diff options
author | akr <akr@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2008-09-03 11:09:25 +0000 |
---|---|---|
committer | akr <akr@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2008-09-03 11:09:25 +0000 |
commit | 4406629bd6f5841db014f9ec5aed860239182e05 (patch) | |
tree | 877255a1972376efd01492a1a18ef22636fcf94e /test/ruby | |
parent | 8108417c5e4088b3b1ab6fe90a9a6d2ff9268892 (diff) | |
download | ruby-4406629bd6f5841db014f9ec5aed860239182e05.tar.gz |
* enc/trans/japanese.trans: new file.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19086 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'test/ruby')
-rw-r--r-- | test/ruby/test_econv.rb | 6 | ||||
-rw-r--r-- | test/ruby/test_transcode.rb | 66 |
2 files changed, 72 insertions, 0 deletions
diff --git a/test/ruby/test_econv.rb b/test/ruby/test_econv.rb index 3e2814bff0..374834bd30 100644 --- a/test/ruby/test_econv.rb +++ b/test/ruby/test_econv.rb @@ -385,6 +385,12 @@ class TestEncodingConverter < Test::Unit::TestCase def test_errinfo_invalid_euc_jp ec = Encoding::Converter.new("EUC-JP", "Shift_JIS") ec.primitive_convert(src="\xff", dst="", nil, 10) + assert_errinfo(:invalid_byte_sequence, "EUC-JP", "Shift_JIS", "\xFF", "", ec) + end + + def test_errinfo_invalid_euc_jp2 + ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1") + ec.primitive_convert(src="\xff", dst="", nil, 10) assert_errinfo(:invalid_byte_sequence, "EUC-JP", "UTF-8", "\xFF", "", ec) end diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb index d03ccac143..81c58fd651 100644 --- a/test/ruby/test_transcode.rb +++ b/test/ruby/test_transcode.rb @@ -57,6 +57,11 @@ class TestTranscode < Test::Unit::TestCase assert_equal(raw.force_encoding(encoding), utf8.encode(encoding, 'utf-8')) end + def check_both_ways2(str1, enc1, str2, enc2) + assert_equal(str1.force_encoding(enc1), str2.encode(enc1, enc2)) + assert_equal(str2.force_encoding(enc2), str1.encode(enc2, enc1)) + 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 @@ -434,6 +439,67 @@ class TestTranscode < Test::Unit::TestCase check_both_ways("\uFF5E", "\xA1\xC1", 'eucJP-ms') # WAVE DASH end + def test_eucjp_sjis + check_both_ways2("\xa1\xa1", "EUC-JP", "\x81\x40", "Shift_JIS") + check_both_ways2("\xa1\xdf", "EUC-JP", "\x81\x7e", "Shift_JIS") + check_both_ways2("\xa1\xe0", "EUC-JP", "\x81\x80", "Shift_JIS") + check_both_ways2("\xa1\xfe", "EUC-JP", "\x81\x9e", "Shift_JIS") + check_both_ways2("\xa2\xa1", "EUC-JP", "\x81\x9f", "Shift_JIS") + check_both_ways2("\xa2\xfe", "EUC-JP", "\x81\xfc", "Shift_JIS") + + check_both_ways2("\xdd\xa1", "EUC-JP", "\x9f\x40", "Shift_JIS") + check_both_ways2("\xdd\xdf", "EUC-JP", "\x9f\x7e", "Shift_JIS") + check_both_ways2("\xdd\xe0", "EUC-JP", "\x9f\x80", "Shift_JIS") + check_both_ways2("\xdd\xfe", "EUC-JP", "\x9f\x9e", "Shift_JIS") + check_both_ways2("\xde\xa1", "EUC-JP", "\x9f\x9f", "Shift_JIS") + check_both_ways2("\xde\xfe", "EUC-JP", "\x9f\xfc", "Shift_JIS") + + check_both_ways2("\xdf\xa1", "EUC-JP", "\xe0\x40", "Shift_JIS") + check_both_ways2("\xdf\xdf", "EUC-JP", "\xe0\x7e", "Shift_JIS") + check_both_ways2("\xdf\xe0", "EUC-JP", "\xe0\x80", "Shift_JIS") + check_both_ways2("\xdf\xfe", "EUC-JP", "\xe0\x9e", "Shift_JIS") + check_both_ways2("\xe0\xa1", "EUC-JP", "\xe0\x9f", "Shift_JIS") + check_both_ways2("\xe0\xfe", "EUC-JP", "\xe0\xfc", "Shift_JIS") + + check_both_ways2("\xf4\xa1", "EUC-JP", "\xea\x9f", "Shift_JIS") + check_both_ways2("\xf4\xa2", "EUC-JP", "\xea\xa0", "Shift_JIS") + check_both_ways2("\xf4\xa3", "EUC-JP", "\xea\xa1", "Shift_JIS") + check_both_ways2("\xf4\xa4", "EUC-JP", "\xea\xa2", "Shift_JIS") # end of JIS X 0208 1983 + check_both_ways2("\xf4\xa5", "EUC-JP", "\xea\xa3", "Shift_JIS") + check_both_ways2("\xf4\xa6", "EUC-JP", "\xea\xa4", "Shift_JIS") # end of JIS X 0208 1990 + + check_both_ways2("\x8e\xa1", "EUC-JP", "\xa1", "Shift_JIS") + check_both_ways2("\x8e\xdf", "EUC-JP", "\xdf", "Shift_JIS") + end + + def test_eucjp_sjis_unassigned + check_both_ways2("\xfd\xa1", "EUC-JP", "\xef\x40", "Shift_JIS") + check_both_ways2("\xfd\xa1", "EUC-JP", "\xef\x40", "Shift_JIS") + check_both_ways2("\xfd\xdf", "EUC-JP", "\xef\x7e", "Shift_JIS") + check_both_ways2("\xfd\xe0", "EUC-JP", "\xef\x80", "Shift_JIS") + check_both_ways2("\xfd\xfe", "EUC-JP", "\xef\x9e", "Shift_JIS") + check_both_ways2("\xfe\xa1", "EUC-JP", "\xef\x9f", "Shift_JIS") + check_both_ways2("\xfe\xfe", "EUC-JP", "\xef\xfc", "Shift_JIS") + end + + def test_eucjp_sjis_undef + assert_raise(Encoding::ConversionUndefined) { "\x8e\xe0".encode("Shift_JIS", "EUC-JP") } + assert_raise(Encoding::ConversionUndefined) { "\x8e\xfe".encode("Shift_JIS", "EUC-JP") } + assert_raise(Encoding::ConversionUndefined) { "\x8f\xa1\xa1".encode("Shift_JIS", "EUC-JP") } + assert_raise(Encoding::ConversionUndefined) { "\x8f\xa1\xfe".encode("Shift_JIS", "EUC-JP") } + assert_raise(Encoding::ConversionUndefined) { "\x8f\xfe\xa1".encode("Shift_JIS", "EUC-JP") } + assert_raise(Encoding::ConversionUndefined) { "\x8f\xfe\xfe".encode("Shift_JIS", "EUC-JP") } + + assert_raise(Encoding::ConversionUndefined) { "\xf0\x40".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xf0\x7e".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xf0\x80".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xf0\xfc".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xfc\x40".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xfc\x7e".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xfc\x80".encode("EUC-JP", "Shift_JIS") } + assert_raise(Encoding::ConversionUndefined) { "\xfc\xfc".encode("EUC-JP", "Shift_JIS") } + end + def test_iso_2022_jp assert_raise(Encoding::InvalidByteSequence) { "\x1b(A".encode("utf-8", "iso-2022-jp") } assert_raise(Encoding::InvalidByteSequence) { "\x1b$(A".encode("utf-8", "iso-2022-jp") } |