mirror of
https://github.com/github/codeql.git
synced 2026-04-25 16:55:19 +02:00
Merge pull request #12992 from Sim4n6/ruby-UBV
[Ruby] Add Unicode Bypass Validation query, test and help file
This commit is contained in:
Arthur Baars
@@ -0,0 +1,29 @@
|
||||
/**
|
||||
* Provides default sources, sinks and sanitizers for detecting
|
||||
* "Unicode transformation"
|
||||
* vulnerabilities, as well as extension points for adding your own.
|
||||
*/
|
||||
|
||||
private import ruby
|
||||
|
||||
/**
|
||||
* Provides default sources, sinks and sanitizers for detecting
|
||||
* "Unicode transformation"
|
||||
* vulnerabilities, as well as extension points for adding your own.
|
||||
*/
|
||||
module UnicodeBypassValidation {
|
||||
/**
|
||||
* A data flow source for "Unicode transformation" vulnerabilities.
|
||||
*/
|
||||
abstract class Source extends DataFlow::Node { }
|
||||
|
||||
/**
|
||||
* A data flow sink for "Unicode transformation" vulnerabilities.
|
||||
*/
|
||||
abstract class Sink extends DataFlow::Node { }
|
||||
|
||||
/**
|
||||
* A sanitizer for "Unicode transformation" vulnerabilities.
|
||||
*/
|
||||
abstract class Sanitizer extends DataFlow::Node { }
|
||||
}
|
||||
@@ -0,0 +1,123 @@
|
||||
/**
|
||||
* Provides a taint-tracking configuration for detecting "Unicode transformation mishandling" vulnerabilities.
|
||||
*/
|
||||
|
||||
private import ruby
|
||||
private import codeql.ruby.dataflow.RemoteFlowSources
|
||||
private import codeql.ruby.Concepts
|
||||
private import codeql.ruby.TaintTracking
|
||||
private import codeql.ruby.ApiGraphs
|
||||
import UnicodeBypassValidationCustomizations::UnicodeBypassValidation
|
||||
|
||||
/** A state signifying that a logical validation has not been performed. */
|
||||
class PreValidation extends DataFlow::FlowState {
|
||||
PreValidation() { this = "PreValidation" }
|
||||
}
|
||||
|
||||
/** A state signifying that a logical validation has been performed. */
|
||||
class PostValidation extends DataFlow::FlowState {
|
||||
PostValidation() { this = "PostValidation" }
|
||||
}
|
||||
|
||||
/**
|
||||
* A taint-tracking configuration for detecting "Unicode transformation mishandling" vulnerabilities.
|
||||
*
|
||||
* This configuration uses two flow states, `PreValidation` and `PostValidation`,
|
||||
* to track the requirement that a logical validation has been performed before the Unicode Transformation.
|
||||
*/
|
||||
class Configuration extends TaintTracking::Configuration {
|
||||
Configuration() { this = "UnicodeBypassValidation" }
|
||||
|
||||
override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
|
||||
source instanceof RemoteFlowSource and state instanceof PreValidation
|
||||
}
|
||||
|
||||
override predicate isAdditionalTaintStep(
|
||||
DataFlow::Node nodeFrom, DataFlow::FlowState stateFrom, DataFlow::Node nodeTo,
|
||||
DataFlow::FlowState stateTo
|
||||
) {
|
||||
(
|
||||
exists(Escaping escaping | nodeFrom = escaping.getAnInput() and nodeTo = escaping.getOutput())
|
||||
or
|
||||
exists(RegexExecution re | nodeFrom = re.getString() and nodeTo = re)
|
||||
or
|
||||
// String Manipulation Method Calls
|
||||
// https://ruby-doc.org/core-2.7.0/String.html
|
||||
exists(DataFlow::CallNode cn |
|
||||
cn.getMethodName() =
|
||||
[
|
||||
[
|
||||
"ljust", "lstrip", "succ", "next", "rjust", "capitalize", "chomp", "gsub", "chop",
|
||||
"downcase", "swapcase", "uprcase", "scrub", "slice", "squeeze", "strip", "sub",
|
||||
"tr", "tr_s", "reverse"
|
||||
] + ["", "!"], "concat", "dump", "each_line", "replace", "insert", "inspect", "lines",
|
||||
"partition", "prepend", "replace", "rpartition", "scan", "split", "undump",
|
||||
"unpack" + ["", "1"]
|
||||
] and
|
||||
nodeFrom = cn.getReceiver() and
|
||||
nodeTo = cn
|
||||
)
|
||||
or
|
||||
exists(DataFlow::CallNode cn |
|
||||
cn.getMethodName() =
|
||||
[
|
||||
"casecmp" + ["", "?"], "center", "count", "each_char", "index", "rindex", "sum",
|
||||
["delete", "delete_prefix", "delete_suffix"] + ["", "!"],
|
||||
["start_with", "end_with" + "eql", "include"] + ["?", "!"], "match" + ["", "?"],
|
||||
] and
|
||||
nodeFrom = cn.getReceiver() and
|
||||
nodeTo = nodeFrom
|
||||
)
|
||||
or
|
||||
exists(DataFlow::CallNode cn |
|
||||
cn = API::getTopLevelMember("CGI").getAMethodCall("escapeHTML") and
|
||||
nodeFrom = cn.getArgument(0) and
|
||||
nodeTo = cn
|
||||
)
|
||||
) and
|
||||
stateFrom instanceof PreValidation and
|
||||
stateTo instanceof PostValidation
|
||||
}
|
||||
|
||||
/* A Unicode Tranformation (Unicode tranformation) is considered a sink when the algorithm used is either NFC or NFKC. */
|
||||
override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
|
||||
(
|
||||
exists(DataFlow::CallNode cn |
|
||||
cn.getMethodName() = "unicode_normalize" and
|
||||
cn.getArgument(0).getConstantValue().getSymbol() = ["nfkc", "nfc", "nfkd", "nfd"] and
|
||||
sink = cn.getReceiver()
|
||||
)
|
||||
or
|
||||
// unicode_utils
|
||||
exists(API::MethodAccessNode mac |
|
||||
mac = API::getTopLevelMember("UnicodeUtils").getMethod(["nfkd", "nfc", "nfd", "nfkc"]) and
|
||||
sink = mac.getParameter(0).asSink()
|
||||
)
|
||||
or
|
||||
// eprun
|
||||
exists(API::MethodAccessNode mac |
|
||||
mac = API::getTopLevelMember("Eprun").getMethod("normalize") and
|
||||
sink = mac.getParameter(0).asSink()
|
||||
)
|
||||
or
|
||||
// unf
|
||||
exists(API::MethodAccessNode mac |
|
||||
mac = API::getTopLevelMember("UNF").getMember("Normalizer").getMethod("normalize") and
|
||||
sink = mac.getParameter(0).asSink()
|
||||
)
|
||||
or
|
||||
// ActiveSupport::Multibyte::Chars
|
||||
exists(DataFlow::CallNode cn, DataFlow::CallNode n |
|
||||
cn =
|
||||
API::getTopLevelMember("ActiveSupport")
|
||||
.getMember("Multibyte")
|
||||
.getMember("Chars")
|
||||
.getMethod("new")
|
||||
.getCallNode() and
|
||||
n = cn.getAMethodCall("normalize") and
|
||||
sink = cn.getArgument(0)
|
||||
)
|
||||
) and
|
||||
state instanceof PostValidation
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,50 @@
|
||||
<!DOCTYPE qhelp PUBLIC "-//Semmle//qhelp//EN" "qhelp.dtd">
|
||||
<qhelp>
|
||||
<overview>
|
||||
<p>Security checks bypass due to a Unicode transformation</p>
|
||||
<p>
|
||||
If ever a unicode tranformation is performed after some security checks or logical
|
||||
validation, the
|
||||
latter could be bypassed due to a potential Unicode characters collision.
|
||||
The validation of concern are any character escaping, any regex validation or any string
|
||||
verification.
|
||||
</p>
|
||||
</overview>
|
||||
<recommendation>
|
||||
<p> Perform a Unicode normalization before the logical validation. </p>
|
||||
</recommendation>
|
||||
<example>
|
||||
|
||||
<p> The following example showcases the bypass of all checks performed by <code>
|
||||
html_escape()</code> due to a post-unicode normalization.</p>
|
||||
<p>For instance: the character U+FE64 (<code>﹤</code>) is not filtered-out by the
|
||||
html_escape() function. But due to the Unicode normalization, the character is
|
||||
transformed and would become U+003C (<code> < </code> ).</p>
|
||||
|
||||
<sample src="./examples/unicode_normalization.rb" />
|
||||
|
||||
</example>
|
||||
<example>
|
||||
|
||||
<p> The next example shows how an early deletion of a character may be bypassed due to a
|
||||
potential Unicode character collision.</p>
|
||||
<p>The character <code><</code> was expected to be omitted from the string <code>s</code>.
|
||||
However, a malicious user may consider using its colliding Unicode character U+FE64 <code>
|
||||
﹤</code> as an alternative. Due to the Late-Unicode normalization with the form NFKC,
|
||||
the resulting string would contain the unintended character <code><</code> . </p>
|
||||
|
||||
<sample src="./examples/unicode_normalization2.rb" />
|
||||
|
||||
</example>
|
||||
<references>
|
||||
<li> Research study: <a
|
||||
href="https://gosecure.github.io/presentations/2021-02-unicode-owasp-toronto/philippe_arteau_owasp_unicode_v4.pdf">
|
||||
Unicode vulnerabilities that could bYte you
|
||||
</a>
|
||||
</li>
|
||||
<li>
|
||||
<a
|
||||
href="https://gosecure.github.io/unicode-pentester-cheatsheet/">Unicode pentest
|
||||
cheatsheet</a>. </li>
|
||||
</references>
|
||||
</qhelp>
|
||||
24
ruby/ql/src/experimental/cwe-176/UnicodeBypassValidation.ql
Normal file
24
ruby/ql/src/experimental/cwe-176/UnicodeBypassValidation.ql
Normal file
@@ -0,0 +1,24 @@
|
||||
/**
|
||||
* @name Bypass Logical Validation Using Unicode Characters
|
||||
* @description A Unicode transformation is using a remote user-controlled data. The transformation is a Unicode normalization using the algorithms "NFC" or "NFKC". In all cases, the security measures implemented or the logical validation performed to escape any injection characters, to validate using regex patterns or to perform string-based checks, before the Unicode transformation are **bypassable** by special Unicode characters.
|
||||
* @kind path-problem
|
||||
* @id rb/unicode-bypass-validation
|
||||
* @precision high
|
||||
* @problem.severity error
|
||||
* @tags security
|
||||
* experimental
|
||||
* external/cwe/cwe-176
|
||||
* external/cwe/cwe-179
|
||||
* external/cwe/cwe-180
|
||||
*/
|
||||
|
||||
import ruby
|
||||
import codeql.ruby.experimental.UnicodeBypassValidationQuery
|
||||
import DataFlow::PathGraph
|
||||
|
||||
from Configuration config, DataFlow::PathNode source, DataFlow::PathNode sink
|
||||
where config.hasFlowPath(source, sink)
|
||||
select sink.getNode(), source, sink,
|
||||
"This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters.",
|
||||
sink.getNode(), "Unicode transformation (Unicode normalization)", source.getNode(),
|
||||
"remote user-controlled data"
|
||||
@@ -0,0 +1,10 @@
|
||||
require "erb"
|
||||
|
||||
class UnicodeNormalizationHtMLSafeController < ActionController::Base
|
||||
def unicodeNormalize
|
||||
unicode_input = params[:unicode_input]
|
||||
unicode_html_safe = ERB::Util.html_escape(unicode_input)
|
||||
normalized_nfkc = unicode_html_safe.unicode_normalize(:nfkc) # $result=BAD
|
||||
normalized_nfc = unicode_html_safe.unicode_normalize(:nfc) # $result=BAD
|
||||
end
|
||||
end
|
||||
@@ -0,0 +1,2 @@
|
||||
s = "﹤xss>"
|
||||
puts s.delete("<").unicode_normalize(:nfkc).include?("<")
|
||||
@@ -0,0 +1,75 @@
|
||||
edges
|
||||
| unicode_normalization.rb:7:5:7:17 | unicode_input | unicode_normalization.rb:8:23:8:35 | unicode_input |
|
||||
| unicode_normalization.rb:7:5:7:17 | unicode_input | unicode_normalization.rb:9:22:9:34 | unicode_input |
|
||||
| unicode_normalization.rb:7:21:7:26 | call to params | unicode_normalization.rb:7:21:7:42 | ...[...] |
|
||||
| unicode_normalization.rb:7:21:7:42 | ...[...] | unicode_normalization.rb:7:5:7:17 | unicode_input |
|
||||
| unicode_normalization.rb:15:5:15:17 | unicode_input | unicode_normalization.rb:16:27:16:39 | unicode_input |
|
||||
| unicode_normalization.rb:15:5:15:17 | unicode_input | unicode_normalization.rb:16:27:16:39 | unicode_input |
|
||||
| unicode_normalization.rb:15:21:15:26 | call to params | unicode_normalization.rb:15:21:15:42 | ...[...] |
|
||||
| unicode_normalization.rb:15:21:15:26 | call to params | unicode_normalization.rb:15:21:15:42 | ...[...] |
|
||||
| unicode_normalization.rb:15:21:15:42 | ...[...] | unicode_normalization.rb:15:5:15:17 | unicode_input |
|
||||
| unicode_normalization.rb:15:21:15:42 | ...[...] | unicode_normalization.rb:15:5:15:17 | unicode_input |
|
||||
| unicode_normalization.rb:16:5:16:23 | unicode_input_manip | unicode_normalization.rb:17:23:17:41 | unicode_input_manip |
|
||||
| unicode_normalization.rb:16:5:16:23 | unicode_input_manip | unicode_normalization.rb:18:22:18:40 | unicode_input_manip |
|
||||
| unicode_normalization.rb:16:27:16:39 | unicode_input | unicode_normalization.rb:16:27:16:59 | call to sub |
|
||||
| unicode_normalization.rb:16:27:16:39 | unicode_input | unicode_normalization.rb:16:27:16:59 | call to sub |
|
||||
| unicode_normalization.rb:16:27:16:59 | call to sub | unicode_normalization.rb:16:5:16:23 | unicode_input_manip |
|
||||
| unicode_normalization.rb:24:5:24:17 | unicode_input | unicode_normalization.rb:25:37:25:49 | unicode_input |
|
||||
| unicode_normalization.rb:24:21:24:26 | call to params | unicode_normalization.rb:24:21:24:42 | ...[...] |
|
||||
| unicode_normalization.rb:24:21:24:42 | ...[...] | unicode_normalization.rb:24:5:24:17 | unicode_input |
|
||||
| unicode_normalization.rb:25:5:25:21 | unicode_html_safe | unicode_normalization.rb:26:23:26:39 | unicode_html_safe |
|
||||
| unicode_normalization.rb:25:5:25:21 | unicode_html_safe | unicode_normalization.rb:27:22:27:38 | unicode_html_safe |
|
||||
| unicode_normalization.rb:25:25:25:50 | call to html_escape | unicode_normalization.rb:25:5:25:21 | unicode_html_safe |
|
||||
| unicode_normalization.rb:25:37:25:49 | unicode_input | unicode_normalization.rb:25:25:25:50 | call to html_escape |
|
||||
| unicode_normalization.rb:33:5:33:17 | unicode_input | unicode_normalization.rb:34:40:34:52 | unicode_input |
|
||||
| unicode_normalization.rb:33:21:33:26 | call to params | unicode_normalization.rb:33:21:33:42 | ...[...] |
|
||||
| unicode_normalization.rb:33:21:33:42 | ...[...] | unicode_normalization.rb:33:5:33:17 | unicode_input |
|
||||
| unicode_normalization.rb:34:5:34:21 | unicode_html_safe | unicode_normalization.rb:35:23:35:39 | unicode_html_safe |
|
||||
| unicode_normalization.rb:34:5:34:21 | unicode_html_safe | unicode_normalization.rb:36:22:36:38 | unicode_html_safe |
|
||||
| unicode_normalization.rb:34:25:34:53 | call to escapeHTML | unicode_normalization.rb:34:25:34:63 | call to html_safe |
|
||||
| unicode_normalization.rb:34:25:34:63 | call to html_safe | unicode_normalization.rb:34:5:34:21 | unicode_html_safe |
|
||||
| unicode_normalization.rb:34:40:34:52 | unicode_input | unicode_normalization.rb:34:25:34:53 | call to escapeHTML |
|
||||
nodes
|
||||
| unicode_normalization.rb:7:5:7:17 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:7:21:7:26 | call to params | semmle.label | call to params |
|
||||
| unicode_normalization.rb:7:21:7:42 | ...[...] | semmle.label | ...[...] |
|
||||
| unicode_normalization.rb:8:23:8:35 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:9:22:9:34 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:15:5:15:17 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:15:5:15:17 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:15:21:15:26 | call to params | semmle.label | call to params |
|
||||
| unicode_normalization.rb:15:21:15:42 | ...[...] | semmle.label | ...[...] |
|
||||
| unicode_normalization.rb:15:21:15:42 | ...[...] | semmle.label | ...[...] |
|
||||
| unicode_normalization.rb:16:5:16:23 | unicode_input_manip | semmle.label | unicode_input_manip |
|
||||
| unicode_normalization.rb:16:27:16:39 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:16:27:16:39 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:16:27:16:59 | call to sub | semmle.label | call to sub |
|
||||
| unicode_normalization.rb:17:23:17:41 | unicode_input_manip | semmle.label | unicode_input_manip |
|
||||
| unicode_normalization.rb:18:22:18:40 | unicode_input_manip | semmle.label | unicode_input_manip |
|
||||
| unicode_normalization.rb:24:5:24:17 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:24:21:24:26 | call to params | semmle.label | call to params |
|
||||
| unicode_normalization.rb:24:21:24:42 | ...[...] | semmle.label | ...[...] |
|
||||
| unicode_normalization.rb:25:5:25:21 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
| unicode_normalization.rb:25:25:25:50 | call to html_escape | semmle.label | call to html_escape |
|
||||
| unicode_normalization.rb:25:37:25:49 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:26:23:26:39 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
| unicode_normalization.rb:27:22:27:38 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
| unicode_normalization.rb:33:5:33:17 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:33:21:33:26 | call to params | semmle.label | call to params |
|
||||
| unicode_normalization.rb:33:21:33:42 | ...[...] | semmle.label | ...[...] |
|
||||
| unicode_normalization.rb:34:5:34:21 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
| unicode_normalization.rb:34:25:34:53 | call to escapeHTML | semmle.label | call to escapeHTML |
|
||||
| unicode_normalization.rb:34:25:34:63 | call to html_safe | semmle.label | call to html_safe |
|
||||
| unicode_normalization.rb:34:40:34:52 | unicode_input | semmle.label | unicode_input |
|
||||
| unicode_normalization.rb:35:23:35:39 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
| unicode_normalization.rb:36:22:36:38 | unicode_html_safe | semmle.label | unicode_html_safe |
|
||||
subpaths
|
||||
#select
|
||||
| unicode_normalization.rb:8:23:8:35 | unicode_input | unicode_normalization.rb:7:21:7:26 | call to params | unicode_normalization.rb:8:23:8:35 | unicode_input | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:8:23:8:35 | unicode_input | Unicode transformation (Unicode normalization) | unicode_normalization.rb:7:21:7:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:9:22:9:34 | unicode_input | unicode_normalization.rb:7:21:7:26 | call to params | unicode_normalization.rb:9:22:9:34 | unicode_input | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:9:22:9:34 | unicode_input | Unicode transformation (Unicode normalization) | unicode_normalization.rb:7:21:7:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:17:23:17:41 | unicode_input_manip | unicode_normalization.rb:15:21:15:26 | call to params | unicode_normalization.rb:17:23:17:41 | unicode_input_manip | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:17:23:17:41 | unicode_input_manip | Unicode transformation (Unicode normalization) | unicode_normalization.rb:15:21:15:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:18:22:18:40 | unicode_input_manip | unicode_normalization.rb:15:21:15:26 | call to params | unicode_normalization.rb:18:22:18:40 | unicode_input_manip | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:18:22:18:40 | unicode_input_manip | Unicode transformation (Unicode normalization) | unicode_normalization.rb:15:21:15:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:26:23:26:39 | unicode_html_safe | unicode_normalization.rb:24:21:24:26 | call to params | unicode_normalization.rb:26:23:26:39 | unicode_html_safe | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:26:23:26:39 | unicode_html_safe | Unicode transformation (Unicode normalization) | unicode_normalization.rb:24:21:24:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:27:22:27:38 | unicode_html_safe | unicode_normalization.rb:24:21:24:26 | call to params | unicode_normalization.rb:27:22:27:38 | unicode_html_safe | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:27:22:27:38 | unicode_html_safe | Unicode transformation (Unicode normalization) | unicode_normalization.rb:24:21:24:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:35:23:35:39 | unicode_html_safe | unicode_normalization.rb:33:21:33:26 | call to params | unicode_normalization.rb:35:23:35:39 | unicode_html_safe | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:35:23:35:39 | unicode_html_safe | Unicode transformation (Unicode normalization) | unicode_normalization.rb:33:21:33:26 | call to params | remote user-controlled data |
|
||||
| unicode_normalization.rb:36:22:36:38 | unicode_html_safe | unicode_normalization.rb:33:21:33:26 | call to params | unicode_normalization.rb:36:22:36:38 | unicode_html_safe | This $@ processes unsafely $@ and any logical validation in-between could be bypassed using special Unicode characters. | unicode_normalization.rb:36:22:36:38 | unicode_html_safe | Unicode transformation (Unicode normalization) | unicode_normalization.rb:33:21:33:26 | call to params | remote user-controlled data |
|
||||
@@ -0,0 +1 @@
|
||||
experimental/cwe-176/UnicodeBypassValidation.ql
|
||||
@@ -0,0 +1,38 @@
|
||||
require "erb"
|
||||
include ERB::Util
|
||||
require 'cgi'
|
||||
|
||||
class UnicodeNormalizationOKController < ActionController::Base
|
||||
def unicodeNormalize
|
||||
unicode_input = params[:unicode_input]
|
||||
normalized_nfkc = unicode_input.unicode_normalize(:nfkc) # $MISSING:result=OK
|
||||
normalized_nfc = unicode_input.unicode_normalize(:nfc) # $MISSING:result=OK
|
||||
end
|
||||
end
|
||||
|
||||
class UnicodeNormalizationStrManipulationController < ActionController::Base
|
||||
def unicodeNormalize
|
||||
unicode_input = params[:unicode_input]
|
||||
unicode_input_manip = unicode_input.sub(/[aeiou]/, "*")
|
||||
normalized_nfkc = unicode_input_manip.unicode_normalize(:nfkc) # $result=BAD
|
||||
normalized_nfc = unicode_input_manip.unicode_normalize(:nfc) # $result=BAD
|
||||
end
|
||||
end
|
||||
|
||||
class UnicodeNormalizationHtMLEscapeController < ActionController::Base
|
||||
def unicodeNormalize
|
||||
unicode_input = params[:unicode_input]
|
||||
unicode_html_safe = html_escape(unicode_input)
|
||||
normalized_nfkc = unicode_html_safe.unicode_normalize(:nfkc) # $result=BAD
|
||||
normalized_nfc = unicode_html_safe.unicode_normalize(:nfc) # $result=BAD
|
||||
end
|
||||
end
|
||||
|
||||
class UnicodeNormalizationCGIHtMLEscapeController < ActionController::Base
|
||||
def unicodeNormalize
|
||||
unicode_input = params[:unicode_input]
|
||||
unicode_html_safe = CGI.escapeHTML(unicode_input).html_safe
|
||||
normalized_nfkc = unicode_html_safe.unicode_normalize(:nfkd) # $result=BAD
|
||||
normalized_nfc = unicode_html_safe.unicode_normalize(:nfd) # $result=BAD
|
||||
end
|
||||
end
|
||||
Reference in New Issue
Block a user