require 'maasha/biopieces'
require 'maasha/fastq'
-allowed_enc = 'auto,sanger,solexa,illumina1.3,illumina1.5,illumina1.8'
+MAX_TEST = 1_000
+
+allowed_enc = 'auto,base_33,base_64'
casts = []
casts << {:long=>'data_in', :short=>'i', :type=>'files!', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
+casts << {:long=>'data_in2', :short=>'j', :type=>'files!', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
casts << {:long=>'num', :short=>'n', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>'0'}
casts << {:long=>'encoding', :short=>'e', :type=>'string', :mandatory=>false, :default=>'auto', :allowed=>allowed_enc, :disallowed=>nil}
options = Biopieces.options_parse(ARGV, casts)
-num = 0
-first = true
-last = false
+encoding = options[:encoding].to_sym
+
+num = 0
+last = false
Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
unless options[:data_in] and options[:data_in].first == '-'
end
end
- if options[:data_in]
- options[:data_in].each do |file|
- encoding = options[:encoding].downcase.delete('.')
+ if options[:data_in] and options[:data_in2]
+ raise "data_in files differ" if options[:data_in].size != options[:data_in2].size
+
+ (0 ... options[:data_in].size).each do |i|
+ file1 = options[:data_in][i]
+ file2 = options[:data_in2][i]
+
+ io1 = Fastq.open(file1, 'r')
+ io2 = Fastq.open(file2, 'r')
+
+ while not io1.eof? and not io2.eof?
+ entry1 = io1.get_entry
+ entry2 = io2.get_entry
- Fastq.open(file, mode='r') do |fastq|
+ if encoding == :auto
+ if entry1.qual_base33? or entry2.qual_base33?
+ encoding = :base_33
+ elsif entry1.qual_base64? or entry2.qual_base64?
+ encoding = :base_64
+ else
+ raise SeqError, "Could not auto-detect quality score encoding"
+ end
+ end
+
+ entry1.qual_convert!(encoding, :base_33)
+ entry2.qual_convert!(encoding, :base_33)
+ entry1.qual_coerce!(:base_33)
+ entry2.qual_coerce!(:base_33)
+
+ if num < MAX_TEST
+ raise SeqError, "Quality score outside valid range" unless entry1.qual_valid?(:base_33)
+ raise SeqError, "Quality score outside valid range" unless entry2.qual_valid?(:base_33)
+ end
+
+ output.puts entry1.to_bp
+ output.puts entry2.to_bp
+
+ num += 2
+
+ if options[:num] and num >= options[:num]
+ last = true
+ break
+ end
+ end
+
+ io1.close
+ io2.close
+
+ break if last
+ end
+ elsif options[:data_in]
+ options[:data_in].each do |file|
+ Fastq.open(file, 'r') do |fastq|
fastq.each do |entry|
- if encoding == 'auto'
- if entry.qual_base33? # sanger or illumina18
- encoding = 'illumina18'
- elsif entry.qual_base64? # solexa or illumina13 or illumina15
- encoding = 'illumina13'
+ if encoding == :auto
+ if entry.qual_base33?
+ encoding = :base_33
+ elsif entry.qual_base64?
+ encoding = :base_64
else
raise SeqError, "Could not auto-detect quality score encoding"
end
end
- entry.convert_scores!(encoding, 'illumina13')
+ entry.qual_convert!(encoding, :base_33)
+ entry.qual_coerce!(:base_33)
- if first
- raise SeqError, "Quality score outside valid range" unless entry.qual_valid?('illumina13')
- first = false
+ if num < MAX_TEST
+ raise SeqError, "Quality score outside valid range" unless entry.qual_valid?(:base_33)
end
output.puts entry.to_bp