Significantly improved internal encoding heuristics and support.

* Default Encoding.default_internal to UTF-8
* Eliminated the use of file-wide magic comments to coerce code evaluated inside the file
* Read templates as BINARY, use default_external or template-wide magic comments
  inside the Template to set the initial encoding
  * This means that template handlers in Ruby 1.9 will receive Strings encoded
    in default_internal (UTF-8 by default)
* Create a better Exception for encoding issues, and use it when the template
  source has bytes that are not compatible with the specified encoding
* Allow template handlers to opt-into handling BINARY. If they do so, they
  need to do some of their own manual encoding work
* Added a "Configuration Gotchas" section to the intro Rails Guide instructing
  users to use UTF-8 for everything
* Use config.encoding= in Ruby 1.8, and raise if a value that is an invalid
  $KCODE value is used

Also:
* Fixed a few tests that were assert() rather than assert_equal() and
  were caught by Minitest requiring a String for the message
* Fixed a test where an assert_select was misformed, also caught by
  Minitest being more restrictive
* Fixed a test where a Rack response was returning a String rather
  than an Enumerable

1 files changed, 128 insertions, 0 deletions

diff --git a/actionpack/test/template/template_test.rb b/actionpack/test/template/template_test.rb
new file mode 100644
index 0000000000..c4a65d84fc
--- /dev/null
+++ b/actionpack/test/template/template_test.rb
@@ -0,0 +1,128 @@
+require "abstract_unit"
+
+# These are the normal settings that will be set up by Railties
+# TODO: Have these tests support other combinations of these values
+Encoding.default_internal = "UTF-8"
+Encoding.default_external = "UTF-8"
+
+class TestERBTemplate < ActiveSupport::TestCase
+  ERBHandler = ActionView::Template::Handlers::ERB
+
+  class Context
+    def initialize
+      @output_buffer = "original"
+    end
+
+    def hello
+      "Hello"
+    end
+
+    def partial
+      ActionView::Template.new(
+        "<%= @_virtual_path %>",
+        "partial",
+        ERBHandler,
+        :virtual_path => "partial"
+      )
+    end
+
+    def logger
+      require "logger"
+      Logger.new(STDERR)
+    end
+
+    def my_buffer
+      @output_buffer
+    end
+  end
+
+  def new_template(body = "<%= hello %>", handler = ERBHandler, details = {})
+    ActionView::Template.new(body, "hello template", ERBHandler, {:virtual_path => "hello"})
+  end
+
+  def render(locals = {})
+    @template.render(@obj, locals)
+  end
+
+  def setup
+    @obj = Context.new
+  end
+
+  def test_basic_template
+    @template = new_template
+    assert_equal "Hello", render
+  end
+
+  def test_locals
+    @template = new_template("<%= my_local %>")
+    assert_equal "I'm a local", render(:my_local => "I'm a local")
+  end
+
+  def test_restores_buffer
+    @template = new_template
+    assert_equal "Hello", render
+    assert_equal "original", @obj.my_buffer
+  end
+
+  def test_virtual_path
+    @template = new_template("<%= @_virtual_path %>" \
+                             "<%= partial.render(self, {}) %>" \
+                             "<%= @_virtual_path %>")
+    assert_equal "hellopartialhello", render
+  end
+
+  if "ruby".encoding_aware?
+    def test_resulting_string_is_utf8
+      @template = new_template
+      assert_equal Encoding::UTF_8, render.encoding
+    end
+
+    def test_no_magic_comment_word_with_utf_8
+      @template = new_template("hello \u{fc}mlat")
+      assert_equal Encoding::UTF_8, render.encoding
+      assert_equal "hello \u{fc}mlat", render
+    end
+
+    # This test ensures that if the default_external
+    # is set to something other than UTF-8, we don't
+    # get any errors and get back a UTF-8 String.
+    def test_default_external_works
+      Encoding.default_external = "ISO-8859-1"
+      @template = new_template("hello \xFCmlat")
+      assert_equal Encoding::UTF_8, render.encoding
+      assert_equal "hello \u{fc}mlat", render
+    ensure
+      Encoding.default_external = "UTF-8"
+    end
+
+    def test_encoding_can_be_specified_with_magic_comment
+      @template = new_template("# encoding: ISO-8859-1\nhello \xFCmlat")
+      assert_equal Encoding::UTF_8, render.encoding
+      assert_equal "\nhello \u{fc}mlat", render
+    end
+
+    # TODO: This is currently handled inside ERB. The case of explicitly
+    # lying about encodings via the normal Rails API should be handled
+    # inside Rails.
+    def test_lying_with_magic_comment
+      assert_raises(ActionView::Template::Error) do
+        @template = new_template("# encoding: UTF-8\nhello \xFCmlat")
+        render
+      end
+    end
+
+    def test_encoding_can_be_specified_with_magic_comment_in_erb
+      @template = new_template("<%# encoding: ISO-8859-1 %>hello \xFCmlat")
+      result = render
+      assert_equal Encoding::UTF_8, render.encoding
+      assert_equal "hello \u{fc}mlat", render
+    end
+
+    def test_error_when_template_isnt_valid_utf8
+      assert_raises(ActionView::Template::Error, /\xFC/) do
+        @template = new_template("hello \xFCmlat")
+        render
+      end
+    end
+  end
+end
\ No newline at end of file