日本語の禁則文字を意識して tokenize する prawn への monkey patch

line_wrap_ext.rb

module Prawn
  module Text
    module Formatted #:nodoc:
      # @private
      class LineWrap #:nodoc:
        def scan_pattern(encoding = ::Encoding::UTF_8)
          ebc = break_chars(encoding)
          eshy = soft_hyphen(encoding)
          ehy = hyphen(encoding)
          ews = whitespace(encoding)
          # https://ja.wikipedia.org/wiki/%E7%A6%81%E5%89%87%E5%87%A6%E7%90%86
          gyoto_kinsoku_moji = ',)\]｝、〕〉》」』】〙〗〟’”｠»ゝゞーァィゥェォッャュョヮヵヶぁぃぅぇぉっゃゅょゎゕゖㇰㇱㇲㇳㇴㇵㇶㇷㇸㇹㇷ゚ㇺㇻㇼㇽㇾㇿ々〻‐゠–〜～ ?!‼⁇⁈⁉・:;/。.'
          gyomatu_kinsoku_moji = '(\[｛〔〈《「『【〘〖〝‘“｟«'
          bunri_kinsi_moji = '—…‥〳〴〵'
          cjk = '\p{Han}\p{Hiragana}\p{Katakana}'

          patterns = [
            "[#{cjk}][#{gyoto_kinsoku_moji}#{bunri_kinsi_moji}]+",
            "[#{gyomatu_kinsoku_moji}]+[#{cjk}]",
            "[#{cjk}]",
            "[^#{ebc}]+#{eshy}",
            "[^#{ebc}]+#{ehy}+",
            "[^#{ebc}]+",
            "[#{ews}]+",
            "#{ehy}+[^#{ebc}]*",
            eshy.to_s,
          ]

          pattern = patterns
            .map { |p| p.encode(encoding) }
            .join('|')

          Regexp.new(pattern)
        end
      end
    end
  end
end