aboutsummaryrefslogtreecommitdiffstats
path: root/test/ruby/enc/test_utf32.rb
diff options
context:
space:
mode:
authornobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-07-16 19:33:15 +0000
committernobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-07-16 19:33:15 +0000
commitc60b57ade0f4b31c2177615dca9839d40baaa49d (patch)
treeaed882f80d4940a1053e56b0747cb95f2689ae2e /test/ruby/enc/test_utf32.rb
parent47e3f4e1aed4b71816e05fe608e97c523ea7ccfd (diff)
downloadruby-c60b57ade0f4b31c2177615dca9839d40baaa49d.tar.gz
* test/ruby/enc: moved tests for particular encodings.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@18095 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'test/ruby/enc/test_utf32.rb')
-rw-r--r--test/ruby/enc/test_utf32.rb93
1 files changed, 93 insertions, 0 deletions
diff --git a/test/ruby/enc/test_utf32.rb b/test/ruby/enc/test_utf32.rb
new file mode 100644
index 0000000000..3d4a458512
--- /dev/null
+++ b/test/ruby/enc/test_utf32.rb
@@ -0,0 +1,93 @@
+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-32le"),
+ "abcdefgh".force_encoding("utf-32le")[0,3])
+ assert_str_equal(
+ "abcdefgh".force_encoding("utf-32be"),
+ "abcdefgh".force_encoding("utf-32be")[0,3])
+ end
+
+ def test_mbc_len
+ al = "abcdefghijkl".force_encoding("utf-32le").each_char.to_a
+ ab = "abcdefghijkl".force_encoding("utf-32be").each_char.to_a
+ assert_equal("abcd".force_encoding("utf-32le"), al.shift)
+ assert_equal("efgh".force_encoding("utf-32le"), al.shift)
+ assert_equal("ijkl".force_encoding("utf-32le"), al.shift)
+ assert_equal("abcd".force_encoding("utf-32be"), ab.shift)
+ assert_equal("efgh".force_encoding("utf-32be"), ab.shift)
+ assert_equal("ijkl".force_encoding("utf-32be"), ab.shift)
+ end
+
+ def ascii_to_utf16le(s)
+ s.unpack("C*").map {|x| [x,0,0,0] }.flatten.pack("C*").force_encoding("utf-32le")
+ end
+
+ def ascii_to_utf16be(s)
+ s.unpack("C*").map {|x| [0,0,0,x] }.flatten.pack("C*").force_encoding("utf-32be")
+ end
+
+ def test_mbc_newline
+ al = ascii_to_utf16le("foo\nbar\nbaz\n").lines.to_a
+ ab = ascii_to_utf16be("foo\nbar\nbaz\n").lines.to_a
+
+ assert_equal(ascii_to_utf16le("foo\n"), al.shift)
+ assert_equal(ascii_to_utf16le("bar\n"), al.shift)
+ assert_equal(ascii_to_utf16le("baz\n"), al.shift)
+ assert_equal(ascii_to_utf16be("foo\n"), ab.shift)
+ assert_equal(ascii_to_utf16be("bar\n"), ab.shift)
+ assert_equal(ascii_to_utf16be("baz\n"), ab.shift)
+
+ sl = "a\0".force_encoding("utf-32le")
+ sb = "a\0".force_encoding("utf-32be")
+ assert_equal(sl, sl.chomp)
+ assert_equal(sb, sb.chomp)
+ end
+
+ def test_mbc_to_code
+ sl = "a\0\0\0".force_encoding("utf-32le")
+ sb = "\0\0\0a".force_encoding("utf-32be")
+ assert_equal("a".ord, sl.ord)
+ assert_equal("a".ord, sb.ord)
+ end
+
+ def utf8_to_utf32(s, e)
+ s.chars.map {|c| c.ord.chr(e) }.join
+ end
+
+ def test_mbc_case_fold
+ rl = Regexp.new(utf8_to_utf32("^(\u3042)(a)\\1\\2$", "utf-32le"), "i")
+ rb = Regexp.new(utf8_to_utf32("^(\u3042)(a)\\1\\2$", "utf-32be"), "i")
+ assert_equal(Encoding.find("utf-32le"), rl.encoding)
+ assert_equal(Encoding.find("utf-32be"), rb.encoding)
+ assert_match(rl, utf8_to_utf32("\u3042a\u3042a", "utf-32le"))
+ assert_match(rb, utf8_to_utf32("\u3042a\u3042a", "utf-32be"))
+ end
+
+ def test_code_to_mbc
+ sl = "a\0\0\0".force_encoding("utf-32le")
+ sb = "\0\0\0a".force_encoding("utf-32be")
+ assert_equal(sl, "a".ord.chr("utf-32le"))
+ assert_equal(sb, "a".ord.chr("utf-32be"))
+ end
+end
+