2007-11-23 01:30:26 -05:00
|
|
|
require 'test/unit'
|
2007-12-23 06:16:34 -05:00
|
|
|
require 'stringio'
|
2007-11-23 01:30:26 -05:00
|
|
|
|
|
|
|
class TestM17N < Test::Unit::TestCase
|
|
|
|
def assert_encoding(encname, actual, message=nil)
|
|
|
|
assert_equal(Encoding.find(encname), actual, message)
|
|
|
|
end
|
|
|
|
|
2007-12-18 00:02:24 -05:00
|
|
|
module AESU
|
|
|
|
def a(str) str.dup.force_encoding("ASCII-8BIT") end
|
|
|
|
def e(str) str.dup.force_encoding("EUC-JP") end
|
2008-01-17 19:54:38 -05:00
|
|
|
def s(str) str.dup.force_encoding("Windows-31J") end
|
2007-12-18 00:02:24 -05:00
|
|
|
def u(str) str.dup.force_encoding("UTF-8") end
|
|
|
|
end
|
|
|
|
include AESU
|
|
|
|
extend AESU
|
2007-12-17 09:59:11 -05:00
|
|
|
|
2007-12-18 00:02:24 -05:00
|
|
|
def assert_strenc(bytes, enc, actual, message=nil)
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_instance_of(String, actual, message)
|
2007-12-18 00:02:24 -05:00
|
|
|
enc = Encoding.find(enc) if String === enc
|
|
|
|
assert_equal(enc, actual.encoding, message)
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_equal(a(bytes), a(actual), message)
|
|
|
|
end
|
2007-11-23 01:30:26 -05:00
|
|
|
|
2007-12-23 13:54:22 -05:00
|
|
|
def assert_warning(pat, mesg=nil)
|
|
|
|
begin
|
|
|
|
org_stderr = $stderr
|
|
|
|
$stderr = StringIO.new(warn = '')
|
|
|
|
yield
|
|
|
|
ensure
|
|
|
|
$stderr = org_stderr
|
|
|
|
end
|
|
|
|
assert_match(pat, warn, mesg)
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_generic_encoding(r)
|
|
|
|
assert(!r.fixed_encoding?)
|
2008-01-17 19:54:38 -05:00
|
|
|
%w[ASCII-8BIT EUC-JP Windows-31J UTF-8].each {|ename|
|
|
|
|
# "\xc2\xa1" is a valid sequence for ASCII-8BIT, EUC-JP, Windows-31J and UTF-8.
|
2007-12-23 13:54:22 -05:00
|
|
|
assert_nothing_raised { r =~ "\xc2\xa1".force_encoding(ename) }
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_fixed_encoding(r)
|
|
|
|
assert(r.fixed_encoding?)
|
2008-01-17 19:54:38 -05:00
|
|
|
%w[ASCII-8BIT EUC-JP Windows-31J UTF-8].each {|ename|
|
2007-12-23 13:54:22 -05:00
|
|
|
enc = Encoding.find(ename)
|
|
|
|
if enc == r.encoding
|
|
|
|
assert_nothing_raised { r =~ "\xc2\xa1".force_encoding(enc) }
|
|
|
|
else
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ "\xc2\xa1".force_encoding(enc) }
|
2007-12-23 13:54:22 -05:00
|
|
|
end
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_generic_ascii(r)
|
2008-01-24 06:47:37 -05:00
|
|
|
assert_encoding("US-ASCII", r.encoding)
|
2007-12-23 13:54:22 -05:00
|
|
|
assert_regexp_generic_encoding(r)
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_fixed_ascii8bit(r)
|
|
|
|
assert_encoding("ASCII-8BIT", r.encoding)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_fixed_eucjp(r)
|
|
|
|
assert_encoding("EUC-JP", r.encoding)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_fixed_sjis(r)
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_encoding("Windows-31J", r.encoding)
|
2007-12-23 13:54:22 -05:00
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_regexp_fixed_utf8(r)
|
|
|
|
assert_encoding("UTF-8", r.encoding)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
end
|
|
|
|
|
2008-01-28 13:04:39 -05:00
|
|
|
def assert_regexp_usascii_literal(r, enc, ex = nil)
|
|
|
|
code = "# -*- encoding: US-ASCII -*-\n#{r}.encoding"
|
|
|
|
if ex
|
|
|
|
assert_raise(ex) { eval(code) }
|
|
|
|
else
|
|
|
|
assert_equal(enc, eval(code))
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2007-12-23 13:54:22 -05:00
|
|
|
def encdump(str)
|
2008-01-19 13:56:50 -05:00
|
|
|
d = str.dump
|
|
|
|
if /\.force_encoding\("[A-Za-z0-9.:_+-]*"\)\z/ =~ d
|
|
|
|
d
|
|
|
|
else
|
|
|
|
"#{d}.force_encoding(#{str.encoding.name.dump})"
|
|
|
|
end
|
2007-12-23 13:54:22 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def encdumpargs(args)
|
|
|
|
r = '('
|
|
|
|
args.each_with_index {|a, i|
|
|
|
|
r << ',' if 0 < i
|
|
|
|
if String === a
|
|
|
|
r << encdump(a)
|
|
|
|
else
|
|
|
|
r << a.inspect
|
|
|
|
end
|
|
|
|
}
|
|
|
|
r << ')'
|
|
|
|
r
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_str_enc_propagation(t, s1, s2)
|
|
|
|
if !s1.ascii_only?
|
|
|
|
assert_equal(s1.encoding, t.encoding)
|
|
|
|
elsif !s2.ascii_only?
|
|
|
|
assert_equal(s2.encoding, t.encoding)
|
|
|
|
else
|
|
|
|
assert([s1.encoding, s2.encoding].include?(t.encoding))
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def assert_same_result(expected_proc, actual_proc)
|
|
|
|
e = nil
|
|
|
|
begin
|
|
|
|
t = expected_proc.call
|
|
|
|
rescue
|
|
|
|
e = $!
|
|
|
|
end
|
|
|
|
if e
|
|
|
|
assert_raise(e.class) { actual_proc.call }
|
|
|
|
else
|
|
|
|
assert_equal(t, actual_proc.call)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def str_enc_compatible?(*strs)
|
|
|
|
encs = []
|
|
|
|
strs.each {|s|
|
|
|
|
encs << s.encoding if !s.ascii_only?
|
|
|
|
}
|
|
|
|
encs.uniq!
|
|
|
|
encs.length <= 1
|
|
|
|
end
|
|
|
|
|
|
|
|
# tests start
|
|
|
|
|
2007-11-23 01:30:26 -05:00
|
|
|
def test_string_ascii_literal
|
2008-09-19 19:09:33 -04:00
|
|
|
assert_encoding("ASCII-8BIT", eval(a(%{""})).encoding)
|
|
|
|
assert_encoding("ASCII-8BIT", eval(a(%{"a"})).encoding)
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|
|
|
|
|
2007-12-01 21:53:46 -05:00
|
|
|
def test_string_eucjp_literal
|
2008-09-19 19:09:33 -04:00
|
|
|
assert_encoding("EUC-JP", eval(e(%{""})).encoding)
|
|
|
|
assert_encoding("EUC-JP", eval(e(%{"a"})).encoding)
|
2007-11-23 01:30:26 -05:00
|
|
|
assert_encoding("EUC-JP", eval(e(%{"\xa1\xa1"})).encoding)
|
|
|
|
assert_encoding("EUC-JP", eval(e(%{"\\xa1\\xa1"})).encoding)
|
2008-09-19 19:09:33 -04:00
|
|
|
assert_encoding("EUC-JP", eval(e(%{"\\x20"})).encoding)
|
|
|
|
assert_encoding("EUC-JP", eval(e(%{"\\n"})).encoding)
|
2007-11-23 01:30:26 -05:00
|
|
|
assert_encoding("EUC-JP", eval(e(%{"\\x80"})).encoding)
|
|
|
|
end
|
|
|
|
|
2008-01-26 06:15:24 -05:00
|
|
|
def test_utf8_literal
|
|
|
|
assert_equal(Encoding::UTF_8, "\u3042".encoding, "[ruby-dev:33406] \"\\u3042\".encoding")
|
2008-01-27 21:26:23 -05:00
|
|
|
assert_raise(SyntaxError) { eval(a('\u3052\x80')) }
|
2008-01-26 06:15:24 -05:00
|
|
|
end
|
|
|
|
|
2007-12-01 11:56:19 -05:00
|
|
|
def test_string_mixed_unicode
|
2007-12-30 09:57:07 -05:00
|
|
|
assert_raise(SyntaxError) { eval(a(%{"\xc2\xa1\\u{6666}"})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{"\xc2\xa1\\u{6666}"})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{"\xc2\xa1\\u{6666}"})) }
|
|
|
|
assert_nothing_raised { eval(u(%{"\xc2\xa1\\u{6666}"})) }
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{"\\u{6666}\xc2\xa1"})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{"\\u{6666}\xc2\xa1"})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{"\\u{6666}\xc2\xa1"})) }
|
|
|
|
assert_nothing_raised { eval(u(%{"\\u{6666}\xc2\xa1"})) }
|
2007-12-06 04:28:26 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_string_inspect
|
2007-12-12 19:21:18 -05:00
|
|
|
assert_equal('"\xFE"', e("\xfe").inspect)
|
|
|
|
assert_equal('"\x8E"', e("\x8e").inspect)
|
|
|
|
assert_equal('"\x8F"', e("\x8f").inspect)
|
|
|
|
assert_equal('"\x8F\xA1"', e("\x8f\xa1").inspect)
|
|
|
|
assert_equal('"\xEF"', s("\xef").inspect)
|
|
|
|
assert_equal('"\xC2"', u("\xc2").inspect)
|
|
|
|
assert_equal('"\xE0\x80"', u("\xe0\x80").inspect)
|
|
|
|
assert_equal('"\xF0\x80\x80"', u("\xf0\x80\x80").inspect)
|
|
|
|
assert_equal('"\xF8\x80\x80\x80"', u("\xf8\x80\x80\x80").inspect)
|
|
|
|
assert_equal('"\xFC\x80\x80\x80\x80"', u("\xfc\x80\x80\x80\x80").inspect)
|
2007-12-06 04:28:26 -05:00
|
|
|
|
2007-12-12 19:21:18 -05:00
|
|
|
assert_equal('"\xFE "', e("\xfe ").inspect)
|
|
|
|
assert_equal('"\x8E "', e("\x8e ").inspect)
|
|
|
|
assert_equal('"\x8F "', e("\x8f ").inspect)
|
|
|
|
assert_equal('"\x8F\xA1 "', e("\x8f\xa1 ").inspect)
|
|
|
|
assert_equal('"\xEF "', s("\xef ").inspect)
|
|
|
|
assert_equal('"\xC2 "', u("\xc2 ").inspect)
|
|
|
|
assert_equal('"\xE0\x80 "', u("\xe0\x80 ").inspect)
|
|
|
|
assert_equal('"\xF0\x80\x80 "', u("\xf0\x80\x80 ").inspect)
|
|
|
|
assert_equal('"\xF8\x80\x80\x80 "', u("\xf8\x80\x80\x80 ").inspect)
|
|
|
|
assert_equal('"\xFC\x80\x80\x80\x80 "', u("\xfc\x80\x80\x80\x80 ").inspect)
|
2007-12-06 04:28:26 -05:00
|
|
|
|
|
|
|
|
2007-12-12 19:21:18 -05:00
|
|
|
assert_equal(e("\"\\xA1\x8f\xA1\xA1\""), e("\xa1\x8f\xa1\xa1").inspect)
|
2007-12-06 04:28:26 -05:00
|
|
|
|
2007-12-09 18:18:25 -05:00
|
|
|
assert_equal('"\x81."', s("\x81.").inspect)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_equal(s("\"\x81@\""), s("\x81@").inspect)
|
|
|
|
|
2007-12-12 19:21:18 -05:00
|
|
|
assert_equal('"\xFC"', u("\xfc").inspect)
|
2007-12-01 11:56:19 -05:00
|
|
|
end
|
|
|
|
|
2008-01-18 00:43:03 -05:00
|
|
|
def test_str_dump
|
|
|
|
[
|
|
|
|
e("\xfe"),
|
|
|
|
e("\x8e"),
|
|
|
|
e("\x8f"),
|
|
|
|
e("\x8f\xa1"),
|
|
|
|
s("\xef"),
|
|
|
|
u("\xc2"),
|
|
|
|
u("\xe0\x80"),
|
|
|
|
u("\xf0\x80\x80"),
|
|
|
|
u("\xf8\x80\x80\x80"),
|
|
|
|
u("\xfc\x80\x80\x80\x80"),
|
|
|
|
|
|
|
|
e("\xfe "),
|
|
|
|
e("\x8e "),
|
|
|
|
e("\x8f "),
|
|
|
|
e("\x8f\xa1 "),
|
|
|
|
s("\xef "),
|
|
|
|
u("\xc2 "),
|
|
|
|
u("\xe0\x80 "),
|
|
|
|
u("\xf0\x80\x80 "),
|
|
|
|
u("\xf8\x80\x80\x80 "),
|
|
|
|
u("\xfc\x80\x80\x80\x80 "),
|
|
|
|
|
|
|
|
|
|
|
|
e("\xa1\x8f\xa1\xa1"),
|
|
|
|
|
|
|
|
s("\x81."),
|
|
|
|
s("\x81@"),
|
|
|
|
|
|
|
|
u("\xfc"),
|
|
|
|
"\u3042",
|
|
|
|
"ascii",
|
2009-04-08 09:05:07 -04:00
|
|
|
|
|
|
|
"\u3042".encode("UTF-16LE"),
|
|
|
|
"\u3042".encode("UTF-16BE"),
|
2008-01-18 00:43:03 -05:00
|
|
|
].each do |str|
|
|
|
|
assert_equal(str, eval(str.dump), "[ruby-dev:33142]")
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2007-12-07 23:31:26 -05:00
|
|
|
def test_validate_redundant_utf8
|
|
|
|
bits_0x10ffff = "11110100 10001111 10111111 10111111"
|
|
|
|
[
|
|
|
|
"0xxxxxxx",
|
|
|
|
"110XXXXx 10xxxxxx",
|
|
|
|
"1110XXXX 10Xxxxxx 10xxxxxx",
|
|
|
|
"11110XXX 10XXxxxx 10xxxxxx 10xxxxxx",
|
|
|
|
"111110XX 10XXXxxx 10xxxxxx 10xxxxxx 10xxxxxx",
|
|
|
|
"1111110X 10XXXXxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx",
|
|
|
|
"11111110 10XXXXXx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx",
|
|
|
|
"11111111 10XXXXXX 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx",
|
|
|
|
].each {|pat0|
|
|
|
|
[
|
|
|
|
pat0.gsub(/x/, '1'),
|
|
|
|
pat0.gsub(/x/, '0')
|
|
|
|
].each {|pat1|
|
|
|
|
[
|
|
|
|
pat1.sub(/X([^X]*)\z/, '1\1').gsub(/X/, "0"),
|
|
|
|
pat1.gsub(/X/, "1"),
|
|
|
|
].each {|pat2|
|
|
|
|
s = [pat2.gsub(/ /, "")].pack("B*").force_encoding("utf-8")
|
|
|
|
if pat2 <= bits_0x10ffff
|
|
|
|
assert(s.valid_encoding?, "#{pat2}")
|
|
|
|
else
|
|
|
|
assert(!s.valid_encoding?, "#{pat2}")
|
|
|
|
end
|
|
|
|
}
|
|
|
|
if / / =~ pat0
|
|
|
|
pat3 = pat1.gsub(/X/, "0")
|
|
|
|
s = [pat3.gsub(/ /, "")].pack("B*").force_encoding("utf-8")
|
|
|
|
assert(!s.valid_encoding?, "#{pat3}")
|
|
|
|
end
|
|
|
|
}
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_validate_surrogate
|
|
|
|
# 1110XXXX 10Xxxxxx 10xxxxxx : 3 bytes UTF-8
|
|
|
|
pats = [
|
|
|
|
"11101101 10011111 10111111", # just before surrogate high
|
|
|
|
"11101101 1010xxxx 10xxxxxx", # surrogate high
|
|
|
|
"11101101 1011xxxx 10xxxxxx", # surrogate low
|
|
|
|
"11101110 10000000 10000000", # just after surrogate low
|
|
|
|
]
|
|
|
|
pats.values_at(1,2).each {|pat0|
|
|
|
|
[
|
|
|
|
pat0.gsub(/x/, '0'),
|
|
|
|
pat0.gsub(/x/, '1'),
|
|
|
|
].each {|pat1|
|
|
|
|
s = [pat1.gsub(/ /, "")].pack("B*").force_encoding("utf-8")
|
|
|
|
assert(!s.valid_encoding?, "#{pat1}")
|
|
|
|
}
|
|
|
|
}
|
|
|
|
pats.values_at(0,3).each {|pat|
|
|
|
|
s = [pat.gsub(/ /, "")].pack("B*").force_encoding("utf-8")
|
|
|
|
assert(s.valid_encoding?, "#{pat}")
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
2007-11-23 01:30:26 -05:00
|
|
|
def test_regexp_too_short_multibyte_character
|
|
|
|
assert_raise(SyntaxError) { eval('/\xfe/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\x8e/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\x8f/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\x8f\xa1/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xef/s') }
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xc2/u') }
|
2007-11-23 01:30:26 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xe0\x80/u') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xf0\x80\x80/u') }
|
2007-12-07 21:50:43 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xf8\x80\x80\x80/u') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xfc\x80\x80\x80\x80/u') }
|
2007-11-23 01:30:26 -05:00
|
|
|
|
|
|
|
# raw 8bit
|
2007-12-01 11:56:19 -05:00
|
|
|
assert_raise(SyntaxError) { eval("/\xfe/e") }
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_raise(SyntaxError) { eval("/\xc2/u") }
|
2007-11-23 01:30:26 -05:00
|
|
|
|
|
|
|
# invalid suffix
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xc2\xff/u') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xc2 /u') }
|
2007-12-07 21:50:43 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xc2\x20/u') }
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_regexp_generic
|
2007-11-26 08:05:08 -05:00
|
|
|
assert_regexp_generic_ascii(/a/)
|
|
|
|
assert_regexp_generic_ascii(Regexp.new(a("a")))
|
2007-12-01 11:56:19 -05:00
|
|
|
assert_regexp_generic_ascii(Regexp.new(e("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.new(s("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.new(u("a")))
|
2007-11-26 08:05:08 -05:00
|
|
|
|
|
|
|
[/a/, Regexp.new(a("a"))].each {|r|
|
|
|
|
assert_equal(0, r =~ a("a"))
|
|
|
|
assert_equal(0, r =~ e("a"))
|
|
|
|
assert_equal(0, r =~ s("a"))
|
|
|
|
assert_equal(0, r =~ u("a"))
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_equal(nil, r =~ a("\xc2\xa1"))
|
|
|
|
assert_equal(nil, r =~ e("\xc2\xa1"))
|
|
|
|
assert_equal(nil, r =~ s("\xc2\xa1"))
|
|
|
|
assert_equal(nil, r =~ u("\xc2\xa1"))
|
2007-11-26 08:05:08 -05:00
|
|
|
}
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|
|
|
|
|
2007-12-22 01:00:56 -05:00
|
|
|
def test_regexp_ascii_none
|
2007-12-23 06:16:34 -05:00
|
|
|
r = /a/n
|
|
|
|
|
|
|
|
assert_warning(%r{regexp match /.../n against to}) {
|
|
|
|
assert_regexp_generic_ascii(r)
|
|
|
|
}
|
|
|
|
|
|
|
|
assert_equal(0, r =~ a("a"))
|
|
|
|
assert_equal(0, r =~ e("a"))
|
|
|
|
assert_equal(0, r =~ s("a"))
|
|
|
|
assert_equal(0, r =~ u("a"))
|
|
|
|
assert_equal(nil, r =~ a("\xc2\xa1"))
|
|
|
|
assert_warning(%r{regexp match /.../n against to EUC-JP string}) {
|
|
|
|
assert_equal(nil, r =~ e("\xc2\xa1"))
|
|
|
|
}
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_warning(%r{regexp match /.../n against to Windows-31J string}) {
|
2007-12-23 06:16:34 -05:00
|
|
|
assert_equal(nil, r =~ s("\xc2\xa1"))
|
|
|
|
}
|
|
|
|
assert_warning(%r{regexp match /.../n against to UTF-8 string}) {
|
|
|
|
assert_equal(nil, r =~ u("\xc2\xa1"))
|
|
|
|
}
|
2008-01-05 11:39:38 -05:00
|
|
|
|
|
|
|
assert_nothing_raised { eval(e("/\\x80/n")) }
|
2007-12-22 01:00:56 -05:00
|
|
|
end
|
|
|
|
|
2007-11-23 01:30:26 -05:00
|
|
|
def test_regexp_ascii
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_ascii8bit(/\xc2\xa1/n)
|
|
|
|
assert_regexp_fixed_ascii8bit(eval(a(%{/\xc2\xa1/})))
|
|
|
|
assert_regexp_fixed_ascii8bit(eval(a(%{/\xc2\xa1/n})))
|
|
|
|
assert_regexp_fixed_ascii8bit(eval(a(%q{/\xc2\xa1/})))
|
2007-11-26 08:05:08 -05:00
|
|
|
|
2008-01-24 06:51:52 -05:00
|
|
|
assert_raise(SyntaxError) { eval("/\xa1\xa1/n".force_encoding("euc-jp")) }
|
|
|
|
|
2007-12-06 04:28:26 -05:00
|
|
|
[/\xc2\xa1/n, eval(a(%{/\xc2\xa1/})), eval(a(%{/\xc2\xa1/n}))].each {|r|
|
2007-11-26 08:05:08 -05:00
|
|
|
assert_equal(nil, r =~ a("a"))
|
|
|
|
assert_equal(nil, r =~ e("a"))
|
|
|
|
assert_equal(nil, r =~ s("a"))
|
|
|
|
assert_equal(nil, r =~ u("a"))
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_equal(0, r =~ a("\xc2\xa1"))
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ e("\xc2\xa1") }
|
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ s("\xc2\xa1") }
|
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ u("\xc2\xa1") }
|
2007-11-26 08:05:08 -05:00
|
|
|
}
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_regexp_euc
|
2007-11-26 08:05:08 -05:00
|
|
|
assert_regexp_fixed_eucjp(/a/e)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_eucjp(/\xc2\xa1/e)
|
|
|
|
assert_regexp_fixed_eucjp(eval(e(%{/\xc2\xa1/})))
|
|
|
|
assert_regexp_fixed_eucjp(eval(e(%q{/\xc2\xa1/})))
|
2007-11-26 08:05:08 -05:00
|
|
|
|
2007-12-01 11:56:19 -05:00
|
|
|
[/a/e].each {|r|
|
2007-11-26 08:05:08 -05:00
|
|
|
assert_equal(0, r =~ a("a"))
|
|
|
|
assert_equal(0, r =~ e("a"))
|
|
|
|
assert_equal(0, r =~ s("a"))
|
|
|
|
assert_equal(0, r =~ u("a"))
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ a("\xc2\xa1") }
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_equal(nil, r =~ e("\xc2\xa1"))
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ s("\xc2\xa1") }
|
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ u("\xc2\xa1") }
|
2007-11-26 08:05:08 -05:00
|
|
|
}
|
2007-11-25 08:25:34 -05:00
|
|
|
|
2007-12-06 04:28:26 -05:00
|
|
|
[/\xc2\xa1/e, eval(e(%{/\xc2\xa1/})), eval(e(%q{/\xc2\xa1/}))].each {|r|
|
2007-11-26 08:05:08 -05:00
|
|
|
assert_equal(nil, r =~ a("a"))
|
|
|
|
assert_equal(nil, r =~ e("a"))
|
|
|
|
assert_equal(nil, r =~ s("a"))
|
|
|
|
assert_equal(nil, r =~ u("a"))
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ a("\xc2\xa1") }
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_equal(0, r =~ e("\xc2\xa1"))
|
2008-12-12 22:49:46 -05:00
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ s("\xc2\xa1") }
|
|
|
|
assert_raise(Encoding::CompatibilityError) { r =~ u("\xc2\xa1") }
|
2007-11-26 08:05:08 -05:00
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_regexp_sjis
|
|
|
|
assert_regexp_fixed_sjis(/a/s)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_sjis(/\xc2\xa1/s)
|
|
|
|
assert_regexp_fixed_sjis(eval(s(%{/\xc2\xa1/})))
|
|
|
|
assert_regexp_fixed_sjis(eval(s(%q{/\xc2\xa1/})))
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|
|
|
|
|
2008-01-06 21:49:01 -05:00
|
|
|
def test_regexp_windows_31j
|
|
|
|
begin
|
|
|
|
Regexp.new("\xa1".force_encoding("windows-31j")) =~ "\xa1\xa1".force_encoding("euc-jp")
|
2008-12-12 22:49:46 -05:00
|
|
|
rescue Encoding::CompatibilityError
|
2008-01-06 21:49:01 -05:00
|
|
|
err = $!
|
|
|
|
end
|
|
|
|
assert_match(/windows-31j/i, err.message)
|
|
|
|
end
|
|
|
|
|
2007-12-08 02:21:05 -05:00
|
|
|
def test_regexp_embed
|
|
|
|
r = eval(e("/\xc2\xa1/"))
|
|
|
|
assert_raise(ArgumentError) { eval(s("/\xc2\xa1\#{r}/s")) }
|
|
|
|
assert_raise(ArgumentError) { eval(s("/\#{r}\xc2\xa1/s")) }
|
|
|
|
|
|
|
|
r = /\xc2\xa1/e
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { eval(s("/\xc2\xa1\#{r}/s")) }
|
|
|
|
assert_raise(ArgumentError) { eval(s("/\#{r}\xc2\xa1/s")) }
|
2007-12-08 02:21:05 -05:00
|
|
|
|
|
|
|
r = eval(e("/\xc2\xa1/"))
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { /\xc2\xa1#{r}/s }
|
2007-12-08 02:21:05 -05:00
|
|
|
|
|
|
|
r = /\xc2\xa1/e
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { /\xc2\xa1#{r}/s }
|
2008-02-14 00:03:07 -05:00
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::US_ASCII, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("us-ascii"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::US_ASCII, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('us-ascii'))
|
|
|
|
assert_equal(Encoding::US_ASCII, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("us-ascii"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('us-ascii'))
|
|
|
|
assert_equal(Encoding::US_ASCII, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('\xa1'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('\xa1'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/bar#{r1}/'.force_encoding('us-ascii'))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/\xa1#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('foo'.force_encoding("us-ascii"))
|
|
|
|
r2 = eval('/\xa1#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, r2.encoding)
|
|
|
|
|
|
|
|
r1 = Regexp.new('\xa1'.force_encoding("ascii-8bit"))
|
|
|
|
r2 = eval('/\xa1#{r1}/'.force_encoding('ascii-8bit'))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, r2.encoding)
|
2007-12-08 02:21:05 -05:00
|
|
|
end
|
|
|
|
|
2008-02-14 01:01:05 -05:00
|
|
|
def test_regexp_named_class
|
|
|
|
assert_match(/[[:space:]]/u, "\u{00a0}")
|
|
|
|
assert_match(/[[:space:]]/, "\u{00a0}")
|
|
|
|
end
|
|
|
|
|
2008-07-04 19:33:04 -04:00
|
|
|
def test_regexp_property
|
|
|
|
s = '\p{Hiragana}'.force_encoding("euc-jp")
|
|
|
|
assert_equal(Encoding::EUC_JP, s.encoding)
|
|
|
|
r = nil
|
|
|
|
assert_nothing_raised {
|
|
|
|
r = Regexp.new(s)
|
|
|
|
}
|
|
|
|
assert(r.fixed_encoding?)
|
|
|
|
assert_match(r, "\xa4\xa2".force_encoding("euc-jp"))
|
|
|
|
|
|
|
|
r = eval('/\p{Hiragana}/'.force_encoding("euc-jp"))
|
|
|
|
assert(r.fixed_encoding?)
|
|
|
|
assert_match(r, "\xa4\xa2".force_encoding("euc-jp"))
|
|
|
|
|
|
|
|
r = /\p{Hiragana}/e
|
|
|
|
assert(r.fixed_encoding?)
|
|
|
|
assert_match(r, "\xa4\xa2".force_encoding("euc-jp"))
|
2008-07-04 19:50:33 -04:00
|
|
|
|
|
|
|
r = eval('/\u{3042}\p{Hiragana}/'.force_encoding("euc-jp"))
|
|
|
|
assert(r.fixed_encoding?)
|
|
|
|
assert_equal(Encoding::UTF_8, r.encoding)
|
|
|
|
|
|
|
|
r = eval('/\p{Hiragana}\u{3042}/'.force_encoding("euc-jp"))
|
|
|
|
assert(r.fixed_encoding?)
|
|
|
|
assert_equal(Encoding::UTF_8, r.encoding)
|
2008-07-04 19:33:04 -04:00
|
|
|
end
|
|
|
|
|
2008-02-13 22:34:12 -05:00
|
|
|
def test_regexp_embed_preprocess
|
|
|
|
r1 = /\xa4\xa2/e
|
|
|
|
r2 = /#{r1}/
|
|
|
|
assert(r2.source.include?(r1.source))
|
|
|
|
end
|
|
|
|
|
2007-11-23 01:30:26 -05:00
|
|
|
def test_begin_end_offset
|
|
|
|
str = e("\244\242\244\244\244\246\244\250\244\252a")
|
|
|
|
assert(/(a)/ =~ str)
|
|
|
|
assert_equal("a", $&)
|
|
|
|
assert_equal(5, $~.begin(0))
|
|
|
|
assert_equal(6, $~.end(0))
|
|
|
|
assert_equal([5,6], $~.offset(0))
|
|
|
|
assert_equal(5, $~.begin(1))
|
|
|
|
assert_equal(6, $~.end(1))
|
|
|
|
assert_equal([5,6], $~.offset(1))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_begin_end_offset_sjis
|
|
|
|
str = s("\x81@@")
|
|
|
|
assert(/@/ =~ str)
|
|
|
|
assert_equal(s("\x81@"), $`)
|
|
|
|
assert_equal("@", $&)
|
|
|
|
assert_equal("", $')
|
|
|
|
assert_equal([1,2], $~.offset(0))
|
|
|
|
end
|
|
|
|
|
2007-11-25 08:25:34 -05:00
|
|
|
def test_quote
|
|
|
|
assert_regexp_generic_ascii(/#{Regexp.quote(a("a"))}#{Regexp.quote(e("e"))}/)
|
|
|
|
|
2008-02-16 21:00:05 -05:00
|
|
|
assert_encoding("US-ASCII", Regexp.quote(a("")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(e("")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(s("")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(u("")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(a("a")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(e("a")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(s("a")).encoding)
|
|
|
|
assert_encoding("US-ASCII", Regexp.quote(u("a")).encoding)
|
2007-11-25 08:25:34 -05:00
|
|
|
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_encoding("ASCII-8BIT", Regexp.quote(a("\xc2\xa1")).encoding)
|
|
|
|
assert_encoding("EUC-JP", Regexp.quote(e("\xc2\xa1")).encoding)
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_encoding("Windows-31J", Regexp.quote(s("\xc2\xa1")).encoding)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_encoding("UTF-8", Regexp.quote(u("\xc2\xa1")).encoding)
|
2007-11-25 08:25:34 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_union_0
|
|
|
|
r = Regexp.union
|
|
|
|
assert_regexp_generic_ascii(r)
|
|
|
|
assert(r !~ a(""))
|
|
|
|
assert(r !~ e(""))
|
|
|
|
assert(r !~ s(""))
|
|
|
|
assert(r !~ u(""))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_union_1_asciionly_string
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(a("")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(e("")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(s("")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(u("")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(a("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(e("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(s("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(u("a")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(a("\t")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(e("\t")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(s("\t")))
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(u("\t")))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_union_1_nonascii_string
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_ascii8bit(Regexp.union(a("\xc2\xa1")))
|
|
|
|
assert_regexp_fixed_eucjp(Regexp.union(e("\xc2\xa1")))
|
|
|
|
assert_regexp_fixed_sjis(Regexp.union(s("\xc2\xa1")))
|
|
|
|
assert_regexp_fixed_utf8(Regexp.union(u("\xc2\xa1")))
|
2007-11-25 08:25:34 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_union_1_regexp
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(//))
|
2007-12-23 06:16:34 -05:00
|
|
|
assert_warning(%r{regexp match /.../n against to}) {
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(//n))
|
|
|
|
}
|
2007-11-25 08:25:34 -05:00
|
|
|
assert_regexp_fixed_eucjp(Regexp.union(//e))
|
|
|
|
assert_regexp_fixed_sjis(Regexp.union(//s))
|
|
|
|
assert_regexp_fixed_utf8(Regexp.union(//u))
|
|
|
|
end
|
|
|
|
|
2007-11-26 08:05:08 -05:00
|
|
|
def test_union_2
|
2007-11-25 08:25:34 -05:00
|
|
|
ary = [
|
|
|
|
a(""), e(""), s(""), u(""),
|
2007-12-06 04:28:26 -05:00
|
|
|
a("\xc2\xa1"), e("\xc2\xa1"), s("\xc2\xa1"), u("\xc2\xa1")
|
2007-11-25 08:25:34 -05:00
|
|
|
]
|
|
|
|
ary.each {|s1|
|
|
|
|
ary.each {|s2|
|
|
|
|
if s1.empty?
|
|
|
|
if s2.empty?
|
|
|
|
assert_regexp_generic_ascii(Regexp.union(s1, s2))
|
|
|
|
else
|
|
|
|
r = Regexp.union(s1, s2)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
assert_equal(s2.encoding, r.encoding)
|
|
|
|
end
|
|
|
|
else
|
|
|
|
if s2.empty?
|
|
|
|
r = Regexp.union(s1, s2)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
assert_equal(s1.encoding, r.encoding)
|
|
|
|
else
|
|
|
|
if s1.encoding == s2.encoding
|
|
|
|
r = Regexp.union(s1, s2)
|
|
|
|
assert_regexp_fixed_encoding(r)
|
|
|
|
assert_equal(s1.encoding, r.encoding)
|
|
|
|
else
|
|
|
|
assert_raise(ArgumentError) { Regexp.union(s1, s2) }
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
}
|
|
|
|
}
|
|
|
|
end
|
2007-12-01 19:16:24 -05:00
|
|
|
|
2007-12-01 21:53:46 -05:00
|
|
|
def test_dynamic_ascii_regexp
|
2007-12-23 06:16:34 -05:00
|
|
|
assert_warning(%r{regexp match /.../n against to}) {
|
|
|
|
assert_regexp_generic_ascii(/#{}/n)
|
|
|
|
}
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_ascii8bit(/#{}\xc2\xa1/n)
|
|
|
|
assert_regexp_fixed_ascii8bit(/\xc2\xa1#{}/n)
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_nothing_raised { s1, s2 = a('\xc2'), a('\xa1'); /#{s1}#{s2}/ }
|
2007-12-01 21:53:46 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_dynamic_eucjp_regexp
|
|
|
|
assert_regexp_fixed_eucjp(/#{}/e)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_eucjp(/#{}\xc2\xa1/e)
|
|
|
|
assert_regexp_fixed_eucjp(/\xc2\xa1#{}/e)
|
2007-12-08 02:21:05 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xc2#{}/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/#{}\xc2/e') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xc2#{}\xa1/e') }
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { s1, s2 = e('\xc2'), e('\xa1'); /#{s1}#{s2}/ }
|
2007-12-01 21:53:46 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_dynamic_sjis_regexp
|
|
|
|
assert_regexp_fixed_sjis(/#{}/s)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_sjis(/#{}\xc2\xa1/s)
|
|
|
|
assert_regexp_fixed_sjis(/\xc2\xa1#{}/s)
|
2007-12-08 02:21:05 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\x81#{}/s') }
|
|
|
|
assert_raise(SyntaxError) { eval('/#{}\x81/s') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\x81#{}\xa1/s') }
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { s1, s2 = s('\x81'), s('\xa1'); /#{s1}#{s2}/ }
|
2007-12-01 21:53:46 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_dynamic_utf8_regexp
|
|
|
|
assert_regexp_fixed_utf8(/#{}/u)
|
2007-12-06 04:28:26 -05:00
|
|
|
assert_regexp_fixed_utf8(/#{}\xc2\xa1/u)
|
|
|
|
assert_regexp_fixed_utf8(/\xc2\xa1#{}/u)
|
2007-12-08 02:21:05 -05:00
|
|
|
assert_raise(SyntaxError) { eval('/\xc2#{}/u') }
|
|
|
|
assert_raise(SyntaxError) { eval('/#{}\xc2/u') }
|
|
|
|
assert_raise(SyntaxError) { eval('/\xc2#{}\xa1/u') }
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_raise(ArgumentError) { s1, s2 = u('\xc2'), u('\xa1'); /#{s1}#{s2}/ }
|
2007-12-01 21:53:46 -05:00
|
|
|
end
|
|
|
|
|
2007-12-08 22:50:11 -05:00
|
|
|
def test_regexp_unicode
|
2007-12-13 08:44:02 -05:00
|
|
|
assert_nothing_raised { eval '/\u{0}/u' }
|
|
|
|
assert_nothing_raised { eval '/\u{D7FF}/u' }
|
|
|
|
assert_raise(SyntaxError) { eval '/\u{D800}/u' }
|
|
|
|
assert_raise(SyntaxError) { eval '/\u{DFFF}/u' }
|
|
|
|
assert_nothing_raised { eval '/\u{E000}/u' }
|
|
|
|
assert_nothing_raised { eval '/\u{10FFFF}/u' }
|
|
|
|
assert_raise(SyntaxError) { eval '/\u{110000}/u' }
|
2007-12-08 22:50:11 -05:00
|
|
|
end
|
|
|
|
|
2007-12-01 21:53:46 -05:00
|
|
|
def test_regexp_mixed_unicode
|
2007-12-30 09:57:07 -05:00
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\xc2\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\xc2\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\xc2\xa1\\u{6666}/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\xc2\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\u{6666}\xc2\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\u{6666}\xc2\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\u{6666}\xc2\xa1/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\u{6666}\xc2\xa1/})) }
|
|
|
|
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\xc2\\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\xc2\\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\xc2\\xa1\\u{6666}/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\xc2\\xa1\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\u{6666}\\xc2\\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\u{6666}\\xc2\\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\u{6666}\\xc2\\xa1/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\u{6666}\\xc2\\xa1/})) }
|
|
|
|
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\xc2\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\xc2\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\xc2\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\xc2\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\u{6666}#{}\xc2\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\u{6666}#{}\xc2\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\u{6666}#{}\xc2\xa1/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\u{6666}#{}\xc2\xa1/})) }
|
|
|
|
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\xc2\\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\xc2\\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\xc2\\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\xc2\\xa1#{}\\u{6666}/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(a(%{/\\u{6666}#{}\\xc2\\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(e(%{/\\u{6666}#{}\\xc2\\xa1/})) }
|
|
|
|
assert_raise(SyntaxError) { eval(s(%{/\\u{6666}#{}\\xc2\\xa1/})) }
|
|
|
|
assert_nothing_raised { eval(u(%{/\\u{6666}#{}\\xc2\\xa1/})) }
|
2007-12-01 19:16:24 -05:00
|
|
|
end
|
2007-12-08 21:29:24 -05:00
|
|
|
|
2007-12-24 06:36:48 -05:00
|
|
|
def test_str_allocate
|
|
|
|
s = String.allocate
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, s.encoding)
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_str_String
|
|
|
|
s = String(10)
|
2008-01-28 04:29:05 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, s.encoding)
|
2007-12-24 06:36:48 -05:00
|
|
|
end
|
|
|
|
|
2007-12-17 09:59:11 -05:00
|
|
|
def test_sprintf_c
|
|
|
|
assert_strenc("\x80", 'ASCII-8BIT', a("%c") % 128)
|
|
|
|
#assert_raise(ArgumentError) { a("%c") % 0xc2a1 }
|
|
|
|
assert_strenc("\xc2\xa1", 'EUC-JP', e("%c") % 0xc2a1)
|
|
|
|
assert_raise(ArgumentError) { e("%c") % 0xc2 }
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_strenc("\xc2", 'Windows-31J', s("%c") % 0xc2)
|
2007-12-17 09:59:11 -05:00
|
|
|
#assert_raise(ArgumentError) { s("%c") % 0xc2a1 }
|
|
|
|
assert_strenc("\u{c2a1}", 'UTF-8', u("%c") % 0xc2a1)
|
|
|
|
assert_strenc("\u{c2}", 'UTF-8', u("%c") % 0xc2)
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) {
|
2008-01-21 22:59:53 -05:00
|
|
|
"%s%s" % [s("\xc2\xa1"), e("\xc2\xa1")]
|
|
|
|
}
|
2007-12-17 09:59:11 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_sprintf_p
|
|
|
|
assert_strenc('""', 'ASCII-8BIT', a("%p") % a(""))
|
|
|
|
assert_strenc('""', 'EUC-JP', e("%p") % e(""))
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_strenc('""', 'Windows-31J', s("%p") % s(""))
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_strenc('""', 'UTF-8', u("%p") % u(""))
|
|
|
|
|
|
|
|
assert_strenc('"a"', 'ASCII-8BIT', a("%p") % a("a"))
|
|
|
|
assert_strenc('"a"', 'EUC-JP', e("%p") % e("a"))
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_strenc('"a"', 'Windows-31J', s("%p") % s("a"))
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_strenc('"a"', 'UTF-8', u("%p") % u("a"))
|
|
|
|
|
|
|
|
assert_strenc('"\xC2\xA1"', 'ASCII-8BIT', a("%p") % a("\xc2\xa1"))
|
|
|
|
assert_strenc("\"\xC2\xA1\"", 'EUC-JP', e("%p") % e("\xc2\xa1"))
|
2008-01-17 19:54:38 -05:00
|
|
|
#assert_strenc("\"\xC2\xA1\"", 'Windows-31J', s("%p") % s("\xc2\xa1"))
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_strenc("\"\xC2\xA1\"", 'UTF-8', u("%p") % u("\xc2\xa1"))
|
|
|
|
|
2009-05-24 19:00:01 -04:00
|
|
|
assert_strenc('"\xC2\xA1"', 'ASCII-8BIT', "%10p" % a("\xc2\xa1"))
|
2008-01-18 10:37:22 -05:00
|
|
|
assert_strenc(" \"\xC2\xA1\"", 'EUC-JP', "%10p" % e("\xc2\xa1"))
|
|
|
|
#assert_strenc(" \"\xC2\xA1\"", 'Windows-31J', "%10p" % s("\xc2\xa1"))
|
|
|
|
assert_strenc(" \"\xC2\xA1\"", 'UTF-8', "%10p" % u("\xc2\xa1"))
|
|
|
|
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_strenc('"\x00"', 'ASCII-8BIT', a("%p") % a("\x00"))
|
|
|
|
assert_strenc('"\x00"', 'EUC-JP', e("%p") % e("\x00"))
|
2008-01-17 19:54:38 -05:00
|
|
|
assert_strenc('"\x00"', 'Windows-31J', s("%p") % s("\x00"))
|
2007-12-17 09:59:11 -05:00
|
|
|
assert_strenc('"\x00"', 'UTF-8', u("%p") % u("\x00"))
|
|
|
|
end
|
|
|
|
|
2008-01-18 10:37:22 -05:00
|
|
|
def test_sprintf_s
|
|
|
|
assert_strenc('', 'ASCII-8BIT', a("%s") % a(""))
|
|
|
|
assert_strenc('', 'EUC-JP', e("%s") % e(""))
|
|
|
|
assert_strenc('', 'Windows-31J', s("%s") % s(""))
|
|
|
|
assert_strenc('', 'UTF-8', u("%s") % u(""))
|
|
|
|
|
|
|
|
assert_strenc('a', 'ASCII-8BIT', a("%s") % a("a"))
|
|
|
|
assert_strenc('a', 'EUC-JP', e("%s") % e("a"))
|
|
|
|
assert_strenc('a', 'Windows-31J', s("%s") % s("a"))
|
|
|
|
assert_strenc('a', 'UTF-8', u("%s") % u("a"))
|
|
|
|
|
|
|
|
assert_strenc("\xC2\xA1", 'ASCII-8BIT', a("%s") % a("\xc2\xa1"))
|
|
|
|
assert_strenc("\xC2\xA1", 'EUC-JP', e("%s") % e("\xc2\xa1"))
|
|
|
|
#assert_strenc("\xC2\xA1", 'Windows-31J', s("%s") % s("\xc2\xa1"))
|
|
|
|
assert_strenc("\xC2\xA1", 'UTF-8', u("%s") % u("\xc2\xa1"))
|
|
|
|
|
|
|
|
assert_strenc(" \xC2\xA1", 'ASCII-8BIT', "%10s" % a("\xc2\xa1"))
|
|
|
|
assert_strenc(" \xA1\xA1", 'EUC-JP', "%10s" % e("\xa1\xa1"))
|
|
|
|
#assert_strenc(" \xC2\xA1", 'Windows-31J', "%10s" % s("\xc2\xa1"))
|
|
|
|
assert_strenc(" \xC2\xA1", 'UTF-8', "%10s" % u("\xc2\xa1"))
|
|
|
|
|
|
|
|
assert_strenc("\x00", 'ASCII-8BIT', a("%s") % a("\x00"))
|
|
|
|
assert_strenc("\x00", 'EUC-JP', e("%s") % e("\x00"))
|
|
|
|
assert_strenc("\x00", 'Windows-31J', s("%s") % s("\x00"))
|
|
|
|
assert_strenc("\x00", 'UTF-8', u("%s") % u("\x00"))
|
2008-01-21 22:59:53 -05:00
|
|
|
assert_equal("EUC-JP", (e("\xc2\xa1 %s") % "foo").encoding.name)
|
2008-01-18 10:37:22 -05:00
|
|
|
end
|
|
|
|
|
2007-12-18 11:01:09 -05:00
|
|
|
def test_str_lt
|
2007-12-17 09:59:11 -05:00
|
|
|
assert(a("a") < a("\xa1"))
|
|
|
|
assert(a("a") < s("\xa1"))
|
|
|
|
assert(s("a") < a("\xa1"))
|
|
|
|
end
|
|
|
|
|
2008-02-21 19:17:42 -05:00
|
|
|
def test_str_multiply
|
|
|
|
str = "\u3042"
|
|
|
|
assert_equal(true, (str * 0).ascii_only?, "[ruby-dev:33895]")
|
|
|
|
assert_equal(false, (str * 1).ascii_only?)
|
2008-02-21 19:33:27 -05:00
|
|
|
assert_equal(false, (str * 2).ascii_only?)
|
2008-02-21 19:17:42 -05:00
|
|
|
end
|
|
|
|
|
2007-12-17 09:59:11 -05:00
|
|
|
def test_str_aref
|
|
|
|
assert_equal(a("\xc2"), a("\xc2\xa1")[0])
|
|
|
|
assert_equal(a("\xa1"), a("\xc2\xa1")[1])
|
|
|
|
assert_equal(nil, a("\xc2\xa1")[2])
|
|
|
|
assert_equal(e("\xc2\xa1"), e("\xc2\xa1")[0])
|
|
|
|
assert_equal(nil, e("\xc2\xa1")[1])
|
|
|
|
assert_equal(s("\xc2"), s("\xc2\xa1")[0])
|
|
|
|
assert_equal(s("\xa1"), s("\xc2\xa1")[1])
|
|
|
|
assert_equal(nil, s("\xc2\xa1")[2])
|
|
|
|
assert_equal(u("\xc2\xa1"), u("\xc2\xa1")[0])
|
|
|
|
assert_equal(nil, u("\xc2\xa1")[1])
|
2008-02-21 19:17:42 -05:00
|
|
|
|
|
|
|
str = "\u3042"
|
2008-02-21 19:42:52 -05:00
|
|
|
assert_equal(true, str[0, 0].ascii_only?, "[ruby-dev:33895]")
|
|
|
|
assert_equal(false, str[0, 1].ascii_only?)
|
|
|
|
assert_equal(false, str[0..-1].ascii_only?)
|
2007-12-17 09:59:11 -05:00
|
|
|
end
|
|
|
|
|
2008-03-05 14:34:15 -05:00
|
|
|
def test_utf8str_aref
|
|
|
|
s = "abcdefghijklmnopqrstuvwxyz\u{3042 3044 3046 3048 304A}"
|
|
|
|
assert_equal("a", s[0])
|
|
|
|
assert_equal("h", s[7])
|
|
|
|
assert_equal("i", s[8])
|
|
|
|
assert_equal("j", s[9])
|
|
|
|
assert_equal("\u{3044}", s[27])
|
|
|
|
assert_equal("\u{3046}", s[28])
|
|
|
|
assert_equal("\u{3048}", s[29])
|
2008-03-08 04:05:34 -05:00
|
|
|
s = "abcdefghijklmnopqrstuvw\u{3042 3044 3046 3048 304A}"
|
|
|
|
assert_equal("\u{3044}", s[24])
|
2008-03-05 14:34:15 -05:00
|
|
|
end
|
|
|
|
|
2007-12-17 09:59:11 -05:00
|
|
|
def test_str_aref_len
|
|
|
|
assert_equal(a("\xa1"), a("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 1])
|
|
|
|
assert_equal(a("\xa1\xc2"), a("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 2])
|
|
|
|
|
|
|
|
assert_equal(e("\xc2\xa2"), e("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 1])
|
|
|
|
assert_equal(e("\xc2\xa2\xc2\xa3"), e("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 2])
|
|
|
|
|
|
|
|
assert_equal(s("\xa1"), s("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 1])
|
|
|
|
assert_equal(s("\xa1\xc2"), s("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 2])
|
|
|
|
|
|
|
|
assert_equal(u("\xc2\xa2"), u("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 1])
|
|
|
|
assert_equal(u("\xc2\xa2\xc2\xa3"), u("\xc2\xa1\xc2\xa2\xc2\xa3")[1, 2])
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_str_aref_substr
|
|
|
|
assert_equal(a("\xa1\xc2"), a("\xc2\xa1\xc2\xa2\xc2\xa3")[a("\xa1\xc2")])
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) { a("\xc2\xa1\xc2\xa2\xc2\xa3")[e("\xa1\xc2")] }
|
2007-12-17 09:59:11 -05:00
|
|
|
|
|
|
|
assert_equal(nil, e("\xc2\xa1\xc2\xa2\xc2\xa3")[e("\xa1\xc2")])
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) { e("\xc2\xa1\xc2\xa2\xc2\xa3")[s("\xa1\xc2")] }
|
2007-12-17 09:59:11 -05:00
|
|
|
|
|
|
|
assert_equal(s("\xa1\xc2"), s("\xc2\xa1\xc2\xa2\xc2\xa3")[s("\xa1\xc2")])
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) { s("\xc2\xa1\xc2\xa2\xc2\xa3")[u("\xa1\xc2")] }
|
2007-12-17 09:59:11 -05:00
|
|
|
|
|
|
|
assert_equal(nil, u("\xc2\xa1\xc2\xa2\xc2\xa3")[u("\xa1\xc2")])
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) { u("\xc2\xa1\xc2\xa2\xc2\xa3")[a("\xa1\xc2")] }
|
2008-01-21 22:59:53 -05:00
|
|
|
assert_nil(e("\xa1\xa2\xa3\xa4")[e("\xa2\xa3")])
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_aset
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s["\xb0\xa3"] = "foo"}
|
2007-12-17 09:59:11 -05:00
|
|
|
end
|
|
|
|
|
2007-12-18 23:13:17 -05:00
|
|
|
def test_str_center
|
2008-01-21 22:59:53 -05:00
|
|
|
assert_encoding("EUC-JP", "a".center(5, e("\xa1\xa2")).encoding)
|
|
|
|
assert_encoding("EUC-JP", e("\xa3\xb0").center(10).encoding)
|
2007-12-20 03:55:35 -05:00
|
|
|
end
|
|
|
|
|
2007-12-20 05:09:32 -05:00
|
|
|
def test_squeeze
|
2008-01-21 22:59:53 -05:00
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb1\xa3\xb3\xa3\xb4")
|
|
|
|
assert_equal(e("\xa3\xb0\xa3\xb1\xa3\xb3\xa3\xb4"), s.squeeze)
|
2007-12-20 05:09:32 -05:00
|
|
|
end
|
|
|
|
|
2007-12-08 21:29:24 -05:00
|
|
|
def test_tr
|
2008-01-21 22:59:53 -05:00
|
|
|
s = s("\x81\x41")
|
2007-12-08 21:29:24 -05:00
|
|
|
assert_equal(s.tr("A", "B"), s)
|
|
|
|
assert_equal(s.tr_s("A", "B"), s)
|
2007-12-20 03:55:35 -05:00
|
|
|
|
|
|
|
assert_nothing_raised {
|
2008-01-21 22:59:53 -05:00
|
|
|
"a".force_encoding("ASCII-8BIT").tr(a("a"), a("a"))
|
2007-12-20 03:55:35 -05:00
|
|
|
}
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
assert_equal(e("\xA1\xA1"), a("a").tr(a("a"), e("\xA1\xA1")))
|
2008-05-15 10:37:18 -04:00
|
|
|
|
|
|
|
assert_equal("X\u3042\u3044X", "A\u3042\u3044\u3046".tr("^\u3042\u3044", "X"))
|
|
|
|
assert_equal("\u3042\u3046" * 100, ("\u3042\u3044" * 100).tr("\u3044", "\u3046"))
|
2007-12-23 09:06:00 -05:00
|
|
|
end
|
|
|
|
|
2007-12-20 05:09:32 -05:00
|
|
|
def test_tr_s
|
2007-12-23 09:06:00 -05:00
|
|
|
assert_equal("\xA1\xA1".force_encoding("EUC-JP"),
|
|
|
|
"a".force_encoding("ASCII-8BIT").tr("a".force_encoding("ASCII-8BIT"), "\xA1\xA1".force_encoding("EUC-JP")))
|
2007-12-23 19:55:36 -05:00
|
|
|
end
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
def test_count
|
|
|
|
assert_equal(0, e("\xa1\xa2").count("z"))
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s.count(a("\xa3\xb0"))}
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_delete
|
|
|
|
assert_equal(1, e("\xa1\xa2").delete("z").length)
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s.delete(a("\xa3\xb2"))}
|
2008-05-15 10:03:21 -04:00
|
|
|
|
|
|
|
a = "\u3042\u3044\u3046\u3042\u3044\u3046"
|
|
|
|
a.delete!("\u3042\u3044", "^\u3044")
|
|
|
|
assert_equal("\u3044\u3046\u3044\u3046", a)
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_include?
|
|
|
|
assert_equal(false, e("\xa1\xa2\xa3\xa4").include?(e("\xa3")))
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
|
|
|
assert_equal(false, s.include?(e("\xb0\xa3")))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_index
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
|
|
|
assert_nil(s.index(e("\xb3\xa3")))
|
|
|
|
assert_nil(e("\xa1\xa2\xa3\xa4").index(e("\xa3")))
|
|
|
|
assert_nil(e("\xa1\xa2\xa3\xa4").rindex(e("\xa3")))
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s.rindex(a("\xb1\xa3"))}
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_next
|
|
|
|
s1 = e("\xa1\xa1")
|
|
|
|
s2 = s1.dup
|
|
|
|
(94*94+94).times { s2.next! }
|
|
|
|
assert_not_equal(s1, s2)
|
|
|
|
end
|
|
|
|
|
2007-12-17 09:59:11 -05:00
|
|
|
def test_sub
|
|
|
|
s = "abc".sub(/b/, "\xa1\xa1".force_encoding("euc-jp"))
|
|
|
|
assert_encoding("EUC-JP", s.encoding)
|
2007-12-19 07:42:19 -05:00
|
|
|
assert_equal(Encoding::EUC_JP, "\xa4\xa2".force_encoding("euc-jp").sub(/./, '\&').encoding)
|
|
|
|
assert_equal(Encoding::EUC_JP, "\xa4\xa2".force_encoding("euc-jp").gsub(/./, '\&').encoding)
|
2007-12-17 09:59:11 -05:00
|
|
|
end
|
2007-12-19 04:30:45 -05:00
|
|
|
|
2008-10-02 07:46:40 -04:00
|
|
|
def test_sub2
|
2009-03-05 22:56:38 -05:00
|
|
|
s = "\x80".force_encoding("ASCII-8BIT")
|
|
|
|
r = Regexp.new("\x80".force_encoding("ASCII-8BIT"))
|
2008-10-02 07:46:40 -04:00
|
|
|
s2 = s.sub(r, "")
|
|
|
|
assert(s2.empty?)
|
|
|
|
assert(s2.ascii_only?)
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_sub3
|
|
|
|
repl = "\x81".force_encoding("sjis")
|
|
|
|
assert_equal(false, repl.valid_encoding?)
|
|
|
|
s = "a@".sub(/a/, repl)
|
|
|
|
assert(s.valid_encoding?)
|
|
|
|
end
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
def test_insert
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
|
|
|
assert_equal(e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4a"), s.insert(-1, "a"))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_scan
|
|
|
|
assert_equal(["a"], e("\xa1\xa2a\xa3\xa4").scan(/a/))
|
|
|
|
end
|
|
|
|
|
2008-02-08 05:18:56 -05:00
|
|
|
def test_dup_scan
|
2008-02-07 23:27:37 -05:00
|
|
|
s1 = e("\xa4\xa2")*100
|
|
|
|
s2 = s1.dup.force_encoding("ascii-8bit")
|
|
|
|
s2.scan(/\A./n) {|f|
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, f.encoding)
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
2008-02-08 05:18:56 -05:00
|
|
|
def test_dup_aref
|
|
|
|
s1 = e("\xa4\xa2")*100
|
|
|
|
s2 = s1.dup.force_encoding("ascii-8bit")
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, s2[10..-1].encoding)
|
|
|
|
end
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
def test_upto
|
|
|
|
s1 = e("\xa1\xa2")
|
|
|
|
s2 = s("\xa1\xa2")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s1.upto(s2) {|x| break }}
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_casecmp
|
|
|
|
s1 = s("\x81\x41")
|
|
|
|
s2 = s("\x81\x61")
|
|
|
|
assert_not_equal(0, s1.casecmp(s2))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_reverse
|
|
|
|
assert_equal(u("\xf0jihgfedcba"), u("abcdefghij\xf0").reverse)
|
|
|
|
end
|
|
|
|
|
2008-05-15 10:37:18 -04:00
|
|
|
def test_reverse_bang
|
|
|
|
s = u("abcdefghij\xf0")
|
|
|
|
s.reverse!
|
|
|
|
assert_equal(u("\xf0jihgfedcba"), s)
|
|
|
|
end
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
def test_plus
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){u("\xe3\x81\x82") + a("\xa1")}
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_chomp
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s.chomp(s("\xa3\xb4"))}
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
2007-12-28 23:27:39 -05:00
|
|
|
def test_gsub
|
|
|
|
s = 'abc'
|
|
|
|
s.ascii_only?
|
|
|
|
s.gsub!(/b/, "\x80")
|
|
|
|
assert_equal(false, s.ascii_only?, "[ruby-core:14566] reported by Sam Ruby")
|
2008-01-05 13:36:56 -05:00
|
|
|
|
|
|
|
s = "abc".force_encoding(Encoding::ASCII_8BIT)
|
|
|
|
t = s.gsub(/b/, "\xa1\xa1".force_encoding("euc-jp"))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, s.encoding)
|
2008-01-05 21:17:18 -05:00
|
|
|
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError) {
|
2008-01-05 21:17:18 -05:00
|
|
|
"abc".gsub(/[ac]/) {
|
|
|
|
$& == "a" ? "\xc2\xa1".force_encoding("euc-jp") :
|
|
|
|
"\xc2\xa1".force_encoding("utf-8")
|
|
|
|
}
|
|
|
|
}
|
2008-01-21 22:59:53 -05:00
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
|
|
|
assert_equal(e("\xa3\xb0z\xa3\xb2\xa3\xb3\xa3\xb4"), s.gsub(/\xa3\xb1/e, "z"))
|
2008-01-26 17:50:56 -05:00
|
|
|
|
|
|
|
assert_equal(Encoding::EUC_JP, (a("").gsub(//) { e("") }.encoding))
|
|
|
|
assert_equal(Encoding::EUC_JP, (a("a").gsub(/a/) { e("") }.encoding))
|
2007-12-28 23:27:39 -05:00
|
|
|
end
|
|
|
|
|
2008-01-19 12:44:23 -05:00
|
|
|
def test_end_with
|
2008-01-21 22:59:53 -05:00
|
|
|
s1 = s("\x81\x40")
|
2008-01-19 20:30:32 -05:00
|
|
|
s2 = "@"
|
|
|
|
assert_equal(false, s1.end_with?(s2), "#{encdump s1}.end_with?(#{encdump s2})")
|
2008-01-19 12:44:23 -05:00
|
|
|
end
|
|
|
|
|
2008-01-21 22:59:53 -05:00
|
|
|
def test_each_line
|
|
|
|
s = e("\xa3\xb0\xa3\xb1\xa3\xb2\xa3\xb3\xa3\xb4")
|
2008-09-18 04:57:33 -04:00
|
|
|
assert_raise(Encoding::CompatibilityError){s.each_line(a("\xa3\xb1")) {|l| }}
|
2008-02-18 01:18:31 -05:00
|
|
|
s = e("\xa4\xa2\nfoo")
|
|
|
|
|
|
|
|
actual = []
|
|
|
|
s.each_line {|line| actual << line }
|
|
|
|
expected = [e("\xa4\xa2\n"), e("foo")]
|
|
|
|
assert_equal(expected, actual)
|
2008-01-21 22:59:53 -05:00
|
|
|
end
|
|
|
|
|
2008-01-20 08:51:32 -05:00
|
|
|
def test_each_char
|
|
|
|
a = [e("\xa4\xa2"), "b", e("\xa4\xa4"), "c"]
|
|
|
|
s = "\xa4\xa2b\xa4\xa4c".force_encoding("euc-jp")
|
|
|
|
assert_equal(a, s.each_char.to_a, "[ruby-dev:33211] #{encdump s}.each_char.to_a")
|
|
|
|
end
|
|
|
|
|
2007-12-19 04:30:45 -05:00
|
|
|
def test_regexp_match
|
|
|
|
assert_equal([0,0], //.match("\xa1\xa1".force_encoding("euc-jp"),-1).offset(0))
|
2008-01-21 22:59:53 -05:00
|
|
|
assert_equal(0, // =~ :a)
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_split
|
|
|
|
assert_equal(e("\xa1\xa2\xa1\xa3").split(//),
|
|
|
|
[e("\xa1\xa2"), e("\xa1\xa3")],
|
|
|
|
'[ruby-dev:32452]')
|
2007-12-19 04:30:45 -05:00
|
|
|
end
|
2007-12-24 06:06:49 -05:00
|
|
|
|
|
|
|
def test_nonascii_method_name
|
|
|
|
eval(e("def \xc2\xa1() @nonascii_method_name = :e end"))
|
|
|
|
eval(u("def \xc2\xa1() @nonascii_method_name = :u end"))
|
|
|
|
eval(e("\xc2\xa1()"))
|
|
|
|
assert_equal(:e, @nonascii_method_name)
|
|
|
|
eval(u("\xc2\xa1()"))
|
|
|
|
assert_equal(:u, @nonascii_method_name)
|
|
|
|
me = method(e("\xc2\xa1"))
|
|
|
|
mu = method(u("\xc2\xa1"))
|
|
|
|
assert_not_equal(me.name, mu.name)
|
|
|
|
assert_not_equal(me.inspect, mu.inspect)
|
2008-04-27 22:12:21 -04:00
|
|
|
assert_equal(e("\xc2\xa1"), me.name.to_s)
|
|
|
|
assert_equal(u("\xc2\xa1"), mu.name.to_s)
|
2007-12-24 06:06:49 -05:00
|
|
|
end
|
2007-12-24 06:36:48 -05:00
|
|
|
|
|
|
|
def test_symbol
|
|
|
|
s1 = "\xc2\xa1".force_encoding("euc-jp").intern
|
|
|
|
s2 = "\xc2\xa1".force_encoding("utf-8").intern
|
|
|
|
assert_not_equal(s1, s2)
|
|
|
|
end
|
|
|
|
|
2008-01-28 10:20:21 -05:00
|
|
|
def test_symbol_op
|
2009-02-24 22:28:00 -05:00
|
|
|
ops = %w"
|
2008-01-28 10:20:21 -05:00
|
|
|
.. ... + - +(binary) -(binary) * / % ** +@ -@ | ^ & ! <=> > >= < <= ==
|
|
|
|
=== != =~ !~ ~ ! [] []= << >> :: `
|
2009-02-24 22:28:00 -05:00
|
|
|
"
|
2008-01-28 10:20:21 -05:00
|
|
|
ops.each do |op|
|
|
|
|
assert_equal(Encoding::US_ASCII, op.intern.encoding, "[ruby-dev:33449]")
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2007-12-24 06:36:48 -05:00
|
|
|
def test_chr
|
|
|
|
0.upto(255) {|b|
|
|
|
|
assert_equal([b].pack("C"), b.chr)
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_marshal
|
2008-01-20 12:12:58 -05:00
|
|
|
s1 = "\xa1\xa1".force_encoding("euc-jp")
|
|
|
|
s2 = Marshal.load(Marshal.dump(s1))
|
|
|
|
assert_equal(s1, s2)
|
2007-12-24 06:36:48 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_env
|
2009-07-13 12:32:00 -04:00
|
|
|
locale_encoding = Encoding.find("locale")
|
2007-12-24 06:36:48 -05:00
|
|
|
ENV.each {|k, v|
|
2009-07-13 12:32:00 -04:00
|
|
|
assert_equal(locale_encoding, k.encoding)
|
|
|
|
assert_equal(locale_encoding, v.encoding)
|
2007-12-24 06:36:48 -05:00
|
|
|
}
|
|
|
|
end
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
|
|
|
|
def test_empty_string
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, "".encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_nil_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, nil.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_nil_inspect
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, nil.inspect.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_true_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, true.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_false_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, false.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_fixnum_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, 1.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_float_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, 1.0.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_bignum_to_s
|
2009-02-24 22:28:00 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, (1 << 129).to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_array_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, [].to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, [nil].to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, [1].to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, [""].to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, ["a"].to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, [nil,1,"","a","\x20",[]].to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_hash_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, {}.to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, {1=>nil,"foo"=>""}.to_s.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
|
|
|
|
2008-02-28 06:58:11 -05:00
|
|
|
def test_encoding_find
|
|
|
|
assert_raise(TypeError) {Encoding.find(nil)}
|
|
|
|
assert_raise(TypeError) {Encoding.find(0)}
|
|
|
|
assert_raise(TypeError) {Encoding.find([])}
|
|
|
|
assert_raise(TypeError) {Encoding.find({})}
|
|
|
|
end
|
|
|
|
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
def test_encoding_to_s
|
2008-01-28 10:20:21 -05:00
|
|
|
assert_equal(Encoding::US_ASCII, Encoding::US_ASCII.to_s.encoding)
|
|
|
|
assert_equal(Encoding::US_ASCII, Encoding::US_ASCII.inspect.encoding)
|
* string.c (rb_str_usascii_new{,2}: defined.
(rb_str_new): set US-ASCII and ENC_CODERANGE_7BIT when empty
string.
* encoding.c (rb_usascii_encoding, rb_usascii_encindex): defined.
(rb_enc_inspect, enc_name, rb_locale_charmap, rb_enc_name_list_i):
use rb_str_ascii_new.
* array.c (recursive_join, inspect_ary): ditto.
* object.c (nil_to_s, nil_inspect, true_to_s, false_to_s,
rb_mod_to_s): ditto.
* hash.c (inspect_hash, rb_hash_inspect, rb_f_getenv, env_fetch,
env_clear, env_to_s, env_inspect): ditto.
* numeric.c (flo_to_s, int_chr, rb_fix2str): ditto.
* bignum.c (rb_big2str): ditto.
* file.c (rb_file_ftype, rb_file_s_dirname, rb_file_s_extname,
file_inspect_join, Init_file): ditto.
* test/ruby/test_ruby_m17n.rb: add checks for encoding of string.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15244 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2008-01-25 11:40:02 -05:00
|
|
|
end
|
2008-01-26 06:19:06 -05:00
|
|
|
|
|
|
|
def test_regexp_source
|
|
|
|
s = "\xa4\xa2".force_encoding("euc-jp")
|
|
|
|
r = Regexp.new(s)
|
|
|
|
t = r.source
|
|
|
|
assert_equal(s, t, "[ruby-dev:33377] Regexp.new(#{encdump s}).source")
|
|
|
|
end
|
2008-01-27 20:26:37 -05:00
|
|
|
|
|
|
|
def test_magic_comment
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("# -*- encoding: US-ASCII -*-\n__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("# -*- encoding: ASCII-8BIT -*-\n__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
end
|
2008-01-28 13:04:39 -05:00
|
|
|
|
2008-08-01 05:38:50 -04:00
|
|
|
def test_magic_comment_vim
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("# vim: filetype=ruby, fileencoding: US-ASCII, ts=3, sw=3\n__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("# vim: filetype=ruby, fileencoding: ASCII-8BIT, ts=3, sw=3\n__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_magic_comment_at_various_positions
|
|
|
|
# after shebang
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("#!/usr/bin/ruby\n# -*- encoding: US-ASCII -*-\n__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("#!/usr/bin/ruby\n# -*- encoding: ASCII-8BIT -*-\n__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
# wrong position
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("\n# -*- encoding: US-ASCII -*-\n__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("\n# -*- encoding: ASCII-8BIT -*-\n__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
|
|
|
|
# leading expressions
|
|
|
|
assert_equal(Encoding::ASCII_8BIT, eval("1+1 # -*- encoding: US-ASCII -*-\n__ENCODING__".force_encoding("ASCII-8BIT")))
|
|
|
|
assert_equal(Encoding::US_ASCII, eval("1+1 # -*- encoding: ASCII-8BIT -*-\n__ENCODING__".force_encoding("US-ASCII")))
|
|
|
|
end
|
|
|
|
|
2008-01-28 13:04:39 -05:00
|
|
|
def test_regexp_usascii
|
|
|
|
assert_regexp_usascii_literal('//', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/#{}/', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/#{"a"}/', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/#{%q"\x80"}/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/#{"\x80"}/', nil, SyntaxError)
|
|
|
|
|
|
|
|
assert_regexp_usascii_literal('/a/', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/a#{}/', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/a#{"a"}/', Encoding::US_ASCII)
|
|
|
|
assert_regexp_usascii_literal('/a#{%q"\x80"}/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/a#{"\x80"}/', nil, SyntaxError)
|
|
|
|
|
|
|
|
assert_regexp_usascii_literal('/\x80/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/\x80#{}/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/\x80#{"a"}/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/\x80#{%q"\x80"}/', Encoding::ASCII_8BIT)
|
|
|
|
assert_regexp_usascii_literal('/\x80#{"\x80"}/', nil, SyntaxError)
|
|
|
|
|
|
|
|
assert_regexp_usascii_literal('/\u1234/', Encoding::UTF_8)
|
|
|
|
assert_regexp_usascii_literal('/\u1234#{}/', Encoding::UTF_8)
|
|
|
|
assert_regexp_usascii_literal('/\u1234#{"a"}/', Encoding::UTF_8)
|
|
|
|
assert_regexp_usascii_literal('/\u1234#{%q"\x80"}/', nil, SyntaxError)
|
|
|
|
assert_regexp_usascii_literal('/\u1234#{"\x80"}/', nil, SyntaxError)
|
|
|
|
assert_regexp_usascii_literal('/\u1234\x80/', nil, SyntaxError)
|
2008-01-29 03:03:51 -05:00
|
|
|
assert_regexp_usascii_literal('/\u1234#{}\x80/', nil, ArgumentError)
|
2008-01-28 13:04:39 -05:00
|
|
|
end
|
2008-01-29 08:07:25 -05:00
|
|
|
|
|
|
|
def test_gbk
|
|
|
|
assert_equal("", "\x81\x40".force_encoding("GBK").chop)
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_euc_tw
|
|
|
|
assert_equal("a", "a\x8e\xa2\xa1\xa1".force_encoding("euc-tw").chop)
|
|
|
|
end
|
2008-02-17 04:43:20 -05:00
|
|
|
|
|
|
|
def test_valid_encoding
|
|
|
|
s = "\xa1".force_encoding("euc-jp")
|
|
|
|
assert_equal(false, s.valid_encoding?)
|
2008-02-17 04:52:50 -05:00
|
|
|
assert_equal(true, (s+s).valid_encoding?, "[ruby-dev:33826]")
|
|
|
|
assert_equal(true, (s*2).valid_encoding?, "[ruby-dev:33826]")
|
|
|
|
assert_equal(true, ("%s%s" % [s, s]).valid_encoding?)
|
|
|
|
assert_equal(true, (s.dup << s).valid_encoding?)
|
|
|
|
assert_equal(true, "".center(2, s).valid_encoding?)
|
|
|
|
|
2008-05-15 10:37:18 -04:00
|
|
|
s = "\xa1\xa1\x8f".force_encoding("euc-jp")
|
|
|
|
assert_equal(false, s.valid_encoding?)
|
|
|
|
assert_equal(true, s.reverse.valid_encoding?)
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_getbyte
|
|
|
|
assert_equal(0x82, u("\xE3\x81\x82\xE3\x81\x84").getbyte(2))
|
|
|
|
assert_equal(0x82, u("\xE3\x81\x82\xE3\x81\x84").getbyte(-4))
|
|
|
|
assert_nil(u("\xE3\x81\x82\xE3\x81\x84").getbyte(100))
|
|
|
|
end
|
|
|
|
|
|
|
|
def test_setbyte
|
|
|
|
s = u("\xE3\x81\x82\xE3\x81\x84")
|
|
|
|
s.setbyte(2, 0x84)
|
|
|
|
assert_equal(u("\xE3\x81\x84\xE3\x81\x84"), s)
|
|
|
|
|
|
|
|
s = u("\xE3\x81\x82\xE3\x81\x84")
|
|
|
|
assert_raise(IndexError) { s.setbyte(100, 0) }
|
|
|
|
|
|
|
|
s = u("\xE3\x81\x82\xE3\x81\x84")
|
|
|
|
s.setbyte(-4, 0x84)
|
|
|
|
assert_equal(u("\xE3\x81\x84\xE3\x81\x84"), s)
|
|
|
|
end
|
2008-05-19 01:20:21 -04:00
|
|
|
|
|
|
|
def test_compatible
|
2008-09-15 01:17:18 -04:00
|
|
|
assert_nil Encoding.compatible?("",0)
|
|
|
|
assert_equal(Encoding::UTF_8, Encoding.compatible?(Encoding::UTF_8, Encoding::UTF_8))
|
|
|
|
assert_equal(Encoding::UTF_8, Encoding.compatible?(Encoding::UTF_8, Encoding::US_ASCII))
|
|
|
|
assert_equal(Encoding::ASCII_8BIT,
|
|
|
|
Encoding.compatible?(Encoding::ASCII_8BIT, Encoding::US_ASCII))
|
|
|
|
assert_nil Encoding.compatible?(Encoding::UTF_8, Encoding::ASCII_8BIT)
|
2008-05-19 01:20:21 -04:00
|
|
|
end
|
|
|
|
|
|
|
|
def test_force_encoding
|
|
|
|
assert(("".center(1, "\x80".force_encoding("utf-8")); true),
|
|
|
|
"moved from btest/knownbug, [ruby-dev:33807]")
|
2009-02-24 22:28:00 -05:00
|
|
|
a = "".force_encoding("ascii-8bit") << 0xC3 << 0xB6
|
|
|
|
assert_equal(1, a.force_encoding("utf-8").size, '[ruby-core:22437]')
|
|
|
|
b = "".force_encoding("ascii-8bit") << 0xC3.chr << 0xB6.chr
|
|
|
|
assert_equal(1, b.force_encoding("utf-8").size, '[ruby-core:22437]')
|
2008-05-19 01:20:21 -04:00
|
|
|
end
|
2008-09-16 12:48:05 -04:00
|
|
|
|
|
|
|
def test_combchar_codepoint
|
|
|
|
assert_equal([0x30BB, 0x309A], "\u30BB\u309A".codepoints.to_a)
|
|
|
|
end
|
2007-11-23 01:30:26 -05:00
|
|
|
end
|