bio 2.0.4 → 2.0.6

data/lib/bio/appl/blast/genomenet.rb

@@ -162,7 +162,8 @@ module Bio::Blast::Remote
       #host = "blast.genome.jp"
       #path = "/sit-bin/nph-blast"
       #path = "/sit-bin/blast" #2005.08.12
-      path = "/tools-bin/blast" #2012.01.12
+      #path = "/tools-bin/blast" #2012.01.12
+      path = "/tools-bin/blastplus" #2018.02.09???
 
       options = make_command_line_options
       opt = Bio::Blast::NCBIOptions.new(options)

data/lib/bio/appl/clustalw/report.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/appl/clustalw/report.rb - CLUSTAL W format data (*.aln) class
 #
@@ -138,7 +139,7 @@ module Bio
         a = @raw.split(/\r?\n\r?\n/)
         @header = a.shift.to_s
         xalign = Bio::Alignment.new
-        @match_line = ''
+        @match_line = String.new
         if a.size > 0 then
           a[0].gsub!(/\A(\r?\n)+/, '')
           a.collect! { |x| x.split(/\r?\n/) }
@@ -151,7 +152,7 @@ module Bio
             @match_line << x.pop.to_s[@tagsize..-1]
           end
           a[0].each do |y|
-            xalign.store(y[0, @tagsize].sub(/\s+\z/, ''), '')
+            xalign.store(y[0, @tagsize].sub(/\s+\z/, ''), String.new)
           end
           a.each do |x|
             x.each do |y|

data/lib/bio/appl/iprscan/report.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/appl/iprscan/report.rb - a class for iprscan output.
 #
@@ -69,7 +70,7 @@ module Bio
       #  end
       #
       def self.parse_raw(io)
-        entry = ''
+        entry = String.new
         while line = io.gets
           if entry != '' and entry.split("\t").first == line.split("\t").first
             entry << line

data/lib/bio/appl/meme/mast.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/appl/meme/mast.rb - Wrapper for running MAST program
 #
@@ -113,7 +114,7 @@ module Meme
 
     def config(options)
       @options = DEFAULT_OPTIONS.merge(options)
-      mfile, opts, flags = "", "", ""
+      mfile, opts, flags = String.new, String.new, String.new
       @options.each_pair do |opt, val|
         if val.nil? or val == false
           next

data/lib/bio/appl/paml/common.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/appl/paml/common.rb - Basic wrapper class common to PAML programs
 #
@@ -270,7 +271,7 @@ module PAML
     def dump_parameters
       keyorder = DEFAULT_PARAMETERS_ORDER
       keys = parameters.keys
-      str = ''
+      str = String.new
       keys.sort do |x, y|
         (keyorder.index(x) || (keyorder.size + keys.index(x))) <=>
           (keyorder.index(y) || (keyorder.size + keys.index(y)))

data/lib/bio/appl/pts1.rb

@@ -90,7 +90,7 @@ class PTS1
   #   serv_fungi_specific = Bio::PTS1.new(2)    # See Bio::PTS1::FUNCTION.
   #
   def initialize(func = 'METAZOA-specific')
-    @uri = "http://mendel.imp.ac.at/jspcgi/cgi-bin/pts1/pts1.cgi"
+    @uri = "https://mendel.imp.ac.at/jspcgi/cgi-bin/pts1/pts1.cgi"
     @output = nil
     @function = function(func)
   end

data/lib/bio/db/embl/common.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/embl.rb - Common methods for EMBL style database classes
 #
@@ -243,8 +244,10 @@ module Common
     unless @data['R']
       ary = Array.new
       get('R').split(/\nRN   /).each do |str|
-        raw = {'RN' => '', 'RC' => '', 'RP' => '', 'RX' => '', 
-               'RA' => '', 'RT' => '', 'RL' => '', 'RG' => ''}
+        raw = {'RN' => String.new, 'RC' => String.new,
+               'RP' => String.new, 'RX' => String.new,
+               'RA' => String.new, 'RT' => String.new,
+               'RL' => String.new, 'RG' => String.new}
         str = 'RN   ' + str unless /^RN   / =~ str
         str.split("\n").each do |line|
           if /^(R[NPXARLCTG])   (.+)/ =~ line

data/lib/bio/db/embl/uniprotkb.rb

@@ -530,22 +530,43 @@ class UniProtKB < EMBLDB
   # http://br.expasy.org/sprot/userman.html#OH_line
   def oh
     unless @data['OH']
-      @data['OH'] = fetch('OH').split("\. ").map {|x|
-        if x =~ /NCBI_TaxID=(\d+);/
-          taxid = $1
-        else
-          raise ArgumentError, ["Error: Invalid OH line format (#{self.entry_id}):",
-                                $!, "\n", get('OH'), "\n"].join
-          
-        end
-        if x =~ /NCBI_TaxID=\d+; (.+)/ 
-          host_name = $1
-          host_name.sub!(/\.$/, '')
-        else
-          host_name = nil
+      oh = []
+      a = fetch('OH').split(/(NCBI\_TaxID\=)(\d+)(\;)/)
+      t = catch :error do
+        taxid = nil
+        host_name = nil
+        while x = a.shift
+          x = x.to_s.strip
+          case x
+          when ''
+            next
+          when 'NCBI_TaxID='
+            if taxid then
+              oh.push({'NCBI_TaxID' => taxid, 'HostName' => host_name})
+              taxid = nil
+              host_name = nil
+            end
+            taxid = a.shift
+            throw :error, :missing_semicolon if a.shift != ';'
+          else
+            throw :error, :missing_taxid if host_name
+            host_name = x
+            host_name.sub!(/\.\z/, '')
+          end
+        end #while x...
+        if taxid then
+          oh.push({'NCBI_TaxID' => taxid, 'HostName' => host_name})
+        elsif host_name then
+          throw :error, :missing_taxid_last
         end
-        {'NCBI_TaxID' => taxid, 'HostName' => host_name}
-      }
+        nil
+      end #t = catch...
+      if t then
+        raise ArgumentError,
+              ["Error: Invalid OH line format (#{self.entry_id}):",
+               $!, "\n", get('OH'), "\n"].join
+      end
+      @data['OH'] = oh
     end
     @data['OH']
   end
@@ -922,6 +943,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_alternative_products(data)
+    return nil unless data
     ap = data.join('')
     return ap unless ap
 
@@ -960,6 +982,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_biophysiochemical_properties(data)
+    return nil unless data
     data = data[0]
 
     hash = {'Absorption' => {}, 
@@ -995,6 +1018,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_caution(data)
+    return nil unless data
     data.join('')
   end
   private :cc_caution
@@ -1004,6 +1028,7 @@ class UniProtKB < EMBLDB
   #
   #   CC       P46527:CDKN1B; NbExp=1; IntAct=EBI-359815, EBI-519280;
   def cc_interaction(data)
+    return nil unless data
     str = data.join('')
     it = str.scan(/(.+?); NbExp=(.+?); IntAct=(.+?);/)
     it.map {|ent|
@@ -1059,6 +1084,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_pathway(data)
+    return nil unless data
     data.map {|x| x.sub(/\.$/, '') }.map {|x|
       x.split(/; | and |: /)
     }[0]
@@ -1067,6 +1093,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_rna_editing(data)
+    return nil unless data
     data = data.join('')
     entry = {'Modified_positions' => [], 'Note' => ""}
     if data =~ /Modified_positions=(.+?)(\.|;)/
@@ -1083,6 +1110,7 @@ class UniProtKB < EMBLDB
 
 
   def cc_subcellular_location(data)
+    return nil unless data
     data.map {|x| 
       x.split('. ').map {|y| 
         y.split('; ').map {|z| 
@@ -1101,6 +1129,7 @@ class UniProtKB < EMBLDB
   #++
 
   def cc_web_resource(data)
+    return nil unless data
     data.map {|x|
       entry = {'Name' => nil, 'Note' => nil, 'URL' => nil}
       x.split(';').each do |y|
@@ -1235,10 +1264,14 @@ class UniProtKB < EMBLDB
     begin
       ftlines.each do |line|
         if /^FT +([^\s]+) +(([^\s]+)\:)?([\<\?]?[0-9]+|\?)(?:\.\.([\>\?]?[0-9]+|\?))?\s*$/ =~ line
-          cur_ft = [$1.to_s,        # Feature Name
-                    "#{$2}#{$4}",   # From
-                    $5.to_s,        # To
-                    []              # Qualifiers
+          f_name = $1.to_s
+          f_from = "#{$2}#{$4}"
+          f_to = $5.to_s
+          f_to = f_from if f_to.empty?
+          cur_ft = [f_name,   # Feature Name
+                    f_from,   # From
+                    f_to,     # To
+                    []        # Qualifiers
                    ]
           table.push cur_ft
           cont = false

data/lib/bio/db/fastq.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/fastq.rb - FASTQ format parser class
 #
@@ -349,7 +350,7 @@ class Fastq
       return self
     end
     if defined? @definition2 then
-      @quality_string ||= ''
+      @quality_string ||= String.new
       if line[0, 1] == "@" and
           @quality_string.size >= @sequence_string.size then
         return false
@@ -358,7 +359,7 @@ class Fastq
         return self
       end
     else
-      @sequence_string ||= ''
+      @sequence_string ||= String.new
       if line[0, 1] == '+' then
         @definition2 = line[1..-1]
       else

data/lib/bio/db/gff.rb

@@ -1,4 +1,5 @@
 # coding: US-ASCII
+# frozen_string_literal: true
 #
 # = bio/db/gff.rb - GFF format class
 #
@@ -137,13 +138,13 @@ module Bio
 
         sc = StringScanner.new(attributes)
         attrs = []
-        token = ''
+        token = String.new
         while !sc.eos?
           if sc.scan(/[^\\\;\"]+/) then
             token.concat sc.matched
           elsif sc.scan(/\;/) then
             attrs.push token unless token.empty?
-            token = ''
+            token = String.new
           elsif sc.scan(/\"/) then
             origtext = sc.matched
             while !sc.eos?
@@ -690,22 +691,22 @@ module Bio
           sc = StringScanner.new(str)
           attr_pairs = []
           tokens = []
-          cur_token = ''
+          cur_token = String.new
           while !sc.eos?
             if sc.scan(/[^\\\;\"\s]+/) then
               cur_token.concat sc.matched
             elsif sc.scan(/\s+/) then
               tokens.push cur_token unless cur_token.empty?
-              cur_token = ''
+              cur_token = String.new
             elsif sc.scan(/\;/) then
               tokens.push cur_token unless cur_token.empty?
-              cur_token = ''
+              cur_token = String.new
               attr_pairs.push tokens
               tokens = []
             elsif sc.scan(/\"/) then
               tokens.push cur_token unless cur_token.empty?
-              cur_token = ''
-              freetext = ''
+              cur_token = String.new
+              freetext = String.new
               while !sc.eos?
                 if sc.scan(/[^\\\"]+/) then
                   freetext.concat sc.matched
@@ -999,10 +1000,15 @@ module Bio
           str.empty? ? '.' : str
         end
 
-        if URI.const_defined?(:Parser) then
+        if URI.const_defined?(:RFC2396_Parser) then
+          # (private) URI::Parser object for escape/unescape GFF3 columns
+          URI_PARSER = URI::RFC2396_Parser.new
+        elsif URI.const_defined?(:Parser) then
           # (private) URI::Parser object for escape/unescape GFF3 columns
           URI_PARSER = URI::Parser.new
+        end
 
+        if const_defined?(:URI_PARSER) then
           # (private) the same as URI::Parser#escape(str, unsafe)
           def _escape(str, unsafe)
             URI_PARSER.escape(str, unsafe)

data/lib/bio/db/newick.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/newick.rb - Newick Standard phylogenetic tree parser / formatter
 #
@@ -150,7 +151,7 @@ module Bio
             # Molphy-style boostrap values
             # let molphy mode if nothing determined
             @options[:original_format] ||= :molphy
-            bstr = ''
+            bstr = String.new
             while t = btokens.shift and t != :']'
               bstr.concat t.to_s
             end
@@ -162,7 +163,7 @@ module Bio
       if !btokens and !leaf_tokens.empty? then
         # syntax error?
       end
-      node.name ||= '' # compatibility for older BioRuby
+      node.name ||= String.new # compatibility for older BioRuby
 
       # returns true
       true
@@ -242,7 +243,7 @@ module Bio
 
         elsif ss.scan(/\'/) then
           # quoted_label
-          t = ''
+          t = String.new
           while true
             if ss.scan(/([^\']*)\'/) then
               t.concat ss[1]
@@ -317,7 +318,7 @@ module Bio
           if previous_token == :',' or previous_token == :'(' then
             # there is a leaf whose name is empty.
             ary.unshift(token)
-            ary.unshift('')
+            ary.unshift(String.new)
             token = nil
           end
         when :'('
@@ -330,7 +331,7 @@ module Bio
           if previous_token == :',' or previous_token == :'(' then
             # there is a leaf whose name is empty.
             ary.unshift(token)
-            ary.unshift('')
+            ary.unshift(String.new)
             token = nil
           else
             edge = Edge.new

data/lib/bio/db/pdb/chain.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/pdb/chain.rb - chain class for PDB
 #
@@ -180,7 +181,7 @@ module Bio
       # gets an amino acid sequence of this chain from ATOM records
       def aaseq
         unless defined? @aaseq
-          string = ""
+          string = String.new
           last_residue_num = nil
           @residues.each do |residue|
             if last_residue_num and 

data/lib/bio/db/pdb/pdb.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/pdb/pdb.rb - PDB database class for PDB file format
 #
@@ -1645,7 +1646,7 @@ module Bio
     # Returns a string of Bio::PDB::Models. This propogates down the heirarchy
     # till you get to Bio::PDB::Record::ATOM which are outputed in PDB format
     def to_s
-      string = ""
+      string = String.new
       @models.each{ |model| string << model.to_s }
       string << "END\n"
       return string

data/lib/bio/db/prosite.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db/prosite.rb - PROSITE database class
 #
@@ -465,6 +466,7 @@ class PROSITE < EMBLDB
   # translated as: Ala-any-[Ser or Thr]-[Ser or Thr]-(any or none)-Val
   #
   def self.pa2re(pattern)
+    pattern = pattern.dup
     pattern.gsub!(/\s/, '')	# remove white spaces
     pattern.sub!(/\.$/, '')	# (1) remove trailing '.'
     pattern.sub!(/^</, '^')	# (2) restricted to the N-terminal : `<'

data/lib/bio/db.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/db.rb - common API for database parsers
 #
@@ -192,19 +193,19 @@ class DB
   # Returns a String with successive white spaces are replaced by one
   # space and stripeed.
   def truncate(str)
-    str ||= ""
+    str ||= String.new
     return str.gsub(/\s+/, ' ').strip
   end
 
   # Returns a tag name of the field as a String.
   def tag_get(str)
-    str ||= ""
+    str ||= String.new
     return str[0,@tagsize].strip
   end
 
   # Returns a String of the field without a tag name.
   def tag_cut(str)
-    str ||= ""
+    str ||= String.new
     str[0,@tagsize] = ''
     return str
   end
@@ -313,7 +314,7 @@ class EMBLDB < DB
 
   # Returns the contents of the entry as a Hash.
   def entry2hash(entry)
-    hash = Hash.new { |h,k| h[k] = '' }
+    hash = Hash.new { |h,k| h[k] = String.new }
     entry.each_line do |line|
       tag = tag_get(line)
       next if tag == 'XX'

data/lib/bio/io/flatfile/buffer.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/io/flatfile/buffer.rb - Input stream buffer for FlatFile
 #
@@ -24,7 +25,7 @@ module Bio
         @io = io
         @path = path
         # initialize prefetch buffer
-        @buffer = ''
+        @buffer = String.new
       end
 
       # Creates a new input stream wrapper from the given IO object.

data/lib/bio/io/flatfile/splitter.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/io/flatfile/splitter.rb - input data splitter for FlatFile
 #
@@ -157,7 +158,7 @@ module Bio
         # Otherwise, returns nil.
         def skip_leader
           if @header then
-            data = ''
+            data = String.new
             while s = stream.gets(@header)
               data << s
               if data.split(/[\r\n]+/)[-1] == @header then

data/lib/bio/pathway.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/pathway.rb - Binary relations and Graph algorithms
 #
@@ -307,7 +308,7 @@ class Pathway
     end
     # end workaround removing depencency to order of Hash#each
 
-    list = ""
+    list = String.new
     enum.each do |from, hash|
       list << "#{from} => "
       # begin workaround removing depencency to order of Hash#each

data/lib/bio/sequence/common.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/sequence/common.rb - common methods for biological sequence
 #
@@ -286,7 +287,7 @@ module Common
     unless position.is_a?(Locations) then
       position = Locations.new(position)
     end
-    s = ''
+    s = String.new
     position.each do |location|
       if location.sequence
         s << location.sequence

data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # bio/util/restriction_enzyme/range/sequence_range/fragment.rb - 
 #
@@ -27,8 +28,8 @@ class Fragment
 
   def for_display(p_str=nil, c_str=nil)
     df = DisplayFragment.new
-    df.primary = ''
-    df.complement = ''
+    df.primary = String.new
+    df.complement = String.new
 
     both_bins = @primary_bin + @complement_bin
     both_bins.each do |item|

data/lib/bio/util/sirna.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 #
 # = bio/util/sirna.rb - Class for designing small inhibitory RNAs
 #
@@ -202,7 +203,7 @@ module Bio
 
       # human readable report
       def report
-        report =  "### siRNA\n"
+        report =  "### siRNA\n".dup
         report << 'Start: ' + @start.to_s + "\n"
         report << 'Stop:  ' + @stop.to_s  + "\n"
         report << 'Rule:  ' + @rule.to_s  + "\n"
@@ -280,7 +281,7 @@ module Bio
       def report
         # raise NomethodError for compatibility
         raise NoMethodError if !defined?(@top_strand) || !@top_strand
-        report = "### shRNA\n"
+        report = "### shRNA\n".dup
         report << "Top strand shRNA (#{@top_strand.length} nt):\n"
         report << "  5'-#{@top_strand.upcase}-3'\n"
         report << "Bottom strand shRNA (#{@bottom_strand.length} nt):\n"

data/lib/bio/version.rb

@@ -10,7 +10,7 @@
 module Bio
 
   # BioRuby version (Array containing Integer)
-  BIORUBY_VERSION = [2, 0, 4].extend(Comparable).freeze
+  BIORUBY_VERSION = [2, 0, 6].extend(Comparable).freeze
 
   # Extra version specifier (String or nil).
   # Existance of the value indicates development version.