rgrove-sanitize 1.0.8.3 → 1.0.8.4

data/HISTORY

@@ -1,8 +1,10 @@
 Sanitize History
 ================================================================================
 
-Version 1.0.8.2 (git)
+Version 1.0.8.4 (git)
   * Migrated from Hpricot to Nokogiri. Requires libxml2 >= 2.7.2 [Adam Hooper]
+  * Added an :output config setting to allow the output format to be specified.
+    Supported formats are :xhtml (the default) and :html (which outputs HTML4).
   * Changed protocol regex to ensure Sanitize doesn't kill URLs with colons in 
     path segments. [Peter Cooper]
 

data/lib/sanitize.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 #--
 # Copyright (c) 2009 Ryan Grove <ryan@wonko.com>
 #
@@ -29,18 +30,6 @@ require 'sanitize/config/relaxed'
 
 class Sanitize
 
-  # Characters that should be replaced with entities in text nodes.
-  ENTITY_MAP = {
-    '<' => '&lt;',
-    '>' => '&gt;',
-    '"' => '&quot;',
-    "'" => '&#39;'
-  }
-
-  # Matches an unencoded ampersand that is not part of a valid character entity
-  # reference.
-  REGEX_AMPERSAND = /&(?!(?:[a-z]+[0-9]{0,2}|#[0-9]+|#x[0-9a-f]+);)/i
-
   # Matches an attribute value that could be treated by a browser as a URL
   # with a protocol prefix, such as "http:" or "javascript:". Any string of zero
   # or more characters followed by a colon is considered a match, even if the
@@ -124,7 +113,24 @@ class Sanitize
       end
     end
 
-    result = fragment.to_xhtml(:encoding => 'UTF-8', :indent => 0).gsub(/>\n/, '>')
+    if @config[:output] == :xhtml
+      output_method = fragment.method(:to_xhtml)
+    elsif @config[:output] == :html
+      output_method = fragment.method(:to_html)
+    else
+      raise Error, "unsupported output format: #{@config[:output]}"
+    end
+
+    if RUBY_VERSION >= '1.9'
+      # Nokogiri 1.3.3 (and possibly earlier versions) always returns a US-ASCII
+      # string no matter what we ask for. This will be fixed in 1.4.0, but for
+      # now we have to hack around it to prevent errors.
+      result = output_method.call(:encoding => 'utf-8', :indent => 0).force_encoding('utf-8')
+      result.gsub!(">\n", '>')
+    else
+      result = output_method.call(:encoding => 'utf-8', :indent => 0).gsub(">\n", '>')
+    end
+
     return result == html ? nil : html[0, html.length] = result
   end
 
@@ -146,18 +152,6 @@ class Sanitize
       sanitize = Sanitize.new(config)
       sanitize.clean!(html)
     end
-
-    # Encodes special HTML characters (<, >, ", ', and &) in _html_ as entity
-    # references and returns the encoded string.
-    def encode_html(html)
-      str = html.dup
-
-      # Encode special chars.
-      ENTITY_MAP.each {|char, entity| str.gsub!(char, entity) }
-
-      # Convert unencoded ampersands to entity references.
-      str.gsub(REGEX_AMPERSAND, '&amp;')
-    end
   end
 
 end

data/lib/sanitize/config.rb

@@ -28,17 +28,21 @@ class Sanitize
       # comments.
       :allow_comments => false,
 
-      # HTML elements to allow. By default, no elements are allowed (which means
-      # that all HTML will be stripped).
-      :elements => [],
+      # HTML attributes to add to specific elements. By default, no attributes
+      # are added.
+      :add_attributes => {},
 
       # HTML attributes to allow in specific elements. By default, no attributes
       # are allowed.
       :attributes => {},
 
-      # HTML attributes to add to specific elements. By default, no attributes
-      # are added.
-      :add_attributes => {},
+      # HTML elements to allow. By default, no elements are allowed (which means
+      # that all HTML will be stripped).
+      :elements => [],
+
+      # Output format. Supported formats are :html and :xhtml (which is the
+      # default).
+      :output => :xhtml,
 
       # URL handling protocols to allow in specific attributes. By default, no
       # protocols are allowed. Use :relative in place of a protocol if you want

data/lib/sanitize/version.rb

@@ -1,3 +1,3 @@
 class Sanitize
-  VERSION = '1.0.8.3'
+  VERSION = '1.0.8.4'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: rgrove-sanitize
 version: !ruby/object:Gem::Version 
-  version: 1.0.8.3
+  version: 1.0.8.4
 platform: ruby
 authors: 
 - Ryan Grove
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-09-04 00:00:00 -07:00
+date: 2009-09-17 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -62,6 +62,7 @@ files:
 - lib/sanitize.rb
 has_rdoc: false
 homepage: http://github.com/rgrove/sanitize/
+licenses: 
 post_install_message: 
 rdoc_options: []
 
@@ -82,7 +83,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.2.0
+rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
 summary: Whitelist-based HTML sanitizer.