bio 1.4.3.0001 → 1.5.0

data/lib/bio/db/phyloxml/phyloxml_parser.rb

@@ -5,7 +5,6 @@
 #               Diana Jaunzeikare <latvianlinuxgirl@gmail.com>
 # License::     The Ruby License
 #
-# $Id:$
 #
 # == Description
 #
@@ -162,6 +161,7 @@ module PhyloXML
         ensure
           obj.close if obj and !obj.closed?
         end
+        ret
       else
         obj
       end
@@ -258,7 +258,7 @@ module PhyloXML
 
       schema = _schema
       begin
-        flag = xml_instance.validate_schema(schema) do |msg, flag|
+        flag = xml_instance.validate_schema(schema) do |msg, _|
           # The document of libxml-ruby says that the block is called
           # when validation failed, but it seems it is never called
           # even when validation failed!

data/lib/bio/db/phyloxml/phyloxml_writer.rb

@@ -5,7 +5,6 @@
 #               Diana Jaunzeikare <latvianlinuxgirl@gmail.com>
 # License::     The Ruby License
 #
-# $Id:$
 #
 # == Description
 #
@@ -205,7 +204,7 @@ module Bio
         end
       end
       return root
-     end
+      end
 
       private
 

data/lib/bio/db/sanger_chromatogram/chromatogram.rb

@@ -4,7 +4,6 @@
 # Copyright::	Copyright (C) 2009 Anthony Underwood <anthony.underwood@hpa.org.uk>, <email2ants@gmail.com>
 # License::	The Ruby License
 #
-# $Id:$
 #
 require 'bio/sequence/adapter'
 module Bio
@@ -103,7 +102,7 @@ module Bio
       @gtrace = tmp_trace.reverse
 
       # reverse base qualities
-      if !@aqual.nil? # if qualities exist
+      if (defined? @aqual) && @aqual # if qualities exist
         tmp_qual = @aqual
         @aqual = @tqual.reverse
         @tqual = tmp_qual.reverse

data/lib/bio/db/transfac.rb

@@ -118,7 +118,7 @@ class TRANSFAC < EMBLDB
         end
       end
       ma_dat.keys.sort.each_with_index do |k, i|
-        rep_nt = ma_dat[k].slice!(-1, 1)
+        ma_dat[k].slice!(-1, 1)
         ma_dat[k].slice!(-1, 1)
         ma_ary[i] = ma_dat[k].split(/\s+/)
         ma_ary[i].each_with_index do |x, j|

data/lib/bio/io/das.rb

@@ -6,7 +6,6 @@
 #		Toshiaki Katayama <k@bioruby.org>
 # License::	The Ruby License
 #
-# $Id:$
 #
 #--
 # == TODO
@@ -49,9 +48,9 @@ class DAS
     ary = []
     result = Bio::Command.post_form("#{@server}/das/dsn")
     doc = REXML::Document.new(result.body)
-    doc.elements.each('/descendant::DSN') do |e|
+    doc.elements.each('/descendant::DSN') do |ee|
       dsn = DSN.new
-      e.elements.each do |e|
+      ee.elements.each do |e|
         case e.name
         when 'SOURCE'
           dsn.source = e.text
@@ -80,10 +79,10 @@ class DAS
     end
     result = Bio::Command.post_form("#{@server}/das/#{src}/entry_points")
     doc = REXML::Document.new(result.body)
-    doc.elements.each('/descendant::ENTRY_POINTS') do |e|
-      entry_point.href = e.attributes['href']
-      entry_point.version = e.attributes['version']
-      e.elements.each do |e|
+    doc.elements.each('/descendant::ENTRY_POINTS') do |ee|
+      entry_point.href = ee.attributes['href']
+      entry_point.version = ee.attributes['version']
+      ee.elements.each do |e|
         segment = SEGMENT.new
         segment.entry_id = e.attributes['id']
         segment.start = e.attributes['start']
@@ -120,9 +119,9 @@ class DAS
       sequence.start = e.attributes['start']
       sequence.stop = e.attributes['stop']
       sequence.version = e.attributes['version']
-      e.elements.each do |e|
-        sequence.sequence = Bio::Sequence::NA.new(e.text)
-        sequence.length = e.attributes['length'].to_i
+      e.elements.each do |el|
+        sequence.sequence = Bio::Sequence::NA.new(el.text)
+        sequence.length = el.attributes['length'].to_i
       end
       ary << sequence
     end
@@ -183,22 +182,22 @@ class DAS
 
     result = Bio::Command.post_form("#{@server}/das/#{dsn}/types", opts)
     doc = REXML::Document.new(result.body)
-    doc.elements.each('/descendant::GFF') do |e|
-      types.version = e.attributes['version']
-      types.href = e.attributes['href']
-      e.elements.each do |e|
+    doc.elements.each('/descendant::GFF') do |ee|
+      types.version = ee.attributes['version']
+      types.href = ee.attributes['href']
+      ee.elements.each do |e|
         segment = SEGMENT.new
         segment.entry_id = e.attributes['id']
         segment.start = e.attributes['start']
         segment.stop = e.attributes['stop']
         segment.version = e.attributes['version']
         segment.label = e.attributes['label']
-        e.elements.each do |e|
+        e.elements.each do |el|
           t = TYPE.new
-          t.entry_id = e.attributes['id']
-          t.method = e.attributes['method']
-          t.category = e.attributes['category']
-          t.count = e.text.to_i
+          t.entry_id = el.attributes['id']
+          t.method = el.attributes['method']
+          t.category = el.attributes['category']
+          t.count = el.text.to_i
           segment.types << t
         end
         types.segments << segment
@@ -234,21 +233,21 @@ class DAS
 
     result = Bio::Command.post_form("#{@server}/das/#{dsn}/features", opts)
     doc = REXML::Document.new(result.body)
-    doc.elements.each('/descendant::GFF') do |e|
-      gff.version = e.attributes['version']
-      gff.href = e.attributes['href']
-      e.elements.each('SEGMENT') do |e|
+    doc.elements.each('/descendant::GFF') do |elem|
+      gff.version = elem.attributes['version']
+      gff.href = elem.attributes['href']
+      elem.elements.each('SEGMENT') do |ele|
         segment = SEGMENT.new
-        segment.entry_id = e.attributes['id']
-        segment.start = e.attributes['start']
-        segment.stop = e.attributes['stop']
-        segment.version = e.attributes['version']
-        segment.label = e.attributes['label']
-        e.elements.each do |e|
+        segment.entry_id = ele.attributes['id']
+        segment.start = ele.attributes['start']
+        segment.stop = ele.attributes['stop']
+        segment.version = ele.attributes['version']
+        segment.label = ele.attributes['label']
+        ele.elements.each do |el|
           feature = FEATURE.new
-          feature.entry_id = e.attributes['id']
-          feature.label = e.attributes['label']
-          e.elements.each do |e|
+          feature.entry_id = el.attributes['id']
+          feature.label = el.attributes['label']
+          el.elements.each do |e|
             case e.name
             when 'TYPE'
               type = TYPE.new
@@ -289,21 +288,21 @@ class DAS
               group.entry_id = e.attributes['id']
               group.label = e.attributes['label']
               group.type = e.attributes['type']
-              e.elements.each do |e|
-                case e.name
+              e.elements.each do |ee|
+                case ee.name
                 when 'NOTE'		# in GROUP
-                  group.notes << e.text
+                  group.notes << ee.text
                 when 'LINK'		# in GROUP
                   link = LINK.new
-                  link.href = e.attributes['href']
-                  link.text = e.text
+                  link.href = ee.attributes['href']
+                  link.text = ee.text
                   group.links << link
                 when 'TARGET'		# in GROUP
                   target = TARGET.new
-                  target.entry_id = e.attributes['id']
-                  target.start = e.attributes['start']
-                  target.stop = e.attributes['stop']
-                  target.name = e.text
+                  target.entry_id = ee.attributes['id']
+                  target.start = ee.attributes['start']
+                  target.stop = ee.attributes['stop']
+                  target.name = ee.text
                   group.targets << target
                 end
               end

data/lib/bio/io/fastacmd.rb

@@ -8,7 +8,6 @@
 #              Jan Aerts <jan.aerts@bbsrc.ac.uk>
 # License::    The Ruby License
 #
-# $Id: fastacmd.rb,v 1.16 2007/04/05 23:35:41 trevor Exp $
 #
 
 require 'bio/db/fasta'
@@ -146,18 +145,3 @@ end # class Fastacmd
 end # class Blast
 end # module Bio
 
-if $0 == __FILE__
-  fastacmd = Bio::Blast::Fastacmd.new("/path_to_my_db/db_name")
-  seq = fastacmd.get_by_id('id_of_entry1')
-  puts seq.class
-  puts seq
-  
-  seqs = fastacmd.fetch(['id_of_entry1','id_of_entry2'])
-  seqs.each do |seq|
-    puts seq
-  end
-
-  fastacmd.each_entry do |fasta|
-    puts fasta.seq.size.to_s + "\t" + fasta.definition
-  end
-end

data/lib/bio/io/fetch.rb

@@ -5,24 +5,31 @@
 #               Copyright (C) 2006 Jan Aerts <jan.aerts@bbsrc.ac.uk>
 # License::     The Ruby License
 #
-#  $Id:$
-#
 # == DESCRIPTION
 #
-# Using BioRuby BioFetch server
-#
-#   br_server = Bio::Fetch.new()
-#   puts br_server.databases
-#   puts br_server.formats('embl')
-#   puts br_server.maxids
-#
-# Using EBI BioFetch server
+# Using EBI Dbfetch server
 #
-#   ebi_server = Bio::Fetch.new('http://www.ebi.ac.uk/cgi-bin/dbfetch')
+#   ebi_server = Bio::Fetch::EBI.new
+#   puts ebi_server.fetch('embl', 'J00231')
 #   puts ebi_server.fetch('embl', 'J00231', 'raw')
 #   puts ebi_server.fetch('embl', 'J00231', 'html')
-#   puts Bio::Fetch.query('genbank', 'J00231')
-#   puts Bio::Fetch.query('genbank', 'J00231', 'raw', 'fasta')
+#
+# Getting metadata from EBI Dbfetch server
+#
+#   puts ebi_server.databases
+#   puts ebi_server.formats('embl')
+#   puts ebi_server.maxids
+#
+# Using EBI Dbfetch server without creating a Bio::Fetch::EBI instance
+#
+#   puts Bio::Fetch::EBI.query('ena_sequence', 'J00231')
+#   puts Bio::Fetch::EBI.query('ena_sequence', 'J00231', 'raw', 'fasta')
+#
+# Using a BioFetch server with specifying URL
+#
+#   server = Bio::Fetch.new('http://www.ebi.ac.uk/Tools/dbfetch/dbfetch')
+#   puts server.fetch('ena_sequence', 'J00231')
+#   puts server.fetch('ena_sequence', 'J00231', 'raw', 'fasta')
 # 
 
 require 'uri'
@@ -37,26 +44,39 @@ module Bio
   # nucleic or amino acid sequence.
   #
   # Possible dbfetch servers include:
-  # * http://bioruby.org/cgi-bin/biofetch.rb (default)
-  # * http://www.ebi.ac.uk/cgi-bin/dbfetch
+  # * http://www.ebi.ac.uk/Tools/dbfetch/dbfetch
+  #
+  # Note that old URL http://www.ebi.ac.uk/cgi-bin/dbfetch still alives
+  # probably because of compatibility, but using the new URL is recommended.
+  #
+  # Historically, there were other dbfetch servers including:
+  # * http://bioruby.org/cgi-bin/biofetch.rb (default before BioRuby 1.4)
+  # But they are unavailable now.
+  #
   #
   # If you're behind a proxy server, be sure to set your HTTP_PROXY
   # environment variable accordingly.
   #
   # = USAGE
   #  require 'bio'
-  #
+  #  
   #  # Retrieve the sequence of accession number M33388 from the EMBL
   #  # database.
-  #  server = Bio::Fetch.new()  #uses default server
+  #  server = Bio::Fetch::EBI.new  #uses EBI server
+  #  puts server.fetch('ena_sequence','M33388')
+  #
+  #  # database name "embl" can also be used though it is not officially listed
   #  puts server.fetch('embl','M33388')
-  #  
-  #  # Do the same thing without creating a Bio::Fetch object. This method always
-  #  # uses the default dbfetch server: http://bioruby.org/cgi-bin/biofetch.rb
-  #  puts Bio::Fetch.query('embl','M33388')
   #
-  #  # To know what databases are available on the bioruby dbfetch server:
-  #  server = Bio::Fetch.new()
+  #  # Do the same thing with explicitly giving the URL.
+  #  server = Bio::Fetch.new(Bio::Fetch::EBI::URL)  #uses EBI server
+  #  puts server.fetch('ena_sequence','M33388')
+  #
+  #  # Do the same thing without creating a Bio::Fetch::EBI object.
+  #  puts Bio::Fetch::EBI.query('ena_sequence','M33388')
+  #
+  #  # To know what databases are available on the dbfetch server:
+  #  server = Bio::Fetch::EBI.new
   #  puts server.databases
   #
   #  # Some databases provide their data in different formats (e.g. 'fasta',
@@ -66,15 +86,62 @@ module Bio
   #
   class Fetch
   
+    # Bio::Fetch::EBI is a client of EBI Dbfetch
+    # (http://www.ebi.ac.uk/Tools/dbfetch/dbfetch).
+    #
+    # An instance of this class works the same as:
+    #  obj = Bio::Fetch.new("http://www.ebi.ac.uk/Tools/dbfetch/dbfetch")
+    #  obj.database = "ena_sequence"
+    #
+    # See the documents of Bio::Fetch for more details.
+    class EBI < Fetch
+
+      # EBI Dbfetch server URL
+      URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch".freeze
+
+      # For the usage, see the document of Bio::Fetch.new.
+      def initialize(url = URL)
+        @database = "ena_sequence"
+        super
+      end
+
+      # Shortcut for using EBI Dbfetch server. You can fetch an entry
+      # without creating an instance of Bio::Fetch::EBI. This method uses
+      # EBI Dbfetch server http://www.ebi.ac.uk/Tools/dbfetch/dbfetch .
+      # 
+      # Example:
+      #   puts Bio::Fetch::EBI.query('refseq','NM_123456')
+      #   puts Bio::Fetch::EBI.query('ena_sequence','J00231')
+      #
+      # ---
+      # *Arguments*:
+      # * _database_: name of database to query (see Bio::Fetch#databases to get list of supported databases)
+      # * _id_: single ID or ID list separated by commas or white space
+      # * _style_: [raw|html] (default = 'raw')
+      # * _format_: name of output format (see Bio::Fetch#formats)
+      def self.query(*args)
+        self.new.fetch(*args)
+      end
+    end #class EBI
+
     # Create a new Bio::Fetch server object that can subsequently be queried
-    # using the Bio::Fetch#fetch method
+    # using the Bio::Fetch#fetch method.
+    #
+    # You must specify _url_ of a server.
+    # The preset default server is deprecated.
+    #
+    # If you want to use a server without explicitly specifying the URL,
+    # use Bio::Fetch::EBI.new that uses EBI Dbfetch server.
+    #
     # ---
     # *Arguments*:
-    # * _url_: URL of dbfetch server (default = 'http://bioruby.org/cgi-bin/biofetch.rb')
+    # * _url_: URL of dbfetch server. (no default value)
     # *Returns*:: Bio::Fetch object
-    def initialize(url = 'http://bioruby.org/cgi-bin/biofetch.rb')
+    def initialize(url = nil)
+      unless url then
+        raise ArgumentError, "No server URL is given in Bio::Fetch.new. The default server URL value have been deprecated. You must explicitly specify the url or use Bio::Fetch::EBI for using EBI Dbfetch."
+      end
       @url = url
-      schema, user, @host, @port, reg, @path, = URI.split(@url)
     end
   
     # The default database to query
@@ -90,8 +157,8 @@ module Bio
     end
   
     # Fetch a database entry as specified by database (db), entry id (id),
-    # 'raw' text or 'html' (style), and format.  When using BioRuby's
-    # BioFetch server, value for the format should not be set.
+    # 'raw' text or 'html' (style), and format.
+    #
     # Examples:
     #   server = Bio::Fetch.new('http://www.ebi.ac.uk/cgi-bin/dbfetch')
     #   puts server.fetch('embl','M33388','raw','fasta')
@@ -111,23 +178,6 @@ module Bio
       _get(query)
     end
   
-    # Shortcut for using BioRuby's BioFetch server. You can fetch an entry
-    # without creating an instance of BioFetch server. This method uses the 
-    # default dbfetch server, which is http://bioruby.org/cgi-bin/biofetch.rb
-    # 
-    # Example:
-    #   puts Bio::Fetch.query('refseq','NM_12345')
-    #
-    # ---
-    # *Arguments*:
-    # * _database_: name of database to query (see Bio::Fetch#databases to get list of supported databases)
-    # * _id_: single ID or ID list separated by commas or white space
-    # * _style_: [raw|html] (default = 'raw')
-    # * _format_: name of output format (see Bio::Fetch#formats)
-    def self.query(*args)
-      self.new.fetch(*args)
-    end
-  
     # Using this method, the user can ask a dbfetch server what databases
     # it supports. This would normally be the first step you'd take when
     # you use a dbfetch server for the first time.
@@ -135,9 +185,8 @@ module Bio
     #  server = Bio::Fetch.new()
     #  puts server.databases # returns "aa aax bl cpd dgenes dr ec eg emb ..."
     #
-    # This method only works for the bioruby dbfetch server. For a list
-    # of databases available from the EBI, see the EBI website at 
-    # http://www.ebi.ac.uk/cgi-bin/dbfetch/
+    # This method works for EBI Dbfetch server (and for the bioruby dbfetch
+    # server). Not all servers support this method.
     # ---
     # *Returns*:: array of database names
     def databases
@@ -145,11 +194,13 @@ module Bio
     end
   
     # Lists the formats that are available for a given database. Like the
-    # Bio::Fetch#databases method, this method is only available on 
-    # the bioruby dbfetch server.
+    # Bio::Fetch#databases method, not all servers support this method.
+    # This method is available on the EBI Dbfetch server (and on the bioruby
+    # dbfetch server).
+    #
     # Example:
-    #  server = Bio::Fetch.new()
-    #  puts server.formats('embl') # returns "default fasta"
+    #  server = Bio::Fetch::EBI.new()
+    #  puts server.formats('embl') # returns [ "default", "annot", ... ]
     # ---
     # *Arguments*:
     # * _database_:: name of database you want the supported formats for
@@ -164,8 +215,13 @@ module Bio
   
     # A dbfetch server will only return entries up to a given maximum number.
     # This method retrieves that number from the server. As for the databases
-    # and formats methods, the maxids method only works for the bioruby
-    # dbfetch server.
+    # and formats methods, not all servers support the maxids method.
+    # This method is available on the EBI Dbfetch server (and on the bioruby
+    # dbfetch server).
+    #
+    # Example:
+    #  server = Bio::Fetch::EBI.new
+    #  puts server.maxids # currently returns 200
     # ---
     # *Arguments*: none
     # *Returns*:: number