source code
# The Computer Language Benchmarks Game
# http://benchmarksgame.alioth.debian.org
#
# regex-dna program contributed by jose fco. gonzalez
# optimized & parallelized by Rick Branson
# optimized for ruby2 by Aaron Tavistock
# converted from regex-dna program
require 'fiber'
seq = $stdin.read.force_encoding("ASCII-8BIT")
origin_len = seq.size
seq.gsub!(/>.*\n|\n/,'')
clean_len = seq.size
matchers = [
'agggtaaa|tttaccct',
'[cgt]gggtaaa|tttaccc[acg]',
'a[act]ggtaaa|tttacc[agt]t',
'ag[act]gtaaa|tttac[agt]ct',
'agg[act]taaa|ttta[agt]cct',
'aggg[acg]aaa|ttt[cgt]ccct',
'agggt[cgt]aa|tt[acg]accct',
'agggta[cgt]a|t[acg]taccct',
'agggtaa[cgt]|[acg]ttaccct'
]
results = matchers.map do |matcher|
Fiber.new do
count = seq.scan( Regexp.new(matcher) ).size
Fiber.yield "#{matcher} #{count}"
end.resume
end
replacements = {
/tHa[Nt]/ => '<4>',
/aND|caN|Ha[DS]|WaS/ => '<3>',
/a[NSt]|BY/ => '<2>',
/<[^>]*>/ => '|',
/\|[^|][^|]*\|/ => '-'
}
seq.gsub!(Regexp.new(replacements.keys.join('|')), replacements)
puts "#{results.join("\n")}\n\n#{origin_len}\n#{clean_len}\n#{seq.size}"