HTML5lib is Back.
Synced with latest version of HTML5lib, which fixes problem with Astral plane characters. I should really do some tests, but the HTML5lib Sanitizer seems to be 2-5 times slower than the old sanitizer.
This commit is contained in:
parent
e1a6827f1f
commit
4dd70af5ae
39 changed files with 4843 additions and 5576 deletions
|
@ -11,7 +11,7 @@ begin
|
|||
def test_chardet
|
||||
File.open(File.join(HTML5LIB_BASE, 'tests', 'encoding', 'chardet', 'test_big5.txt')) do |file|
|
||||
stream = HTML5lib::HTMLInputStream.new(file, :chardet => true)
|
||||
assert_equal 'big5', stream.charEncoding.downcase
|
||||
assert_equal 'big5', stream.char_encoding.downcase
|
||||
end
|
||||
end
|
||||
rescue LoadError
|
||||
|
@ -28,7 +28,7 @@ end
|
|||
|
||||
define_method 'test_%s_%d' % [ test_name, index + 1 ] do
|
||||
stream = HTML5lib::HTMLInputStream.new(input, :chardet => false)
|
||||
assert_equal encoding.downcase, stream.charEncoding.downcase, input
|
||||
assert_equal encoding.downcase, stream.char_encoding.downcase, input
|
||||
end
|
||||
end
|
||||
end
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue