multibyte_string_scanner_learning_spec.rb

#!/usr/bin/env ruby
# vim:set fileencoding=utf-8 filetype=ruby
$KCODE = 'u'

describe "text spliting" do
  before do
    special = [
      [0x3001].pack("U"), # ten
      [0x3002].pack("U"), # maru
      [0x30fc].pack("U"), # bar/multibyte hyphun
    ].join("|")
    ascii = "[[:alnum:]]|[[:punct:]]"
    @re = /(?:#{ascii})+|.(?:#{special})*|\s+/
  end

  it '"ほげほげRuby on Railsふーばー、日本語。".scan(@re).should == ["ほ", "げ", "ほ", "げ", "Ruby", " ", "on", " ", "Rails", "ふー", "ばー、", "日", "本", "語。"]' do
    text = "ほげほげRuby on Railsふーばー、日本語。"
    text.scan(@re).should == ["ほ", "げ", "ほ", "げ", "Ruby", " ", "on", " ", "Rails", "ふー", "ばー、", "日", "本", "語。"]
  end

  it '"moronatural@gmail.comが私のメールアドレスです。".scan(@re).should == ["moronatural@gmail.com", "が", "私","の","メー","ル","ア","ド","レ","ス", "で", "す。"]' do
    text = "moronatural@gmail.comが私のメールアドレスです。"
    text.scan(@re).should == 
      ["moronatural@gmail.com", "が", "私","の","メー","ル","ア","ド","レ","ス", "で", "す。"]
  end
end