* encoding.c (rb_enc_mbclen): return minlen instead of 1 when

  a character is not found properly.

* string.c (rb_enc_strlen): round up string length with fixed
  multibyte encoding such as UTF-32.
  (rb_enc_strlen_cr): ditto.
  (rb_str_substr): fix substring with fixed multibyte encoding.
  (rb_str_justify): check number of characters.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15573 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 27 insertions, 0 deletions

diff --git a/test/ruby/test_utf32.rb b/test/ruby/test_utf32.rb
new file mode 100644
index 0000000000..f81524f29e
--- /dev/null
+++ b/test/ruby/test_utf32.rb
@@ -0,0 +1,27 @@
+require 'test/unit'
+
+class TestUTF32 < Test::Unit::TestCase
+  def encdump(str)
+    d = str.dump
+    if /\.force_encoding\("[A-Za-z0-9.:_+-]*"\)\z/ =~ d
+      d
+    else
+      "#{d}.force_encoding(#{str.encoding.name.dump})"
+    end
+  end
+
+  def assert_str_equal(expected, actual, message=nil)
+    full_message = build_message(message, <<EOT)
+#{encdump expected} expected but not equal to
+#{encdump actual}.
+EOT
+    assert_block(full_message) { expected == actual }
+  end
+
+  def test_substr
+    assert_str_equal(
+      "abcdefgh".force_encoding("utf-32be"),
+      "abcdefgh".force_encoding("utf-32be")[0,3])
+  end
+end
+