* numeric.c (rb_enc_uint_char): raise RangeError when added codepoint

is invalid. [Feature #5855] [Bug #5863] [Bug #5864]

* string.c (rb_str_concat): ditto.

* string.c (rb_str_concat): set encoding as ASCII-8BIT when the string
  is US-ASCII and the argument is an integer greater than 127.

* regenc.c (onigenc_mb2_code_to_mbclen): rearrange error code.

* enc/euc_jp.c (code_to_mbclen): ditto.

* enc/shift_jis.c (code_to_mbclen): ditto.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@34236 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
naruse 2012-01-08 20:42:45 +00:00
parent 5393622dad
commit 800f04c6a5
9 changed files with 79 additions and 20 deletions

View file

@ -22,6 +22,6 @@ class TestShiftJIS < Test::Unit::TestCase
s = "あいうえお"
s << 0x82a9
assert_equal("あいうえおか", s)
assert_raise(ArgumentError) { s << 0x82 }
assert_raise(RangeError) { s << 0x82 }
end
end

View file

@ -1161,6 +1161,7 @@ class TestM17N < Test::Unit::TestCase
def test_str_concat
assert_equal(1, "".concat(0xA2).size)
assert_equal(Encoding::ASCII_8BIT, "".force_encoding("US-ASCII").concat(0xA2).encoding)
assert_equal("A\x84\x31\xA4\x39".force_encoding("GB18030"),
"A".force_encoding("GB18030") << 0x8431A439)
end
@ -1220,6 +1221,14 @@ class TestM17N < Test::Unit::TestCase
2206368128.chr(Encoding::UTF_8)
}
assert_not_match(/-\d+ out of char range/, e.message)
assert_raise(RangeError){ 0x80.chr("US-ASCII") }
assert_raise(RangeError){ 0x80.chr("SHIFT_JIS") }
assert_raise(RangeError){ 0xE0.chr("SHIFT_JIS") }
assert_raise(RangeError){ 0x100.chr("SHIFT_JIS") }
assert_raise(RangeError){ 0xA0.chr("EUC-JP") }
assert_raise(RangeError){ 0x100.chr("EUC-JP") }
assert_raise(RangeError){ 0xA1A0.chr("EUC-JP") }
end
def test_marshal

View file

@ -808,8 +808,6 @@ class TestRegexp < Test::Unit::TestCase
#assert_match(/^(\ufb05)\1\1$/i, "\ufb05\ufb06st") # this must be bug...
assert_match(/^\ufb05{3}$/i, "\ufb05\ufb06st")
assert_match(/^\u03b9\u0308\u0301$/i, "\u0390")
assert_nothing_raised { 0x03ffffff.chr("utf-8").size }
assert_nothing_raised { 0x7fffffff.chr("utf-8").size }
end
def test_unicode_age