re = /(?<=[^\/]>)[^>\P{IsBasicLatin}]*[\p{IsHiragana}\p{IsKatakana}\p{IsCJKUnifiedIdeographs}]+[^>\P{IsBasicLatin}]*(?=<\/)/i
str = '<tag3>Some text before 日本語 and some text after</tag3><tag>Before text 漢字</tag>.'
# Print the match result
str.scan(re) do |match|
puts match.to_s
end
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Ruby, please visit: http://ruby-doc.org/core-2.2.0/Regexp.html