ruby 正规表现による文字列の抜き出しとその変换

Posted 2021-05-16

require 'pp'
require 'mojinizer'

target = 'English. 漢字と、カタカナを含む文字列。ﾊﾝｶｸ!龠русский'
regex_patterns = [
  /\w/,
  /\p{Katakana}/,
  /\p{Hiragana}/,
  /\p{Han}/
]
match_data =
  regex_patterns.reduce([]) do |ar, regex|
    data = target.scan(regex).join
    pp data
    ar << data
  end

match_data.each do |target|
  pp target.romaji unless target.contains_kanji?
end

=begin
"English"
"カタカナﾊﾝｶｸ"
"とをむ"
"漢字含文字列龠"
=end

=begin
"English"
"katakanaﾊﾝｶｸ"
"towomu"
=end