san.rb

def sanitize(str)
  
  # https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#_reserved_characters
  escaped_characters = Regexp.escape('\\+-&|!(){}[]^~*?:')
  str = str.gsub(/([#{escaped_characters}])/, '\\\\\1')

  # AND, OR and NOT are used by lucene as logical operators.
  ['AND', 'OR', 'NOT'].each do |word|
    escaped_word = word.split('').map {|char| "\\#{char}" }.join('')
    str = str.gsub(/\s*\b(#{word.upcase})\b\s*/, " #{escaped_word} ")
  end

  # Escape odd quotes
  quote_count = str.count '"'
  str = str.gsub(/(.*)"(.*)/, '\1\"\3') if quote_count % 2 == 1

  str
end