Created
April 20, 2019 20:01
-
-
Save ivan3bx/e21ee7eee834314c71daa4cae6653554 to your computer and use it in GitHub Desktop.
implementing the soundex algorithm for fun
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'minitest/autorun' | |
require 'text' | |
# An exercise to implement the 'soundex' algorithm | |
# | |
# See https://en.wikipedia.org/wiki/Soundex for details | |
# | |
# Compare with 'text' gem impl: https://github.com/threedaymonk/text/blob/master/lib/text/soundex.rb | |
class Soundex | |
def process(input) | |
return nil unless input.is_a?(String) | |
return nil unless input =~ /^[A-Za-z]/ | |
input = input.downcase.gsub(/hw/, '').split('') | |
result = input.each_with_object("") do |letter, acc| | |
case letter | |
when /[aeiouy]/ | |
acc << '0' # insert vowel spacer | |
when /[bfpv]/ | |
acc << '1' | |
when /[cgjkqsxz]/ | |
acc << '2' | |
when /[dt]/ | |
acc << '3' | |
when /[l]/ | |
acc << '4' | |
when /[mn]/ | |
acc << '5' | |
when /[r]/ | |
acc << '6' | |
end | |
end | |
# Rule #3 (remove duplicate numbers including first position) | |
result.gsub!(/(\d)\1/, '\\1') | |
# Place first letter of input in first position | |
result[0] = input[0].upcase | |
# Remove any vowel spacers | |
result.delete!('0') | |
# Return four character representation (first letter + 3 numbers) | |
result.ljust(4, '0')[0, 4] | |
end | |
end | |
class TestSoundex < Minitest::Test | |
def setup | |
@soundex = Soundex.new | |
end | |
def test_non_words | |
assert_nil @soundex.process(nil) | |
assert_nil @soundex.process('') | |
assert_nil @soundex.process('123') | |
end | |
def test_short_words | |
assert_equal 'A000', @soundex.process('a') | |
assert_equal 'A500', @soundex.process('am') | |
end | |
def test_words | |
assert_equal 'F623', @soundex.process('first') | |
assert_equal 'T623', @soundex.process('thirst') | |
assert_equal 'W623', @soundex.process('worst') | |
assert_equal 'C623', @soundex.process('cursed') | |
end | |
def test_hw_rule | |
assert_equal 'A261', @soundex.process('Ashcroft') | |
assert_equal 'A261', @soundex.process('Ashcraft') | |
end | |
def test_tricky_words | |
assert_equal 'T522', @soundex.process('Tymczak') | |
assert_equal 'P236', @soundex.process('Pfister') | |
assert_equal 'H555', @soundex.process('Honeymoon') | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment