bench/shootout/regexdna.ruby

   1 # The Computer Language Shootout
   2 # http://shootout.alioth.debian.org/
   3 #
   4 # contributed by jose fco. gonzalez
   5 seq = STDIN.readlines.join
   6 ilen = seq.size
   7
   8 seq.gsub!(/>.*\n|\n/,"")
   9 clen = seq.length
  10
  11 [
  12   /agggtaaa|tttaccct/i,
  13   /[cgt]gggtaaa|tttaccc[acg]/i,
  14   /a[act]ggtaaa|tttacc[agt]t/i,
  15   /ag[act]gtaaa|tttac[agt]ct/i,
  16   /agg[act]taaa|ttta[agt]cct/i,
  17   /aggg[acg]aaa|ttt[cgt]ccct/i,
  18   /agggt[cgt]aa|tt[acg]accct/i,
  19   /agggta[cgt]a|t[acg]taccct/i,
  20   /agggtaa[cgt]|[acg]ttaccct/i
  21 ].each {|f| puts "#{f.source} #{seq.scan(f).size}" }
  22
  23 {
  24 'B' => '(c|g|t)', 'D' => '(a|g|t)', 'H' => '(a|c|t)', 'K' => '(g|t)',
  25 'M' => '(a|c)', 'N' => '(a|c|g|t)', 'R' => '(a|g)', 'S' => '(c|t)',
  26 'V' => '(a|c|g)', 'W' => '(a|t)', 'Y' => '(c|t)'
  27 }.each { |f,r| seq.gsub!(f,r) }
  28
  29 puts
  30 puts ilen
  31 puts clen
  32 puts seq.length