forage 0.0.2

data/bin/forage

@@ -0,0 +1,16 @@
+#!/usr/bin/env ruby
+
+require File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib', 'forage'))
+
+if ARGV.length != 2
+  $stderr.puts "usage: forage filename.fasta query(regex)"
+  exit
+end
+
+forage = Forage.new File.open(ARGV[0]), ARGV[1]
+
+forage.each do |matches|
+  matches[1].each_with_index do |match, i|
+    puts ">#{matches[0]}:#{i}\n#{match}"
+  end
+end

data/lib/forage.rb

@@ -0,0 +1,47 @@
+class Forage
+  attr_accessor :handle, :iupac, :regex
+
+  def initialize(handle, query)
+    @handle = handle
+    
+    @iupac = Hash.new { |h, k| h[k] = k }.merge(
+      { 'R' => 'AG', 'Y' => 'CTUY', 'S' => 'GCS', 'W' => 'ATUW', 'K' =>
+      'GTUK', 'M' => 'ACM', 'B' => 'CGTUB', 'D' => 'AGTUD', 'H' => 'ACTUH',
+      'V' => 'ACGV', 'N' => '.', '-' => '.'}
+    )
+    
+    @regex = self.convert query
+  end
+
+  # return [header, [matches]]
+  def each
+    self.fasta do |record|
+      next if record[0] == nil
+      header = record[0]
+      sequence = record[1]
+      matches = sequence.scan(@regex)
+      yield [header, matches] if matches != []
+    end
+  end
+
+  # convert string to regex
+  def convert(s)
+    @regex = s.each_char.collect { |n| "[#{@iupac[n]}]" }.join
+    Regexp.new @regex
+  end
+  
+  # parse fasta-formatted data
+  def fasta
+    sequence, header = nil, nil
+    @handle.each do |line|
+      if line[0].chr == '>'
+        yield [ header, sequence ]
+        sequence = ''
+        header = line[1..-1].strip
+      else
+        sequence << line.strip.tr(' ','')
+      end
+    end
+    yield [ header, sequence ]
+  end
+end

metadata

@@ -0,0 +1,48 @@
+--- !ruby/object:Gem::Specification
+name: forage
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+  prerelease: 
+platform: ruby
+authors:
+- Austin G. Davis-Richardson
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-07-06 00:00:00.000000000Z
+dependencies: []
+description: Forage is grep for nucleotide data. With Forage, you can grep nucleotide
+  sequences in FASTA using the IUPAC ambiguous nucleotides code.
+email: harekrishna@gmail.com
+executables:
+- forage
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/forage
+- lib/forage.rb
+homepage: http://www.github.com/audy/forage
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: forage
+rubygems_version: 1.8.5
+signing_key: 
+specification_version: 3
+summary: Grep for nucleotide data.
+test_files: []