From b2ea0b5a51a558478af60e9df4c643dd58552086 Mon Sep 17 00:00:00 2001
From: martinahansen <martinahansen@74ccb610-7750-0410-82ae-013aeee3265d>
Date: Fri, 21 Jun 2013 09:35:03 +0000
Subject: [PATCH] added edit_distance method to seq.rb

git-svn-id: http://biopieces.googlecode.com/svn/trunk@2184 74ccb610-7750-0410-82ae-013aeee3265d
---
 code_ruby/lib/maasha/seq.rb                   | 18 ++++++++++------
 .../test/maasha/{ => seq}/test_levenshtein.rb | 21 ++++++++++++-------
 code_ruby/test/maasha/test_seq.rb             |  9 ++++++--
 3 files changed, 33 insertions(+), 15 deletions(-)
 rename code_ruby/test/maasha/{ => seq}/test_levenshtein.rb (72%)

diff --git a/code_ruby/lib/maasha/seq.rb b/code_ruby/lib/maasha/seq.rb
index 2788e5d..e4b6bfd 100644
--- a/code_ruby/lib/maasha/seq.rb
+++ b/code_ruby/lib/maasha/seq.rb
@@ -27,9 +27,10 @@ require 'maasha/seq/digest'
 require 'maasha/seq/trim'
 require 'narray'
 
-autoload :BackTrack,   'maasha/seq/backtrack.rb'
-autoload :Dynamic,     'maasha/seq/dynamic.rb'
-autoload :Homopolymer, 'maasha/seq/homopolymer.rb'
+autoload :BackTrack,   'maasha/seq/backtrack'
+autoload :Dynamic,     'maasha/seq/dynamic'
+autoload :Homopolymer, 'maasha/seq/homopolymer'
+autoload :Levenshtein, 'maasha/seq/levenshtein'
 
 # Residue alphabets
 DNA     = %w[a t c g]
@@ -68,7 +69,6 @@ TRANS_TAB11 = {
   "GTG" => "V", "GCG" => "A", "GAG" => "E", "GGG" => "G"
 }
 
-
 # Error class for all exceptions to do with Seq.
 class SeqError < StandardError; end
 
@@ -384,8 +384,14 @@ class Seq
 
   # Method to determine the Hamming Distance between
   # two Sequence objects (case insensitive).
-  def hamming_distance(seq)
-    self.seq.upcase.hamming_distance(seq.seq.upcase)
+  def hamming_distance(entry)
+    self.seq.upcase.hamming_distance(entry.seq.upcase)
+  end
+
+  # Method to determine the Edit Distance between
+  # two Sequence objects (case insensitive).
+  def edit_distance(entry)
+    Levenshtein.distance(self.seq, entry.seq)
   end
 
   # Method that generates a random sequence of a given length and type.
diff --git a/code_ruby/test/maasha/test_levenshtein.rb b/code_ruby/test/maasha/seq/test_levenshtein.rb
similarity index 72%
rename from code_ruby/test/maasha/test_levenshtein.rb
rename to code_ruby/test/maasha/seq/test_levenshtein.rb
index fca9029..a260829 100755
--- a/code_ruby/test/maasha/test_levenshtein.rb
+++ b/code_ruby/test/maasha/seq/test_levenshtein.rb
@@ -27,27 +27,34 @@ $:.unshift File.join(File.dirname(__FILE__), '..', '..')
 
 require 'test/unit'
 require 'test/helper'
-require 'maasha/levenshtein'
+require 'maasha/seq/levenshtein'
 
 class LevenshteinTest < Test::Unit::TestCase
   test "Levenshtein.distance returns 0 with identical strings" do
-    assert_equal(0, Levenshtein.distance("foo", "foo"))
+    assert_equal(0, Levenshtein.distance("atcg", "atcg"))
   end
   
   test "Levenshtein.distance returns s length if t is empty" do
-    assert_equal(3, Levenshtein.distance("foo", ""))
+    assert_equal(4, Levenshtein.distance("atcg", ""))
   end
 
   test "Levenshtein.distance returns t length if s is empty" do
-    assert_equal(5, Levenshtein.distance("", "fobar"))
+    assert_equal(5, Levenshtein.distance("", "atcgn"))
   end
 
   test "Levenshtein.distance with mismatch only returns correctly" do
-    assert_equal(1, Levenshtein.distance("foo", "fox"))
+    assert_equal(1, Levenshtein.distance("atcg", "atgg"))
+  end
+
+  test "Levenshtein.distance with ambiguity code returns correctly" do
+    assert_equal(0, Levenshtein.distance("atcg", "nnnn"))
+  end
+
+  test "Levenshtein.distance with insertion returns correctly" do
+    assert_equal(1, Levenshtein.distance("atcg", "attcg"))
   end
 
   test "Levenshtein.distance returns correctly" do
-    assert_equal(3, Levenshtein.distance("kitten", "sitting"))
-    assert_equal(3, Levenshtein.distance("Saturday", "Sunday"))
+    assert_equal(2, Levenshtein.distance("atcg", "tgncg"))
   end
 end
diff --git a/code_ruby/test/maasha/test_seq.rb b/code_ruby/test/maasha/test_seq.rb
index 8eed8d5..5947ee8 100755
--- a/code_ruby/test/maasha/test_seq.rb
+++ b/code_ruby/test/maasha/test_seq.rb
@@ -298,13 +298,18 @@ class TestSeq < Test::Unit::TestCase
     assert_equal("UAGCuagc", @entry.complement!.seq)
   end
 
-
-  test "#hamming distance returns correctly" do
+  test "#hamming_distance returns correctly" do
     seq1 = Seq.new("test1", "ATCG")
     seq2 = Seq.new("test2", "atgg")
     assert_equal(1, seq1.hamming_distance(seq2))
   end
 
+  test "#edit_distance returns correctly" do
+    seq1 = Seq.new("test1", "ATCG")
+    seq2 = Seq.new("test2", "tgncg")
+    assert_equal(2, seq1.edit_distance(seq2))
+  end
+
   test "#generate with length < 1 raises" do
     assert_raise(SeqError) { @entry.generate(-10, :dna) }
     assert_raise(SeqError) { @entry.generate(0, :dna) }
-- 
2.39.5