X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_bin%2Fwrite_fasta_files;h=dfeabb20a5555517af240461eb574cb79ed2f125;hb=5de6112b70b59420b245ce636a8b2e3c90acbe00;hp=3ffeb82c5608eff45e7b72e53ad49484b4540152;hpb=3eb0e92699257e81781dd85dfd215ec12070b2df;p=biopieces.git diff --git a/bp_bin/write_fasta_files b/bp_bin/write_fasta_files index 3ffeb82..dfeabb2 100755 --- a/bp_bin/write_fasta_files +++ b/bp_bin/write_fasta_files @@ -33,28 +33,40 @@ require 'maasha/fasta' require 'pp' casts = [] -casts << {:long=>'key', :short=>'k', :type=>'string', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil} -casts << {:long=>'dir', :short=>'d', :type=>'dir!', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil} -casts << {:long=>'no_stream', :short=>'x', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil} +casts << {long: 'key', short: 'k', type: 'string', mandatory: true, default: nil, allowed: nil, disallowed: nil} +casts << {long: 'dir', short: 'd', type: 'dir!', mandatory: true, default: nil, allowed: nil, disallowed: nil} +casts << {long: 'prefix', short: 'p', type: 'string', mandatory: false, default: nil, allowed: nil, disallowed: nil} +casts << {long: 'wrap', short: 'w', type: 'uint', mandatory: false, default: nil, allowed: nil, disallowed: "0"} +casts << {long: 'compress', short: 'Z', type: 'string', mandatory: false, default: nil, allowed: "gzip,bzip,bzip2", disallowed: nil} +casts << {long: 'no_stream', short: 'x', type: 'flag', mandatory: false, default: nil, allowed: nil, disallowed: nil} options = Biopieces.options_parse(ARGV, casts) -key = options[:key].to_sym - -fh_hash = {} +key = options[:key].to_sym +compress = options[:compress] ? options[:compress].to_sym : nil +fh_hash = {} Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output| input.each_record do |record| if record[:SEQ_NAME] and record[:SEQ] and record[key] - if fh_hash.has_key? record[key].to_sym + seq = Seq.new_bp(record) + + if fh_hash[record[key].to_sym] fasta_io = fh_hash[record[key].to_sym] else - mid_file = File.join(options[:dir], record[key] + ".fasta") - fasta_io = Fasta.open(mid_file, "w") + if options[:prefix] + fasta_file = File.join(options[:dir], [options[:prefix], record[key]].join("_") + ".fasta") + else + fasta_file = File.join(options[:dir], record[key] + ".fasta") + end + + fasta_file << ".gz" if compress == :gzip + fasta_file << ".bz2" if compress == :bzip or compress == :bzip2 + fasta_io = Fasta.open(fasta_file, "w", compress: compress) fh_hash[record[key].to_sym] = fasta_io end - fasta_io.puts record + fasta_io.puts seq.to_fasta(options[:wrap]) end output.puts record unless options[:no_stream]