Class: Appydave::Tools::Dam::FuzzyMatcher

Inherits:
Object
  • Object
show all
Defined in:
lib/appydave/tools/dam/fuzzy_matcher.rb

Overview

Fuzzy matching for brand names using Levenshtein distance

Class Method Summary collapse

Class Method Details

.find_matches(input, candidates, threshold: 3) ⇒ Array<String>

Find closest matches to input string



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
 
# File 'lib/appydave/tools/dam/fuzzy_matcher.rb', line 14

def find_matches(input, candidates, threshold: 3)
  return [] if input.nil? || input.empty? || candidates.empty?

  # Calculate distances and filter by threshold
  matches = candidates.map do |candidate|
    distance = levenshtein_distance(input.downcase, candidate.downcase)
    { candidate: candidate, distance: distance }
  end

  # Filter by threshold
  matches = matches.select { |m| m[:distance] <= threshold }

  # Sort by distance (closest first)
  matches.sort_by { |m| m[:distance] }.map { |m| m[:candidate] }
end

.levenshtein_distance(str1, str2) ⇒ Integer

Calculate Levenshtein distance between two strings



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/appydave/tools/dam/fuzzy_matcher.rb', line 34

def levenshtein_distance(str1, str2)
  return str2.length if str1.empty?
  return str1.length if str2.empty?

  # Create distance matrix
  matrix = Array.new(str1.length + 1) { Array.new(str2.length + 1) }

  # Initialize first row and column
  (0..str1.length).each { |i| matrix[i][0] = i }
  (0..str2.length).each { |j| matrix[0][j] = j }

  # Calculate distances
  (1..str1.length).each do |i|
    (1..str2.length).each do |j|
      cost = str1[i - 1] == str2[j - 1] ? 0 : 1
      matrix[i][j] = [
        matrix[i - 1][j] + 1,      # deletion
        matrix[i][j - 1] + 1,      # insertion
        matrix[i - 1][j - 1] + cost # substitution
      ].min
    end
  end

  matrix[str1.length][str2.length]
end