BioDSL 1.0.1 → 1.0.2

data/lib/BioDSL/commands/read_fastq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of BioDSL (www.github.com/maasha/BioDSL).              #
+# This software is part of BioDSL (http://maasha.github.io/BioDSL).            #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -143,7 +143,7 @@ module BioDSL
         case
         when @options[:first] && @pair then read_first_pair(output)
         when @options[:first]          then read_first_single(output)
-        when @options[:last]  && @pair then read_last_pair(output)
+        when @options[:last] && @pair  then read_last_pair(output)
         when @options[:last]           then read_last_single(output)
         when @pair                     then read_all_pair(output)
         else
@@ -176,12 +176,12 @@ module BioDSL
       return unless input
 
       input.each do |record|
-        @status[:records_in]  += 1
+        @status[:records_in] += 1
         @status[:records_out] += 1
 
         if (seq = record[:SEQ])
           @status[:sequences_in] += 1
-          @status[:residues_in]  += seq.length
+          @status[:residues_in] += seq.length
         end
 
         output << record
@@ -197,10 +197,10 @@ module BioDSL
           ios.each do |entry|
             check_entry(entry)
             output << entry.to_bp
-            @status[:records_out]   += 1
+            @status[:records_out] += 1
             @status[:sequences_out] += 1
-            @status[:residues_out]  += entry.length
-            return if @status[:sequences_out] >= @options[:first]
+            @status[:residues_out] += entry.length
+            break if @status[:sequences_out] >= @options[:first]
           end
         end
       end
@@ -220,10 +220,10 @@ module BioDSL
               reverse_complement(entry2) if @options[:reverse_complement]
               output << entry1.to_bp
               output << entry2.to_bp
-              @status[:records_out]   += 2
+              @status[:records_out] += 2
               @status[:sequences_out] += 2
-              @status[:residues_out]  += entry1.length + entry2.length
-              return if @status[:sequences_out] >= @options[:first]
+              @status[:residues_out] += entry1.length + entry2.length
+              break if @status[:sequences_out] >= @options[:first]
             end
           end
         end
@@ -279,9 +279,9 @@ module BioDSL
           ios.each do |entry|
             check_entry(entry)
             output << entry.to_bp
-            @status[:records_out]   += 1
+            @status[:records_out] += 1
             @status[:sequences_out] += 1
-            @status[:residues_out]  += entry.length
+            @status[:residues_out] += entry.length
           end
         end
       end
@@ -299,9 +299,9 @@ module BioDSL
               reverse_complement(entry2) if @options[:reverse_complement]
               output << entry1.to_bp
               output << entry2.to_bp
-              @status[:records_out]   += 2
+              @status[:records_out] += 2
               @status[:sequences_out] += 2
-              @status[:residues_out]  += entry1.length + entry2.length
+              @status[:residues_out] += entry1.length + entry2.length
             end
           end
         end
@@ -405,9 +405,9 @@ module BioDSL
       @buffer.each do |entry|
         output << entry.to_bp
 
-        @status[:records_out]   += 1
+        @status[:records_out] += 1
         @status[:sequences_out] += 1
-        @status[:residues_out]  += entry.length
+        @status[:residues_out] += entry.length
       end
     end
   end

data/lib/BioDSL/commands/read_table.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -173,7 +173,6 @@ module BioDSL
   #    {:Organism=>"Mouse"}
   #    {:Organism=>"Cat"}
   #
-  # rubocop: disable ClassLength
   class ReadTable
     STATS = %i(records_in records_out)
 
@@ -321,7 +320,7 @@ module BioDSL
       return unless output
       input.each do |record|
         output << record
-        @status[:records_in]  += 1
+        @status[:records_in] += 1
         @status[:records_out] += 1
       end
     end

data/lib/BioDSL/commands/reverse_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -102,10 +102,10 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
       entry.reverse!
 
-      @status[:sequences_in]  += 1
+      @status[:sequences_in] += 1
       @status[:sequences_out] += 1
-      @status[:residues_in]   += entry.length
-      @status[:residues_out]  += entry.length
+      @status[:residues_in] += entry.length
+      @status[:residues_out] += entry.length
 
       record.merge! entry.to_bp
     end

data/lib/BioDSL/commands/slice_align.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -231,7 +231,7 @@ module BioDSL
     def defaults
       @max_mis = @options[:max_mismatches] || 2
       @max_ins = @options[:max_insertions] || 1
-      @max_del = @options[:max_deletions]  || 1
+      @max_del = @options[:max_deletions] || 1
     end
 
     # Parse FASTA file with one gapped template sequence if specified.
@@ -312,7 +312,7 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       setup_slice(entry) unless @slice
 
@@ -321,7 +321,7 @@ module BioDSL
       record.merge! entry.to_bp
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += entry.length
+      @status[:residues_out] += entry.length
     end
 
     # Usings primers to locate slice positions in entry.

data/lib/BioDSL/commands/slice_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -138,12 +138,12 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       entry = entry[@options[:slice]]
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += entry.length
+      @status[:residues_out] += entry.length
 
       record.merge! entry.to_bp
     end

data/lib/BioDSL/commands/sort.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 

data/lib/BioDSL/commands/split_pair_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -146,12 +146,11 @@ module BioDSL
     # @param output [Enumerator::Yielder] Output stream.
     # @param record [Hash]                BioDSL record.
     #
-    # rubocop: disable Metrics/AbcSize
     def split_pair_seq(output, record)
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       pos = get_split_pos(record, entry)
 
@@ -161,13 +160,13 @@ module BioDSL
       output << entry2.to_bp
 
       @status[:sequences_out] += 2
-      @status[:residues_out]  += entry1.length + entry2.length
-      @status[:records_out]   += 2
+      @status[:residues_out] += entry1.length + entry2.length
+      @status[:records_out] += 2
     end
 
     # Given a record locate the sequence split position.
     #
-    # @param record [Hash]           BioDSL record.
+    # @param record [Hash] BioDSL record.
     # @param entry  [BioDSL::Seq] Sequence entry.
     #
     # @return [Integer] Sequence split position.
@@ -210,7 +209,7 @@ module BioDSL
     def fix_seq_names(entry1, entry2)
       if entry1.seq_name =~ /^[^ ]+ \d:/
         entry2.seq_name.sub!(/ \d:/, ' 2:')
-      elsif entry1.seq_name =~ /^.+\/\d$/
+      elsif entry1.seq_name =~ %r{^.+\/\d$}
         entry2.seq_name[-1] = '2'
       else
         fail "Could not match sequence name: #{entry1.seq_name}"

data/lib/BioDSL/commands/split_values.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -82,7 +82,7 @@ module BioDSL
     #
     # @return [SplitValues] Class instance.
     def initialize(options)
-      @options     = options
+      @options = options
 
       check_options
 

data/lib/BioDSL/commands/trim_primer.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -131,10 +131,10 @@ module BioDSL
     # @return [TrimPrimer] Class instance.
     def initialize(options)
       @options = options
-      @options[:overlap_min]       ||= 1
-      @options[:mismatch_percent]  ||= 0
+      @options[:overlap_min] ||= 1
+      @options[:mismatch_percent] ||= 0
       @options[:insertion_percent] ||= 0
-      @options[:deletion_percent]  ||= 0
+      @options[:deletion_percent] ||= 0
       @pattern = pattern
       @hit     = false
 
@@ -153,6 +153,7 @@ module BioDSL
 
           if record[:SEQ] && record[:SEQ].length > 0
             @status[:sequences_in] += 1
+            @status[:sequences_out] += 1
 
             case @options[:direction]
             when :forward then trim_forward(record)
@@ -198,7 +199,7 @@ module BioDSL
     def trim_forward(record)
       entry = BioDSL::Seq.new_bp(record)
 
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       while @pattern.length >= @options[:overlap_min]
         if (match = match_forward(entry))
@@ -235,6 +236,8 @@ module BioDSL
     def merge_forward(record, entry, match)
       entry = entry[match.pos + match.length..-1]
 
+      @status[:residues_out] += entry.length
+
       record.merge!(entry.to_bp)
       record[:TRIM_PRIMER_DIR] = 'FORWARD'
       record[:TRIM_PRIMER_POS] = match.pos
@@ -248,7 +251,7 @@ module BioDSL
     def trim_reverse(record)
       entry = BioDSL::Seq.new_bp(record)
 
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       while @pattern.length >= @options[:overlap_min]
         if (match = match_reverse(entry))
@@ -288,6 +291,8 @@ module BioDSL
     def merge_reverse(record, entry, match)
       entry = entry[0...match.pos]
 
+      @status[:residues_out] += entry.length
+
       record.merge!(entry.to_bp)
       record[:TRIM_PRIMER_DIR] = 'REVERSE'
       record[:TRIM_PRIMER_POS] = match.pos
@@ -302,9 +307,9 @@ module BioDSL
     #
     # @return [Hash] Match options hash.
     def match_options(length)
-      mis = (length * @options[:mismatch_percent]  * 0.01).round
+      mis = (length * @options[:mismatch_percent] * 0.01).round
       ins = (length * @options[:insertion_percent] * 0.01).round
-      del = (length * @options[:deletion_percent]  * 0.01).round
+      del = (length * @options[:deletion_percent] * 0.01).round
 
       {max_mismatches: mis,
        max_insertions: ins,

data/lib/BioDSL/commands/trim_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -164,8 +164,8 @@ module BioDSL
     # Set defaul options.
     def defaults
       @options[:quality_min] ||= 20
-      @options[:mode]        ||= :both
-      @options[:length_min]  ||= 3
+      @options[:mode] ||= :both
+      @options[:length_min] ||= 3
     end
 
     # Trim sequence in a given record with sequence info.
@@ -175,7 +175,7 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       case @mode
       when :both  then entry.quality_trim!(@min, @len)
@@ -184,7 +184,7 @@ module BioDSL
       end
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += entry.length
+      @status[:residues_out] += entry.length
 
       record.merge! entry.to_bp
     end

data/lib/BioDSL/commands/uchime_ref.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -71,8 +71,8 @@ module BioDSL
       @options = options
       aux_exist('usearch')
       check_options
-      @options[:cpus]   ||= 1
-      @options[:strand] ||= 'plus'  # This option cant be changed in usearch7.0
+      @options[:cpus] ||= 1
+      @options[:strand] ||= 'plus' # This option cant be changed in usearch7.0
     end
 
     # Return command lambda for uchime_ref.
@@ -115,7 +115,7 @@ module BioDSL
 
           if record[:SEQ]
             @status[:sequences_in] += 1
-            @status[:residues_in]  += record[:SEQ].length
+            @status[:residues_in] += record[:SEQ].length
             seq_name = record[:SEQ_NAME] || i.to_s
 
             entry = BioDSL::Seq.new(seq_name: seq_name, seq: record[:SEQ])
@@ -161,8 +161,8 @@ module BioDSL
 
           output << record
           @status[:sequences_out] += 1
-          @status[:residues_out]  += entry.length
-          @status[:records_out]   += 1
+          @status[:residues_out] += entry.length
+          @status[:records_out] += 1
         end
       end
     end

data/lib/BioDSL/commands/uclust.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -232,9 +232,9 @@ module BioDSL
             record.merge!(entry.to_bp)
 
             output << record
-            @status[:records_out]   += 1
+            @status[:records_out] += 1
             @status[:sequences_out] += 1
-            @status[:residues_out]  += entry.length
+            @status[:residues_out] += entry.length
           end
         end
       end
@@ -273,9 +273,9 @@ module BioDSL
 
         if (r = results[record[:SEQ_NAME]])
           output << record.merge(r)
-          @status[:records_out]   += 1
+          @status[:records_out] += 1
           @status[:sequences_out] += 1
-          @status[:residues_out]  += record[:SEQ].length
+          @status[:residues_out] += record[:SEQ].length
         else
           fail BioDSL::UsearchError, 'Sequence name: ' \
             "#{record[:SEQ_NAME]} not found in uclust results"