add canonicalization tests based on rfc

Rakefile

@@ -1,2 +1,14 @@
+require 'rake/testtask'
 require 'bundler'
+
+task :default => [:test]
+
+desc 'Run tests.'
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'lib' << 'test'
+  t.pattern = 'test/**/*_test.rb'
+  t.verbose = true
+end
+
 Bundler::GemHelper.install_tasks
+

test/canonicalization_test.rb

@@ -0,0 +1,55 @@
+
+require 'test_helper'
+
+class CanonicalizationTest < Test::Unit::TestCase
+  # from section 3.4.6 of rfc4871
+  def setup
+    @input = <<-eos.rfc_format
+      A: <SP> X <CRLF>
+      B <SP> : <SP> Y <HTAB><CRLF>
+      <HTAB> Z <SP><SP><CRLF>
+      <CRLF>
+      <SP> C <SP><CRLF>
+      D <SP><HTAB><SP> E <CRLF>
+      <CRLF>
+      <CRLF>
+    eos
+    @mail = Dkim::SignedMail.new(@input)
+    @mail.signable_headers = ['A', 'B']
+  end
+  def test_relaxed_header
+    @mail.header_canonicalization = 'relaxed'
+    expected_header = <<-eos.rfc_format
+      a:X <CRLF>
+      b:Y <SP> Z <CRLF>
+    eos
+    assert_equal expected_header, @mail.canonical_header
+  end
+  def test_relaxed_body
+    @mail.body_canonicalization = 'relaxed'
+    expected_body = <<-eos.rfc_format
+      <SP> C <CRLF>
+      D <SP> E <CRLF>
+    eos
+    assert_equal expected_body, @mail.canonical_body
+  end
+
+  def test_simple_header
+    @mail.header_canonicalization = 'simple'
+    expected_header = <<-eos.rfc_format
+      A: <SP> X <CRLF>
+      B <SP> : <SP> Y <HTAB><CRLF>
+      <HTAB> Z <SP><SP><CRLF>
+    eos
+    assert_equal expected_header, @mail.canonical_header
+  end
+  def test_simple_body
+    @mail.body_canonicalization = 'simple'
+    expected_body = <<-eos.rfc_format
+      <SP> C <SP><CRLF>
+      D <SP><HTAB><SP> E <CRLF>
+    eos
+    assert_equal expected_body, @mail.canonical_body
+  end
+end
+

test/test_helper.rb

@@ -0,0 +1,27 @@
+
+require 'test/unit'
+require 'dkim'
+
+class String
+  # Parse the format used in rfc4871
+  #
+  # In the following examples, actual whitespace is used only for
+  # clarity.  The actual input and output text is designated using
+  # bracketed descriptors: "<SP>" for a space character, "<HTAB>" for a
+  # tab character, and "<CRLF>" for a carriage-return/line-feed sequence.
+  # For example, "X <SP> Y" and "X<SP>Y" represent the same three
+  # characters.
+  def rfc_format
+    str = self.dup
+    str.gsub!(/\s/,'')
+    str.gsub!(/<SP>/,' ')
+    str.gsub!(/<CRLF>/,"\r\n")
+    str.gsub!(/<HTAB>/,"\t")
+    str
+  end
+end
+
+# examples used in rfc
+Dkim::domain = 'example.com'
+
+