diff options
-rw-r--r-- | ChangeLog | 5 | ||||
-rw-r--r-- | lib/uri/common.rb | 4 | ||||
-rw-r--r-- | test/uri/test_common.rb | 3 |
3 files changed, 11 insertions, 1 deletions
@@ -1,3 +1,8 @@ +Wed Jul 31 17:55:55 2013 Shota Fukumori <her@sorah.jp> + + * lib/uri/common.rb (URI.decode_www_form_component): + Don't raise error when str includes multibyte characters. + Wed Jul 31 17:45:39 2013 Masaki Matsushita <glass.saga@gmail.com> * string.c (rb_str_rindex): performance improvement by using diff --git a/lib/uri/common.rb b/lib/uri/common.rb index 1da9f47647..8c657cdee7 100644 --- a/lib/uri/common.rb +++ b/lib/uri/common.rb @@ -899,7 +899,9 @@ module URI # See URI.encode_www_form_component, URI.decode_www_form def self.decode_www_form_component(str, enc=Encoding::UTF_8) raise ArgumentError, "invalid %-encoding (#{str})" unless /\A[^%]*(?:%\h\h[^%]*)*\z/ =~ str - str.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc) + str.dup.force_encoding("ASCII-8BIT") \ + .gsub(/\+|%\h\h/, TBLDECWWWCOMP_) \ + .force_encoding(enc) end # Generate URL-encoded form data from given +enum+. diff --git a/test/uri/test_common.rb b/test/uri/test_common.rb index 65a92f3868..1675257d5c 100644 --- a/test/uri/test_common.rb +++ b/test/uri/test_common.rb @@ -91,6 +91,9 @@ class TestCommon < Test::Unit::TestCase "AZ%5B%5C%5D%5E_%60az%7B%7C%7D%7E")) assert_equal("\xA1\xA2".force_encoding(Encoding::EUC_JP), URI.decode_www_form_component("%A1%A2", "EUC-JP")) + assert_equal("\xE3\x81\x82\xE3\x81\x82".force_encoding("UTF-8"), + URI.decode_www_form_component("\xE3\x81\x82%E3%81%82".force_encoding("UTF-8"))) + assert_raise(ArgumentError){URI.decode_www_form_component("%")} end |