Accent Removal Benchmark 1

gistfile1.rb

require 'benchmark'
require 'i18n'

I18n.config.available_locales = :en

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

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

str = File.read(File.expand_path("benchmark_input.txt"))

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