Module Bio::NCBIDB::Common
In: lib/bio/db/genbank/common.rb  (CVS)

Description

This module defines a common framework among GenBank, GenPept, RefSeq, and DDBJ. For more details, see the documentations in each genbank/*.rb files.

References

Methods

Constants

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

Public Class methods

[Source]

# File lib/bio/db/genbank/common.rb, line 30
  def initialize(entry)
    super(entry, TAGSIZE)
  end

Public Instance methods

Returns the first part of the VERSION record as "ACCESSION.VERSION" String.

[Source]

# File lib/bio/db/genbank/common.rb, line 57
  def acc_version
    versions.first.to_s
  end

Returns the ACCESSION part of the acc_version.

[Source]

# File lib/bio/db/genbank/common.rb, line 62
  def accession
    acc_version.split(/\./).first.to_s
  end

ACCESSION — Returns contents of the ACCESSION record as an Array.

[Source]

# File lib/bio/db/genbank/common.rb, line 46
  def accessions
    accession.split(/\s+/)
  end

COMMENT — Returns contents of the COMMENT record as a String.

[Source]

# File lib/bio/db/genbank/common.rb, line 183
  def comment
    field_fetch('COMMENT')
  end

[Source]

# File lib/bio/db/genbank/common.rb, line 120
  def common_name
    source['common_name']
  end

DEFINITION — Returns contents of the DEFINITION record as a String.

[Source]

# File lib/bio/db/genbank/common.rb, line 40
  def definition
    field_fetch('DEFINITION')
  end

FEATURES — Returns contents of the FEATURES record as a Bio::Features object.

[Source]

# File lib/bio/db/genbank/common.rb, line 190
  def features
    unless @data['FEATURES']
      ary = []
      in_quote = false
      get('FEATURES').each_line do |line|
        next if line =~ /^FEATURES/

        # feature type  (source, CDS, ...)
        head = line[0,20].to_s.strip

        # feature value (position or /qualifier=)
        body = line[20,60].to_s.chomp

        # sub-array [ feature type, position, /q="data", ... ]
        if line =~ /^ {5}\S/
          ary.push([ head, body ])

        # feature qualifier start (/q="data..., /q="data...", /q=data, /q)
        elsif body =~ /^ \// and not in_quote           # gb:IRO125195
          ary.last.push(body)
          
          # flag for open quote (/q="data...)
          if body =~ /="/ and body !~ /"$/
            in_quote = true
          end

        # feature qualifier continued (...data..., ...data...")
        else
          ary.last.last << body

          # flag for closing quote (/q="data... lines  ...")
          if body =~ /"$/
            in_quote = false
          end
        end
      end

      ary.collect! do |subary|
        parse_qualifiers(subary)
      end

      @data['FEATURES'] = Features.new(ary)
    end
    if block_given?
      @data['FEATURES'].each do |f|
        yield f
      end
    else
      @data['FEATURES']
    end
  end

Returns the second part of the VERSION record as a "GI:#######" String.

[Source]

# File lib/bio/db/genbank/common.rb, line 72
  def gi
    versions.last
  end

KEYWORDS — Returns contents of the KEYWORDS record as an Array of Strings.

[Source]

# File lib/bio/db/genbank/common.rb, line 84
  def keywords
    @data['KEYWORDS'] ||= fetch('KEYWORDS').chomp('.').split(/; /)
  end

LOCUS — Locus class must be defined in child classes.

[Source]

# File lib/bio/db/genbank/common.rb, line 35
  def locus
    # must be overrided in each subclass
  end

NID — Returns contents of the NID record as a String.

[Source]

# File lib/bio/db/genbank/common.rb, line 78
  def nid
    field_fetch('NID')
  end

[Source]

# File lib/bio/db/genbank/common.rb, line 125
  def organism
    source['organism']
  end

ORIGIN — Returns contents of the ORIGIN record as a String.

[Source]

# File lib/bio/db/genbank/common.rb, line 244
  def origin
    unless @data['ORIGIN']
      ori, seqstr = get('ORIGIN').split("\n", 2)
      seqstr ||= ""
      @data['ORIGIN'] = truncate(tag_cut(ori))
      @data['SEQUENCE'] = seqstr.tr("0-9 \t\n\r\/", '')
    end
    @data['ORIGIN']
  end

REFERENCE — Returns contents of the REFERENCE records as an Array of Bio::Reference objects.

[Source]

# File lib/bio/db/genbank/common.rb, line 136
  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+/) if authors[-1]
            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+) \((\d+)\)$/
        hash['journal']  = $1
        hash['volume']   = $2
        hash['issue']    = $3
        hash['pages']    = $4
        hash['year']     = $5
            else
        hash['journal'] = journal
            end
          when /MEDLINE/
            hash['medline']     = truncate(tag_cut(field))
          when /PUBMED/
            hash['pubmed']      = truncate(tag_cut(field))
          end
        end
        ary.push(Reference.new(hash))
      end
      @data['REFERENCE'] = References.new(ary)
    end
    if block_given?
      @data['REFERENCE'].each do |r|
        yield r
      end
    else
      @data['REFERENCE']
    end
  end

SEGMENT — Returns contents of the SEGMENT record as a "m/n" form String.

[Source]

# File lib/bio/db/genbank/common.rb, line 90
  def segment
    @data['SEGMENT'] ||= fetch('SEGMENT').scan(/\d+/).join("/")
  end

SOURCE — Returns contents of the SOURCE record as a Hash.

[Source]

# File lib/bio/db/genbank/common.rb, line 96
  def source
    unless @data['SOURCE']
      name, org = get('SOURCE').split('ORGANISM')
      org ||= ""
      if org[/\S+;/]
        organism = $`
        taxonomy = $& + $'
      elsif org[/\S+\./]                                # rs:NC_001741
        organism = $`
        taxonomy = $& + $'
      else
        organism = org
        taxonomy = ''
      end
      @data['SOURCE'] = {
        'common_name'   => truncate(tag_cut(name)),
        'organism'      => truncate(organism),
        'taxonomy'      => truncate(taxonomy),
      }
      @data['SOURCE'].default = ''
    end
    @data['SOURCE']
  end

[Source]

# File lib/bio/db/genbank/common.rb, line 129
  def taxonomy
    source['taxonomy']
  end
vernacular_name()

Alias for common_name

Returns the VERSION part of the acc_version as a Fixnum

[Source]

# File lib/bio/db/genbank/common.rb, line 67
  def version
    acc_version.split(/\./).last.to_i
  end

VERSION — Returns contents of the VERSION record as an Array of Strings.

[Source]

# File lib/bio/db/genbank/common.rb, line 52
  def versions
    @data['VERSION'] ||= fetch('VERSION').split(/\s+/)
  end

[Validate]