mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
Sat Dec 22 15:54:54 2007 Martin Duerst <duerst@it.aoyama.ac.jp>
* test/ruby/test_transcode.rb: Added simple tests for EUC-JP and Shift_JIS and tests for ASCII-only range git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14486 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
duerst
parent
d9c407981c
commit
a95ae9619f
2 changed files with 51 additions and 32 deletions
|
|
@ -1,3 +1,8 @@
|
|||
Sat Dec 22 15:54:54 2007 Martin Duerst <duerst@it.aoyama.ac.jp>
|
||||
|
||||
* test/ruby/test_transcode.rb: Added simple tests for
|
||||
EUC-JP and Shift_JIS and tests for ASCII-only range
|
||||
|
||||
Sat Dec 22 18:20:13 2007 NAKAMURA Usaku <usa@ruby-lang.org>
|
||||
|
||||
* common.mk (version.o): add dependency. [ruby-dev:32680]
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
# -*- encoding: ASCII-8BIT -*- # make sure this runs in binary mode
|
||||
# some of the comments are in UTF-8
|
||||
|
||||
require 'test/unit'
|
||||
class TestTranscode < Test::Unit::TestCase
|
||||
|
|
@ -21,8 +22,6 @@ class TestTranscode < Test::Unit::TestCase
|
|||
# maybe 'convert to UTF-8' would be nice :-)
|
||||
assert_raise(ArgumentError) { 'abc'.encode }
|
||||
assert_raise(ArgumentError) { 'abc'.encode! }
|
||||
assert_raise(ArgumentError) { 'abc'.force_encoding('Shift_JIS').encode('UTF-8') } # temporary
|
||||
assert_raise(ArgumentError) { 'abc'.force_encoding('Shift_JIS').encode!('UTF-8') } # temporary
|
||||
assert_raise(ArgumentError) { 'abc'.encode('foo', 'bar') }
|
||||
assert_raise(ArgumentError) { 'abc'.encode!('foo', 'bar') }
|
||||
assert_raise(ArgumentError) { 'abc'.force_encoding('utf-8').encode('foo') }
|
||||
|
|
@ -51,40 +50,57 @@ class TestTranscode < Test::Unit::TestCase
|
|||
assert_equal("\u20AC"*200000, ("\xA4"*200000).encode('utf-8', 'iso-8859-15'))
|
||||
assert_equal("\u20AC"*200000, ("\xA4"*200000).encode!('utf-8', 'iso-8859-15'))
|
||||
end
|
||||
|
||||
|
||||
def check_both_ways(utf8, raw, encoding)
|
||||
assert_equal(utf8, raw.encode('utf-8', encoding))
|
||||
assert_equal(raw, utf8.encode(encoding).force_encoding('ASCII-8BIT'))
|
||||
end
|
||||
|
||||
def test_encodings
|
||||
# temporary, fix encoding
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".force_encoding('iso-8859-1').encode('utf-8'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-1'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-2'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-3'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-4'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-9'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-10'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-13'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-14'))
|
||||
assert_equal("D\u00FCrst", "D\xFCrst".encode('utf-8', 'iso-8859-15'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-1'), "D\u00FCrst".encode('iso-8859-1'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-2'), "D\u00FCrst".encode('iso-8859-2'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-3').encoding, "D\u00FCrst".encode('iso-8859-3').encoding)
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-4'), "D\u00FCrst".encode('iso-8859-4'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-9'), "D\u00FCrst".encode('iso-8859-9'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-10'), "D\u00FCrst".encode('iso-8859-10'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-13'), "D\u00FCrst".encode('iso-8859-13'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-14'), "D\u00FCrst".encode('iso-8859-14'))
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-15'), "D\u00FCrst".encode('iso-8859-15'))
|
||||
assert_equal("r\xE9sum\xE9".force_encoding('iso-8859-1'), "r\u00E9sum\u00E9".encode('iso-8859-1'))
|
||||
assert_equal("el\xF5\xEDr\xE1s".force_encoding('iso-8859-2'),
|
||||
"\u0065\u006C\u0151\u00ED\u0072\u00E1\u0073".encode('iso-8859-2'))
|
||||
assert_equal("\xE3\xCA\xC8".force_encoding('iso-8859-6'), "\u0643\u062A\u0628".encode('iso-8859-6'))
|
||||
assert_equal( "\xDF\xD5\xE0\xD5\xD2\xDE\xD4".force_encoding('iso-8859-5'),
|
||||
"\u043F\u0435\u0440\u0435\u0432\u043E\u0434".encode('iso-8859-5'))
|
||||
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("\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("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')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-4')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-9')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-10')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-13')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-14')
|
||||
check_both_ways("D\u00FCrst", "D\xFCrst", 'iso-8859-15')
|
||||
check_both_ways("r\u00E9sum\u00E9", "r\xE9sum\xE9", 'iso-8859-1') # résumé
|
||||
check_both_ways("\u0065\u006C\u0151\u00ED\u0072\u00E1\u0073", "el\xF5\xEDr\xE1s", 'iso-8859-2') # előírás
|
||||
check_both_ways("\u043F\u0435\u0440\u0435\u0432\u043E\u0434",
|
||||
"\xDF\xD5\xE0\xD5\xD2\xDE\xD4", 'iso-8859-5') # перевод
|
||||
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')
|
||||
end
|
||||
|
||||
def test_twostep
|
||||
assert_equal("D\xFCrst".force_encoding('iso-8859-2'), "D\xFCrst".encode('iso-8859-2', 'iso-8859-1'))
|
||||
end
|
||||
|
||||
def test_ascii_range
|
||||
encodings = [
|
||||
'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3',
|
||||
'ISO-8859-4', 'ISO-8859-5', 'ISO-8859-6',
|
||||
'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
|
||||
'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-13',
|
||||
'ISO-8859-14', 'ISO-8859-15',
|
||||
'EUC-JP', 'SHIFT_JIS'
|
||||
]
|
||||
all_ascii = (0..127).to_a.pack 'C*'
|
||||
encodings.each do |enc|
|
||||
test_start = all_ascii
|
||||
assert_equal(test_start, test_start.encode('UTF-8',enc).encode(enc).force_encoding('ASCII-8BIT'))
|
||||
end
|
||||
end
|
||||
|
||||
def test_all_bytes
|
||||
encodings_8859 = [
|
||||
'ISO-8859-1', 'ISO-8859-2',
|
||||
|
|
@ -99,9 +115,7 @@ class TestTranscode < Test::Unit::TestCase
|
|||
'ISO-8859-13','ISO-8859-14','ISO-8859-15',
|
||||
#'ISO-8859-16', # not available
|
||||
]
|
||||
all_bytes = (0..255).collect {|x| x}.pack 'C*'
|
||||
test_start = all_bytes
|
||||
test_start.encode('UTF-8','ISO-8859-1').encode('ISO-8859-1')
|
||||
all_bytes = (0..255).to_a.pack 'C*'
|
||||
encodings_8859.each do |enc|
|
||||
test_start = all_bytes
|
||||
assert_equal(test_start, test_start.encode('UTF-8',enc).encode(enc).force_encoding('ASCII-8BIT'))
|
||||
|
|
|
|||
Loading…
Reference in a new issue