1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00

merge revision(s) 5b1bf8dd2d: [Backport #16099]

UTF LE is fixed at least the first 2 bytes

	* io.c (io_strip_bom): if the first 2 bytes are 0xFF0xFE, it
	should be a little-endian UTF, 16 or 32.  [Bug #16099]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_6@67746 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nagachika 2019-08-18 06:53:02 +00:00
parent e1d3b318fb
commit 1ea42115af
4 changed files with 9 additions and 12 deletions

7
io.c
View file

@ -6129,12 +6129,9 @@ io_strip_bom(VALUE io)
return ENCINDEX_UTF_32LE;
}
rb_io_ungetbyte(io, b4);
rb_io_ungetbyte(io, b3);
}
else {
rb_io_ungetbyte(io, b3);
return ENCINDEX_UTF_16LE;
}
rb_io_ungetbyte(io, b3);
return ENCINDEX_UTF_16LE;
}
rb_io_ungetbyte(io, b2);
break;

View file

@ -87,7 +87,7 @@ class TestFile < Test::Unit::TestCase
end
def test_bom_32le
assert_bom(["\xFF\xFE\0", "\0"], __method__)
assert_bom(["\xFF", "\xFE\0\0"], __method__)
end
def test_truncate_wbuf

View file

@ -2082,14 +2082,14 @@ EOT
def test_strip_bom
with_tmpdir {
text = "\uFEFFa"
stripped = "a"
text = "\uFEFF\u0100a"
stripped = "\u0100a"
%w/UTF-8 UTF-16BE UTF-16LE UTF-32BE UTF-32LE/.each do |name|
path = '%s-bom.txt' % name
content = text.encode(name)
generate_file(path, content)
result = File.read(path, mode: 'rb:BOM|UTF-8')
assert_equal(content[1].force_encoding("ascii-8bit"),
assert_equal(content[1..-1].force_encoding("ascii-8bit"),
result.force_encoding("ascii-8bit"))
result = File.read(path, mode: 'rb:BOM|UTF-8:UTF-8')
assert_equal(Encoding::UTF_8, result.encoding)
@ -2099,10 +2099,10 @@ EOT
bug3407 = '[ruby-core:30641]'
path = 'UTF-8-bom.txt'
result = File.read(path, encoding: 'BOM|UTF-8')
assert_equal("a", result.force_encoding("ascii-8bit"), bug3407)
assert_equal(stripped.b, result.force_encoding("ascii-8bit"), bug3407)
bug8323 = '[ruby-core:54563] [Bug #8323]'
expected = "a\xff".force_encoding("utf-8")
expected = (stripped.b + "\xff").force_encoding("utf-8")
open(path, 'ab') {|f| f.write("\xff")}
result = File.read(path, encoding: 'BOM|UTF-8')
assert_not_predicate(result, :valid_encoding?, bug8323)

View file

@ -1,6 +1,6 @@
#define RUBY_VERSION "2.6.3"
#define RUBY_RELEASE_DATE RUBY_RELEASE_YEAR_STR"-"RUBY_RELEASE_MONTH_STR"-"RUBY_RELEASE_DAY_STR
#define RUBY_PATCHLEVEL 96
#define RUBY_PATCHLEVEL 97
#define RUBY_RELEASE_YEAR 2019
#define RUBY_RELEASE_MONTH 8