various URL formats
   * @param {string} url - The URL to extract from
   * @returns {Promise<Object>} - Package information if available
   */
  static async extractPackageInfo(url) {
    const parsed = this.parseUrl(url);
    
    if (!parsed.isValid) {
      throw new Error(parsed.error || 'Invalid URL format');
    }

    return {
      author: parsed.author,
      name: parsed.name,
      identifier: `${parsed.author}/${parsed.name}`,
      urls: this.generateUrls(parsed.author, parsed.name)
    };
  }

  /**
   * Check if a URL is a ContentDB package URL
   * @param {string} url - The URL to check
   * @returns {boolean} - Whether it's a ContentDB package URL
   */
  static isContentDBUrl(url) {
    return this.parseUrl(url).isValid;
  }

  /**
   * Normalize a URL to standard format
   * @param {string} url - The URL to normalize
   * @returns {string} - Normalized URL
   */
  static normalizeUrl(url) {
    const parsed = this.parseUrl(url);
    
    if (!parsed.isValid) {
      throw new Error(parsed.error || 'Invalid URL format');
    }

    return parsed.fullUrl;
  }
}

module.exports = ContentDBUrlParser;