split digest.rb from seq.rb

git-svn-id: http://biopieces.googlecode.com/svn/trunk@1299 74ccb610-7750-0410-82ae-013aeee3265d

diff --git a/code_ruby/Maasha/lib/digest.rb b/code_ruby/Maasha/lib/digest.rb
new file mode 100644 (file)
index 0000000..3268a9d
--- /dev/null
+++ b/code_ruby/Maasha/lib/digest.rb
@@ -0,0 +1,108 @@
+# Copyright (C) 2007-2011 Martin A. Hansen.
+
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+
+# This program 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 General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+
+# http://www.gnu.org/copyleft/gpl.html
+
+# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+
+# This software is part of the Biopieces framework (www.biopieces.org).
+
+# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+
+require 'seq'
+
+# Error class for all exceptions to do with Digest.
+class DigestError < StandardError; end
+
+class Digest
+  include Enumerable
+
+  # Initialize a digest object with the following arguments:
+  # - seq: A sequence object.
+  # - pattern: A restriction enzyme recognition pattern.
+  # - cut_pos: Offset from match position where the enzyme cuts.
+  def initialize(seq, pattern, cut_pos)
+    @seq     = seq
+    @pattern = disambiguate(pattern)
+    @cut_pos = cut_pos
+    @offset  = 0
+  end
+
+  # Method to get the next digestion product from a sequence.
+  def each
+    @seq.seq.upcase.scan @pattern do
+      pos = $`.length + @cut_pos - 1
+     
+      if pos >= 0 and pos < @seq.length - 2
+        seq = Seq.new("#{@seq.seq_name}[#{@offset}-#{pos}]", @seq.seq[@offset .. pos], @seq.type)
+
+        yield seq
+      end
+
+      @offset = pos + 1
+    end
+
+    if @offset < 0
+      @offset = 0
+    elsif @offset > @seq.length
+      @offset = 0
+    end
+
+    seq = Seq.new("#{@seq.seq_name}[#{@offset}-#{@seq.length - 1}]", @seq.seq[@offset .. @seq.length], @seq.type)
+
+    yield seq
+
+    self # conventionally
+  end
+
+  private
+
+  # Method that returns a regexp object with a restriction
+  # enzyme pattern with ambiguity codes substituted to the
+  # appropriate regexp.
+  def disambiguate(pattern)
+    ambiguity = {
+      'A' => "A",
+      'T' => "T",
+      'U' => "T",
+      'C' => "C",
+      'G' => "G",
+      'M' => "[AC]",
+      'R' => "[AG]",
+      'W' => "[AT]",
+      'S' => "[CG]",
+      'Y' => "[CT]",
+      'K' => "[GT]",
+      'V' => "[ACG]",
+      'H' => "[ACT]",
+      'D' => "[AGT]",
+      'B' => "[CGT]",
+      'N' => "[GATC]"
+    }
+
+    new_pattern = ""
+
+    pattern.upcase.each_char do |char|
+      if ambiguity.has_key? char
+        new_pattern << ambiguity[char]
+      else
+        raise DigestError, "Could not disambiguate residue: #{char}"
+      end
+    end
+
+    Regexp.new(new_pattern)
+  end
+end

diff --git a/code_ruby/Maasha/lib/seq.rb b/code_ruby/Maasha/lib/seq.rb
index a63741f5aa8ec22fd38aa7a8f326c4f1fa19073e..bf07ab3e7cf93c738ef2d1a2919592fe49bb6d31 100644 (file)
--- a/code_ruby/Maasha/lib/seq.rb
+++ b/code_ruby/Maasha/lib/seq.rb
@@ -23,6 +23,7 @@
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
 
 require 'amatch'
+require 'digest'
 
 # Residue alphabets
 DNA     = %w[a t c g]
@@ -418,89 +419,6 @@ class Seq
   end
 end
 
-# Error class for all exceptions to do with Digest.
-class DigestError < StandardError; end
-
-class Digest
-  include Enumerable
-
-  # Initialize a digest object with the following arguments:
-  # - seq: A sequence object.
-  # - pattern: A restriction enzyme recognition pattern.
-  # - cut_pos: Offset from match position where the enzyme cuts.
-  def initialize(seq, pattern, cut_pos)
-    @seq     = seq
-    @pattern = disambiguate(pattern)
-    @cut_pos = cut_pos
-    @offset  = 0
-  end
-
-  # Method to get the next digestion product from a sequence.
-  def each
-    @seq.seq.upcase.scan @pattern do
-      pos = $`.length + @cut_pos - 1
-     
-      if pos >= 0 and pos < @seq.length - 2
-        seq = Seq.new("#{@seq.seq_name}[#{@offset}-#{pos}]", @seq.seq[@offset .. pos], @seq.type)
-
-        yield seq
-      end
-
-      @offset = pos + 1
-    end
-
-    if @offset < 0
-      @offset = 0
-    elsif @offset > @seq.length
-      @offset = 0
-    end
-
-    seq = Seq.new("#{@seq.seq_name}[#{@offset}-#{@seq.length - 1}]", @seq.seq[@offset .. @seq.length], @seq.type)
-
-    yield seq
-
-    self # conventionally
-  end
-
-  private
-
-  # Method that returns a regexp object with a restriction
-  # enzyme pattern with ambiguity codes substituted to the
-  # appropriate regexp.
-  def disambiguate(pattern)
-    ambiguity = {
-      'A' => "A",
-      'T' => "T",
-      'U' => "T",
-      'C' => "C",
-      'G' => "G",
-      'M' => "[AC]",
-      'R' => "[AG]",
-      'W' => "[AT]",
-      'S' => "[CG]",
-      'Y' => "[CT]",
-      'K' => "[GT]",
-      'V' => "[ACG]",
-      'H' => "[ACT]",
-      'D' => "[AGT]",
-      'B' => "[CGT]",
-      'N' => "[GATC]"
-    }
-
-    new_pattern = ""
-
-    pattern.upcase.each_char do |char|
-      if ambiguity.has_key? char
-        new_pattern << ambiguity[char]
-      else
-        raise DigestError, "Could not disambiguate residue: #{char}"
-      end
-    end
-
-    Regexp.new(new_pattern)
-  end
-end
-
 __END__