Accent Removal Benchmark 2

benchmark2.rb

require 'benchmark'
require 'i18n'

I18n.config.available_locales = :en

COMBINING_DIACRITICS = [*0x1DC0..0x1DFF, *0x0300..0x036F, *0xFE20..0xFE2F].pack('U*').freeze

def removeaccents(str)
  str
    .unicode_normalize(:nfd) # Decompose characters
    .tr(COMBINING_DIACRITICS, '')
    .unicode_normalize(:nfc) # Recompose characters
end

lines = File.readlines(File.expand_path("~/Desktop/1200_strings_average_length_110_chars.txt"))

Benchmark.bmbm do |x|
  x.report("I18n") { lines.each { |line| I18n.transliterate(line) } }
  x.report("removeaccents") { lines.each { |line| removeaccents(line) } }
end