obo_parser 0.2.0 → 0.2.1

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.2.1

data/lib/obo_parser.rb

@@ -9,24 +9,31 @@ module OboParser
 require File.expand_path(File.join(File.dirname(__FILE__), 'tokens'))
 require File.expand_path(File.join(File.dirname(__FILE__), 'parser'))
 require File.expand_path(File.join(File.dirname(__FILE__), 'lexer'))
+require File.expand_path(File.join(File.dirname(__FILE__), 'utilities'))
 
 
 class OboParser # Node
   attr_accessor :terms, :typedefs
 
-  def initialize
+  def initialize # :yields: true
     @terms = []
     @typedefs = [] 
+    true
   end
 
-  def term_strings
+  def term_strings # :yields: Array of Strings
     @terms.collect{|t| t.name}.sort
   end
- 
-  def term_hash
+
+  def term_hash # :yields: Hash (String => String) (name => id)
+    # Warning! This assumes terms are unqiue, they are not required to be so. 
     @terms.inject({}) {|sum, t| sum.update(t.name => t.id)}
   end
- 
+
+  def id_hash # :yields: Hash (String => String (id => name)
+    # ids are unique
+    @terms.inject({}) {|sum, t| sum.update(t.id => t.name)}
+  end
 
   class Stanza
     attr_accessor :name, :id, :tags
@@ -104,3 +111,4 @@ end
 
 
 
+

data/lib/utilities.rb

@@ -0,0 +1,118 @@
+require 'rubygems'
+require 'ruby-debug'
+require 'obo_parser'
+
+module OboParser::Utilities
+
+  # Example usage
+	#	of1 = File.read('hao1.obo')	
+	#	of2 = File.read('hao2.obo')	
+	#	of3 = File.read('hao3.obo')	
+	#	of4 = File.read('hao4.obo')	
+  #
+  #  OboParser::Utilities::dump_comparison_by_id([of1, of2, of3, of4])
+
+  def self.dump_comparison_by_id(files = []) # :yields: String
+    of = [] 
+    files.each_with_index do |f, i|
+      of[i] = parse_obo_file(f)	
+    end
+    
+    all_data = {}
+
+    of.each do |f|
+      tmp_hash = f.id_hash
+      tmp_hash.keys.each do |id|
+        if all_data[id]
+          all_data[id].push tmp_hash[id]
+        else
+          all_data[id] = [tmp_hash[id]]
+        end
+      end
+    end
+
+    puts "\nA list of all labels used across all submitted files for a given ID\n\n"
+    all_data.keys.sort.each do |k|
+      if all_data[k].uniq.size > 1
+        puts "#{k}\t: #{all_data[k].uniq.join(', ')}"
+      end
+    end
+  end
+
+  def self.alignment_translate(infile = nil) # :yields: String
+    # infile is a tab delimited 2 column file that contains IDs in the from FOO_1234
+    # The file is replicated to STDOUT replacing the ID with the Term
+
+    agreement = ARGV[0]
+    raise "Provide a file with comparison." if agreement.nil? 
+    comparison = File.read(agreement)
+   
+    obo_files = Dir.entries('.').inject([]){|sum, a| sum.push( a =~ /\.obo\Z/ ? a : nil)}.compact!
+    identifiers = {}
+
+    obo_files.each do |f|
+      puts "Reading: #{f}"
+      identifiers.merge!(  parse_obo_file(File.read(f)).id_hash )
+    end
+    
+    comparison.each do |l|
+      v1, v2 = l.split("\t")
+      # puts "#{v1} - #{v2}"
+
+      next if v1.nil? || v2.nil?
+
+      v1.gsub!(/_/, ":")
+      v1.strip!
+      v2.gsub!(/_/, ":")
+      v2.strip!
+
+      puts (identifiers[v1].nil? ? 'NOT FOUND' : identifiers[v1]) +
+            "\t" +
+           (identifiers[v2].nil? ? 'NOT FOUND' : identifiers[v2]) 
+    end
+
+  end 
+
+
+  def self.shared_labels(files = []) # :yields: String
+
+  # Returns labels found in all passed ontologies 
+
+  # Usage:
+
+  # of1 = File.read('fly_anatomy.obo')	
+  # of2 = File.read('hao.obo')	
+  # of3 = File.read('mosquito_anatomy.obo')	
+
+  # shared_labels([of1, of6])
+
+    comparison = {}
+
+    files.each do |f|
+      o = parse_obo_file(f)
+      o.term_hash.keys.each do |k|
+        tmp = k.gsub(/adult/, "").strip
+        tmp = k.gsub(/embryonic\/larval/, "").strip
+        if comparison[tmp]
+          comparison[tmp] += 1
+        else
+          comparison.merge!(tmp => 1)
+        end
+      end
+    end
+   
+   match = [] 
+    comparison.keys.each do |k|
+      if comparison[k] == files.size 
+        match.push k
+      end
+    end
+
+   puts  match.sort.join("\n")
+
+   puts "\n#{match.length} total."
+
+  end 
+
+ 
+end

data/obo_parser.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{obo_parser}
-  s.version = "0.2.0"
+  s.version = "0.2.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["mjy"]
-  s.date = %q{2010-03-17}
+  s.date = %q{2011-02-28}
   s.description = %q{Provides all-in-one object containing the contents of an OBO formatted file.  OBO version 1.2 is targeted, though this should work for 1.0. }
   s.email = %q{diapriid@gmail.com}
   s.extra_rdoc_files = [
@@ -31,6 +31,7 @@ Gem::Specification.new do |s|
      "lib/obo_parser.rb",
      "lib/parser.rb",
      "lib/tokens.rb",
+     "lib/utilities.rb",
      "obo_parser.gemspec",
      "tasks/obo_parser_tasks.rake",
      "test/cell.obo",

data/test/test_obo_parser.rb

@@ -71,7 +71,6 @@ class Test_Lexer < Test::Unit::TestCase
     assert_equal 'PATO:0001301', t.value
   end
 
-
   def test_parse_term
      lexer = OboParser::Lexer.new("[Term]")
      assert lexer.pop(OboParser::Tokens::Term)

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 2
-  - 0
-  version: 0.2.0
+  - 1
+  version: 0.2.1
 platform: ruby
 authors: 
 - mjy
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-03-17 00:00:00 -04:00
+date: 2011-02-28 00:00:00 -05:00
 default_executable: 
 dependencies: []
 
@@ -42,6 +42,7 @@ files:
 - lib/obo_parser.rb
 - lib/parser.rb
 - lib/tokens.rb
+- lib/utilities.rb
 - obo_parser.gemspec
 - tasks/obo_parser_tasks.rake
 - test/cell.obo