require 'test/unit'


# jruby 1.7.4 (1.9.3p392) 2013-05-16 2390d3b on Java HotSpot(TM) 64-Bit Server VM 1.6.0_51-b11-457-11M4509 [darwin-x86_64]
class TestField < Test::Unit::TestCase

  def test_confused_bytecount





    string_with_ctrl = "hello\x1fhello".force_encoding("UTF-8")
    # control chars like \x1F ARE legal UTF-8, this is correct:
    assert string_with_ctrl.valid_encoding?

    # It's even considered ascii_only? -- this is correct, both MRI and jruby
    assert string_with_ctrl.ascii_only?


    # For reasons I can't explain, I can only reproduce the 
    # problem right now by doing a split, on the control char
    # (this does represent my actual use case)
    # Whether the split operand is tagged ASCII or UTF-8 does not matter,
    # case is identical either way. 
    elements = string_with_ctrl.split("\x1F".force_encoding("UTF-8"))  

    # For some reason weirdness only happens on the second one in the split
    # in this case. 
    second = elements[1]


    # For a string composed of all one-byte wide ascii, as this one is...
    assert_equal "hello", second
    assert second.ascii_only?

    # string[0] and string.byteslice(0) shoudl be identical. They are
    # different when the string contains multi-byte chars. 
    # using #[], we're okay
    assert_equal "h", second[0]

    # But on jruby, this following actually raises an exception!
    assert_equal "h", second.byteslice(0)
    # That one up there actually just raised!!!
    # Java::JavaLang::ArrayIndexOutOfBoundsException: 12
    #  org.jruby.util.ByteList.equal(ByteList.java:960)

    # In other cases I saw in my real app, it didn't raise, but
    # did return the WRONG bytes. Ie, not a 'h' above as expected, or
    # not:


    assert_equal second[0], second.byteslice(0)
    # but in jruby we never even get here, we raise. 

    # In MRI, we pass ALL these tests with no exceptions. 
    # (ruby 1.9.3p448 (2013-06-27 revision 41675) [x86_64-darwin12.4.0])
  end

end