bio 2.0.1 → 2.0.4

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

@@ -174,7 +174,7 @@ class UniProtKB < EMBLDB
   #
   # http://www.uniprot.org/docs/sp_news.htm
   def parse_DE_line_rel14(str)
-    # Retruns if it is not the new format since Rel.14
+    # Returns if it is not the new format since Rel.14
     return nil unless /^DE   (RecName|AltName|SubName)\: / =~ str
     ret = []
     cur = nil
@@ -248,9 +248,8 @@ class UniProtKB < EMBLDB
   #  SYNONYM        >=0
   #  CONTEINS       >=0
   def protein_name
-    @data['DE'] ||= parse_DE_line_rel14(get('DE'))
-    parsed_de_line = @data['DE']
-    if parsed_de_line then
+    parsed_de_line = self.de
+    if parsed_de_line.kind_of?(Array) then
       # since UniProtKB release 14.0 of 22-Jul-2008
       name = nil
       parsed_de_line.each do |a|
@@ -275,7 +274,6 @@ class UniProtKB < EMBLDB
     return name
   end
 
-
   # returns synonyms (unofficial and/or alternative names).
   # Returns an Array containing String objects.
   #
@@ -292,9 +290,8 @@ class UniProtKB < EMBLDB
   # synonyms are each placed in () following the official name on the DE line.
   def synonyms
     ary = Array.new
-    @data['DE'] ||= parse_DE_line_rel14(get('DE'))
-    parsed_de_line = @data['DE']
-    if parsed_de_line then
+    parsed_de_line = self.de
+    if parsed_de_line.kind_of?(Array) then
       # since UniProtKB release 14.0 of 22-Jul-2008
       parsed_de_line.each do |a|
         case a[0]
@@ -330,6 +327,20 @@ class UniProtKB < EMBLDB
     return ary
   end
 
+  # Returns an Array (for new format since rel 14)
+  # or a String (for old format before rel 14) for the DE line.
+  #
+  def de
+    return @data['DE'] if @data['DE']
+    parsed_de_line = parse_DE_line_rel14(get('DE'))
+    case parsed_de_line
+    when Array # new format since rel14
+      @data['DE'] ||= parsed_de_line
+    else
+      super
+    end
+    @data['DE']
+  end
 
   # returns gene names in the GN line.
   #
@@ -1197,9 +1208,124 @@ class UniProtKB < EMBLDB
     return ft[feature_key] if feature_key
     return @data['FT'] if @data['FT']
 
+    ftstr = get('FT')
+    ftlines = ftstr.split("\n")
+    for i in 0..10 do
+      if /^FT +([^\s]+) +(([^\s]+)\:)?([\<\?]?[0-9]+|\?)(?:\.\.([\>\?]?[0-9]+|\?))?\s*$/ =~ ftlines[i] &&
+         /^FT +\/([^\s\=]+)(?:\=(\")?(.+)(\")?)?\s*$/ =~ ftlines[i+1] then
+        fmt_2019_11 = true
+        break #for i
+      end
+    end #for i
+
+    hash = if fmt_2019_11 then
+             ft_2019_11_parser(ftlines)
+           else
+             ft_legacy_parser(ftlines)
+           end
+    @data['FT'] = hash
+  end
+
+  # FT parser since UniProt release 2019_11
+  # https://www.uniprot.org/release-notes/2019-12-18-release#text%5Fft
+  def ft_2019_11_parser(ftlines)
+    table = []
+    cur_ft = nil
+    cont = false
+    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
+                   ]
+          table.push cur_ft
+          cont = false
+        elsif cont && /^FT {19}/ =~ line
+          str = $'
+          str.rstrip!
+          orig = cur_ft[3][-1][1].to_s
+          if orig.size > 0 && orig[-1] != ' ' &&
+             str.length > 0 && str[0] != ' ' then
+            orig.concat ' '
+          end
+          orig.concat str
+          cur_ft[3][-1][1] = orig
+          if cont && orig[-1] == "\""
+            orig.chop!
+            cont = false
+          end
+        elsif /^FT +\/([^\s\=]+)(?:\=(\")?(.+))?\s*$/ =~ line
+          key = $1
+          val = $3
+          val.rstrip!
+          cur_ft[3].push [ key, val ]
+          cont = false
+          if $2 == "\""
+            if val.to_s[-1] == "\""
+              val.chop!
+            else
+              cont = true
+            end
+          end
+        else
+          raise "FT parse error: #{line.inspect}"
+        end
+      end
+
+      hash = {}
+      table.each do |feature|
+        cur_h = {
+          # Removing '<', '>' or '?' in FROM/TO endopoint.
+          'From' => feature[1].sub(/\D/, '').to_i,  
+          'To'   => feature[2].sub(/\D/, '').to_i, 
+          'diff' => [],
+          'original' => feature
+        }
+        hash[feature[0]] ||= []
+        hash[feature[0]].push cur_h
+        feature[3].each do |a|
+          case a[0]
+          when 'From', 'To', 'Description', 'FTId', 'diff', 'original'
+            ; # do nothing
+          else
+            cur_h[a[0]] = a[1]
+          end
+        end
+        if cur_h["id"] then
+          cur_h['FTId'] = cur_h['id']
+        end
+
+        case feature[0]
+        when 'VARSPLIC', 'VARIANT', 'VAR_SEQ', 'CONFLICT'
+          case cur_h['note'].to_s
+          when /(\w[\w ]*\w*) - ?> (\w[\w ]*\w*)/
+            original_res = $1
+            changed_res = $2
+            original_res = original_res.gsub(/ /,'').strip
+            chenged_res = changed_res.gsub(/ /,'').strip
+          when /Missing/i
+            original_res = seq.subseq(cur_h['From'],
+                                      cur_h['To'])
+            changed_res = ''
+          end
+          cur_h['diff'] = [original_res, chenged_res]
+        end
+      end
+    rescue
+      raise "Invalid FT Lines(#{$!}) in #{entry_id}:, \n'#{self.get('FT')}'\n"
+    end
+
+    hash
+  end
+  private :ft_2019_11_parser
+  
+  # FT parser for the format before Uniprot release 2019_11
+  def ft_legacy_parser(ftlines)
     table = []
     begin
-      get('FT').split("\n").each do |line|
+      ftlines.each do |line|
         if line =~ /^FT   \w/
           feature = line.chomp.ljust(74)
           table << [feature[ 5..12].strip,   # Feature Name
@@ -1256,10 +1382,9 @@ class UniProtKB < EMBLDB
       raise "Invalid FT Lines(#{$!}) in #{entry_id}:, \n'#{self.get('FT')}'\n"
     end
 
-    @data['FT'] = hash
+    hash
   end
-
-
+  private :ft_legacy_parser
 
   # returns a Hash of conteins in the SQ lines.
   # * Bio::UniProtKBL#sq  -> hsh

data/lib/bio/db/go.rb

@@ -193,7 +193,7 @@ class GO
     # Delimiter
     RS = DELIMITER 
 
-    # Retruns an Array of parsed gene_association flatfile.
+    # Returns an Array of parsed gene_association flatfile.
     # Block is acceptable.  
     def self.parser(str)
       if block_given?
@@ -226,7 +226,7 @@ class GO
     # Returns Db_Reference variable.
     attr_reader :db_reference      # -> []
 
-    # Retruns Evidence code variable.
+    # Returns Evidence code variable.
     attr_reader :evidence
 
     # Returns the entry is associated with this value.

data/lib/bio/sequence/common.rb

@@ -303,6 +303,118 @@ module Common
   end
   alias splicing splice
 
+#--
+# Workaround for Ruby 3.0.0 incompatible changes
+if ::RUBY_VERSION > "3"
+
+  # Acts almost the same as String#split.
+  def split(*arg)
+    if block_given?
+      super
+    else
+      ret = super(*arg)
+      ret.collect! { |x| self.class.new('').replace(x) }
+      ret
+    end
+  end
+
+  %w( * ljust rjust center ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        self.class.new('').replace(super)
+      end
+    }
+  end
+
+  %w( chomp chop
+      delete delete_prefix delete_suffix
+      lstrip rstrip strip
+      reverse
+      squeeze
+      succ next
+      tr tr_s
+      capitalize upcase downcase swapcase
+  ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        s = self.dup
+        s.#{w}!(*arg)
+        s
+      end
+    }
+  end
+
+  %w( sub gsub ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg, &block)
+        s = self.dup
+        s.#{w}!(*arg, &block)
+        s
+      end
+    }
+  end
+
+  #Reference: https://nacl-ltd.github.io/2018/11/08/gsub-wrapper.html
+  #(Title: Is it possible to implement gsub wrapper?)
+  %w( sub! gsub! ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg, &block)
+        if block_given? then
+          super(*arg) do |m|
+            b = Thread.current[:_backref]
+            Thread.current[:_backref] = ::Regexp.last_match
+            block.binding.eval("$~ = Thread.current[:_backref]")
+            Thread.current[:_backref] = b
+            block.call(self.class.new('').replace(m))
+          end
+        else
+          super
+        end
+      end
+    }
+  end
+
+  %w( each_char each_grapheme_cluster each_line ).each do |w|
+    module_eval %Q{
+      def #{w}
+        if block_given?
+          super { |c| yield(self.class.new('').replace(c)) }
+        else
+          enum_for(:#{w})
+        end
+     end
+    }
+  end
+
+  %w( slice [] slice! ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        r = super
+        r ? self.class.new('').replace(r) : r
+      end
+    }
+  end
+
+  %w( partition rpartition ).each do |w|
+    module_eval %Q{
+      def #{w}(sep)
+        r = super
+        if r.kind_of?(Array)
+          r[1] == sep ?
+            [ self.class.new('').replace(r[0]),
+              r[1],
+              self.class.new('').replace(r[2]) ] :
+            r.collect { |x| self.class.new('').replace(x) }
+        else
+          r
+        end
+      end
+    }
+  end
+#++
+
+end # if ::RUBY_VERSION > "3"
+
 end # Common
 
 end # Sequence

data/lib/bio/sequence/format.rb

@@ -10,6 +10,7 @@
 #
 
 require 'erb'
+require 'date'
 
 module Bio
 

data/lib/bio/tree.rb

@@ -605,7 +605,7 @@ module Bio
     end
 
     # Gets path from node1 to node2.
-    # Retruns an array of nodes, including node1 and node2.
+    # Returns an array of nodes, including node1 and node2.
     # If node1 and/or node2 do not exist, IndexError is raised.
     # If node1 and node2 are not connected, NoPathError is raised.
     # The result is unspecified for cyclic trees.

data/lib/bio/version.rb

@@ -10,7 +10,7 @@
 module Bio
 
   # BioRuby version (Array containing Integer)
-  BIORUBY_VERSION = [2, 0, 1].extend(Comparable).freeze
+  BIORUBY_VERSION = [2, 0, 4].extend(Comparable).freeze
 
   # Extra version specifier (String or nil).
   # Existance of the value indicates development version.