(.*?)<\/pre>/m).flatten
!       return result
!     end

!     # Search the PubMed database by given keywords using E-Utils and returns 
!     # an array of PubMed IDs.
!     # 
!     # For information on the possible arguments, see
!     # http://eutils.ncbi.nlm.nih.gov/entrez/query/static/esearch_help.html#PubMed
!     # ---
!     # *Arguments*:
!     # * _id_: query string (required)
!     # * _field_
!     # * _reldate_
!     # * _mindate_
!     # * _maxdate_
!     # * _datetype_
!     # * _retstart_
!     # * _retmax_ (default 100)
!     # * _retmode_
!     # * _rettype_
!     # *Returns*:: array of PubMed IDs
!     def self.esearch(str, hash = {})
!       hash['retmax'] = 100 unless hash['retmax']

!       opts = []
!       hash.each do |k, v|
!         opts << "#{k}=#{v}"
!       end

!       host = "eutils.ncbi.nlm.nih.gov"
!       path = "/entrez/eutils/esearch.fcgi?tool=bioruby&db=pubmed&#{opts.join('&')}&term="

!       http = Bio::Command.new_http(host)
!       response, = http.get(path + CGI.escape(str))
!       result = response.body
!       result = result.scan(/(.*?)<\/Id>/m).flatten
!       return result
!     end

!     # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!     # entrez query.
!     # ---
!     # *Arguments*:
!     # * _id_: PubMed ID (required)
!     # *Returns*:: MEDLINE formatted String
!     def self.query(id)
!       host = "www.ncbi.nlm.nih.gov"
!       path = "/entrez/query.fcgi?tool=bioruby&cmd=Text&dopt=MEDLINE&db=PubMed&uid="

!       http = Bio::Command.new_http(host)
!       response, = http.get(path + id.to_s)
!       result = response.body
!       if result =~ /#{id}\s+Error/
!         raise( result )
!       else
!         result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
!         return result
!       end
      end

!     # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!     # entrez pmfetch.
!     # ---
!     # *Arguments*:
!     # * _id_: PubMed ID (required)
!     # *Returns*:: MEDLINE formatted String
!     def self.pmfetch(id)
!       host = "www.ncbi.nlm.nih.gov"
!       path = "/entrez/utils/pmfetch.fcgi?tool=bioruby&mode=text&report=medline&db=PubMed&id="

!       http = Bio::Command.new_http(host)
!       response, = http.get(path + id.to_s)
!       result = response.body
!       if result =~ /#{id}\s+Error/
!         raise( result )
!       else
!         result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
!         return result
!       end
      end

!     # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!     # entrez efetch. Multiple PubMed IDs can be provided:
!     #   Bio::PubMed.efetch(123)
!     #   Bio::PubMed.efetch(123,456,789)
!     #   Bio::PubMed.efetch([123,456,789])
!     # ---
!     # *Arguments*:
!     # * _ids_: list of PubMed IDs (required)
!     # *Returns*:: MEDLINE formatted String
!     def self.efetch(*ids)
!       return [] if ids.empty?
! 
!       host = "eutils.ncbi.nlm.nih.gov"
!       path = "/entrez/eutils/efetch.fcgi?tool=bioruby&db=pubmed&retmode=text&rettype=medline&id="

!       ids = ids.join(",")

!       http = Bio::Command.new_http(host)
!       response, = http.get(path + ids)
!       result = response.body
!       result = result.split(/\n\n+/)
!       return result
!     end

    end

! end

--- 15,194 ----
  module Bio

! # == Description
! #
! # The Bio::PubMed class provides several ways to retrieve bibliographic
! # information from the PubMed database at
! # http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed. Basically, two
! # types of queries are possible:
! #
! # * searching for PubMed IDs given a query string:
! #   * Bio::PubMed#search
! #   * Bio::PubMed#esearch
! #
! # * retrieving the MEDLINE text (i.e. authors, journal, abstract, ...)
! #   given a PubMed ID
! #   * Bio::PubMed#query
! #   * Bio::PubMed#pmfetch
! #   * Bio::PubMed#efetch
! #
! # The different methods within the same group are interchangeable and should
! # return the same result.
! # 
! # Additional information about the MEDLINE format and PubMed programmable
! # APIs can be found on the following websites:
! #
! # * Overview: http://www.ncbi.nlm.nih.gov/entrez/query/static/overview.html
! # * How to link: http://www.ncbi.nlm.nih.gov/entrez/query/static/linking.html
! # * MEDLINE format: http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html#MEDLINEDisplayFormat
! # * Search field descriptions and tags: http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html#SearchFieldDescriptionsandTags
! # * Entrez utilities index: http://www.ncbi.nlm.nih.gov/entrez/utils/utils_index.html
! # * PmFetch CGI help: http://www.ncbi.nlm.nih.gov/entrez/utils/pmfetch_help.html
! # * E-Utilities CGI help: http://eutils.ncbi.nlm.nih.gov/entrez/query/static/eutils_help.html
! #
! # == Usage
! #
! #   require 'bio'
! #
! #   # If you don't know the pubmed ID:
! #   Bio::PubMed.search("(genome AND analysis) OR bioinformatics)").each do |x|
! #     p x
! #   end
! #   Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics)").each do |x|
! #     p x
! #   end
! #   
! #   # To retrieve the MEDLINE entry for a given PubMed ID:
! #   puts Bio::PubMed.query("10592173")
! #   puts Bio::PubMed.pmfetch("10592173")
! #   puts Bio::PubMed.efetch("10592173", "14693808")
! #   # This can be converted into a Bio::MEDLINE object:
! #   manuscript = Bio::PubMed.query("10592173")
! #   medline = Bio::MEDLINE(manuscript)
! #  
! class PubMed

!   # Search the PubMed database by given keywords using entrez query and returns
!   # an array of PubMed IDs.
!   # ---
!   # *Arguments*:
!   # * _id_: query string (required)
!   # *Returns*:: array of PubMed IDs
!   def self.search(str)
!     host = "www.ncbi.nlm.nih.gov"
!     path = "/entrez/query.fcgi?tool=bioruby&cmd=Search&doptcmdl=MEDLINE&db=PubMed&term="

!     http = Bio::Command.new_http(host)
!     response, = http.get(path + CGI.escape(str))
!     result = response.body
!     result = result.gsub("\r", "\n").squeeze("\n")
!     result = result.scan(/(.*?)<\/pre>/m).flatten
!     return result
!   end

!   # Search the PubMed database by given keywords using E-Utils and returns 
!   # an array of PubMed IDs.
!   # 
!   # For information on the possible arguments, see
!   # http://eutils.ncbi.nlm.nih.gov/entrez/query/static/esearch_help.html#PubMed
!   # ---
!   # *Arguments*:
!   # * _id_: query string (required)
!   # * _field_
!   # * _reldate_
!   # * _mindate_
!   # * _maxdate_
!   # * _datetype_
!   # * _retstart_
!   # * _retmax_ (default 100)
!   # * _retmode_
!   # * _rettype_
!   # *Returns*:: array of PubMed IDs
!   def self.esearch(str, hash = {})
!     hash['retmax'] = 100 unless hash['retmax']

!     opts = []
!     hash.each do |k, v|
!       opts << "#{k}=#{v}"
!     end

!     host = "eutils.ncbi.nlm.nih.gov"
!     path = "/entrez/eutils/esearch.fcgi?tool=bioruby&db=pubmed&#{opts.join('&')}&term="

!     http = Bio::Command.new_http(host)
!     response, = http.get(path + CGI.escape(str))
!     result = response.body
!     result = result.scan(/(.*?)<\/Id>/m).flatten
!     return result
!   end

!   # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!   # entrez query.
!   # ---
!   # *Arguments*:
!   # * _id_: PubMed ID (required)
!   # *Returns*:: MEDLINE formatted String
!   def self.query(id)
!     host = "www.ncbi.nlm.nih.gov"
!     path = "/entrez/query.fcgi?tool=bioruby&cmd=Text&dopt=MEDLINE&db=PubMed&uid="

!     http = Bio::Command.new_http(host)
!     response, = http.get(path + id.to_s)
!     result = response.body
!     if result =~ /#{id}\s+Error/
!       raise( result )
!     else
!       result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
!       return result
      end
+   end

!   # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!   # entrez pmfetch.
!   # ---
!   # *Arguments*:
!   # * _id_: PubMed ID (required)
!   # *Returns*:: MEDLINE formatted String
!   def self.pmfetch(id)
!     host = "www.ncbi.nlm.nih.gov"
!     path = "/entrez/utils/pmfetch.fcgi?tool=bioruby&mode=text&report=medline&db=PubMed&id="

!     http = Bio::Command.new_http(host)
!     response, = http.get(path + id.to_s)
!     result = response.body
!     if result =~ /#{id}\s+Error/
!       raise( result )
!     else
!       result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
!       return result
      end
+   end

!   # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
!   # entrez efetch. Multiple PubMed IDs can be provided:
!   #   Bio::PubMed.efetch(123)
!   #   Bio::PubMed.efetch(123,456,789)
!   #   Bio::PubMed.efetch([123,456,789])
!   # ---
!   # *Arguments*:
!   # * _ids_: list of PubMed IDs (required)
!   # *Returns*:: MEDLINE formatted String
!   def self.efetch(*ids)
!     return [] if ids.empty?

!     host = "eutils.ncbi.nlm.nih.gov"
!     path = "/entrez/eutils/efetch.fcgi?tool=bioruby&db=pubmed&retmode=text&rettype=medline&id="

!     ids = ids.join(",")

+     http = Bio::Command.new_http(host)
+     response, = http.get(path + ids)
+     result = response.body
+     result = result.split(/\n\n+/)
+     return result
    end

! end # PubMed
! 
! end # Bio

From k at dev.open-bio.org  Tue Sep 19 01:49:22 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:49:22 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/io sql.rb,1.4,1.5
Message-ID: <200609190549.k8J5nMjc031590@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/io
In directory dev.open-bio.org:/tmp/cvs-serv31586/lib/bio/io

Modified Files:
	sql.rb 
Log Message:
* changed to RDoc
* license is changed from LGPL to Ruby's

Index: sql.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/io/sql.rb,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** sql.rb	26 Sep 2005 13:04:28 -0000	1.4
--- sql.rb	19 Sep 2006 05:49:19 -0000	1.5
***************
*** 1,22 ****
  #
! # bio/io/sql.rb - BioSQL access module
! #
! #   Copyright (C) 2002 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/io/sql.rb - BioSQL access module
  #
! # Copyright::  Copyright (C) 2002 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 31,321 ****
  module Bio

!   class SQL

!     def initialize(db = 'dbi:Mysql:biosql', user = nil, pass = nil)
!       @dbh = DBI.connect(db, user, pass)
!     end

!     def close
!       @dbh.disconnect
!     end

!     def fetch(accession)	# or display_id for fall back
!       query = "select * from bioentry where accession = ?"
!       entry = @dbh.execute(query, accession).fetch
!       return Sequence.new(@dbh, entry) if entry

!       query = "select * from bioentry where display_id = ?"
!       entry = @dbh.execute(query, accession).fetch
!       return Sequence.new(@dbh, entry) if entry
!     end
!     alias get_by_id fetch

!     # for lazy fetching

!     class Sequence

!       def initialize(dbh, entry)
!         @dbh = dbh
!         @bioentry_id = entry['bioentry_id']
!         @database_id = entry['biodatabase_id']
!         @entry_id = entry['display_id']
!         @accession = entry['accession']
!         @version = entry['entry_version']
!         @division = entry['division']
!       end
!       attr_reader :accession, :division, :entry_id, :version

!       def to_fasta
!         if seq = seq
!           return seq.to_fasta(@accession)
!         end
        end

!       def seq
!         query = "select * from biosequence where bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         return unless row

!         mol = row['molecule']
!         seq = row['biosequence_str']

!         case mol
!         when /.na/i			# 'dna' or 'rna'
!           Bio::Sequence::NA.new(seq)
!         else				# 'protein'
!           Bio::Sequence::AA.new(seq)
!         end
        end

!       def subseq(from, to)
!         length = to - from + 1
!         query = "select molecule, substring(biosequence_str, ?, ?) as subseq" +
!                 " from biosequence where bioentry_id = ?"
!         row = @dbh.execute(query, from, length, @bioentry_id).fetch
!         return unless row

!         mol = row['molecule']
!         seq = row['subseq']

!         case mol
!         when /.na/i			# 'dna' or 'rna'
!           Bio::Sequence::NA.new(seq)
!         else				# 'protein'
!           Bio::Sequence::AA.new(seq)
!         end
        end

!       def features
!         array = []
!         query = "select * from seqfeature where bioentry_id = ?"
!         @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!           next unless row

!           f_id = row['seqfeature_id']
!           k_id = row['seqfeature_key_id']
!           s_id = row['seqfeature_source_id']
!           rank = row['seqfeature_rank'].to_i - 1

!           # key : type (gene, CDS, ...)
!           type = feature_key(k_id)

!           # source : database (EMBL/GenBank/SwissProt)
!           database = feature_source(s_id)

!           # location : position
!           locations = feature_locations(f_id)

!           # qualifier
!           qualifiers = feature_qualifiers(f_id)
!   
!           # rank
!           array[rank] = Bio::Feature.new(type, locations, qualifiers)
!         end
!         return Bio::Features.new(array)
        end

!       def references
!         array = []
!         query = <<-END
!           select * from bioentry_reference, reference
!           where bioentry_id = ? and
!           bioentry_reference.reference_id = reference.reference_id
!         END
!         @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!           next unless row

!           hash = {
!             'start'	=> row['reference_start'],
!             'end'	=> row['reference_end'],
!             'journal'	=> row['reference_location'],
!             'title'	=> row['reference_title'],
!             'authors'	=> row['reference_authors'],
!             'medline'	=> row['reference_medline']
!           }
!           hash.default = ''

!           rank = row['reference_rank'].to_i - 1
!           array[rank] = hash
!         end
!         return array
        end

!       def comment
!         query = "select * from comment where bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         row ? row['comment_text'] : ''
!       end
! 
!       def comments
!         array = []
!         query = "select * from comment where bioentry_id = ?"
!         @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!           next unless row
!           rank = row['comment_rank'].to_i - 1
!           array[rank] = row['comment_text']
!         end
!         return array
!       end

!       def database
!         query = "select * from biodatabase where biodatabase_id = ?"
!         row = @dbh.execute(query, @database_id).fetch
!         row ? row['name'] : ''
        end

!       def date
!         query = "select * from bioentry_date where bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         row ? row['date'] : ''
!       end

!       def dblink
!         query = "select * from bioentry_direct_links where source_bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         row ? [row['dbname'], row['accession']] : []
!       end

!       def definition
!         query = "select * from bioentry_description where bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         row ? row['description'] : ''
!       end

!       def keyword
!         query = "select * from bioentry_keywords where bioentry_id = ?"
!         row = @dbh.execute(query, @bioentry_id).fetch
!         row ? row['keywords'] : ''
!       end

!       def taxonomy
!         query = <<-END
!           select full_lineage, common_name, ncbi_taxa_id
!           from bioentry_taxa, taxa
!           where bioentry_id = ? and bioentry_taxa.taxa_id = taxa.taxa_id
!         END
!         row = @dbh.execute(query, @bioentry_id).fetch
!         @lineage = row ? row['full_lineage'] : ''
!         @common_name = row ? row['common_name'] : ''
!         @ncbi_taxa_id = row ? row['ncbi_taxa_id'] : ''
!         row ? [@lineage, @common_name, @ncbi_taxa_id] : []
!       end

!       def lineage
!         taxonomy unless @lineage
!         return @lineage
!       end

!       def common_name
!         taxonomy unless @common_name
!         return @common_name
!       end

!       def ncbi_taxa_id
!         taxonomy unless @ncbi_taxa_id
!         return @ncbi_taxa_id
!       end

-       private

!       def feature_key(k_id)
!         query = "select * from seqfeature_key where seqfeature_key_id = ?"
!         row = @dbh.execute(query, k_id).fetch
!         row ? row['key_name'] : ''
!       end

!       def feature_source(s_id)
!         query = "select * from seqfeature_source where seqfeature_source_id = ?"
!         row = @dbh.execute(query, s_id).fetch
!         row ? row['source_name'] : ''
!       end

!       def feature_locations(f_id)
!         locations = []
!         query = "select * from seqfeature_location where seqfeature_id = ?"
!         @dbh.execute(query, f_id).fetch_all.each do |row|
!           next unless row

!           location = Bio::Location.new
!           location.strand = row['seq_strand']
!           location.from = row['seq_start']
!           location.to = row['seq_end']

!           xref = feature_locations_remote(row['seqfeature_location_id'])
!           location.xref_id = xref.shift unless xref.empty?

!           # just omit fuzzy location for now...
!           #feature_locations_qv(row['seqfeature_location_id'])

!           rank = row['location_rank'].to_i - 1
!           locations[rank] = location
!         end
!         return Bio::Locations.new(locations)
!       end

!       def feature_locations_remote(l_id)
!         query = "select * from remote_seqfeature_name where seqfeature_location_id = ?"
!         row = @dbh.execute(query, l_id).fetch
!         row ? [row['accession'], row['version']] : []
        end

!       def feature_locations_qv(l_id)
!         query = "select * from location_qualifier_value where seqfeature_location_id = ?"
!         row = @dbh.execute(query, l_id).fetch
!         row ? [row['qualifier_value'], row['slot_value']] : []
!       end

!       def feature_qualifiers(f_id)
!         qualifiers = []
!         query = "select * from seqfeature_qualifier_value where seqfeature_id = ?"
!         @dbh.execute(query, f_id).fetch_all.each do |row|
!           next unless row

!           key = feature_qualifiers_key(row['seqfeature_qualifier_id'])
!           value = row['qualifier_value']
!           qualifier = Bio::Feature::Qualifier.new(key, value)

!           rank = row['seqfeature_qualifier_rank'].to_i - 1
!           qualifiers[rank] = qualifier
!         end
!         return qualifiers.compact	# .compact is nasty hack for a while
!       end

!       def feature_qualifiers_key(q_id)
!         query = "select * from seqfeature_qualifier where seqfeature_qualifier_id = ?"
!         row = @dbh.execute(query, q_id).fetch
!         row ? row['qualifier_name'] : ''
        end
      end

    end

! end

--- 18,316 ----
  module Bio

! class SQL

!   def initialize(db = 'dbi:Mysql:biosql', user = nil, pass = nil)
!     @dbh = DBI.connect(db, user, pass)
!   end

!   def close
!     @dbh.disconnect
!   end

!   # Returns Bio::SQL::Sequence object.
!   def fetch(accession)	# or display_id for fall back
!     query = "select * from bioentry where accession = ?"
!     entry = @dbh.execute(query, accession).fetch
!     return Sequence.new(@dbh, entry) if entry

!     query = "select * from bioentry where display_id = ?"
!     entry = @dbh.execute(query, accession).fetch
!     return Sequence.new(@dbh, entry) if entry
!   end
!   alias get_by_id fetch

!   # for lazy fetching

!   class Sequence

!     def initialize(dbh, entry)
!       @dbh = dbh
!       @bioentry_id = entry['bioentry_id']
!       @database_id = entry['biodatabase_id']
!       @entry_id = entry['display_id']
!       @accession = entry['accession']
!       @version = entry['entry_version']
!       @division = entry['division']
!     end
!     attr_reader :accession, :division, :entry_id, :version

!     def to_fasta
!       if seq = seq
!         return seq.to_fasta(@accession)
        end
+     end

!     # Returns Bio::Sequence::NA or AA object.
!     def seq
!       query = "select * from biosequence where bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       return unless row

!       mol = row['molecule']
!       seq = row['biosequence_str']

!       case mol
!       when /.na/i			# 'dna' or 'rna'
!         Bio::Sequence::NA.new(seq)
!       else				# 'protein'
!         Bio::Sequence::AA.new(seq)
        end
+     end

!     # Returns Bio::Sequence::NA or AA object (by lazy fetching).
!     def subseq(from, to)
!       length = to - from + 1
!       query = "select molecule, substring(biosequence_str, ?, ?) as subseq" +
!               " from biosequence where bioentry_id = ?"
!       row = @dbh.execute(query, from, length, @bioentry_id).fetch
!       return unless row

!       mol = row['molecule']
!       seq = row['subseq']

!       case mol
!       when /.na/i			# 'dna' or 'rna'
!         Bio::Sequence::NA.new(seq)
!       else				# 'protein'
!         Bio::Sequence::AA.new(seq)
        end
+     end

!     # Returns Bio::Features object.
!     def features
!       array = []
!       query = "select * from seqfeature where bioentry_id = ?"
!       @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!         next unless row

!         f_id = row['seqfeature_id']
!         k_id = row['seqfeature_key_id']
!         s_id = row['seqfeature_source_id']
!         rank = row['seqfeature_rank'].to_i - 1

!         # key : type (gene, CDS, ...)
!         type = feature_key(k_id)

!         # source : database (EMBL/GenBank/SwissProt)
!         database = feature_source(s_id)

!         # location : position
!         locations = feature_locations(f_id)

!         # qualifier
!         qualifiers = feature_qualifiers(f_id)
! 
!         # rank
!         array[rank] = Bio::Feature.new(type, locations, qualifiers)
        end
+       return Bio::Features.new(array)
+     end

!     # Returns reference informations in Array of Hash (not Bio::Reference).
!     def references
!       array = []
!       query = <<-END
!         select * from bioentry_reference, reference
!         where bioentry_id = ? and
!         bioentry_reference.reference_id = reference.reference_id
!       END
!       @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!         next unless row

!         hash = {
!           'start'	=> row['reference_start'],
!           'end'	=> row['reference_end'],
!           'journal'	=> row['reference_location'],
!           'title'	=> row['reference_title'],
!           'authors'	=> row['reference_authors'],
!           'medline'	=> row['reference_medline']
!         }
!         hash.default = ''

!         rank = row['reference_rank'].to_i - 1
!         array[rank] = hash
        end
+       return array
+     end

!     # Returns the first comment.  For complete comments, use comments method.
!     def comment
!       query = "select * from comment where bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       row ? row['comment_text'] : ''
!     end

!     # Returns comments in an Array of Strings.
!     def comments
!       array = []
!       query = "select * from comment where bioentry_id = ?"
!       @dbh.execute(query, @bioentry_id).fetch_all.each do |row|
!         next unless row
!         rank = row['comment_rank'].to_i - 1
!         array[rank] = row['comment_text']
        end
+       return array
+     end

!     def database
!       query = "select * from biodatabase where biodatabase_id = ?"
!       row = @dbh.execute(query, @database_id).fetch
!       row ? row['name'] : ''
!     end

!     def date
!       query = "select * from bioentry_date where bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       row ? row['date'] : ''
!     end

!     def dblink
!       query = "select * from bioentry_direct_links where source_bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       row ? [row['dbname'], row['accession']] : []
!     end

!     def definition
!       query = "select * from bioentry_description where bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       row ? row['description'] : ''
!     end

!     def keyword
!       query = "select * from bioentry_keywords where bioentry_id = ?"
!       row = @dbh.execute(query, @bioentry_id).fetch
!       row ? row['keywords'] : ''
!     end

!     # Use lineage, common_name, ncbi_taxa_id methods to extract in detail.
!     def taxonomy
!       query = <<-END
!         select full_lineage, common_name, ncbi_taxa_id
!         from bioentry_taxa, taxa
!         where bioentry_id = ? and bioentry_taxa.taxa_id = taxa.taxa_id
!       END
!       row = @dbh.execute(query, @bioentry_id).fetch
!       @lineage = row ? row['full_lineage'] : ''
!       @common_name = row ? row['common_name'] : ''
!       @ncbi_taxa_id = row ? row['ncbi_taxa_id'] : ''
!       row ? [@lineage, @common_name, @ncbi_taxa_id] : []
!     end

!     def lineage
!       taxonomy unless @lineage
!       return @lineage
!     end

!     def common_name
!       taxonomy unless @common_name
!       return @common_name
!     end

+     def ncbi_taxa_id
+       taxonomy unless @ncbi_taxa_id
+       return @ncbi_taxa_id
+     end

!     private

!     def feature_key(k_id)
!       query = "select * from seqfeature_key where seqfeature_key_id = ?"
!       row = @dbh.execute(query, k_id).fetch
!       row ? row['key_name'] : ''
!     end

!     def feature_source(s_id)
!       query = "select * from seqfeature_source where seqfeature_source_id = ?"
!       row = @dbh.execute(query, s_id).fetch
!       row ? row['source_name'] : ''
!     end

!     def feature_locations(f_id)
!       locations = []
!       query = "select * from seqfeature_location where seqfeature_id = ?"
!       @dbh.execute(query, f_id).fetch_all.each do |row|
!         next unless row

!         location = Bio::Location.new
!         location.strand = row['seq_strand']
!         location.from = row['seq_start']
!         location.to = row['seq_end']

!         xref = feature_locations_remote(row['seqfeature_location_id'])
!         location.xref_id = xref.shift unless xref.empty?

!         # just omit fuzzy location for now...
!         #feature_locations_qv(row['seqfeature_location_id'])

!         rank = row['location_rank'].to_i - 1
!         locations[rank] = location
        end
+       return Bio::Locations.new(locations)
+     end

!     def feature_locations_remote(l_id)
!       query = "select * from remote_seqfeature_name where seqfeature_location_id = ?"
!       row = @dbh.execute(query, l_id).fetch
!       row ? [row['accession'], row['version']] : []
!     end

!     def feature_locations_qv(l_id)
!       query = "select * from location_qualifier_value where seqfeature_location_id = ?"
!       row = @dbh.execute(query, l_id).fetch
!       row ? [row['qualifier_value'], row['slot_value']] : []
!     end

!     def feature_qualifiers(f_id)
!       qualifiers = []
!       query = "select * from seqfeature_qualifier_value where seqfeature_id = ?"
!       @dbh.execute(query, f_id).fetch_all.each do |row|
!         next unless row

!         key = feature_qualifiers_key(row['seqfeature_qualifier_id'])
!         value = row['qualifier_value']
!         qualifier = Bio::Feature::Qualifier.new(key, value)

!         rank = row['seqfeature_qualifier_rank'].to_i - 1
!         qualifiers[rank] = qualifier
        end
+       return qualifiers.compact	# .compact is nasty hack for a while
      end

+     def feature_qualifiers_key(q_id)
+       query = "select * from seqfeature_qualifier where seqfeature_qualifier_id = ?"
+       row = @dbh.execute(query, q_id).fetch
+       row ? row['qualifier_name'] : ''
+     end
    end

! end # SQL
! 
! end # Bio

***************
*** 365,428 ****
  end

- 
- =begin
- 
- = Bio::SQL
- 
- --- Bio::SQL.new(db = 'dbi:Mysql:biosql', user = nil, pass = nil)
- 
- --- Bio::SQL.close
- 
- --- Bio::SQL#fetch(accession)
- 
-       Returns Bio::SQL::Sequence object.
- 
- == Bio::SQL::Sequence
- 
- --- Bio::SQL::Sequence.new(dbh, entry)
- 
- --- Bio::SQL::Sequence#accession -> String
- --- Bio::SQL::Sequence#comment -> String
- 
-       Returns the first comment.  For complete comments, use comments method.
- 
- --- Bio::SQL::Sequence#comments -> Array
- 
-       Returns comments in an Array of Strings.
- 
- --- Bio::SQL::Sequence#common_name -> String
- --- Bio::SQL::Sequence#database -> String
- --- Bio::SQL::Sequence#date -> String
- --- Bio::SQL::Sequence#dblink -> Array
- --- Bio::SQL::Sequence#definition -> String
- --- Bio::SQL::Sequence#division -> String
- --- Bio::SQL::Sequence#entry_id -> String
- 
- --- Bio::SQL::Sequence#features
- 
-       Returns Bio::Features object.
- 
- --- Bio::SQL::Sequence#keyword -> String
- --- Bio::SQL::Sequence#lineage -> String
- --- Bio::SQL::Sequence#ncbi_taxa_id -> String
- 
- --- Bio::SQL::Sequence#references -> Array
- 
-       Returns reference informations in Array of Hash (not Bio::Reference).
- 
- --- Bio::SQL::Sequence#seq
- 
-       Returns Bio::Sequence::NA or AA object.
- 
- --- Bio::SQL::Sequence#subseq(from, to)
- 
-       Returns Bio::Sequence::NA or AA object (by lazy fetching).
- 
- --- Bio::SQL::Sequence#taxonomy -> DBI::Row
- 
-       Use lineage, common_name, ncbi_taxa_id methods to extract in detail.
- 
- --- Bio::SQL::Sequence#version -> String
- 
- =end
- 
--- 360,361 ----

From k at dev.open-bio.org  Tue Sep 19 01:50:47 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:50:47 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg brite.rb,0.6,0.7
Message-ID: <200609190550.k8J5ol6R031669@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31665/lib/bio/db/kegg

Modified Files:
	brite.rb 
Log Message:
* license is changed from LGPL to Ruby's

Index: brite.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/brite.rb,v
retrieving revision 0.6
retrieving revision 0.7
diff -C2 -d -r0.6 -r0.7
*** brite.rb	8 Sep 2005 01:22:11 -0000	0.6
--- brite.rb	19 Sep 2006 05:50:45 -0000	0.7
***************
*** 1,22 ****
  #
! # bio/db/kegg/brite.rb - KEGG/BRITE database class
! #
! #   Copyright (C) 2001 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/db/kegg/brite.rb - KEGG/BRITE database class
  #
! # Copyright::  Copyright (C) 2001 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 24,51 ****

  module Bio

!   class KEGG
! 
!     class BRITE < KEGGDB
! 
!       DELIMITER	= RS = "\n///\n"
!       TAGSIZE	= 12

!       def initialize(entry)
!         super(entry, TAGSIZE)
!       end

!       # ENTRY
!       # DEFINITION
!       # RELATION
!       # FACTORS
!       # INTERACTION
!       # SOURCE
!       # REFERENCE

!     end

!   end

! end

--- 11,41 ----

  module Bio
+ class KEGG

! # == Note
! #
! # This class is not completely implemented, but obsolete as the original
! # database BRITE has changed it's meaning.
! #
! class BRITE < KEGGDB

!   DELIMITER	= RS = "\n///\n"
!   TAGSIZE	= 12

!   def initialize(entry)
!     super(entry, TAGSIZE)
!   end

!   # ENTRY
!   # DEFINITION
!   # RELATION
!   # FACTORS
!   # INTERACTION
!   # SOURCE
!   # REFERENCE

! end # BRITE

! end # KEGG
! end # Bio

From k at dev.open-bio.org  Tue Sep 19 01:51:31 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:51:31 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg compound.rb,0.11,0.12
Message-ID: <200609190551.k8J5pVOi031729@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31725/lib/bio/db/kegg

Modified Files:
	compound.rb 
Log Message:
* license is changed from LGPL to Ruby's

Index: compound.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/compound.rb,v
retrieving revision 0.11
retrieving revision 0.12
diff -C2 -d -r0.11 -r0.12
*** compound.rb	8 Sep 2005 01:22:11 -0000	0.11
--- compound.rb	19 Sep 2006 05:51:29 -0000	0.12
***************
*** 1,22 ****
  #
! # bio/db/kegg/compound.rb - KEGG COMPOUND database class
! #
! #   Copyright (C) 2001, 2002, 2004 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/db/kegg/compound.rb - KEGG COMPOUND database class
  #
! # Copyright::  Copyright (C) 2001, 2002, 2004 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 24,114 ****

  module Bio

!   class KEGG
! 
!     class COMPOUND < KEGGDB
! 
!       DELIMITER	= RS = "\n///\n"
!       TAGSIZE	= 12
! 
!       def initialize(entry)
!         super(entry, TAGSIZE)
!       end

!       # ENTRY
!       def entry_id
!         unless @data['ENTRY']
!           @data['ENTRY'] = fetch('ENTRY').split(/\s+/).first
!         end
!         @data['ENTRY']
!       end

!       # NAME
!       def names
!         lines_fetch('NAME') 
!       end
!       def name
!         names[0]
!       end

!       # FORMULA
!       def formula
!         field_fetch('FORMULA')
!       end

!       # MASS
!       def mass
!         field_fetch('MASS').to_f
!       end

!       # REACTION
!       def reactions
!         unless @data['REACTION']
!           @data['REACTION'] = fetch('REACTION').split(/\s+/)
!         end
!         @data['REACTION']
!       end

!       # RPAIR
!       def rpairs
!         unless @data['RPAIR']
!           @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
!         end
!         @data['RPAIR']
!       end

!       # PATHWAY
!       def pathways
!         lines_fetch('PATHWAY') 
!       end

!       # ENZYME
!       def enzymes
!         unless @data['ENZYME']
!           field = fetch('ENZYME')
!           if /\(/.match(field)	# old version
!             @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
!           else
!             @data['ENZYME'] = field.scan(/\S+/)
!           end
!         end
!         @data['ENZYME']
!       end

!       # DBLINKS
!       def dblinks
!         lines_fetch('DBLINKS')
!       end

!       # ATOM, BOND
!       def kcf
!         return "#{get('ATOM')}#{get('BOND')}"
        end
- 
      end

    end

! end

--- 11,99 ----

  module Bio
+ class KEGG

! class COMPOUND < KEGGDB

!   DELIMITER	= RS = "\n///\n"
!   TAGSIZE	= 12

!   def initialize(entry)
!     super(entry, TAGSIZE)
!   end

!   # ENTRY
!   def entry_id
!     unless @data['ENTRY']
!       @data['ENTRY'] = fetch('ENTRY').split(/\s+/).first
!     end
!     @data['ENTRY']
!   end

!   # NAME
!   def names
!     lines_fetch('NAME') 
!   end
!   def name
!     names[0]
!   end

!   # FORMULA
!   def formula
!     field_fetch('FORMULA')
!   end

!   # MASS
!   def mass
!     field_fetch('MASS').to_f
!   end

!   # REACTION
!   def reactions
!     unless @data['REACTION']
!       @data['REACTION'] = fetch('REACTION').split(/\s+/)
!     end
!     @data['REACTION']
!   end

!   # RPAIR
!   def rpairs
!     unless @data['RPAIR']
!       @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
!     end
!     @data['RPAIR']
!   end

!   # PATHWAY
!   def pathways
!     lines_fetch('PATHWAY') 
!   end

!   # ENZYME
!   def enzymes
!     unless @data['ENZYME']
!       field = fetch('ENZYME')
!       if /\(/.match(field)	# old version
!         @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
!       else
!         @data['ENZYME'] = field.scan(/\S+/)
        end
      end
+     @data['ENZYME']
+   end
+ 
+   # DBLINKS
+   def dblinks
+     lines_fetch('DBLINKS')
+   end

+   # ATOM, BOND
+   def kcf
+     return "#{get('ATOM')}#{get('BOND')}"
    end

! end # COMPOUND
! 
! end # KEGG
! end # Bio

From k at dev.open-bio.org  Tue Sep 19 01:52:07 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:52:07 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg enzyme.rb,0.8,0.9
Message-ID: <200609190552.k8J5q73d031772@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31768/lib/bio/db/kegg

Modified Files:
	enzyme.rb 
Log Message:
* license is changed from LGPL to Ruby's

Index: enzyme.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/enzyme.rb,v
retrieving revision 0.8
retrieving revision 0.9
diff -C2 -d -r0.8 -r0.9
*** enzyme.rb	8 Sep 2005 01:22:11 -0000	0.8
--- enzyme.rb	19 Sep 2006 05:52:05 -0000	0.9
***************
*** 1,22 ****
  #
! # bio/db/kegg/enzyme.rb - KEGG/ENZYME database class
! #
! #   Copyright (C) 2001, 2002 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/db/kegg/enzyme.rb - KEGG/ENZYME database class
  #
! # Copyright::  Copyright (C) 2001, 2002 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 24,125 ****

  module Bio

!   class KEGG
! 
!     class ENZYME < KEGGDB
! 
!       DELIMITER	= RS = "\n///\n"
!       TAGSIZE	= 12
! 
!       def initialize(entry)
!         super(entry, TAGSIZE)
!       end

!       # ENTRY
!       def entry_id
!         field_fetch('ENTRY')
!       end

!       # NAME
!       def names
!         lines_fetch('NAME')
!       end
!       def name
!         names[0]
!       end

!       # CLASS
!       def classes
!         lines_fetch('CLASS')
!       end

!       # SYSNAME
!       def sysname
!         field_fetch('SYSNAME')
!       end

!       # REACTION ';'
!       def reaction
!         field_fetch('REACTION')
!       end
!       
!       # SUBSTRATE
!       def substrates
!         lines_fetch('SUBSTRATE')
!       end

!       # PRODUCT
!       def products
!         lines_fetch('PRODUCT')
!       end

!       # COFACTOR
!       def cofactors
!         lines_fetch('COFACTOR')
!       end

!       # COMMENT
!       def comment
!         field_fetch('COMMENT')
!       end

!       # PATHWAY
!       def pathways
!         lines_fetch('PATHWAY')
!       end

!       # GENES
!       def genes
!         lines_fetch('GENES')
!       end

!       # DISEASE
!       def diseases
!         lines_fetch('DISEASE')
!       end

!       # MOTIF
!       def motifs
!         lines_fetch('MOTIF')
!       end

!       # STRUCTURES
!       def structures
!         unless @data['STRUCTURES']
!           @data['STRUCTURES'] =
!             fetch('STRUCTURES').sub(/(PDB: )*/,'').split(/\s+/)
!         end
!         @data['STRUCTURES']
!       end

!       # DBLINKS
!       def dblinks
!         lines_fetch('DBLINKS')
!       end

      end

    end

! end

--- 11,110 ----

  module Bio
+ class KEGG

! class ENZYME < KEGGDB

!   DELIMITER	= RS = "\n///\n"
!   TAGSIZE	= 12

!   def initialize(entry)
!     super(entry, TAGSIZE)
!   end

!   # ENTRY
!   def entry_id
!     field_fetch('ENTRY')
!   end

!   # NAME
!   def names
!     lines_fetch('NAME')
!   end
!   def name
!     names[0]
!   end

!   # CLASS
!   def classes
!     lines_fetch('CLASS')
!   end

!   # SYSNAME
!   def sysname
!     field_fetch('SYSNAME')
!   end

!   # REACTION ';'
!   def reaction
!     field_fetch('REACTION')
!   end
!   
!   # SUBSTRATE
!   def substrates
!     lines_fetch('SUBSTRATE')
!   end

!   # PRODUCT
!   def products
!     lines_fetch('PRODUCT')
!   end

!   # COFACTOR
!   def cofactors
!     lines_fetch('COFACTOR')
!   end

!   # COMMENT
!   def comment
!     field_fetch('COMMENT')
!   end

!   # PATHWAY
!   def pathways
!     lines_fetch('PATHWAY')
!   end

!   # GENES
!   def genes
!     lines_fetch('GENES')
!   end

!   # DISEASE
!   def diseases
!     lines_fetch('DISEASE')
!   end

!   # MOTIF
!   def motifs
!     lines_fetch('MOTIF')
!   end

+   # STRUCTURES
+   def structures
+     unless @data['STRUCTURES']
+       @data['STRUCTURES'] =
+         fetch('STRUCTURES').sub(/(PDB: )*/,'').split(/\s+/)
      end
+     @data['STRUCTURES']
+   end

+   # DBLINKS
+   def dblinks
+     lines_fetch('DBLINKS')
    end

! end # ENZYME
! 
! end # KEGG
! end # Bio

From k at dev.open-bio.org  Tue Sep 19 01:52:47 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:52:47 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg genome.rb,0.14,0.15
Message-ID: <200609190552.k8J5qlIc031815@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31811/lib/bio/db/kegg

Modified Files:
	genome.rb 
Log Message:
* license is changed from LGPL to Ruby's
* document is changed to RDoc

Index: genome.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/genome.rb,v
retrieving revision 0.14
retrieving revision 0.15
diff -C2 -d -r0.14 -r0.15
*** genome.rb	8 Sep 2005 01:22:11 -0000	0.14
--- genome.rb	19 Sep 2006 05:52:45 -0000	0.15
***************
*** 1,22 ****
  #
! # bio/db/kegg/genome.rb - KEGG/GENOME database class
! #
! #   Copyright (C) 2001, 2002 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/db/kegg/genome.rb - KEGG/GENOME database class
  #
! # Copyright::  Copyright (C) 2001, 2002 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 24,213 ****

  module Bio

!   class KEGG
! 
!     class GENOME < KEGGDB

!       DELIMITER	= RS = "\n///\n"
!       TAGSIZE	= 12

!       def initialize(entry)
!         super(entry, TAGSIZE)
!       end

!       # ENTRY
!       def entry_id
!         field_fetch('ENTRY')
!       end
!       
!       # NAME
!       def name
!         field_fetch('NAME')
!       end

!       # DEFINITION
!       def definition
!         field_fetch('DEFINITION')
!       end
!       alias organism definition

!       # TAXONOMY
!       def taxonomy
!         unless @data['TAXONOMY']
!           taxid, lineage = subtag2array(get('TAXONOMY'))
!           taxid   = taxid   ? truncate(tag_cut(taxid))   : ''
!           lineage = lineage ? truncate(tag_cut(lineage)) : ''
!           @data['TAXONOMY'] = {
!             'taxid'	=> taxid,
!             'lineage'	=> lineage,
!           }
!           @data['TAXONOMY'].default = ''
!         end
!         @data['TAXONOMY']
!       end

!       def taxid
!         taxonomy['taxid']
!       end

!       def lineage
!         taxonomy['lineage']
!       end

!       # COMMENT
!       def comment
!         field_fetch('COMMENT')
!       end
!       
!       # REFERENCE
!       def references
!         unless @data['REFERENCE']
!           ary = []
!           toptag2array(get('REFERENCE')).each do |ref|
!             hash = Hash.new('')
!             subtag2array(ref).each do |field|
!               case tag_get(field)
!               when /AUTHORS/
!                 authors = truncate(tag_cut(field))
!                 authors = authors.split(', ')
!                 authors[-1] = authors[-1].split(/\s+and\s+/)
!                 authors = authors.flatten.map { |a| a.sub(',', ', ') }
!                 hash['authors']	= authors
!               when /TITLE/
!                 hash['title']	= truncate(tag_cut(field))
!               when /JOURNAL/
!                 journal = truncate(tag_cut(field))
!                 if journal =~ /(.*) (\d+):(\d+)-(\d+) \((\d+)\) \[UI:(\d+)\]$/
!                   hash['journal']	= $1
!                   hash['volume']	= $2
!                   hash['pages']		= $3
!                   hash['year']		= $5
!                   hash['medline']	= $6
!                 else
!                   hash['journal'] = journal
!                 end
!               end
              end
-             ary.push(Reference.new(hash))
            end
-           @data['REFERENCE'] = References.new(ary)
          end
!         @data['REFERENCE']
        end

!       # CHROMOSOME
!       def chromosomes
!         unless @data['CHROMOSOME']
!           @data['CHROMOSOME'] = []
!           toptag2array(get('CHROMOSOME')).each do |chr|
!             hash = Hash.new('')
!             subtag2array(chr).each do |field|
!               hash[tag_get(field)] = truncate(tag_cut(field))
!             end
!             @data['CHROMOSOME'].push(hash)
!           end
          end
!         @data['CHROMOSOME']
        end

!       # PLASMID
!       def plasmids
!         unless @data['PLASMID']
!           @data['PLASMID'] = []
!           toptag2array(get('PLASMID')).each do |chr|
!             hash = Hash.new('')
!             subtag2array(chr).each do |field|
!               hash[tag_get(field)] = truncate(tag_cut(field))
!             end
!             @data['PLASMID'].push(hash)
!           end
          end
!         @data['PLASMID']
        end

!       # SCAFFOLD
!       def scaffolds
!         unless @data['SCAFFOLD']
!           @data['SCAFFOLD'] = []
!           toptag2array(get('SCAFFOLD')).each do |chr|
!             hash = Hash.new('')
!             subtag2array(chr).each do |field|
!               hash[tag_get(field)] = truncate(tag_cut(field))
!             end
!             @data['SCAFFOLD'].push(hash)
!           end
          end
!         @data['SCAFFOLD']
        end

!       # STATISTICS
!       def statistics
!         unless @data['STATISTICS']
!           hash = Hash.new(0.0)
!           get('STATISTICS').each_line do |line|
!             case line
!             when /nucleotides:\s+(\d+)/
!               hash['nalen'] = $1.to_i
!             when /protein genes:\s+(\d+)/
!               hash['num_gene'] = $1.to_i
!             when /RNA genes:\s+(\d+)/
!               hash['num_rna'] = $1.to_i
!             when /G\+C content:\s+(\d+.\d+)/
!               hash['gc'] = $1.to_f
!             end
!           end
!           @data['STATISTICS'] = hash
          end
-         @data['STATISTICS']
-       end
- 
-       def nalen
-         statistics['nalen']
        end
!       alias length nalen

!       def num_gene
!         statistics['num_gene']
!       end

!       def num_rna
!         statistics['num_rna']
!       end

!       def gc
!         statistics['gc']
!       end

!       # GENOMEMAP
!       def genomemap
!         field_fetch('GENOMEMAP')
!       end

!     end
!     
    end

! end

--- 11,214 ----

  module Bio
+ class KEGG

! # == Description
! #
! # Parser for the KEGG GENOME database
! #
! # == References
! #
! # * ftp://ftp.genome.jp/pub/kegg/genomes/genome
! #
! class GENOME < KEGGDB

!   DELIMITER	= RS = "\n///\n"
!   TAGSIZE	= 12

!   def initialize(entry)
!     super(entry, TAGSIZE)
!   end

!   # ENTRY -- Returns contents of the ENTRY record as a String.
!   def entry_id
!     field_fetch('ENTRY')
!   end
!   
!   # NAME -- Returns contents of the NAME record as a String.
!   def name
!     field_fetch('NAME')
!   end

!   # DEFINITION -- Returns contents of the DEFINITION record as a String.
!   def definition
!     field_fetch('DEFINITION')
!   end
!   alias organism definition

!   # TAXONOMY -- Returns contents of the TAXONOMY record as a Hash.
!   def taxonomy
!     unless @data['TAXONOMY']
!       taxid, lineage = subtag2array(get('TAXONOMY'))
!       taxid   = taxid   ? truncate(tag_cut(taxid))   : ''
!       lineage = lineage ? truncate(tag_cut(lineage)) : ''
!       @data['TAXONOMY'] = {
!         'taxid'	=> taxid,
!         'lineage'	=> lineage,
!       }
!       @data['TAXONOMY'].default = ''
!     end
!     @data['TAXONOMY']
!   end

!   # Returns NCBI taxonomy ID from the TAXONOMY record as a String.
!   def taxid
!     taxonomy['taxid']
!   end

!   # Returns contents of the TAXONOMY/LINEAGE record as a String.
!   def lineage
!     taxonomy['lineage']
!   end

!   # COMMENT -- Returns contents of the COMMENT record as a String.
!   def comment
!     field_fetch('COMMENT')
!   end
!   
!   # REFERENCE -- Returns contents of the REFERENCE records as an Array of
!   # Bio::Reference objects.
!   def references
!     unless @data['REFERENCE']
!       ary = []
!       toptag2array(get('REFERENCE')).each do |ref|
!         hash = Hash.new('')
!         subtag2array(ref).each do |field|
!           case tag_get(field)
!           when /AUTHORS/
!             authors = truncate(tag_cut(field))
!             authors = authors.split(', ')
!             authors[-1] = authors[-1].split(/\s+and\s+/)
!             authors = authors.flatten.map { |a| a.sub(',', ', ') }
!             hash['authors']	= authors
!           when /TITLE/
!             hash['title']	= truncate(tag_cut(field))
!           when /JOURNAL/
!             journal = truncate(tag_cut(field))
!             if journal =~ /(.*) (\d+):(\d+)-(\d+) \((\d+)\) \[UI:(\d+)\]$/
!               hash['journal']	= $1
!               hash['volume']	= $2
!               hash['pages']		= $3
!               hash['year']		= $5
!               hash['medline']	= $6
!             else
!               hash['journal'] = journal
              end
            end
          end
!         ary.push(Reference.new(hash))
        end
+       @data['REFERENCE'] = References.new(ary)
+     end
+     @data['REFERENCE']
+   end

!   # CHROMOSOME -- Returns contents of the CHROMOSOME records as an Array
!   # of Hash.
!   def chromosomes
!     unless @data['CHROMOSOME']
!       @data['CHROMOSOME'] = []
!       toptag2array(get('CHROMOSOME')).each do |chr|
!         hash = Hash.new('')
!         subtag2array(chr).each do |field|
!           hash[tag_get(field)] = truncate(tag_cut(field))
          end
!         @data['CHROMOSOME'].push(hash)
        end
+     end
+     @data['CHROMOSOME']
+   end

!   # PLASMID -- Returns contents of the PLASMID records as an Array of Hash.
!   def plasmids
!     unless @data['PLASMID']
!       @data['PLASMID'] = []
!       toptag2array(get('PLASMID')).each do |chr|
!         hash = Hash.new('')
!         subtag2array(chr).each do |field|
!           hash[tag_get(field)] = truncate(tag_cut(field))
          end
!         @data['PLASMID'].push(hash)
        end
+     end
+     @data['PLASMID']
+   end

!   # SCAFFOLD -- Returns contents of the SCAFFOLD records as an Array of Hash.
!   def scaffolds
!     unless @data['SCAFFOLD']
!       @data['SCAFFOLD'] = []
!       toptag2array(get('SCAFFOLD')).each do |chr|
!         hash = Hash.new('')
!         subtag2array(chr).each do |field|
!           hash[tag_get(field)] = truncate(tag_cut(field))
          end
!         @data['SCAFFOLD'].push(hash)
        end
+     end
+     @data['SCAFFOLD']
+   end

!   # STATISTICS -- Returns contents of the STATISTICS record as a Hash.
!   def statistics
!     unless @data['STATISTICS']
!       hash = Hash.new(0.0)
!       get('STATISTICS').each_line do |line|
!         case line
!         when /nucleotides:\s+(\d+)/
!           hash['nalen'] = $1.to_i
!         when /protein genes:\s+(\d+)/
!           hash['num_gene'] = $1.to_i
!         when /RNA genes:\s+(\d+)/
!           hash['num_rna'] = $1.to_i
!         when /G\+C content:\s+(\d+.\d+)/
!           hash['gc'] = $1.to_f
          end
        end
!       @data['STATISTICS'] = hash
!     end
!     @data['STATISTICS']
!   end

!   # Returns number of nucleotides from the STATISTICS record as a Fixnum.
!   def nalen
!     statistics['nalen']
!   end
!   alias length nalen

!   # Returns number of protein genes from the STATISTICS record as a Fixnum.
!   def num_gene
!     statistics['num_gene']
!   end

!   # Returns number of rna from the STATISTICS record as a Fixnum.
!   def num_rna
!     statistics['num_rna']
!   end

!   # Returns G+C content from the STATISTICS record as a Float.
!   def gc
!     statistics['gc']
!   end

!   # GENOMEMAP -- Returns contents of the GENOMEMAP record as a String.
!   def genomemap
!     field_fetch('GENOMEMAP')
    end

! end # GENOME
!     
! end # KEGG
! end # Bio

***************
*** 253,362 ****

- =begin
- 
- = Bio::KEGG::GENOME
- 
- === Initialize
- 
- --- Bio::KEGG::GENOME.new(entry)
- 
- === ENTRY
- 
- --- Bio::KEGG::GENOME#entry_id -> String
- 
-       Returns contents of the ENTRY record as a String.
- 
- === NAME
- 
- --- Bio::KEGG::GENOME#name -> String
- 
-       Returns contents of the NAME record as a String.
- 
- === DEFINITION
- 
- --- Bio::KEGG::GENOME#definition -> String
- 
-       Returns contents of the DEFINITION record as a String.
- 
- --- Bio::KEGG::GENOME#organism -> String
- 
-       Alias for the 'definition' method.
- 
- === TAXONOMY
- 
- --- Bio::KEGG::GENOME#taxonomy -> Hash
- 
-       Returns contents of the TAXONOMY record as a Hash.
- 
- --- Bio::KEGG::GENOME#taxid -> String
- 
-       Returns NCBI taxonomy ID from the TAXONOMY record as a String.
- 
- --- Bio::KEGG::GENOME#lineage -> String
- 
-       Returns contents of the TAXONOMY/LINEAGE record as a String.
- 
- === COMMENT
- 
- --- Bio::KEGG::GENOME#comment -> String
- 
-       Returns contents of the COMMENT record as a String.
- 
- === REFERENCE
- 
- --- Bio::GenBank#references -> Array
- 
-       Returns contents of the REFERENCE records as an Array of Bio::Reference
-       objects.
- 
- === CHROMOSOME
- 
- --- Bio::KEGG::GENOME#chromosomes -> Array
- 
-       Returns contents of the CHROMOSOME records as an Array of Hash.
- 
- === PLASMID
- 
- --- Bio::KEGG::GENOME#plasmids -> Array
- 
-       Returns contents of the PLASMID records as an Array of Hash.
- 
- === SCAFFOLD
- 
- --- Bio::KEGG::GENOME#scaffolds -> Array
- 
-       Returns contents of the SCAFFOLD records as an Array of Hash.
- 
- === STATISTICS
- 
- --- Bio::KEGG::GENOME#statistics -> Hash
- 
-       Returns contents of the STATISTICS record as a Hash.
- 
- --- Bio::KEGG::GENOME#nalen -> Fixnum
- 
-       Returns number of nucleotides from the STATISTICS record as a Fixnum.
- 
- --- Bio::KEGG::GENOME#num_gene -> Fixnum
- 
-       Returns number of protein genes from the STATISTICS record as a Fixnum.
- 
- --- Bio::KEGG::GENOME#num_rna -> Fixnum
- 
-       Returns number of rna from the STATISTICS record as a Fixnum.
- 
- --- Bio::KEGG::GENOME#gc -> Float
- 
-       Returns G+C content from the STATISTICS record as a Float.
- 
- === GENOMEMAP
- 
- --- Bio::KEGG::GENOME#genomemap -> String
- 
-       Returns contents of the GENOMEMAP record as a String.
- 
- == SEE ALSO
- 
-   ftp://ftp.genome.jp/pub/kegg/genomes/genome
- 
- =end
--- 254,255 ----

From k at dev.open-bio.org  Tue Sep 19 01:53:15 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:53:15 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg glycan.rb,1.2,1.3
Message-ID: <200609190553.k8J5rF4d031858@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31854/lib/bio/db/kegg

Modified Files:
	glycan.rb 
Log Message:
* license is changed from LGPL to Ruby's

Index: glycan.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/glycan.rb,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** glycan.rb	8 Sep 2005 01:22:11 -0000	1.2
--- glycan.rb	19 Sep 2006 05:53:13 -0000	1.3
***************
*** 1,22 ****
  #
! # bio/db/kegg/glycan.rb - KEGG GLYCAN database class
! #
! #   Copyright (C) 2004 KATAYAMA Toshiaki 
! #
! #  This library is free software; you can redistribute it and/or
! #  modify it under the terms of the GNU Lesser General Public
! #  License as published by the Free Software Foundation; either
! #  version 2 of the License, or (at your option) any later version.
! #
! #  This library is distributed in the hope that it will be useful,
! #  but WITHOUT ANY WARRANTY; without even the implied warranty of
! #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
! #  Lesser General Public License for more details.
  #
! #  You should have received a copy of the GNU Lesser General Public
! #  License along with this library; if not, write to the Free Software
! #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
  #
! #  $Id$
  #

--- 1,9 ----
  #
! # = bio/db/kegg/glycan.rb - KEGG GLYCAN database class
  #
! # Copyright::  Copyright (C) 2004 Toshiaki Katayama 
! # License::    Ruby's
  #
! # $Id$
  #

***************
*** 24,193 ****

  module Bio

!   class KEGG
! 
!     class GLYCAN < KEGGDB

!       DELIMITER	= RS = "\n///\n"
!       TAGSIZE	= 12

!       def initialize(entry)
!         super(entry, TAGSIZE)
!       end

!       # ENTRY
!       def entry_id
!         unless @data['ENTRY']
!           @data['ENTRY'] = fetch('ENTRY').split(/\s+/).first
!         end
!         @data['ENTRY']
!       end

!       # NAME
!       def name
!         field_fetch('NAME') 
!       end

!       # COMPOSITION
!       def composition
!         unless @data['COMPOSITION']
!           hash = Hash.new(0)
!           fetch('COMPOSITION').scan(/\((\S+)\)(\d+)/).each do |key, val|
!             hash[key] = val.to_i
!           end
!           @data['COMPOSITION'] = hash
!         end
!         @data['COMPOSITION']
        end

!       # MASS
!       def mass
!         unless @data['MASS']
!           hash = Hash.new
!           fetch('MASS').scan(/(\S+)\s+\((\S+)\)/).each do |val, key|
!             hash[key] = val.to_f
!           end
!           @data['MASS'] = hash
!         end
!         @data['MASS']
        end

!       # CLASS
!       def keggclass
!         field_fetch('CLASS') 
!       end

!       # BINDING
!       def bindings
!         unless @data['BINDING']
!           ary = Array.new
!           lines = lines_fetch('BINDING')
!           lines.each do |line|
!             if /^\S/.match(line)
!               ary << line
!             else
!               ary.last << " #{line.strip}"
!             end
!           end
!           @data['BINDING'] = ary
          end
-         @data['BINDING']
        end

!       # COMPOUND
!       def compounds
!         unless @data['COMPOUND']
!           @data['COMPOUND'] = fetch('COMPOUND').split(/\s+/)
!         end
!         @data['COMPOUND']
!       end

!       # REACTION
!       def reactions
!         unless @data['REACTION']
!           @data['REACTION'] = fetch('REACTION').split(/\s+/)
!         end
!         @data['REACTION']
!       end

!       # PATHWAY
!       def pathways
!         lines_fetch('PATHWAY') 
!       end

!       # ENZYME
!       def enzymes
!         unless @data['ENZYME']
!           field = fetch('ENZYME')
!           if /\(/.match(field)	# old version
!             @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
!           else
!             @data['ENZYME'] = field.scan(/\S+/)
!           end
!         end
!         @data['ENZYME']
        end

!       # ORTHOLOG
!       def orthologs
!         unless @data['ORTHOLOG']
!           ary = Array.new
!           lines = lines_fetch('ORTHOLOG')
!           lines.each do |line|
!             if /^\S/.match(line)
!               ary << line
!             else
!               ary.last << " #{line.strip}"
!             end
!           end
!           @data['ORTHOLOG'] = ary
          end
-         @data['ORTHOLOG']
        end

!       # REFERENCE
!       def references
!         unless @data['REFERENCE']
!           ary = Array.new
!           lines = lines_fetch('REFERENCE')
!           lines.each do |line|
!             if /^\d+\s+\[PMID/.match(line)
!               ary << line
!             else
!               ary.last << " #{line.strip}"
!             end
!           end
!           @data['REFERENCE'] = ary
          end
-         @data['REFERENCE']
        end

!       # DBLINKS
!       def dblinks
!         unless @data['DBLINKS']
!           ary = Array.new
!           lines = lines_fetch('DBLINKS')
!           lines.each do |line|
!             if /^\S/.match(line)
!               ary << line
!             else
!               ary.last << " #{line.strip}"
!             end
!           end
!           @data['DBLINKS'] = ary
          end
-         @data['DBLINKS']
        end
! 
!       # ATOM, BOND
!       def kcf
!         return "#{get('NODE')}#{get('EDGE')}"
!       end
! 
      end

    end

! end

--- 11,178 ----

  module Bio
+ class KEGG

! class GLYCAN < KEGGDB

!   DELIMITER	= RS = "\n///\n"
!   TAGSIZE	= 12

!   def initialize(entry)
!     super(entry, TAGSIZE)
!   end

!   # ENTRY
!   def entry_id
!     unless @data['ENTRY']
!       @data['ENTRY'] = fetch('ENTRY').split(/\s+/).first
!     end
!     @data['ENTRY']
!   end

!   # NAME
!   def name
!     field_fetch('NAME') 
!   end

!   # COMPOSITION
!   def composition
!     unless @data['COMPOSITION']
!       hash = Hash.new(0)
!       fetch('COMPOSITION').scan(/\((\S+)\)(\d+)/).each do |key, val|
!         hash[key] = val.to_i
        end
+       @data['COMPOSITION'] = hash
+     end
+     @data['COMPOSITION']
+   end

!   # MASS
!   def mass
!     unless @data['MASS']
!       hash = Hash.new
!       fetch('MASS').scan(/(\S+)\s+\((\S+)\)/).each do |val, key|
!         hash[key] = val.to_f
        end
+       @data['MASS'] = hash
+     end
+     @data['MASS']
+   end

!   # CLASS
!   def keggclass
!     field_fetch('CLASS') 
!   end

!   # BINDING
!   def bindings
!     unless @data['BINDING']
!       ary = Array.new
!       lines = lines_fetch('BINDING')
!       lines.each do |line|
!         if /^\S/.match(line)
!           ary << line
!         else
!           ary.last << " #{line.strip}"
          end
        end
+       @data['BINDING'] = ary
+     end
+     @data['BINDING']
+   end

!   # COMPOUND
!   def compounds
!     unless @data['COMPOUND']
!       @data['COMPOUND'] = fetch('COMPOUND').split(/\s+/)
!     end
!     @data['COMPOUND']
!   end

!   # REACTION
!   def reactions
!     unless @data['REACTION']
!       @data['REACTION'] = fetch('REACTION').split(/\s+/)
!     end
!     @data['REACTION']
!   end

!   # PATHWAY
!   def pathways
!     lines_fetch('PATHWAY') 
!   end

!   # ENZYME
!   def enzymes
!     unless @data['ENZYME']
!       field = fetch('ENZYME')
!       if /\(/.match(field)	# old version
!         @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
!       else
!         @data['ENZYME'] = field.scan(/\S+/)
        end
+     end
+     @data['ENZYME']
+   end

!   # ORTHOLOG
!   def orthologs
!     unless @data['ORTHOLOG']
!       ary = Array.new
!       lines = lines_fetch('ORTHOLOG')
!       lines.each do |line|
!         if /^\S/.match(line)
!           ary << line
!         else
!           ary.last << " #{line.strip}"
          end
        end
+       @data['ORTHOLOG'] = ary
+     end
+     @data['ORTHOLOG']
+   end

!   # REFERENCE
!   def references
!     unless @data['REFERENCE']
!       ary = Array.new
!       lines = lines_fetch('REFERENCE')
!       lines.each do |line|
!         if /^\d+\s+\[PMID/.match(line)
!           ary << line
!         else
!           ary.last << " #{line.strip}"
          end
        end
+       @data['REFERENCE'] = ary
+     end
+     @data['REFERENCE']
+   end

!   # DBLINKS
!   def dblinks
!     unless @data['DBLINKS']
!       ary = Array.new
!       lines = lines_fetch('DBLINKS')
!       lines.each do |line|
!         if /^\S/.match(line)
!           ary << line
!         else
!           ary.last << " #{line.strip}"
          end
        end
!       @data['DBLINKS'] = ary
      end
+     @data['DBLINKS']
+   end

+   # ATOM, BOND
+   def kcf
+     return "#{get('NODE')}#{get('EDGE')}"
    end

! end # GLYCAN
! 
! end # KEGG
! end # Bio

From k at dev.open-bio.org  Tue Sep 19 01:54:32 2006
From: k at dev.open-bio.org (Katayama Toshiaki)
Date: Tue, 19 Sep 2006 05:54:32 +0000
Subject: [BioRuby-cvs] bioruby/lib/bio/db/kegg keggtab.rb,1.8,1.9
Message-ID: <200609190554.k8J5sWw4031901@dev.open-bio.org>

Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31897/lib/bio/db/kegg

Modified Files:
	keggtab.rb 
Log Message:
* document is changed to RDoc

Index: keggtab.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/keggtab.rb,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** keggtab.rb	8 May 2006 14:26:35 -0000	1.8
--- keggtab.rb	19 Sep 2006 05:54:29 -0000	1.9
***************
*** 2,8 ****
  # = bio/db/kegg/keggtab.rb - KEGG keggtab class
  #
! # Copyright::	Copyright (C) 2001 Mitsuteru C. Nakao 
! # 		Copyright (C) 2003, 2006 KATAYAMA Toshiaki 
! # License::	Ruby's
  #
  #  $Id$
--- 2,8 ----
  # = bio/db/kegg/keggtab.rb - KEGG keggtab class
  #
! # Copyright::  Copyright (C) 2001 Mitsuteru C. Nakao 
! #              Copyright (C) 2003, 2006 Toshiaki Katayama 
! # License::    Ruby's
  #
  #  $Id$
***************
*** 12,23 ****
  class KEGG

  # Parse 'keggtab' KEGG database definition file which also includes
! # Taxonomic category of the KEGG organisms.  The 'keggtab' file can
! # be found in
  #
! # * (())
  #
  class Keggtab

    def initialize(file_path, bioroot = nil)
      @bioroot = ENV['BIOROOT'] || bioroot
--- 12,55 ----
  class KEGG

+ # == Description
+ #
  # Parse 'keggtab' KEGG database definition file which also includes
! # Taxonomic category of the KEGG organisms.
  #
! # == References
! #
! # The 'keggtab' file is included in
! #
! # * ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.tar.gz
! # * ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.weekly.last.tar.Z
! #
! # == Format
! #
! # File format is something like
! # 
! #   # KEGGTAB
! #   #
! #   # name            type            directory                    abbreviation
! #   #
! #   enzyme            enzyme          $BIOROOT/db/ideas/ligand     ec
! #   ec                alias           enzyme
! #   (snip)
! #   # Human
! #   h.sapiens         genes           $BIOROOT/db/kegg/genes       hsa
! #   H.sapiens         alias           h.sapiens
! #   hsa               alias           h.sapiens
! #   (snip)
! #   #
! #   # Taxonomy
! #   #
! #   (snip)
! #   animals           alias           hsa+mmu+rno+dre+dme+cel
! #   eukaryotes        alias           animals+plants+protists+fungi
! #   genes             alias           eubacteria+archaea+eukaryotes
  #
  class Keggtab

+   # Path for keggtab file and optionally set bioroot top directory.
+   # Environmental variable BIOROOT overrides bioroot.
    def initialize(file_path, bioroot = nil)
      @bioroot = ENV['BIOROOT'] || bioroot
***************
*** 29,33 ****
      end
    end
!   attr_reader :bioroot, :db_names

--- 61,68 ----
      end
    end
! 
!   # Returns a string of the BIOROOT path prefix.
!   attr_reader :bioroot
!   attr_reader :db_names

***************
*** 35,38 ****
--- 70,74 ----

    class DB
+     # Create a container object for database definitions.
      def initialize(db_name, db_type, db_path, db_abbrev)
        @name = db_name
***************
*** 42,46 ****
        @aliases = Array.new
      end
!     attr_reader :name, :type, :path, :abbrev, :aliases
      alias korg abbrev
      alias keggorg abbrev
--- 78,94 ----
        @aliases = Array.new
      end
!     # Database name. (e.g. 'enzyme', 'h.sapies', 'e.coli', ...)
!     attr_reader :name
!     # Definition type. (e.g. 'enzyme', 'alias', 'genes', ...)
!     attr_reader :type
!     # Database flat file path. (e.g. '$BIOROOT/db/kegg/genes', ...)
!     attr_reader :path
!     # Short name for the database. (e.g. 'ec', 'hsa', 'eco', ...)
!     # korg and keggorg are alias for abbrev method.
!     attr_reader :abbrev
!     # Array containing all alias names for the database.
!     # (e.g. ["H.sapiens", "hsa"], ["E.c