[ruby-core:27210] Re: [PATCH] fix CGI::escape to work with blocks, avoid dollar variables

(2009/12/17 21:16), Gaston Ramos wrote:
> El Thu, 17 de Dec de 2009, a las 11:20:32AM +0900, NARUSE, Yui dijo:
>>>
>>> http://www.justskins.com/forums/bug-when-rerouting-string-gsub-with-a-block-using-1-a-52852.html
>>
>>
>> Even if you patch cgi.rb, you can use only matched string ($&) which is
>> passed as block parameter.
>> There are $~ (Regexp.last_match), $` (pre_match), $' (post_match) and $1,
>> $2, $3 and so on.
>> So your patch is fortunately adopted to cgi.rb, but not universal.
>>
>> So I'm against such a sectional patch.
> 
> I couldn't understand your point, can you explain me wich is the problem? I
> can't read japanase. Please Can you give an example where my patch doesn't work?

I mean, your stating point: allow overriding String#gsub.
Even if you fix cgi.rb, other problem will happen.


Anyway, following patch is twice faster than current implementation
and doesn't use dollar variables.

diff --git a/lib/cgi/util.rb b/lib/cgi/util.rb
index 42f1336..c2cc495 100644
--- a/lib/cgi/util.rb
+++ b/lib/cgi/util.rb
@@ -1,24 +1,198 @@
 class CGI
   @@accept_charset="UTF-8" unless defined?(@@accept_charset)
+
+  TABLE_FOR_URLENCODE__ = {
+    "\x00" => "%00", "\x01" => "%01", "\x02" => "%02", "\x03" => "%03",
+    "\x04" => "%04", "\x05" => "%05", "\x06" => "%06", "\x07" => "%07",
+    "\x08" => "%08", "\x09" => "%09", "\x0A" => "%0A", "\x0B" => "%0B",
+    "\x0C" => "%0C", "\x0D" => "%0D", "\x0E" => "%0E", "\x0F" => "%0F",
+    "\x10" => "%10", "\x11" => "%11", "\x12" => "%12", "\x13" => "%13",
+    "\x14" => "%14", "\x15" => "%15", "\x16" => "%16", "\x17" => "%17",
+    "\x18" => "%18", "\x19" => "%19", "\x1A" => "%1A", "\x1B" => "%1B",
+    "\x1C" => "%1C", "\x1D" => "%1D", "\x1E" => "%1E", "\x1F" => "%1F",
+    " " => "+", "!" => "%21", '"' => "%22", "#" => "%23",
+    "$" => "%24", "%" => "%25", "&" => "%26", "'" => "%27",
+    "(" => "%28", ")" => "%29", "*" => "%2A", "+" => "%2B",
+    "," => "%2C", "-" => "%2D", "." => "%2E", "/" => "%2F",
+    ":" => "%3A", ";" => "%3B", "<" => "%3C", "=" => "%3D",
+    ">" => "%3E", "?" => "%3F", "@" => "%40", "[" => "%5B",
+    "\\" => "%5C", "]" => "%5D", "^" => "%5E", "_" => "%5F",
+    "`" => "%60", "{" => "%7B",
+    "|" => "%7C", "}" => "%7D", "~" => "%7E", "\x7F" => "%7F",
+    "\x80" => "%80", "\x81" => "%81", "\x82" => "%82", "\x83" => "%83",
+    "\x84" => "%84", "\x85" => "%85", "\x86" => "%86", "\x87" => "%87",
+    "\x88" => "%88", "\x89" => "%89", "\x8A" => "%8A", "\x8B" => "%8B",
+    "\x8C" => "%8C", "\x8D" => "%8D", "\x8E" => "%8E", "\x8F" => "%8F",
+    "\x90" => "%90", "\x91" => "%91", "\x92" => "%92", "\x93" => "%93",
+    "\x94" => "%94", "\x95" => "%95", "\x96" => "%96", "\x97" => "%97",
+    "\x98" => "%98", "\x99" => "%99", "\x9A" => "%9A", "\x9B" => "%9B",
+    "\x9C" => "%9C", "\x9D" => "%9D", "\x9E" => "%9E", "\x9F" => "%9F",
+    "\xA0" => "%A0", "\xA1" => "%A1", "\xA2" => "%A2", "\xA3" => "%A3",
+    "\xA4" => "%A4", "\xA5" => "%A5", "\xA6" => "%A6", "\xA7" => "%A7",
+    "\xA8" => "%A8", "\xA9" => "%A9", "\xAA" => "%AA", "\xAB" => "%AB",
+    "\xAC" => "%AC", "\xAD" => "%AD", "\xAE" => "%AE", "\xAF" => "%AF",
+    "\xB0" => "%B0", "\xB1" => "%B1", "\xB2" => "%B2", "\xB3" => "%B3",
+    "\xB4" => "%B4", "\xB5" => "%B5", "\xB6" => "%B6", "\xB7" => "%B7",
+    "\xB8" => "%B8", "\xB9" => "%B9", "\xBA" => "%BA", "\xBB" => "%BB",
+    "\xBC" => "%BC", "\xBD" => "%BD", "\xBE" => "%BE", "\xBF" => "%BF",
+    "\xC0" => "%C0", "\xC1" => "%C1", "\xC2" => "%C2", "\xC3" => "%C3",
+    "\xC4" => "%C4", "\xC5" => "%C5", "\xC6" => "%C6", "\xC7" => "%C7",
+    "\xC8" => "%C8", "\xC9" => "%C9", "\xCA" => "%CA", "\xCB" => "%CB",
+    "\xCC" => "%CC", "\xCD" => "%CD", "\xCE" => "%CE", "\xCF" => "%CF",
+    "\xD0" => "%D0", "\xD1" => "%D1", "\xD2" => "%D2", "\xD3" => "%D3",
+    "\xD4" => "%D4", "\xD5" => "%D5", "\xD6" => "%D6", "\xD7" => "%D7",
+    "\xD8" => "%D8", "\xD9" => "%D9", "\xDA" => "%DA", "\xDB" => "%DB",
+    "\xDC" => "%DC", "\xDD" => "%DD", "\xDE" => "%DE", "\xDF" => "%DF",
+    "\xE0" => "%E0", "\xE1" => "%E1", "\xE2" => "%E2", "\xE3" => "%E3",
+    "\xE4" => "%E4", "\xE5" => "%E5", "\xE6" => "%E6", "\xE7" => "%E7",
+    "\xE8" => "%E8", "\xE9" => "%E9", "\xEA" => "%EA", "\xEB" => "%EB",
+    "\xEC" => "%EC", "\xED" => "%ED", "\xEE" => "%EE", "\xEF" => "%EF",
+    "\xF0" => "%F0", "\xF1" => "%F1", "\xF2" => "%F2", "\xF3" => "%F3",
+    "\xF4" => "%F4", "\xF5" => "%F5", "\xF6" => "%F6", "\xF7" => "%F7",
+    "\xF8" => "%F8", "\xF9" => "%F9", "\xFA" => "%FA", "\xFB" => "%FB",
+    "\xFC" => "%FC", "\xFD" => "%FD", "\xFE" => "%FE", "\xFF" => "%FF"}
+
   # URL-encode a string.
   #   url_encoded_string = CGI::escape("'Stop!' said Fred")
   #      # => "%27Stop%21%27+said+Fred"
   def CGI::escape(string)
-    string.gsub(/([^ a-zA-Z0-9_.-]+)/) do
-      '%' + $1.unpack('H2' * $1.bytesize).join('%').upcase
-    end.tr(' ', '+')
+    str = string.dup.force_encoding(Encoding::ASCII_8BIT)
+    str.gsub!(/[^a-zA-Z0-9_.-]/, TABLE_FOR_URLENCODE__)
+    str.force_encoding(Encoding::US_ASCII)
   end
 
+  TABLE_FOR_URLDECODE__ = {
+    "%00" => "\x00", "%01" => "\x01", "%02" => "\x02", "%03" => "\x03",
+    "%04" => "\x04", "%05" => "\x05", "%06" => "\x06", "%07" => "\a",
+    "%08" => "\b", "%09" => "\t", "%0a" => "\n", "%0A" => "\n",
+    "%0b" => "\v", "%0B" => "\v", "%0c" => "\f", "%0C" => "\f",
+    "%0d" => "\r", "%0D" => "\r", "%0e" => "\x0E", "%0E" => "\x0E",
+    "%0f" => "\x0F", "%0F" => "\x0F", "%10" => "\x10", "%11" => "\x11",
+    "%12" => "\x12", "%13" => "\x13", "%14" => "\x14", "%15" => "\x15",
+    "%16" => "\x16", "%17" => "\x17", "%18" => "\x18", "%19" => "\x19",
+    "%1a" => "\x1A", "%1A" => "\x1A", "%1b" => "\e", "%1B" => "\e",
+    "%1c" => "\x1C", "%1C" => "\x1C", "%1d" => "\x1D", "%1D" => "\x1D",
+    "%1e" => "\x1E", "%1E" => "\x1E", "%1f" => "\x1F", "%1F" => "\x1F",
+    "%20" => " ", "%21" => "!", "%22" => "\"", "%23" => "#",
+    "%24" => "$", "%25" => "%", "%26" => "&", "%27" => "'",
+    "%28" => "(", "%29" => ")", "%2a" => "*", "%2A" => "*",
+    "%2b" => "+", "%2B" => "+", "%2c" => ",", "%2C" => ",",
+    "%2d" => "-", "%2D" => "-", "%2e" => ".", "%2E" => ".",
+    "%2f" => "/", "%2F" => "/", "%30" => "0", "%31" => "1",
+    "%32" => "2", "%33" => "3", "%34" => "4", "%35" => "5",
+    "%36" => "6", "%37" => "7", "%38" => "8", "%39" => "9",
+    "%3a" => ":", "%3A" => ":", "%3b" => ";", "%3B" => ";",
+    "%3c" => "<", "%3C" => "<", "%3d" => "=", "%3D" => "=",
+    "%3e" => ">", "%3E" => ">", "%3f" => "?", "%3F" => "?",
+    "%40" => "@", "%41" => "A", "%42" => "B", "%43" => "C",
+    "%44" => "D", "%45" => "E", "%46" => "F", "%47" => "G",
+    "%48" => "H", "%49" => "I", "%4a" => "J", "%4A" => "J",
+    "%4b" => "K", "%4B" => "K", "%4c" => "L", "%4C" => "L",
+    "%4d" => "M", "%4D" => "M", "%4e" => "N", "%4E" => "N",
+    "%4f" => "O", "%4F" => "O", "%50" => "P", "%51" => "Q",
+    "%52" => "R", "%53" => "S", "%54" => "T", "%55" => "U",
+    "%56" => "V", "%57" => "W", "%58" => "X", "%59" => "Y",
+    "%5a" => "Z", "%5A" => "Z", "%5b" => "[", "%5B" => "[",
+    "%5c" => "\\", "%5C" => "\\", "%5d" => "]", "%5D" => "]",
+    "%5e" => "^", "%5E" => "^", "%5f" => "_", "%5F" => "_",
+    "%60" => "`", "%61" => "a", "%62" => "b", "%63" => "c",
+    "%64" => "d", "%65" => "e", "%66" => "f", "%67" => "g",
+    "%68" => "h", "%69" => "i", "%6a" => "j", "%6A" => "j",
+    "%6b" => "k", "%6B" => "k", "%6c" => "l", "%6C" => "l",
+    "%6d" => "m", "%6D" => "m", "%6e" => "n", "%6E" => "n",
+    "%6f" => "o", "%6F" => "o", "%70" => "p", "%71" => "q",
+    "%72" => "r", "%73" => "s", "%74" => "t", "%75" => "u",
+    "%76" => "v", "%77" => "w", "%78" => "x", "%79" => "y",
+    "%7a" => "z", "%7A" => "z", "%7b" => "{", "%7B" => "{",
+    "%7c" => "|", "%7C" => "|", "%7d" => "}", "%7D" => "}",
+    "%7e" => "~", "%7E" => "~", "%7f" => "\x7F", "%7F" => "\x7F",
+    "%80" => "\x80", "%81" => "\x81", "%82" => "\x82", "%83" => "\x83",
+    "%84" => "\x84", "%85" => "\x85", "%86" => "\x86", "%87" => "\x87",
+    "%88" => "\x88", "%89" => "\x89", "%8a" => "\x8A", "%8A" => "\x8A",
+    "%8b" => "\x8B", "%8B" => "\x8B", "%8c" => "\x8C", "%8C" => "\x8C",
+    "%8d" => "\x8D", "%8D" => "\x8D", "%8e" => "\x8E", "%8E" => "\x8E",
+    "%8f" => "\x8F", "%8F" => "\x8F", "%90" => "\x90", "%91" => "\x91",
+    "%92" => "\x92", "%93" => "\x93", "%94" => "\x94", "%95" => "\x95",
+    "%96" => "\x96", "%97" => "\x97", "%98" => "\x98", "%99" => "\x99",
+    "%9a" => "\x9A", "%9A" => "\x9A", "%9b" => "\x9B", "%9B" => "\x9B",
+    "%9c" => "\x9C", "%9C" => "\x9C", "%9d" => "\x9D", "%9D" => "\x9D",
+    "%9e" => "\x9E", "%9E" => "\x9E", "%9f" => "\x9F", "%9F" => "\x9F",
+    "%a0" => "\xA0", "%a1" => "\xA1", "%a2" => "\xA2", "%a3" => "\xA3",
+    "%a4" => "\xA4", "%a5" => "\xA5", "%a6" => "\xA6", "%a7" => "\xA7",
+    "%a8" => "\xA8", "%a9" => "\xA9", "%aa" => "\xAA", "%aA" => "\xAA",
+    "%ab" => "\xAB", "%aB" => "\xAB", "%ac" => "\xAC", "%aC" => "\xAC",
+    "%ad" => "\xAD", "%aD" => "\xAD", "%ae" => "\xAE", "%aE" => "\xAE",
+    "%af" => "\xAF", "%aF" => "\xAF", "%A0" => "\xA0", "%A1" => "\xA1",
+    "%A2" => "\xA2", "%A3" => "\xA3", "%A4" => "\xA4", "%A5" => "\xA5",
+    "%A6" => "\xA6", "%A7" => "\xA7", "%A8" => "\xA8", "%A9" => "\xA9",
+    "%Aa" => "\xAA", "%AA" => "\xAA", "%Ab" => "\xAB", "%AB" => "\xAB",
+    "%Ac" => "\xAC", "%AC" => "\xAC", "%Ad" => "\xAD", "%AD" => "\xAD",
+    "%Ae" => "\xAE", "%AE" => "\xAE", "%Af" => "\xAF", "%AF" => "\xAF",
+    "%b0" => "\xB0", "%b1" => "\xB1", "%b2" => "\xB2", "%b3" => "\xB3",
+    "%b4" => "\xB4", "%b5" => "\xB5", "%b6" => "\xB6", "%b7" => "\xB7",
+    "%b8" => "\xB8", "%b9" => "\xB9", "%ba" => "\xBA", "%bA" => "\xBA",
+    "%bb" => "\xBB", "%bB" => "\xBB", "%bc" => "\xBC", "%bC" => "\xBC",
+    "%bd" => "\xBD", "%bD" => "\xBD", "%be" => "\xBE", "%bE" => "\xBE",
+    "%bf" => "\xBF", "%bF" => "\xBF", "%B0" => "\xB0", "%B1" => "\xB1",
+    "%B2" => "\xB2", "%B3" => "\xB3", "%B4" => "\xB4", "%B5" => "\xB5",
+    "%B6" => "\xB6", "%B7" => "\xB7", "%B8" => "\xB8", "%B9" => "\xB9",
+    "%Ba" => "\xBA", "%BA" => "\xBA", "%Bb" => "\xBB", "%BB" => "\xBB",
+    "%Bc" => "\xBC", "%BC" => "\xBC", "%Bd" => "\xBD", "%BD" => "\xBD",
+    "%Be" => "\xBE", "%BE" => "\xBE", "%Bf" => "\xBF", "%BF" => "\xBF",
+    "%c0" => "\xC0", "%c1" => "\xC1", "%c2" => "\xC2", "%c3" => "\xC3",
+    "%c4" => "\xC4", "%c5" => "\xC5", "%c6" => "\xC6", "%c7" => "\xC7",
+    "%c8" => "\xC8", "%c9" => "\xC9", "%ca" => "\xCA", "%cA" => "\xCA",
+    "%cb" => "\xCB", "%cB" => "\xCB", "%cc" => "\xCC", "%cC" => "\xCC",
+    "%cd" => "\xCD", "%cD" => "\xCD", "%ce" => "\xCE", "%cE" => "\xCE",
+    "%cf" => "\xCF", "%cF" => "\xCF", "%C0" => "\xC0", "%C1" => "\xC1",
+    "%C2" => "\xC2", "%C3" => "\xC3", "%C4" => "\xC4", "%C5" => "\xC5",
+    "%C6" => "\xC6", "%C7" => "\xC7", "%C8" => "\xC8", "%C9" => "\xC9",
+    "%Ca" => "\xCA", "%CA" => "\xCA", "%Cb" => "\xCB", "%CB" => "\xCB",
+    "%Cc" => "\xCC", "%CC" => "\xCC", "%Cd" => "\xCD", "%CD" => "\xCD",
+    "%Ce" => "\xCE", "%CE" => "\xCE", "%Cf" => "\xCF", "%CF" => "\xCF",
+    "%d0" => "\xD0", "%d1" => "\xD1", "%d2" => "\xD2", "%d3" => "\xD3",
+    "%d4" => "\xD4", "%d5" => "\xD5", "%d6" => "\xD6", "%d7" => "\xD7",
+    "%d8" => "\xD8", "%d9" => "\xD9", "%da" => "\xDA", "%dA" => "\xDA",
+    "%db" => "\xDB", "%dB" => "\xDB", "%dc" => "\xDC", "%dC" => "\xDC",
+    "%dd" => "\xDD", "%dD" => "\xDD", "%de" => "\xDE", "%dE" => "\xDE",
+    "%df" => "\xDF", "%dF" => "\xDF", "%D0" => "\xD0", "%D1" => "\xD1",
+    "%D2" => "\xD2", "%D3" => "\xD3", "%D4" => "\xD4", "%D5" => "\xD5",
+    "%D6" => "\xD6", "%D7" => "\xD7", "%D8" => "\xD8", "%D9" => "\xD9",
+    "%Da" => "\xDA", "%DA" => "\xDA", "%Db" => "\xDB", "%DB" => "\xDB",
+    "%Dc" => "\xDC", "%DC" => "\xDC", "%Dd" => "\xDD", "%DD" => "\xDD",
+    "%De" => "\xDE", "%DE" => "\xDE", "%Df" => "\xDF", "%DF" => "\xDF",
+    "%e0" => "\xE0", "%e1" => "\xE1", "%e2" => "\xE2", "%e3" => "\xE3",
+    "%e4" => "\xE4", "%e5" => "\xE5", "%e6" => "\xE6", "%e7" => "\xE7",
+    "%e8" => "\xE8", "%e9" => "\xE9", "%ea" => "\xEA", "%eA" => "\xEA",
+    "%eb" => "\xEB", "%eB" => "\xEB", "%ec" => "\xEC", "%eC" => "\xEC",
+    "%ed" => "\xED", "%eD" => "\xED", "%ee" => "\xEE", "%eE" => "\xEE",
+    "%ef" => "\xEF", "%eF" => "\xEF", "%E0" => "\xE0", "%E1" => "\xE1",
+    "%E2" => "\xE2", "%E3" => "\xE3", "%E4" => "\xE4", "%E5" => "\xE5",
+    "%E6" => "\xE6", "%E7" => "\xE7", "%E8" => "\xE8", "%E9" => "\xE9",
+    "%Ea" => "\xEA", "%EA" => "\xEA", "%Eb" => "\xEB", "%EB" => "\xEB",
+    "%Ec" => "\xEC", "%EC" => "\xEC", "%Ed" => "\xED", "%ED" => "\xED",
+    "%Ee" => "\xEE", "%EE" => "\xEE", "%Ef" => "\xEF", "%EF" => "\xEF",
+    "%f0" => "\xF0", "%f1" => "\xF1", "%f2" => "\xF2", "%f3" => "\xF3",
+    "%f4" => "\xF4", "%f5" => "\xF5", "%f6" => "\xF6", "%f7" => "\xF7",
+    "%f8" => "\xF8", "%f9" => "\xF9", "%fa" => "\xFA", "%fA" => "\xFA",
+    "%fb" => "\xFB", "%fB" => "\xFB", "%fc" => "\xFC", "%fC" => "\xFC",
+    "%fd" => "\xFD", "%fD" => "\xFD", "%fe" => "\xFE", "%fE" => "\xFE",
+    "%ff" => "\xFF", "%fF" => "\xFF", "%F0" => "\xF0", "%F1" => "\xF1",
+    "%F2" => "\xF2", "%F3" => "\xF3", "%F4" => "\xF4", "%F5" => "\xF5",
+    "%F6" => "\xF6", "%F7" => "\xF7", "%F8" => "\xF8", "%F9" => "\xF9",
+    "%Fa" => "\xFA", "%FA" => "\xFA", "%Fb" => "\xFB", "%FB" => "\xFB",
+    "%Fc" => "\xFC", "%FC" => "\xFC", "%Fd" => "\xFD", "%FD" => "\xFD",
+    "%Fe" => "\xFE", "%FE" => "\xFE", "%Ff" => "\xFF", "%FF" => "\xFF",
+    "+" => " "}
 
-  # URL-decode a string with encoding(optional).
-  #   string = CGI::unescape("%27Stop%21%27+said+Fred")
-  #      # => "'Stop!' said Fred"
-  def CGI::unescape(string,encoding=@@accept_charset)
-    str=string.tr('+', ' ').gsub(/((?:%[0-9a-fA-F]{2})+)/) do
-      [$1.delete('%')].pack('H*')
-    end.force_encoding(encoding)
-    str.valid_encoding? ? str : str.force_encoding(string.encoding)
-  end
+    # URL-decode a string with encoding(optional).
+    #   string = CGI::unescape("%27Stop%21%27+said+Fred")
+    #      # => "'Stop!' said Fred"
+    def CGI::unescape(string,encoding=@@accept_charset)
+      str = string.gsub(/%[0-9a-fA-F]{2}|\+/, TABLE_FOR_URLDECODE__).
+        force_encoding(encoding)
+      str.valid_encoding? ? str : str.force_encoding(string.encoding)
+    end
 
   TABLE_FOR_ESCAPE_HTML__ = {
     '&' => '&amp;',

-- 
NARUSE, Yui  <[e-mail]>