diff options
Diffstat (limited to 'test/ruby/test_transcode.rb')
| -rw-r--r-- | test/ruby/test_transcode.rb | 141 |
1 files changed, 7 insertions, 134 deletions
diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb index 8052c82194..123111e4cc 100644 --- a/test/ruby/test_transcode.rb +++ b/test/ruby/test_transcode.rb @@ -1,4 +1,4 @@ -# encoding: ASCII-8BIT # make sure this runs in binary mode +# -*- encoding: ASCII-8BIT -*- # make sure this runs in binary mode # some of the comments are in UTF-8 require 'test/unit' @@ -51,7 +51,7 @@ class TestTranscode < Test::Unit::TestCase end def check_both_ways(utf8, raw, encoding) - assert_equal(utf8.force_encoding('utf-8'), raw.encode('utf-8', encoding),utf8.dump) + assert_equal(utf8.force_encoding('utf-8'), raw.encode('utf-8', encoding)) assert_equal(raw.force_encoding(encoding), utf8.encode(encoding, 'utf-8')) end @@ -60,42 +60,13 @@ class TestTranscode < Test::Unit::TestCase assert_equal(str2.force_encoding(enc2), str1.encode(enc2, enc1)) end - def test_encoding_of_ascii_originating_from_binary - binary_string = [0x82, 0x74, 0x68, 0x69, 0x73, 0x20, 0x69, 0x73, 0x20, - 0x61, 0x20, 0x76, 0x65, 0x72, 0x79, 0x20, 0x6c, 0x6f, - 0x6e, 0x67, 0x20, 0x73, 0x74, 0x72, 0x69, 0x6e, 0x67] - class << binary_string - # create a copy on write substring that contains - # just the ascii characters (i.e. this is...), in JRuby - # the underlying string have the same buffer backing - # it up, but the offset of the string will be 1 instead - # of 0. - def make_cow_substring - pack('C27').slice(1, 26) - end - end - - ascii_string = binary_string.make_cow_substring - assert_equal("this is a very long string", ascii_string) - assert_equal(Encoding::ASCII_8BIT, ascii_string.encoding) - utf8_string = nil - assert_nothing_raised("JRUBY-6764") do - utf8_string = ascii_string.encode(Encoding::UTF_8) - end - assert_equal("this is a very long string", utf8_string) - assert_equal(Encoding::UTF_8, utf8_string.encoding) - end - def test_encodings check_both_ways("\u307E\u3064\u3082\u3068 \u3086\u304D\u3072\u308D", "\x82\xdc\x82\xc2\x82\xe0\x82\xc6 \x82\xe4\x82\xab\x82\xd0\x82\xeb", 'shift_jis') # まつもと ゆきひろ check_both_ways("\u307E\u3064\u3082\u3068 \u3086\u304D\u3072\u308D", "\xa4\xde\xa4\xc4\xa4\xe2\xa4\xc8 \xa4\xe6\xa4\xad\xa4\xd2\xa4\xed", 'euc-jp') - check_both_ways("\u307E\u3064\u3082\u3068 \u3086\u304D\u3072\u308D", - "\xa4\xde\xa4\xc4\xa4\xe2\xa4\xc8 \xa4\xe6\xa4\xad\xa4\xd2\xa4\xed", 'euc-jp-2004') check_both_ways("\u677E\u672C\u884C\u5F18", "\x8f\xbc\x96\x7b\x8d\x73\x8d\x4f", 'shift_jis') # 松本行弘 check_both_ways("\u677E\u672C\u884C\u5F18", "\xbe\xbe\xcb\xdc\xb9\xd4\xb9\xb0", 'euc-jp') - check_both_ways("\u677E\u672C\u884C\u5F18", "\xbe\xbe\xcb\xdc\xb9\xd4\xb9\xb0", 'euc-jp-2004') check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-1') # Dürst check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-2') check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-3') @@ -112,7 +83,6 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u0643\u062A\u0628", "\xE3\xCA\xC8", 'iso-8859-6') # كتب check_both_ways("\u65E5\u8A18", "\x93\xFA\x8BL", 'shift_jis') # 日記 check_both_ways("\u65E5\u8A18", "\xC6\xFC\xB5\xAD", 'euc-jp') - check_both_ways("\u65E5\u8A18", "\xC6\xFC\xB5\xAD", 'euc-jp-2004') check_both_ways("\uC560\uC778\uAD6C\uD568\u0020\u6734\uC9C0\uC778", "\xBE\xD6\xC0\xCE\xB1\xB8\xC7\xD4\x20\xDA\xD3\xC1\xF6\xC0\xCE", 'euc-kr') # 애인구함 朴지인 check_both_ways("\uC544\uD58F\uD58F\u0020\uB620\uBC29\uD6BD\uB2D8\u0020\uC0AC\uB791\uD716", @@ -1049,21 +1019,6 @@ class TestTranscode < Test::Unit::TestCase check_utf_16_both_ways("\u{F00FF}", "\xDB\x80\xDC\xFF") end - def test_utf_16_bom - expected = "\u{3042}\u{3044}\u{20bb7}" - assert_equal(expected, %w/fffe4230443042d8b7df/.pack("H*").encode("UTF-8","UTF-16")) - check_both_ways(expected, %w/feff30423044d842dfb7/.pack("H*"), "UTF-16") - assert_raise(Encoding::InvalidByteSequenceError){%w/feffdfb7/.pack("H*").encode("UTF-8","UTF-16")} - assert_raise(Encoding::InvalidByteSequenceError){%w/fffeb7df/.pack("H*").encode("UTF-8","UTF-16")} - end - - def test_utf_32_bom - expected = "\u{3042}\u{3044}\u{20bb7}" - assert_equal(expected, %w/fffe00004230000044300000b70b0200/.pack("H*").encode("UTF-8","UTF-32")) - check_both_ways(expected, %w/0000feff000030420000304400020bb7/.pack("H*"), "UTF-32") - assert_raise(Encoding::InvalidByteSequenceError){%w/0000feff00110000/.pack("H*").encode("UTF-8","UTF-32")} - end - def check_utf_32_both_ways(utf8, raw) copy = raw.dup 0.step(copy.length-1, 4) do |i| @@ -1185,15 +1140,9 @@ class TestTranscode < Test::Unit::TestCase assert_equal("\uFFFD!", "\xff!".encode("utf-8", "euc-jp", :invalid=>:replace)) assert_equal("\uFFFD!", - "\xff!".encode("utf-8", "euc-jp-2004", :invalid=>:replace)) - assert_equal("\uFFFD!", "\xa1!".encode("utf-8", "euc-jp", :invalid=>:replace)) assert_equal("\uFFFD!", - "\xa1!".encode("utf-8", "euc-jp-2004", :invalid=>:replace)) - assert_equal("\uFFFD!", "\x8f\xa1!".encode("utf-8", "euc-jp", :invalid=>:replace)) - assert_equal("\uFFFD!", - "\x8f\xa1!".encode("utf-8", "euc-jp-2004", :invalid=>:replace)) assert_equal("?", "\xdc\x00".encode("EUC-JP", "UTF-16BE", :invalid=>:replace), "[ruby-dev:35776]") @@ -1210,7 +1159,6 @@ class TestTranscode < Test::Unit::TestCase def test_invalid_replace_string assert_equal("a<x>A", "a\x80A".encode("us-ascii", "euc-jp", :invalid=>:replace, :replace=>"<x>")) - assert_equal("a<x>A", "a\x80A".encode("us-ascii", "euc-jp-2004", :invalid=>:replace, :replace=>"<x>")) end def test_undef_replace @@ -1325,64 +1273,6 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u795E\u6797\u7FA9\u535A", "\xBF\xC0\xCE\xD3\xB5\xC1\xC7\xEE", 'euc-jp') # 神林義博 end - def test_euc_jp_2004 - check_both_ways("\u3000", "\xA1\xA1", 'euc-jp-2004') # full-width space - check_both_ways("\u00D7", "\xA1\xDF", 'euc-jp-2004') # × - check_both_ways("\u00F7", "\xA1\xE0", 'euc-jp-2004') # ÷ - check_both_ways("\u25C7", "\xA1\xFE", 'euc-jp-2004') # ◇ - check_both_ways("\u25C6", "\xA2\xA1", 'euc-jp-2004') # ◆ - check_both_ways("\uFF07", "\xA2\xAF", 'euc-jp-2004') # ＇ - check_both_ways("\u309F", "\xA2\xB9", 'euc-jp-2004') # ゟ - check_both_ways("\u2284", "\xA2\xC2", 'euc-jp-2004') # ⊄ - check_both_ways("\u2306", "\xA2\xC9", 'euc-jp-2004') # ⌆ - check_both_ways("\u2295", "\xA2\xD1", 'euc-jp-2004') # ⊕ - check_both_ways("\u3017", "\xA2\xDB", 'euc-jp-2004') # 〗 - check_both_ways("\u2262", "\xA2\xEB", 'euc-jp-2004') # ≢ - check_both_ways("\u2194", "\xA2\xF1", 'euc-jp-2004') # ↔ - check_both_ways("\u266E", "\xA2\xFA", 'euc-jp-2004') # ♮ - check_both_ways("\u2669", "\xA2\xFD", 'euc-jp-2004') # ♩ - check_both_ways("\u25EF", "\xA2\xFE", 'euc-jp-2004') # ◯ - check_both_ways("\u2935", "\xA3\xAF", 'euc-jp-2004') # ⤵ - check_both_ways("\u29BF", "\xA3\xBA", 'euc-jp-2004') # ⦿ - check_both_ways("\u2022", "\xA3\xC0", 'euc-jp-2004') # • - check_both_ways("\u2213", "\xA3\xDB", 'euc-jp-2004') # ∓ - check_both_ways("\u2127", "\xA3\xE0", 'euc-jp-2004') # ℧ - check_both_ways("\u30A0", "\xA3\xFB", 'euc-jp-2004') # ゠ - check_both_ways("\uFF54", "\xA3\xF4", 'euc-jp-2004') # ｔ - assert_raise(Encoding::UndefinedConversionError) { "\xA5\xF7".encode("utf-8", 'euc-jp-2004') } - check_both_ways("\u2664", "\xA6\xB9", 'euc-jp-2004') # ♤ - check_both_ways("\u2663", "\xA6\xC0", 'euc-jp-2004') # ♣ - check_both_ways("\u03C2", "\xA6\xD9", 'euc-jp-2004') # ς - check_both_ways("\u23BE", "\xA7\xC2", 'euc-jp-2004') # ⎾ - check_both_ways("\u23CC", "\xA7\xD0", 'euc-jp-2004') # ⏌ - check_both_ways("\u30F7", "\xA7\xF2", 'euc-jp-2004') # ヷ - check_both_ways("\u3251", "\xA8\xC1", 'euc-jp-2004') # ㉑ - check_both_ways("\u{20B9F}", "\xCF\xD4", 'euc-jp-2004') # 𠮑 - check_both_ways("\u541E", "\xCF\xFE", 'euc-jp-2004') # 吞 - check_both_ways("\u6A97", "\xDD\xA1", 'euc-jp-2004') # 檗 - check_both_ways("\u6BEF", "\xDD\xDF", 'euc-jp-2004') # 毯 - check_both_ways("\u9EBE", "\xDD\xE0", 'euc-jp-2004') # 麾 - check_both_ways("\u6CBE", "\xDD\xFE", 'euc-jp-2004') # 沾 - check_both_ways("\u6CBA", "\xDE\xA1", 'euc-jp-2004') # 沺 - check_both_ways("\u6ECC", "\xDE\xFE", 'euc-jp-2004') # 滌 - check_both_ways("\u6F3E", "\xDF\xA1", 'euc-jp-2004') # 漾 - check_both_ways("\u70DD", "\xDF\xDF", 'euc-jp-2004') # 烝 - check_both_ways("\u70D9", "\xDF\xE0", 'euc-jp-2004') # 烙 - check_both_ways("\u71FC", "\xDF\xFE", 'euc-jp-2004') # 燼 - check_both_ways("\u71F9", "\xE0\xA1", 'euc-jp-2004') # 燹 - check_both_ways("\u73F1", "\xE0\xFE", 'euc-jp-2004') # 珱 - check_both_ways("\u5653", "\xF4\xA7", 'euc-jp-2004') # 噓 - #check_both_ways("\u9ADC", "\xFC\xE3", 'euc-jp') # 髜 (IBM extended) - - check_both_ways("\u9DD7", "\xFE\xE5", 'euc-jp-2004') # 鷗 - check_both_ways("\u{2000B}", "\xAE\xA2", 'euc-jp-2004') # 𠀋 - check_both_ways("\u{2A6B2}", "\x8F\xFE\xF6", 'euc-jp-2004') # 𪚲 - - check_both_ways("\u677E\u672C\u884C\u5F18", "\xBE\xBE\xCB\xDC\xB9\xD4\xB9\xB0", 'euc-jp-2004') # 松本行弘 - check_both_ways("\u9752\u5C71\u5B66\u9662\u5927\u5B66", "\xC0\xC4\xBB\xB3\xB3\xD8\xB1\xA1\xC2\xE7\xB3\xD8", 'euc-jp-2004') # 青山学院大学 - check_both_ways("\u795E\u6797\u7FA9\u535A", "\xBF\xC0\xCE\xD3\xB5\xC1\xC7\xEE", 'euc-jp-2004') # 神林義博 - end - def test_eucjp_ms check_both_ways("\u2116", "\xAD\xE2", 'eucJP-ms') # NUMERO SIGN check_both_ways("\u221A", "\xA2\xE5", 'eucJP-ms') # SQUARE ROOT @@ -1907,9 +1797,9 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u77AC", "\xC0\xFE", 'Big5') # 瞬 check_both_ways("\u8B96", "\xC6\x40", 'Big5') # 讖 check_both_ways("\u7C72", "\xC6\x7E", 'Big5') # 籲 - #assert_raise(Encoding::UndefinedConversionError) { "\xC6\xA1".encode("utf-8", 'Big5') } + #assert_raise(Encoding::UndefinedConversionError) { "\xC6\xA1".encode("utf-8", 'Big5') } #assert_raise(Encoding::UndefinedConversionError) { "\xC7\x40".encode("utf-8", 'Big5') } - #assert_raise(Encoding::UndefinedConversionError) { "\xC8\x40".encode("utf-8", 'Big5') } + assert_raise(Encoding::UndefinedConversionError) { "\xC8\x40".encode("utf-8", 'Big5') } check_both_ways("\u4E42", "\xC9\x40", 'Big5') # 乂 check_both_ways("\u6C15", "\xC9\x7E", 'Big5') # 氕 check_both_ways("\u6C36", "\xC9\xA1", 'Big5') # 氶 @@ -1942,7 +1832,7 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u9F0A", "\xF9\x7E", 'Big5') # 鼊 check_both_ways("\u9FA4", "\xF9\xA1", 'Big5') # 龤 check_both_ways("\u9F98", "\xF9\xD5", 'Big5') # 龘 - #assert_raise(Encoding::UndefinedConversionError) { "\xF9\xD6".encode("utf-8", 'Big5') } + assert_raise(Encoding::UndefinedConversionError) { "\xF9\xD6".encode("utf-8", 'Big5') } check_both_ways("\u795E\u6797\u7FA9\u535A", "\xAF\xAB\xAA\x4C\xB8\x71\xB3\xD5", 'Big5') # 神林義博 end @@ -1974,7 +1864,7 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u77AC", "\xC0\xFE", 'Big5-HKSCS') # 瞬 check_both_ways("\u8B96", "\xC6\x40", 'Big5-HKSCS') # 讖 check_both_ways("\u7C72", "\xC6\x7E", 'Big5-HKSCS') # 籲 - #assert_raise(Encoding::UndefinedConversionError) { "\xC6\xA1".encode("utf-8", 'Big5-HKSCS') } + #assert_raise(Encoding::UndefinedConversionError) { "\xC6\xA1".encode("utf-8", 'Big5-HKSCS') } #assert_raise(Encoding::UndefinedConversionError) { "\xC7\x40".encode("utf-8", 'Big5-HKSCS') } #assert_raise(Encoding::UndefinedConversionError) { "\xC8\x40".encode("utf-8", 'Big5-HKSCS') } check_both_ways("\u4E42", "\xC9\x40", 'Big5-HKSCS') # 乂 @@ -2009,7 +1899,7 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\u9F0A", "\xF9\x7E", 'Big5-HKSCS') # 鼊 check_both_ways("\u9FA4", "\xF9\xA1", 'Big5-HKSCS') # 龤 check_both_ways("\u9F98", "\xF9\xD5", 'Big5-HKSCS') # 龘 - #check_both_ways("\u{23ED7}", "\x8E\x40", 'Big5-HKSCS') # 𣻗 + check_both_ways("\u{23ED7}", "\x8E\x40", 'Big5-HKSCS') # 𣻗 #assert_raise(Encoding::UndefinedConversionError) { "\xF9\xD6".encode("utf-8", 'Big5-HKSCS') } check_both_ways("\u795E\u6797\u7FA9\u535A", "\xAF\xAB\xAA\x4C\xB8\x71\xB3\xD5", 'Big5-HKSCS') # 神林義博 end @@ -2043,21 +1933,4 @@ class TestTranscode < Test::Unit::TestCase assert_equal("[ISU]", "\u{1F4BA}".encode("SJIS-KDDI", fallback: {"\u{1F4BA}" => "[ISU]"})) end - - def test_fallback_hash_default - fallback = Hash.new {|h, x| "U+%.4X" % x.unpack("U")} - assert_equal("U+3042", "\u{3042}".encode("US-ASCII", fallback: fallback)) - end - - def test_fallback_proc - fallback = proc {|x| "U+%.4X" % x.unpack("U")} - assert_equal("U+3042", "\u{3042}".encode("US-ASCII", fallback: fallback)) - end - - def test_fallback_method - def (fallback = "U+%.4X").escape(x) - self % x.unpack("U") - end - assert_equal("U+3042", "\u{3042}".encode("US-ASCII", fallback: fallback.method(:escape))) - end end |