parser.rb

segment = ARGV[0]
taxa = "reference_HAs.fasta"
fasta = "2009pdm_extracts.fasta"

search = IO.read( taxa ).split('>').inject({}) do |accumulator,line|
	sorting = line.strip.split("\n")
	name = sorting.shift
	accumulator[name.split("|")[1]] = 0
	accumulator
end

result = IO.read(fasta).split('>').inject([]) do |accumulator,line|
	sorting = line.strip.split("\n")
	name = sorting.shift
	headers = name.split('|')
	dna = sorting.join('')
	if headers[2] =~ /Segment:#{segment}/ && search[headers[1]]
		accumulator << headers[1]
	end
	accumulator
end
 
not_found = (search.keys - result)

puts "not found are #{not_found.inspect}"