hpricot_scrub 0.2.0 → 0.2.1

data/Manifest.txt

@@ -3,6 +3,7 @@ README.txt
 CHANGELOG.txt
 Manifest.txt
 setup.rb
+lib/hpricot_scrub/hpricot_scrub.rb
 lib/hpricot_scrub/version.rb
 lib/hpricot_scrub.rb
 test/test_helper.rb

data/lib/hpricot_scrub/hpricot_scrub.rb

@@ -0,0 +1,94 @@
+require 'rubygems'
+
+if defined?(Kernel::gem)
+  gem('hpricot', '>= 0.5')
+else
+  require_gem('hpricot', '>= 0.5')
+end
+
+require 'hpricot'
+
+module Hpricot
+  module Scrubable
+    def scrubable?
+      ! [Hpricot::Text, Hpricot::BogusETag].include?(self.class)
+    end
+  end
+
+  class Elements
+    def strip
+      each { |x| x.strip }
+    end
+    
+    def strip_attributes(safe=[])
+      each { |x| x.strip_attributes(safe) }
+    end
+  end
+
+  class BaseEle
+    include Scrubable
+  end
+
+  class Elem
+    include Scrubable
+
+    def scrub(config)
+      children.reverse.each { |c| 
+        c.scrub(config) if c.scrubable? && ! config[:allow_tags].include?(c.name)
+      }
+      strip unless config[:allow_tags].include?(name)
+    end
+
+    def remove
+      parent.children.delete(self)
+    end
+
+    def strip
+      children.each { |c| c.strip if c.scrubable? }
+
+      if strip_removes?
+        remove
+      else
+        parent.replace_child self, Hpricot.make(inner_html) unless parent.nil?
+      end
+    end
+    
+    def strip_attributes(safe=[])
+      attributes.each {|atr|
+        remove_attribute(atr[0]) unless safe.include?(atr[0])
+      } unless attributes.nil?
+    end
+    
+    def strip_removes?
+      # I'm sure there are others that shuould be ripped instead of stripped
+      attributes && attributes['type'] =~ /script|css/
+    end
+  end
+
+  class Doc
+    def scrub(config={})
+      config = {
+        :remove_tags => [],
+        :allow_tags => [],
+        :allow_attributes => []
+      }.merge(config)
+      
+      config[:remove_tags].each { |tag| (self/tag).remove }
+      config[:allow_tags].each { |tag|
+        (self/tag).strip_attributes(config[:allow_attributes])
+      }
+      children.reverse.each {|c| c.scrub(config) if c.scrubable? }
+      self
+    end
+  end
+end
+
+class String
+  def scrub!
+    self.gsub!(/^(\n|.)*$/, Hpricot(self).scrub.inner_html)
+  end
+
+  def scrub
+    dup.scrub!
+  end
+end

data/lib/hpricot_scrub/version.rb

@@ -2,7 +2,7 @@ module HpricotScrub #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 0
     MINOR = 2
-    TINY  = 0
+    TINY  = 1
 
     STRING = [MAJOR, MINOR, TINY].join('.')
   end

data/lib/hpricot_scrub.rb

@@ -1 +1,4 @@
-Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }
+# Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }
+
+require File.dirname(__FILE__) + '/hpricot_scrub/hpricot_scrub.rb'
+require File.dirname(__FILE__) + '/hpricot_scrub/version.rb'

metadata

@@ -3,7 +3,7 @@ rubygems_version: 0.9.1
 specification_version: 1
 name: hpricot_scrub
 version: !ruby/object:Gem::Version 
-  version: 0.2.0
+  version: 0.2.1
 date: 2007-03-04 00:00:00 -08:00
 summary: Scrub HTML with Hpricot
 require_paths: 
@@ -34,6 +34,7 @@ files:
 - CHANGELOG.txt
 - Manifest.txt
 - setup.rb
+- lib/hpricot_scrub/hpricot_scrub.rb
 - lib/hpricot_scrub/version.rb
 - lib/hpricot_scrub.rb
 - test/test_helper.rb