wbzyl-rack-htmltidy 0.0.6

data/README.markdown

@@ -0,0 +1,70 @@
+# Rack::HTMLTidy
+
+*Rack::HTMLTidy* is a middleware that adds HTML validation
+for Rack applications. It uses Dave's Raggett HTML Tidy
+to check HTML pages. The results are written to log.
+The middleware uses the 
+[*TidyLib* C library](http://tidy.sourceforge.net/)
+and the 
+[*tidy*](http://github.com/ak47/tidy/) gem.
+
+The idea of using middleware to validate HTML belongs to
+Marcin Kulik, [Rack middleware using HTML
+Tidy](http://sickill.net/blog/2009/05/10/rack-middleware-using-html-tidy.html).
+
+**Limitations of [TidyLib](http://tidy.sourceforge.net/libintro.html)**:
+Currently, all character encoding support is hard wired into the
+library. This means we do a poor job of supporting many popular
+encodings such as GB2312, euc-kr, eastern European languages,
+cyrillic, etc. Any of these languages must first be transcoded into
+ISO-10646/Unicode before Tidy can work with it.
+
+## Using with Rack application
+
+*Rack::HTMLTidy* can be used with any Rack application,
+for example with a **Sinatra** application.
+If your application includes a rackup file
+or uses *Rack::Builder* to construct the application pipeline, 
+simply require and use as follows:
+
+    gem 'wbzyl-rack-htmltidy'
+    require 'rack/htmltidy'
+
+    use Rack::HTMLTidy, :errors => true, :diagnostics => true, :path => "/usr/lib/libtidy-0.99.so.0"
+
+    run app
+
+Remember to update the `:path` option to the location of *TidyLib* on your system.
+
+## Using with Rails 2.3.2
+
+In order to use include the following in a Rails application
+*config/environment.rb* file:
+
+    require 'rack/htmltidy'
+
+    Rails::Initializer.run do |config|  
+      config.gem "rack-htmltidy"
+      config.middleware.use(Rack::HTMLTidy,
+        :errors => true, 
+        :diagnostics => true,
+        :path => "/usr/lib/libtidy-0.99.so.0")
+    end  
+
+Check the Rack configuration:
+
+    rake middleware
+
+Remember to update the `:path` option to the location of *TidyLib* on your system.
+
+
+## Miscellaneous stuff
+
+To install *TidyLib* on Fedora 9 and above:
+
+    yum install libtidy libtidy-devel
+
+To fix this bug: `tidybuf.rb:40: [BUG] Segmentation fault`,
+clone, build and install the *tidy* gem from here:
+
+    git://github.com/ak47/tidy.git

data/Rakefile

@@ -0,0 +1,24 @@
+require "rake"
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gemspec|
+    gemspec.name         = "rack-htmltidy"
+    gemspec.summary      = "HTML Tidy."
+    gemspec.email        = "matwb@univ.gda.pl"  
+    gemspec.homepage     = "http://github.com/wbzyl/rack-tidy"
+    gemspec.authors      = ["Wlodek Bzyl"]
+    gemspec.description  = gemspec.summary
+    
+    gemspec.files = %w[LICENSE Rakefile VERSION.yml] + FileList['lib/**/*.rb']
+    
+    gemspec.add_runtime_dependency 'rack', '>=1.0.0'
+    gemspec.add_runtime_dependency 'tidy', '>=1.1.2'  # patched
+    
+    gemspec.add_development_dependency 'rack-test', '>=0.3.0'
+  end
+rescue LoadError
+  puts "Jeweler not available."
+  puts "Install it with:"
+  puts "  sudo gem install technicalpickles-jeweler -s http://gems.github.com"
+end

data/VERSION.yml

@@ -0,0 +1,4 @@
+--- 
+:patch: 6
+:major: 0
+:minor: 0

data/lib/rack/htmltidy.rb

@@ -0,0 +1,63 @@
+gem 'rack'
+require 'rack/utils'
+
+gem 'tidy'
+require 'tidy'
+
+module Rack
+  class HTMLTidy
+    include Rack::Utils
+    
+    FORMAT = %{|| Tidy: %s - [%s] "%s %s%s %s"\n%s}
+
+    def initialize(app, opts={})
+      @app = app
+      @errors = opts[:errors] || false
+      @diagnostics = opts[:diagnostics] || false
+      @logger = opts[:logger]
+      
+      @path = opts[:path] || "/usr/lib/libtidy-0.99.so.0"      
+      ::Tidy.path = @path
+    end
+ 
+    def call(env)
+      status, headers, response = @app.call(env)
+
+      headers = HeaderHash.new(headers)
+
+      if !STATUS_WITH_NO_ENTITY_BODY.include?(status) &&
+         !headers['transfer-encoding'] &&
+          headers['content-type'] &&
+          headers['content-type'].include?("text/html")
+
+        ::Tidy.open(:show_warnings => true, "char-encoding" => "utf8") do |tidy|
+          html = ""
+          response.each { |part| html += part }
+          tidy.clean(html)
+          log(env, tidy, "errors") if @errors && tidy.errors.length > 0
+          log(env, tidy, "diagnostics") if @diagnostics && tidy.diagnostics.length > 0
+        end
+      end
+      
+      [status, headers, response]
+    end
+    
+    private
+
+    def log(env, tidy, what)
+      now = Time.now
+      logger = @logger || env['rack.errors']
+      
+      logger.write FORMAT % [
+        what,
+        now.strftime("%d/%b/%Y %H:%M:%S"),
+        env["REQUEST_METHOD"],
+        env["PATH_INFO"],
+        env["QUERY_STRING"].empty? ? "" : "?"+env["QUERY_STRING"],
+        env["HTTP_VERSION"],
+        tidy.send(what)
+      ]
+    end
+    
+  end
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification 
+name: wbzyl-rack-htmltidy
+version: !ruby/object:Gem::Version 
+  version: 0.0.6
+platform: ruby
+authors: 
+- Wlodek Bzyl
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-06-05 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rack
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.0.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: tidy
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.1.2
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: rack-test
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.3.0
+    version: 
+description: HTML Tidy.
+email: matwb@univ.gda.pl
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.markdown
+files: 
+- LICENSE
+- Rakefile
+- VERSION.yml
+- lib/rack/htmltidy.rb
+- README.markdown
+has_rdoc: false
+homepage: http://github.com/wbzyl/rack-tidy
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 3
+summary: HTML Tidy.
+test_files: []
+