1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* lib/cgi.rb (CGI::unescapeHTML): more encoding sensible unescaping.

Browse Source 
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@18798 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
naruse 2008-08-23 21:40:59 +00:00
parent 33dd0c35f1
commit 29449d70be
2 changed files with 34 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ChangeLog
View File

@ -1,3 +1,7 @@
Sun Aug 24 06:39:05 2008 NARUSE, Yui <naruse@ruby-lang.org>
* lib/cgi.rb (CGI::unescapeHTML): more encoding sensible unescaping.
Sun Aug 24 04:23:19 2008 NARUSE, Yui <naruse@ruby-lang.org> Sun Aug 24 04:23:19 2008 NARUSE, Yui <naruse@ruby-lang.org>
* encoding.c (enc_compatible_p): raise TypeError when argument is Encoding. * encoding.c (enc_compatible_p): raise TypeError when argument is Encoding.

29
lib/cgi.rb
View File

@ -375,6 +375,19 @@ class CGI
# # => "Usage: foo \"bar\" <baz>" # # => "Usage: foo \"bar\" <baz>"
def CGI::unescapeHTML(string) def CGI::unescapeHTML(string)
enc = string.encoding enc = string.encoding
if [Encoding::UTF_16BE, Encoding::UTF_16LE, Encoding::UTF_32BE, Encoding::UTF_32LE].include?(enc)
return string.gsub(Regexp.new('&(amp|quot|gt|lt|#[0-9]+|#x[0-9A-Fa-f]+);'.encode(enc))) do
case $1.encode("US-ASCII")
when 'amp' then '&'.encode(enc)
when 'quot' then '"'.encode(enc)
when 'gt' then '>'.encode(enc)
when 'lt' then '<'.encode(enc)
when /\A#0*(\d+)\z/ then $1.to_i.chr(enc)
when /\A#x([0-9a-f]+)\z/i then $1.hex.chr(enc)
end
end
end
asciicompat = Encoding.compatible?(string, "a")
string.gsub(/&(amp|quot|gt|lt|\#[0-9]+|\#x[0-9A-Fa-f]+);/) do string.gsub(/&(amp|quot|gt|lt|\#[0-9]+|\#x[0-9A-Fa-f]+);/) do
match = $1.dup match = $1.dup
case match case match
@ -382,15 +395,19 @@ class CGI
when 'quot' then '"' when 'quot' then '"'
when 'gt' then '>' when 'gt' then '>'
when 'lt' then '<' when 'lt' then '<'
when /\A#0*(\d+)\z/ then when /\A#0*(\d+)\z/
if Integer($1) < 256 if enc == Encoding::UTF_8
Integer($1).chr.force_encoding(enc) $1.to_i.chr(enc)
elsif $1.to_i < 128 && asciicompat
$1.to_i.chr
else else
"&##{$1};" "&##{$1};"
end end
when /\A#x([0-9a-f]+)\z/i then when /\A#x([0-9a-f]+)\z/i
if $1.hex < 256 if enc == Encoding::UTF_8
$1.hex.chr.force_encoding(enc) $1.hex.chr(enc)
elsif $1.hex < 128 && asciicompat
$1.hex.chr
else else
"&#x#{$1};" "&#x#{$1};"
end end