agentsqripts/lib/utils/levenshtein.js

Comprehensive static code analysis toolkit for identifying technical debt, security vulnerabilities, performance issues, and code quality problems

/**
 * @file Levenshtein distance algorithm implementation for string similarity analysis
 * @description Single responsibility: Calculate edit distance between strings using dynamic programming
 * 
 * This utility module implements the Levenshtein distance algorithm to measure string
 * similarity by calculating the minimum number of single-character edits (insertions,
 * deletions, substitutions) required to transform one string into another. It serves
 * as a fundamental component for code similarity detection, duplicate identification,
 * and fuzzy matching across the AgentSqripts analysis platform.
 * 
 * Algorithm design rationale:
 * - Dynamic programming approach ensures O(m*n) time complexity for optimal performance
 * - Matrix-based calculation provides accurate edit distance measurement
 * - Null/empty string handling ensures robust operation with edge cases
 * - Single-function module maintains focus and testability
 * - Standard algorithm implementation enables predictable and reliable results
 * 
 * Technical implementation:
 * - Matrix initialization establishes base cases for empty string transformations
 * - Character comparison optimizes for identical character sequences
 * - Three-operation minimum calculation (substitution, insertion, deletion)
 * - Bottom-up dynamic programming eliminates redundant calculations
 * - Final matrix position contains the complete edit distance result
 */

/**
 * Calculate Levenshtein distance between two strings
 * @param {string} str1 - First string
 * @param {string} str2 - Second string
 * @returns {number} Edit distance
 */
function levenshtein(str1, str2) {
  if (!str1 || !str2) return Math.max(str1?.length || 0, str2?.length || 0);
  
  const matrix = [];
  
  // Initialize the first column
  for (let i = 0; i <= str2.length; i++) {
    matrix[i] = [i];
  }
  
  // Initialize the first row
  for (let j = 0; j <= str1.length; j++) {
    matrix[0][j] = j;
  }
  
  // Calculate distances
  for (let i = 1; i <= str2.length; i++) {
    for (let j = 1; j <= str1.length; j++) {
      if (str2.charAt(i - 1) === str1.charAt(j - 1)) {
        matrix[i][j] = matrix[i - 1][j - 1];
      } else {
        matrix[i][j] = Math.min(
          matrix[i - 1][j - 1] + 1, // substitution
          matrix[i][j - 1] + 1,     // insertion
          matrix[i - 1][j] + 1      // deletion
        );
      }
    }
  }
  
  return matrix[str2.length][str1.length];
}

module.exports = levenshtein;