Strip emoji

strip-emoji.rb

# this scrubs emoji sequences from a string - i think it covers all of them

def strip_emoji ( str )
    str = str.force_encoding('utf-8').encode
    clean_text = ""

    # emoticons  1F601 - 1F64F
    regex = /[\u{1f600}-\u{1f64f}]/
    clean_text = str.gsub regex, ''

    #dingbats 2702 - 27B0
    regex = /[\u{2702}-\u{27b0}]/
    clean_text = clean_text.gsub regex, ''

    # transport/map symbols
    regex = /[\u{1f680}-\u{1f6ff}]/
    clean_text = clean_text.gsub regex, ''

    # enclosed chars  24C2 - 1F251
    regex = /[\u{24C2}-\u{1F251}]/
    clean_text = clean_text.gsub regex, ''

    # symbols & pics
    regex = /[\u{1f300}-\u{1f5ff}]/
    clean_text = clean_text.gsub regex, ''
end


def test_strip_emoji
    f = File.open("emoji.txt", "r")
    f.each_line do |line|
      puts strip_emoji_full(line)
    end
    f.close
end