crazy_harry 0.0.3

data/.gitignore

@@ -0,0 +1,6 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+.rvmrc
+coverage/*

data/Gemfile

@@ -0,0 +1,6 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in crazy_harry.gemspec
+gemspec
+
+gem 'rake'

data/Guardfile

@@ -0,0 +1,10 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec', :version => 2, :cli => '--color' do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/crazy_harry/(.+)\.rb$})   { |m| ["spec/lib/crazy_harry/#{m[1]}_spec.rb", "spec/integration/crazy_harry/#{m[1]}_spec.rb", "spec/lib/crazy_harry_spec.rb"] }
+  watch(%r{^lib/(.+)\.rb$})               { |m| ["spec/lib/#{m[1]}_spec.rb", "spec/integration/#{m[1]}_spec.rb"] }
+  watch('spec/spec_helper.rb')            { "spec" }
+end
+

data/README.md

@@ -0,0 +1,116 @@
+# CrazyHarry
+
+[![Build Status](https://secure.travis-ci.org/lonelyplanet/crazy_harry.png)](http://travis-ci.org/lonelyplanet/crazy_harry)
+
+CrazyHarry is a high-level html fragment sanitiser/cleaner in use at
+[Lonely Planet](http://www.lonelyplanet.com).  It is based on [Flavour
+Jones's](http://mike.daless.io) [Loofah Gem](https://github.com/flavorjones). 
+
+[Loofah](https://github.com/flavorjones) is a great tool and we've been
+using it in a number of different projects.  Hoewever, we found that we
+were repeating the same types of cleaning job in multiple places. 
+
+CrazyHarry wraps up a number these tasks in a simple DSL, while adding commands for a few edge cases that are not straightforward with Loofah.
+
+## Installation 
+
+    gem 'crazy_harry' 
+
+    bundle install 
+
+## Usage
+
+    object_with_description.each do |obj|
+
+      if descriptions[l.external_id]
+        sanitised_fragment = CrazyHarry.fragment(descriptions[obj.external_id])
+          .redact!( unsafe: true,     tags: 'img')
+          .change!( from: 'b',        to: 'h3' )
+          .change!( from: 'strong',   to: 'h3' )
+
+        obj.update_column(:description, sanitised_fragment.to_s)
+      end
+    end
+
+## Default Actions
+
+It automatically removes blank tags, converts `<br \>` tags to wrapped
+paragraphs and de-dupes content.  
+
+## Chaining
+
+As per the previous example, all calls **except** `.strip!` (which removes
+all markup) may be chained.  (`.strip!` can be the last element in a
+chain.  See below). 
+
+## Scoping and Targeting by Content
+
+All commands except `.strip!` accept `scope:` and `text:` attributes:
+
+    CrazyHarry.fragment( '<div><b>Hotels</b></div><p><b>Hotels</b></p><b>Tents</b>' ).change!( from: 'b', to: 'em', scope: 'p' ).to_s
+
+will produce: 
+
+    <div><b>Hotels</b></div><p><em>Hotels</em></p><b>Tents</b>
+
+while:
+
+    CrazyHarry.fragment( 'Hot <b>hotels</b> in <b>Saigon</b>' ).change!( from: 'b', to: 'em', text: 'hotels' ).to_s
+
+will produce:
+
+    Hot <em>hotels</em> in <b>Saigon</b>
+
+
+## Adding Attributes
+
+Use the `.translate` command to do this:
+
+    harry.fragment( '<b>Header</b><p>Content</p>' ).translate!( add_attributes: { class: 'partner'} ).to_s
+
+will return:
+
+    <b class="partner">Header</b><p class="partner">Content</p>
+
+If a tag already has an attribute, the new attribute will be appended to
+the existing one:
+
+    <b class="bright-red partner">Header</b><p class="partner">Content</p>
+
+## Stripping
+
+### Specific Tags
+
+Use the `.redact!` command.  It **does not** strip unsafe tags by default.
+To do this, pass the `unsafe: true` option.
+
+### All Tags
+
+Use the `.strip!` command.  It can be used as the last tag in a chain
+(with `.translate( from_text: <some text>, to_text: <other text> )`, for instance), but should generally be the only call
+you make. 
+
+## Text Translation 
+
+The `.translate!` command can change tag content, preserving case:
+
+    CrazyHarry.fragment( '<h3>Lodging</h3> lodging' ).translate!( from_text: 'lodging', to_text: 'hotel' ).to_s
+
+will return:
+ 
+    <h3>Hotel</h3> lodging
+
+## Known Issues/TODO
+
+  * De-duping does not take account of whitespace.  So, `<p>Some Content</p>` and `<p>Some Content </p>` will not be treated as duplicates.
+  * Be able to turn off default actions.
+  * It should be able to work on documents as well as fragments.
+  * Merge `.translate!` with `.change!` 
+
+## Contributing
+
+  1. Fork it
+  2. Create your feature branch (`git checkout -b my-new-feature`)
+  3. Commit your changes (`git commit -am 'Added some feature'`)
+  4. Push to the branch (`git push origin my-new-feature`)
+  5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+task :default => :spec
+
+RSpec::Core::RakeTask.new

data/crazy_harry.gemspec

@@ -0,0 +1,28 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "crazy_harry/version"
+
+Gem::Specification.new do |s|
+  s.name        = "crazy_harry"
+  s.version     = CrazyHarry::VERSION
+  s.authors     = ["TA Tyree"]
+  s.email       = ["todd.tyree@lonelyplanet.co.uk"]
+  s.homepage    = "https://github.com/lonelyplanet/crazy_harry"
+  s.summary     = %q{A High level HTML fragment sanitizer.}
+  s.description = %q{CrazyHarry is a high-level html fragment sanitiser/cleaner based on Loofah.}
+
+  s.rubyforge_project = "crazy_harry"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  # specify any dependencies here; for example:
+  s.add_development_dependency 'rspec'
+  s.add_development_dependency 'guard'
+  s.add_development_dependency 'guard-rspec'
+  s.add_development_dependency 'simplecov'
+
+  s.add_runtime_dependency 'loofah'
+end

data/lib/crazy_harry.rb

@@ -0,0 +1,27 @@
+require 'loofah'
+
+%w(default change redact translate base version).each do |load_lib|
+  require_relative "crazy_harry/#{load_lib}"
+end
+
+module CrazyHarry
+
+  attr_accessor :base
+
+  class << self
+
+    def fragment(fragment)
+      base = Base.new(fragment: fragment)
+      base.no_blanks!
+      base.convert_br_to_p!
+      base.dedupe!
+      base
+    end
+
+    def to_s
+      @base.to_s
+    end
+
+  end
+
+end

data/lib/crazy_harry/base.rb

@@ -0,0 +1,31 @@
+module CrazyHarry
+  class Base
+    include CrazyHarry::Default
+    include CrazyHarry::Change
+    include CrazyHarry::Redact
+    include CrazyHarry::Translate
+
+    attr_accessor :fragment, :scope, :steps, :text
+
+    def initialize(opts = {})
+      self.fragment = Loofah.fragment(opts.delete(:fragment)) if opts.has_key?(:fragment)
+      self.steps = []
+    end
+
+    def to_s
+      self.fragment.to_s.squeeze(' ').strip
+    end
+
+    private
+
+    def run!
+      steps.compact.delete_if do |step|
+        if steps.size > 0
+          fragment.scrub!(step)
+          true
+        end
+      end
+    end
+
+  end
+end

data/lib/crazy_harry/change.rb

@@ -0,0 +1,59 @@
+module CrazyHarry
+  module Change
+
+    BLOCK_CONVERSION_ELEMENTS = {
+      inlines:  %w(br),
+      blocks:   %w(div p)
+    }
+
+    attr_accessor :from, :to
+
+    def change!(opts)
+      self.from  =  opts.delete(:from)
+      self.to    =  opts.delete(:to)
+      self.text  =  opts.delete(:text)
+      self.scope =  opts.delete(:scope)
+
+      self.steps << generic_from_to
+      self.steps << unwrap_unnecessary_paragraphs
+
+      run!
+
+      self
+    end
+
+    private
+
+    def change_this_node?(node)
+      ( self.text       ? node.text == self.text                          : true ) &&
+      ( self.scope      ? node.parent.name == self.scope                  : true ) &&
+      ( node.name == self.from )
+    end
+
+    def convert_inline_element_to_block?
+      BLOCK_CONVERSION_ELEMENTS[:inlines].include?(self.from) &&
+      BLOCK_CONVERSION_ELEMENTS[:blocks].include?(self.to)
+    end
+
+    def generic_from_to
+      return if convert_inline_element_to_block?
+
+      Loofah::Scrubber.new do |node|
+        node.name = self.to if change_this_node?(node)
+      end
+    end
+
+    def unwrap_unnecessary_paragraphs
+      Loofah::Scrubber.new do |node|
+        node.replace(node.children.first) if unnecessary_paragraph?(node)
+      end
+    end
+
+    def unnecessary_paragraph?(node)
+      node.name == 'p' &&
+      node.children.size == 1 &&
+      Loofah::Elements::BLOCK_LEVEL.include?(node.children.first.name)
+    end
+
+  end
+end

data/lib/crazy_harry/default.rb

@@ -0,0 +1,67 @@
+module CrazyHarry
+  module Default
+    TARGET_ELEMENTS = ['b'].to_set 
+    TARGET_ELEMENTS.merge(Loofah::Elements::BLOCK_LEVEL)
+
+    def no_blanks! 
+      self.steps << remove_blank_elements
+      run!
+      self
+    end
+
+    def dedupe!
+      self.fragment = Loofah.fragment(html_with_duplicates_removed_from_the_bottom_up)
+      self
+    end
+
+    def convert_br_to_p!
+      fragment.xpath('br/following-sibling::text()|br/preceding-sibling::text()').each do |node|
+        node.replace(Nokogiri.make("<p>#{node.to_html.strip}</p>")) unless node.content =~ /\A\s*\z/
+      end
+
+      fragment.scrub!(scrub_tag('br'))
+    end
+
+    private
+
+    def scrub_tag(tag_name)
+      Loofah::Scrubber.new do |node|
+        if node.name == tag_name
+          node.remove
+          Loofah::Scrubber::STOP # don't bother with the rest of the subtree
+        end
+      end
+    end
+
+    def this_element?(element)
+      name = element.respond_to?(:name) ? element.name : element
+      TARGET_ELEMENTS.include?(name) 
+    end
+
+    def remove_blank_elements
+      Loofah::Scrubber.new do |node|
+        node.remove if this_element?(node) && node.content.empty?
+      end
+    end
+
+    def html_with_duplicates_removed_from_the_bottom_up
+      all_elements.reverse.delete_if{ |e| all_elements_less_current_element(e).include?(e) }.reverse.compact.join('')
+    end
+
+    def all_elements_less_current_element(element)
+      remove = true
+
+      all_elements_less_current_node = all_elements.delete_if do |e|
+        if e == element && remove
+          remove = false
+          true
+        end
+      end
+    end
+
+    def all_elements
+      @all_elements ||= self.fragment.children.map(&:to_html)
+    end
+
+  end
+end

data/lib/crazy_harry/redact.rb

@@ -0,0 +1,73 @@
+module CrazyHarry
+  module Redact
+
+    class InvalidStripMethod < StandardError; end;
+
+    STRIP_METHODS =  %w(strip prune escape whitewash)
+
+    attr_accessor :attributes, :tags, :unsafe
+
+    def strip!
+      fragment.to_text
+    end
+
+    def redact!(opts = {})
+      self.unsafe       = opts.delete(:unsafe) || opts == {}
+      self.tags         = [opts.delete(:tags)].compact.flatten
+      self.attributes   = opts.delete(:attributes)
+      self.text         = opts.delete(:text)
+      self.scope        = opts.delete(:scope)
+      prune             = opts.delete(:prune)
+
+      self.steps << strip_unsafe  if self.unsafe
+      self.steps << strip_tags    unless prune || self.tags == []
+      self.steps << prune_tags    if prune
+
+      run!
+
+      self
+    end
+
+    private
+
+    def redact_this_node?(node)
+      ( self.text       ? node.text == self.text                          : true ) &&
+      ( self.scope      ? node.parent.name == self.scope                  : true ) &&
+      ( self.attributes ? self.attributes.any?{ |a,v| node[a.to_s] == v } : true ) &&
+      self.tags.include?(node.name)
+    end
+
+    def strip_unsafe
+      fail InvalidStripMethod, "vaild methods are #{STRIP_METHODS.join(', ')}." unless valid_strip_method?
+
+      STRIP_METHODS.include?(self.unsafe.to_s) ? self.unsafe.to_sym : :prune
+    end
+
+    def valid_strip_method?
+      return true if self.unsafe == true || STRIP_METHODS.include?(self.unsafe.to_s)
+    end
+
+    def strip_tags
+      Loofah::Scrubber.new do |node|
+        content = block_node?(node) ? "#{node.content}\n" : "#{node.content} "
+        node.replace(content) if redact_this_node?(node)
+      end
+    end
+
+    def block_node?(node)
+      Loofah::Elements::BLOCK_LEVEL.include?(node.name)
+    end
+
+    # TODO: Refactor and DRY out--nearly identical to
+    # ::Default#scrub_tag
+    def prune_tags
+      Loofah::Scrubber.new do |node|
+        if redact_this_node?(node)
+          node.remove
+          Loofah::Scrubber::STOP # don't bother with the rest of the subtree
+        end
+      end
+    end
+    
+  end
+end

data/lib/crazy_harry/translate.rb

@@ -0,0 +1,56 @@
+module CrazyHarry
+  module Translate
+
+    attr_accessor :add_attributes, :from_text, :to_text
+
+    def translate!(opts = {})
+      self.add_attributes   = opts.delete(:add_attributes)
+      self.from_text        = opts.delete(:from_text)
+      self.to_text          = opts.delete(:to_text)
+      self.text             = opts.delete(:text)
+      self.scope            = opts.delete(:scope)
+
+      self.steps << change_attributes if self.add_attributes
+      self.steps << change_text if change_text?
+
+      run!
+
+      self
+    end
+
+    private
+
+    def translate_this_node?(node)
+     ( self.text       ? node.text == self.text                          : true ) &&
+     ( self.scope      ? node.parent.name == self.scope                  : true )
+    end
+
+    def change_text?
+      self.from_text && self.to_text
+    end
+
+    # TODO move this to CrazyHarry::Change.
+    def change_attributes
+      Loofah::Scrubber.new do |node|
+        if translate_this_node?(node)
+          self.add_attributes.map do |k,v|
+            node_key = k.to_s
+
+            node[node_key] = [node[node_key], v].compact.join(' ') unless node[node_key].to_s[/#{v}/]
+          end
+        end
+      end
+    end
+
+    def change_text
+      Loofah::Scrubber.new do |node|
+        capitalized_from = self.from_text.capitalize
+        capitalized_to   = self.to_text.capitalize
+
+        node.content = node.content.gsub(/#{self.from_text.downcase}/, self.to_text.downcase) if node.content[/#{self.from_text.downcase}/]
+        node.content = node.content.gsub(/#{capitalized_from}/, capitalized_to) if node.content[/#{capitalized_from}/]
+      end
+    end
+
+  end
+end

data/lib/crazy_harry/version.rb

@@ -0,0 +1,3 @@
+module CrazyHarry
+  VERSION = "0.0.3"
+end

data/rvmrc.example

@@ -0,0 +1 @@
+rvm use 1.9.3@crazy_harry --create

data/spec/fixtures/golden_nugget.html

@@ -0,0 +1,50 @@
+<p>
+<b>Location. </b> 
+<br />
+Golden Nugget formerly Trump Marina is located in Atlantic City, close to Atlantic City Aquarium, Steel Pier, and Atlantic City Hall. Nearby points of interest also include Atlantic City Public Library and Absecon Lighthouse. 
+</p>
+<p>
+<b>Resort Features. </b>
+<br />
+Dining options at Golden Nugget formerly Trump Marina include 8 restaurants. 4 bars/lounges, a beach bar, and a poolside bar are open for drinks. Room service is available 24 hours a day. Recreational amenities include a children's pool and a health club. The property's full service health spa has massage/treatment rooms and beauty services. This 3 star property has a business center and offers small meeting rooms and audio visual equipment. Wireless and wired high speed Internet access is available in public areas (surcharges apply)..
+</p>
+<p>
+<b>Guestrooms. </b> 
+<br /> 
+728 air conditioned guestrooms at Golden Nugget formerly Trump Marina feature coffee/tea makers and blackout drapes/curtains. Bathrooms feature complimentary toiletries and hair dryers. Wired high speed Internet access is available for a surcharge. Televisions have pay movies. Also included are irons/ironing boards and clock radios. Guests may request a turndown service and wake up calls. Housekeeping is available daily. 
+</p>
+<br /><br /> 
+<p><strong>Notifications and Fees:</strong>
+<br />
+</p>
+<p></p>
+<p></p>
+<p></p>
+<p>The following fees and deposits are charged by the property at time of service, check in, or check out.  
+<ul>
+  <li>Self parking fee: USD 5 per stay</li>
+  <li>Valet parking fee: USD 10 per stay</li>
+  <li>Fee for in room high speed Internet (wired): USD 12.99 (for 24 hours, rates may vary)</li>
+  <li>Rollaway bed fee: USD 25. per stay</li>
+</ul>
+</p>
+<p>
+The above list may not be comprehensive. Fees and deposits may not include tax and are subject to change.
+</p> 
+<br /><br /> 
+<p>
+<strong>Notifications and Fees:</strong>
+<br />
+</p>
+<p></p>
+<p></p>
+<p></p>
+<p>The following fees and deposits are charged by the property at time of service, check in, or check out.  
+<ul>
+  <li>Self parking fee: USD 5 per stay</li>
+  <li>Valet parking fee: USD 10 per stay</li>
+  <li>Fee for in room high speed Internet (wired): USD 12.99 (for 24 hours, rates may vary)</li>
+  <li>Rollaway bed fee: USD 25. per stay</li>
+</ul>
+</p>
+<p>The above list may not be comprehensive. Fees and deposits may not include tax and are subject to change. </p>

data/spec/fixtures/golden_nugget_corrected.html

@@ -0,0 +1,24 @@
+<p>
+<h3>Location. </h3> 
+
+Golden Nugget formerly Trump Marina is located in Atlantic City, close to Atlantic City Aquarium, Steel Pier, and Atlantic City Hall. Nearby points of interest also include Atlantic City Public Library and Absecon Lighthouse. 
+</p>
+<p>
+<h3>Resort Features. </h3>
+
+Dining options at Golden Nugget formerly Trump Marina include 8 restaurants. 4 bars/lounges, a beach bar, and a poolside bar are open for drinks. Room service is available 24 hours a day. Recreational amenities include a children's pool and a health club. The property's full service health spa has massage/treatment rooms and beauty services. This 3 star property has a business center and offers small meeting rooms and audio visual equipment. Wireless and wired high speed Internet access is available in public areas (surcharges apply)..
+</p><p>
+<h3>Guestrooms. </h3> 
+
+728 air conditioned guestrooms at Golden Nugget formerly Trump Marina feature coffee/tea makers and blackout drapes/curtains. Bathrooms feature complimentary toiletries and hair dryers. Wired high speed Internet access is available for a surcharge. Televisions have pay movies. Also included are irons/ironing boards and clock radios. Guests may request a turndown service and wake up calls. Housekeeping is available daily. 
+
+</p><p><h3>Notifications and Fees:</h3>
+</p><p>The following fees and deposits are charged by the property at time of service, check in, or check out.
+</p><ul>
+<li>Self parking fee: USD 5 per stay</li>
+ <li>Valet parking fee: USD 10 per stay</li>
+ <li>Fee for in room high speed Internet (wired): USD 12.99 (for 24 hours, rates may vary)</li>
+ <li>Rollaway bed fee: USD 25. per stay</li>
+</ul><p>
+The above list may not be comprehensive. Fees and deposits may not include tax and are subject to change.
+</p>

data/spec/integration/crazy_harry_spec.rb

@@ -0,0 +1,23 @@
+require 'spec_helper'
+
+describe CrazyHarry do
+
+  let(:harry) { CrazyHarry }
+
+  it "should allow method chaining" do
+    harry.fragment('<script>STEAL COOKIE!</script><em>Place</em><p>Lodging</p><b>Location:</b>')
+      .redact!( unsafe: true, tags: 'em' )
+      .change!( from: 'b', to: 'h3' )
+      .translate!( from_text: 'Lodging', to_text: 'Hotel', add_attributes: { class: 'partner' } )
+      .to_s.should == 'Place <p class="partner">Hotel</p><h3 class="partner">Location:</h3>'
+  end
+
+  it "should not care about the chain order" do
+    harry.fragment('<script>STEAL COOKIE!</script><em>Place</em><p>Lodging</p><b>Location:</b>')
+      .translate!( from_text: 'Lodging', to_text: 'Hotel', add_attributes: { class: 'partner' } )
+      .redact!( unsafe: true, tags: 'em' )
+      .change!( from: 'b', to: 'h3' )
+      .to_s.should == 'Place <p class="partner">Hotel</p><h3 class="partner">Location:</h3>'
+  end
+
+end

data/spec/lib/change_spec.rb

@@ -0,0 +1,83 @@
+require 'spec_helper'
+
+describe CrazyHarry::Change do
+
+  #   Change br to p
+  #   Change b to h3 where b has text: "location"
+  #   Change b to em where b inside p
+  #
+  #   Add attribute: "partner" to all tags
+  #
+  #   Another ADS suggestion.  Not sure it if it needed for the first cut.
+  #   Transform "lodging" to "hotel"
+
+  context "change" do
+
+    let(:harry){ CrazyHarry }
+
+    it "should be able to change one tag to another" do
+      harry.fragment( '<b>Location:</b>' ).change!( from: 'b', to: 'h3' ).to_s.should == '<h3>Location:</h3>'
+    end
+
+    it "should unwrap unnecessary paragraphs" do
+      harry.fragment('<p><strong>Header</strong><br /></p>').change!(from: 'strong', to: 'h3').to_s.should == 
+        '<h3>Header</h3>'
+    end
+
+    it "should not unwrap paragraphs indiscriminately" do
+      harry.fragment('<p><b>Header</b><br />Content</p>').change!(from: 'b', to: 'h3').to_s.should ==
+        '<p><h3>Header</h3>Content</p>'
+    end
+
+    context "chaining" do
+
+       it "should be able to chain calls" do
+        harry.fragment(  '<b>Location:</b><br />Saigon' ).change!( from: 'b', to: 'h3').change!( from: 'br', to: 'p' ).to_s.should ==
+          '<h3>Location:</h3><p>Saigon</p>'
+      end
+
+      it "should not care about the order of the chain" do
+        harry.fragment(  '<b>Location:</b><br />Saigon' ).change!( from: 'br', to: 'p' ).change!( from: 'b', to: 'h3' ).to_s.should ==
+          '<h3>Location:</h3><p>Saigon</p>'
+      end
+
+    end
+
+    it "should be able to change all the tags it finds" do
+      harry.fragment( '<b>1</b><b>2</b><b>3</b>' ).change!( from: 'b', to: 'h3' ).to_s.should == '<h3>1</h3><h3>2</h3><h3>3</h3>'
+    end
+
+    it "should be able to change a span tag to a div" do
+      harry.fragment( '<span>Hotel Details</span>' ).change!( from: 'span', to: 'div' ).to_s.should == '<div>Hotel Details</div>'
+    end
+
+    it "should not change things that it isn't directed to" do
+      harry.fragment( '<h3>Hotel Details</h3>' ).change!( from: 'span', to: 'div' ).to_s.should == '<h3>Hotel Details</h3>'
+    end
+
+    it "shouldn't choke if it gets invalid tags" do
+      harry.fragment( '<h3>Hotel Details</h3>' ).change!( from: 'snoogenflozen', to: 'snarglebat' ).to_s.should == '<h3>Hotel Details</h3>'
+    end
+
+    context "targeting and scoping" do
+
+      it "should change all occurrences" do
+       harry.fragment( '<div><b>Hotels</b></div><p><b>Hotels</b></p><b>Tents</b><div><p><b>Campervan</b></p></div>' ).change!( from: 'b', to: 'em').to_s.should ==
+          '<div><em>Hotels</em></div><p><em>Hotels</em></p><em>Tents</em><div><p><em>Campervan</em></p></div>'
+      end
+
+      it "should be able to target changes by content" do
+        harry.fragment( 'Hot <b>hotels</b> in <b>Saigon</b>' ).change!( from: 'b', to: 'em', text: 'hotels' ).to_s.should ==
+          'Hot <em>hotels</em> in <b>Saigon</b>'
+      end
+
+      it "should be able to scope changes to specific blocks" do
+        harry.fragment( '<div><b>Hotels</b></div><p><b>Hotels</b></p><b>Tents</b>' ).change!( from: 'b', to: 'em', scope: 'p' ).to_s.should ==
+          '<div><b>Hotels</b></div><p><em>Hotels</em></p><b>Tents</b>'
+      end
+
+    end
+
+  end
+ 
+end

data/spec/lib/crazy_harry_spec.rb

@@ -0,0 +1,86 @@
+require 'spec_helper'
+
+describe CrazyHarry do
+  TAGS_TO_REMOVE = {
+      paragraph:  '<p></p>',
+      ul:         '<ul></ul>',
+      div:        '<div></div>'
+    }
+
+  let(:harry) { CrazyHarry }
+
+  context "default actions" do
+
+    it "should relentlessly remove br tags" do
+      harry.fragment('<p>hello</p><br /><strong>HELLO</strong><br /><br />').to_s.should == '<p>hello</p><strong>HELLO</strong>'
+    end
+
+    context "removing blank tags" do
+
+      TAGS_TO_REMOVE.each do |name,example|
+        it "should automatically remove blank #{name} tags" do
+          harry.fragment("#{example}<p>Hello!</p>").to_s.should == '<p>Hello!</p>'
+        end
+      end
+
+    end
+
+    context "inline tags to blocks" do
+
+      it "should automatically change br to p" do
+        harry.fragment( 'Hotel Details<br />' ).to_s.should == '<p>Hotel Details</p>'
+      end
+
+      it "should automatically change multiple br tags to a single p" do
+        harry.fragment(  'Hotel Details<br /><br /><br />' ).to_s.should == '<p>Hotel Details</p>'
+      end
+
+      it "should automatically clear whitespace when converting line-style to block-style" do
+         harry.fragment(  'hotel<br />        hostel      <br />').to_s.should == '<p>hotel</p><p>hostel</p>'
+      end
+
+      it "should automatically change all br tags to wrapped p tags" do
+        harry.fragment( 'hotel<br /> hostel<br /> tent<br />').to_s.should == '<p>hotel</p><p>hostel</p><p>tent</p>'
+      end
+
+      it "should automatically change all multiple br tags to wrapped tags" do
+        harry.fragment(  'hotel<br /><br /><br/> hostel<br /> tent<br />').to_s.should == '<p>hotel</p><p>hostel</p><p>tent</p>'
+      end
+
+      it "should automatically change leading inline tags to block tags" do
+        harry.fragment(  '<br /><br />hotel').to_s.should == '<p>hotel</p>'
+      end
+
+      it "should ignore stray inline tags if they don't appear relevant to the context" do
+        harry.fragment(  '<br /><br />hotel <br />hostel<br />').to_s.should == '<p>hotel</p><p>hostel</p>'
+      end
+
+    end
+
+    context "de-duping" do
+
+      it "should automatically de-dupe lists" do
+        harry.fragment('<ul><li>Duplicate.</li></ul><ul><li>Duplicate.</li></ul>').to_s.should == '<ul><li>Duplicate.</li></ul>'
+      end
+
+      it "should automatically de-dupe paragraphs" do
+        harry.fragment('<p>Lorem Ipsum</p><p>Lorem Ipsum</p>').to_s.should == '<p>Lorem Ipsum</p>'
+      end
+
+      it "should not remove duplicate content that exsists at a different markup level" do
+        harry.fragment('<p><strong>Location:</strong></p><strong>Location:</strong>').to_s.should == '<p><strong>Location:</strong></p><strong>Location:</strong>'
+      end
+
+      it "should not alter other content when it de-dupes" do
+        harry.fragment('<h3>Here</h3><p>Yep, here.</p><h3>Here</h3><p>Here again.</p>').to_s.should == '<h3>Here</h3><p>Yep, here.</p><p>Here again.</p>'
+      end
+
+      it "should de-dupe if the only content difference is whitespace" do
+        pending "Too complicated for the first cut."
+      end
+
+    end
+
+  end
+
+end

data/spec/lib/redact_spec.rb

@@ -0,0 +1,122 @@
+require 'spec_helper'
+
+describe CrazyHarry::Redact do
+
+  #   Strip all tags  -- should convert </p> and <br> to linebreaks by default
+  #   Strip tags from text: "HostelWorld"
+  #   Strip tags from text: "HostelWorld" inside h3
+  #
+  #   ADS suggested ability to remove tag and content, so 'kill'  Probably
+  #   more appropriate for script and image tags
+  #
+  #   Kill a where a has attribute: "nofollow", text: "visit Disneyland"
+  #   Kill img
+
+  let(:harry){ CrazyHarry }
+
+  context "strip all tags" do 
+
+    it "should be able to strip all tags" do
+      harry.fragment( "<b>a</b>b<br /><h3>c</h3><img src='blah.jpg' />" ).strip!.should == "a\nb\n\nc\n"
+    end
+
+  end
+
+  context "strip specific tags" do
+
+    it "should be able to strip unsafe tags" do
+      harry.fragment( 'Me steal <script>Cookie!</script>').redact!( unsafe: true ).to_s.should == 'Me steal'
+      harry.fragment( 'What is that <bloog>thing</bloog>?').redact!( unsafe: true ).to_s.should == 'What is that ?'
+    end
+
+    it "should allow the unsafe strip method to be overridden (it prunes by default)" do
+      fragment = 'Me steal <script>Cookie!</script>'
+      harry.fragment( fragment).redact!( unsafe: :escape ).to_s.should == 'Me steal &lt;script&gt;Cookie!&lt;/script&gt;'
+      harry.fragment( fragment).redact!( unsafe: :strip ).to_s.should == 'Me steal Cookie!'
+    end
+
+    it "should prune unsafe tags if called without any arguments" do
+      harry.fragment( 'Me steal <script>Cookie!</script>').redact!.to_s.should == 'Me steal'
+    end
+
+    it "should raise an error if asked for an unknown strip method" do
+      -> { harry.fragment( 'Any old thing').redact!( unsafe: 'magical_magic' ).to_s }.should raise_error(CrazyHarry::Redact::InvalidStripMethod)
+    end
+
+    it "should be able to strip a specific tag" do
+      harry.fragment( '<b>Location:</b><p>Saigon</p>' ).redact!( tags: 'b' ).to_s.should == "Location: <p>Saigon</p>"
+    end
+
+    it "should strip every occurrence of a tag" do
+      harry.fragment( '<b>Location:</b><p>Saigon</p><b>Rates:</b>' ).redact!( tags: 'b' ).to_s.should == "Location: <p>Saigon</p>Rates:"
+    end
+
+    it "should be able to strip multiple tags" do
+      harry.fragment( '<b>One</b><p>Saigon <em>Plaza</em></p>').redact!( tags: %w(b em)).to_s.should == "One <p>Saigon Plaza </p>"
+    end
+
+    it "should close a paragraph tag early if the fragment has an illegally nested header tag" do
+      harry.fragment( '<b>One</b><p>Saigon <h3>Plaza</h3></p>').redact!( tags: %w(b h3)).to_s.should == "One <p>Saigon </p>Plaza"
+    end
+
+    context "chaining and multiple arguments" do
+
+      it "should be able to chain calls" do
+        harry.fragment( '<b>Location:</b><script>Steal Cookie</script><em>Plaza</em>' ).redact!( tags: 'b' ).redact!( unsafe: true ).to_s.should ==
+          'Location: <em>Plaza</em>'
+      end
+
+      it "should accept multiple, different commands in a single call" do
+        harry.fragment( '<b>Location:</b><script>Steal Cookie</script><em>Plaza</em>' ).redact!( tags: 'b', unsafe: true ).to_s.should ==
+          'Location: <em>Plaza</em>'
+      end
+
+    end
+
+    context "whitespace and breaks" do
+
+      it "shouldn't add excessive extra whitespace" do
+        harry.fragment( '<b>Location: </b> <b>Prices:</b>' ).redact!( tags: 'b' ).to_s.should == 'Location: Prices:'
+      end
+
+      it "should add a newline after a stripped block element" do
+        harry.fragment( '<h3>Location:</h3><p>Lorem ipsum</p>' ).redact!( tags: 'h3' ).to_s.should == "Location:\n<p>Lorem ipsum</p>"
+      end
+
+    end
+
+    context "targeting and scope" do
+
+      it "should allow strip to be targeted by the tag content" do
+        harry.fragment( '<h3>Location:</h3><h3>Ho Chi Minh City</h3>' ).redact!( tags: 'h3', text: 'Location:' ).to_s.should ==
+          "Location:\n<h3>Ho Chi Minh City</h3>"
+      end
+
+      it "should allow strip to be targeted by an attribute" do
+        harry.fragment( '<h3 class="big">Big</h3><h3 class="red">Red</h3>').redact!( tags: 'h3', attributes: { class: 'red' } ).to_s.should ==
+          '<h3 class="big">Big</h3>Red'
+      end
+
+      it "should be able to scope changes to specific blocks" do
+        harry.fragment( '<div><b>Hotels</b></div><p><b>Hotels</b></p><b>Tents</b>' ).redact!( tags: 'b', scope: 'p' ).to_s.should ==
+          '<div><b>Hotels</b></div><p>Hotels </p><b>Tents</b>'
+      end
+
+      it "should allow strip to be targeted and scoped" do
+        harry.fragment( '<b>Location:</b><p><b>Big</b> <b>Bad</b> Hotel</p>' ).redact!( tags: 'b', scope: 'p', text: 'Big' ).to_s.should ==
+          '<b>Location:</b><p>Big <b>Bad</b> Hotel</p>'
+      end
+
+    end
+
+  end
+
+  context 'pruning' do
+
+    it 'should be able to prune a tag, removing the tag and its contents' do
+      harry.fragment( 'I do not want <h3>Big</h3> images.').redact!( tags: 'h3', prune: true ).to_s.should == 'I do not want images.'
+    end
+
+  end
+
+end

data/spec/lib/translate_spec.rb

@@ -0,0 +1,46 @@
+require 'spec_helper'
+
+describe CrazyHarry::Translate do
+
+  #   Add attribute: "partner" to all tags
+  #   Transform "lodging" to "hotel"
+
+  let(:harry) { CrazyHarry }
+
+  it "should be able to add an attribute to all tags" do
+    harry.fragment( '<b>a</b><h3>c</h3>' ).translate!( add_attributes: { class: 'from-partner'} ).to_s.should ==
+      '<b class="from-partner">a</b><h3 class="from-partner">c</h3>'
+  end
+
+  it "should be able to add multiple attributes to all tags" do
+    harry.fragment( '<b>a</b><h3>c</h3>' ).translate!( add_attributes: { class: 'boo', bubba: 'beau' } ).to_s.should ==
+      '<b class="boo" bubba="beau">a</b><h3 class="boo" bubba="beau">c</h3>'
+  end
+
+  it "should append information to existing attributes" do
+    harry.fragment( '<h3 class="red">Lorem</h3>' ).translate!( add_attributes: { class: 'from-partner'} ).to_s.should ==
+      '<h3 class="red from-partner">Lorem</h3>'
+  end
+
+  it "should be able to tranlate free text in the fragment, preservering case" do
+    harry.fragment( '<h3>Lodging</h3> lodging' ).translate!( from_text: 'lodging', to_text: 'hotel' ).to_s.should ==
+      '<h3>Hotel</h3> hotel'
+  end
+
+  context "targeting and scope" do
+
+    it "should only add attributes to targeted content"  do
+      harry.fragment( '<h3>Location:</h3><h3>Saigon</h3>' ).translate!( add_attributes: { class: 'partner' }, text: 'Location:' ).to_s.should ==
+        '<h3 class="partner">Location:</h3><h3>Saigon</h3>'
+    end
+
+    it "should be able to scope changes to specific blocks" do
+      harry.fragment( '<div><b>Hotel</b></div><p><b>Hotel</b></p><b>Tent</b>' ).translate!( add_attributes: { class: 'ugly' }, scope: 'p' ).to_s.should ==
+        '<div><b>Hotel</b></div><p><b class="ugly">Hotel</b></p><b>Tent</b>'
+    end
+
+  end
+
+
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,12 @@
+require 'rubygems'
+require 'bundler'
+require 'simplecov'
+
+SimpleCov.start if ENV["COVERAGE"]
+
+Bundler.require :default, :development
+
+require 'rspec'
+
+RSpec.configure do |config|
+end

metadata

@@ -0,0 +1,130 @@
+--- !ruby/object:Gem::Specification
+name: crazy_harry
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+  prerelease: 
+platform: ruby
+authors:
+- TA Tyree
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-06-26 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &2151932960 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2151932960
+- !ruby/object:Gem::Dependency
+  name: guard
+  requirement: &2151930220 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2151930220
+- !ruby/object:Gem::Dependency
+  name: guard-rspec
+  requirement: &2151928080 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2151928080
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: &2151940320 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2151940320
+- !ruby/object:Gem::Dependency
+  name: loofah
+  requirement: &2151939040 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2151939040
+description: CrazyHarry is a high-level html fragment sanitiser/cleaner based on Loofah.
+email:
+- todd.tyree@lonelyplanet.co.uk
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Guardfile
+- README.md
+- Rakefile
+- crazy_harry.gemspec
+- lib/crazy_harry.rb
+- lib/crazy_harry/base.rb
+- lib/crazy_harry/change.rb
+- lib/crazy_harry/default.rb
+- lib/crazy_harry/redact.rb
+- lib/crazy_harry/translate.rb
+- lib/crazy_harry/version.rb
+- rvmrc.example
+- spec/fixtures/golden_nugget.html
+- spec/fixtures/golden_nugget_corrected.html
+- spec/integration/crazy_harry_spec.rb
+- spec/lib/change_spec.rb
+- spec/lib/crazy_harry_spec.rb
+- spec/lib/redact_spec.rb
+- spec/lib/translate_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/lonelyplanet/crazy_harry
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: crazy_harry
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: A High level HTML fragment sanitizer.
+test_files:
+- spec/fixtures/golden_nugget.html
+- spec/fixtures/golden_nugget_corrected.html
+- spec/integration/crazy_harry_spec.rb
+- spec/lib/change_spec.rb
+- spec/lib/crazy_harry_spec.rb
+- spec/lib/redact_spec.rb
+- spec/lib/translate_spec.rb
+- spec/spec_helper.rb