html5-rack-tidy 0.2.3

data/README.md

@@ -0,0 +1,109 @@
+# Tidy Markup Cleaner for Rack
+
+*NOTE:* This is a fork of the rack-tidy gem.
+This fork only provides basic HTML5 Doctype support.
+
+Rack::Tidy cleans text/html markup by automatically 
+indenting and reformatting content. Best results are achieved 
+with valid markup, when you simply want to use this component 
+to produce clean (X)HTML rendered by templating systems such as ERb.
+
+Rack::Tidy relies on the power of the Tidy gem and defaults to settings
+based on convention. However, you can override these through configuration.
+
+For more information about the Rack specification, check out http://rack.rubyforge.org
+
+## Installation
+
+### Bundler:
+
+Add this to your Gemfile:
+
+    gem "html5-rack-tidy", "~> 0.2.3"
+
+With a local copy:
+
+    $ git clone git://github.com/customink/html5-rack-tidy.git
+
+And in your Gemfile:
+
+    gem "html5-rack-tidy", :path => "path/to/your/local/copy"
+
+### Command Line
+
+Prerequisites:
+
+  * Rack gem (sudo gem install rack)
+  * Tidy gem (sudo gem install tidy)
+
+Enter this at the command-line:
+
+    $ sudo gem install html5-rack-tidy
+
+With a local working copy:
+
+    $ git clone git://github.com/customink/html5-rack-tidy.git
+    $ rake build && sudo rake install
+
+## Usage
+
+### Basic Usage
+
+Rack::Tidy is implemented as a piece of Rack middleware and can be used with
+any Rack-based application. If your application includes a rackup (`.ru`) file
+or uses Rack::Builder to construct the application pipeline, simply require
+and use as follows:
+
+    require 'rack/tidy'
+
+    use Rack::Tidy
+    run app
+
+### Using with Rails
+
+Add this to your `config/environment.rb`:
+
+    # above Rails::Initializer block
+    require 'rack/tidy'
+
+    # inside Rails::Initializer block
+    config.middleware.use Rack::Tidy
+
+You should now see `Rack::Tidy` listed in the middleware pipeline:
+
+    rake middleware
+    
+### Configuration Options
+
+The Tidy gem requires setting an internal path variable that points to the Tidy library,
+which will differ per platform. Rack::Tidy defaults to '/usr/lib/libtidy.A.dylib'
+which is the default location for the Tidy gem on Mac Leopard. To override the constant,
+simply define it in your application's configuration file:
+        
+    TIDY_LIB = '/usr/lib/tidylib.so'
+
+Need Rack::Tidy to ignore certain paths? In your config, pass in an optional array of paths:
+
+    # Rails example
+    config.middleware.use Rack::Tidy, 
+      :ignore_paths => ['/admin', '/cms']
+
+Rack::Tidy relies on convention with regard to Tidy's configuration (see Rack::Tidy::Cleaner for details). If you want to override/set attributes supported by the Tidy gem, declare them in your configuration as an optional hash:
+
+    # Rails example
+    config.middleware.use Rack::Tidy,
+      'indent-spaces' => 4
+
+To specify the HTML5 Doctype:
+
+    config.middleware.use Rack::Tidy,
+      'doctype' => 'html5'
+
+See http://tidy.sourceforge.net/docs/quickref.html for Tidy gem config options
+
+## Copyright
+
+Copyright (c) 2009 Phil Misiowiec, Webficient LLC. See MIT-LICENSE for details.
+
+Modifications made by CustomInk, LLC (2011) without consent from Phil Misiowiec of Webficient, LLC as allowed by the licensing terms.
+

data/lib/rack/tidy.rb

@@ -0,0 +1,66 @@
+require 'rack'
+
+# = Tidy Markup Cleaner for Rack
+#
+# Rack::Tidy cleans text/html markup by automatically 
+# indenting and reformatting content. Best results are achieved 
+# with valid markup, when you simply want to use this component 
+# to produce clean (X)HTML rendered by templating systems such as ERb.
+#
+# Rack::Tidy relies on the power of the Tidy gem and defaults to settings
+# based on convention. However, you can override these through configuration.
+#
+# === Usage
+#
+# Within a rackup file (or with Rack::Builder):
+#   require 'rack/tidy'
+#   use Rack::Tidy,
+#     :ignore_paths => ['/admin', '/cms'],
+#     'indent-spaces' => 4
+#   run app
+#
+# Rails example:
+#   # above Rails::Initializer block
+#   require 'rack/tidy'
+#
+#   # inside Rails::Initializer block 
+#   config.middleware.use Rack::Tidy,
+#     :ignore_paths => ['/admin', '/cms'],
+#     'indent-spaces' => 4
+module Rack::Tidy
+  autoload :Cleaner, 'rack/tidy/cleaner'
+  
+
+  # look for libtidy lib in different OSes
+  def self.find_libtidy_path
+    [ "/usr/lib64/libtidy.so",    # CentOs 64bit
+      "/usr/lib/libtidy.so",      # CentOs/Fedora
+      "/usr/lib/tidylib.so",     # (Ubuntu)
+      "/usr/lib/libtidy.A.dylib", # MacOS / default
+    ].each{|p|
+      if File.exist?(p) 
+        puts "Found libtidy in: #{p}"
+        return p         
+      end
+    }
+    puts "html5-rack-tidy couldn't find the libtidy library in your system"
+    puts "Run:  yum install libtidy-devel on Fedora/CentOS"
+    raise "libtidy NOT FOUND!"
+  end
+  
+  
+  # Specify path of Tidy library, e.g.
+  #   "/usr/lib/libtidy.A.dylib" (Mac; also the default if not set)
+  #   "/usr/lib/tidylib.so" (Ubuntu)
+  #   "/usr/lib/libtidy-0.99.so.0" (Fedora/CentOS)
+  TIDY_LIB = defined?(::TIDY_LIB) ? ::TIDY_LIB : find_libtidy_path
+  
+  # Create a new Rack::Tidy middleware component that cleans text/html markup
+  # using the Tidy gem. The +options+ Hash can be used to specify which paths
+  # should be ignored during processing as well as Tidy gem configuration values. 
+  # See Cleaner for defaults and http://tidy.sourceforge.net/docs/quickref.html 
+  # for more options
+  def self.new(backend, options = {})
+    Cleaner.new(backend, options)
+  end
+end

data/lib/rack/tidy/cleaner.rb

@@ -0,0 +1,71 @@
+require 'tidy'
+
+module Rack::Tidy
+  # This class is the interface between Rack and the Tidy gem
+  class Cleaner
+    
+    # Defaults for the Tidy gem config
+    DEFAULT_TIDY_OPTS = {
+      'char-encoding'     => 'utf8',
+      'indent'            => true,
+      'indent-spaces'     => 2,
+      'tidy-mark'         => false,
+      'wrap'              => 0 }
+          
+    # Tidy gem options, see http://tidy.sourceforge.net/docs/quickref.html
+    attr_accessor :tidy_options
+    
+    # Paths to be ignored during Rack::Tidy processing
+    attr_accessor :ignore_paths
+                
+    def initialize(app, options = {})
+      ::Tidy.path = TIDY_LIB
+      @app = app
+      self.ignore_paths = options[:ignore_paths] || []
+      self.tidy_options = DEFAULT_TIDY_OPTS.merge(options)
+    end
+    
+    # method required by Rack interface
+    def call(env)
+      call! env
+    end
+
+    # thread safe version using shallow copy of env
+    def call!(env)
+      @env = env.dup
+      status, @headers, response = @app.call(@env)      
+      if should_clean?
+        @headers.delete('Content-Length')
+        response = Rack::Response.new(
+          tidy_markup(response.respond_to?(:body) ? response.body : response),
+          status,
+          @headers
+        )
+        response.finish
+        response.to_a
+      else
+        [status, @headers, response]
+      end
+    end
+    
+    private
+              
+      def should_clean? #:nodoc:
+        @headers["Content-Type"] && 
+        @headers["Content-Type"].include?("text/html") &&         
+        self.ignore_paths.none? { |p| @env["PATH_INFO"].start_with?(p) }
+      end
+      
+      def tidy_markup(content) #:nodoc:
+        # Brow beat in HTML5 Doctype support
+        cfg = self.tidy_options
+        if cfg['doctype'] == 'html5'
+          doctype = "<!DOCTYPE html>\n\n"
+          cfg['doctype'] = 'omit'
+        end
+        ##
+
+        ::Tidy.open(self.tidy_options) { |tidy| (doctype||'') + tidy.clean(content) }
+      end
+  end
+end

metadata

@@ -0,0 +1,198 @@
+--- !ruby/object:Gem::Specification 
+name: html5-rack-tidy
+version: !ruby/object:Gem::Version 
+  hash: 17
+  prerelease: 
+  segments: 
+  - 0
+  - 2
+  - 3
+  version: 0.2.3
+platform: ruby
+authors: 
+- Phil Misiowiec
+- Robert Bialek
+- CustomInk, LLC
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-06-01 00:00:00 -04:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 1
+        - 0
+        - 0
+        version: 1.0.0
+  requirement: *id001
+  prerelease: false
+  name: bundler
+  type: :development
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 15
+        segments: 
+        - 1
+        - 6
+        - 0
+        version: 1.6.0
+  requirement: *id002
+  prerelease: false
+  name: jeweler
+  type: :development
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 41
+        segments: 
+        - 0
+        - 9
+        - 9
+        version: 0.9.9
+  requirement: *id003
+  prerelease: false
+  name: rcov
+  type: :development
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 27
+        segments: 
+        - 1
+        - 3
+        - 0
+        version: 1.3.0
+  requirement: *id004
+  prerelease: false
+  name: rack
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 1
+        - 1
+        - 2
+        version: 1.1.2
+  requirement: *id005
+  prerelease: false
+  name: tidy
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 15
+        segments: 
+        - 1
+        - 6
+        - 0
+        version: 1.6.0
+  requirement: *id006
+  prerelease: false
+  name: jeweler
+  type: :development
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 27
+        segments: 
+        - 1
+        - 2
+        - 2
+        version: 1.2.2
+  requirement: *id007
+  prerelease: false
+  name: redgreen
+  type: :development
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id008 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 37
+        segments: 
+        - 2
+        - 11
+        - 3
+        version: 2.11.3
+  requirement: *id008
+  prerelease: false
+  name: shoulda
+  type: :development
+description: Rack middleware for automatically cleaning markup using Tidy. Now with HTML5 support!
+email: rubygems@customink.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.md
+files: 
+- lib/rack/tidy.rb
+- lib/rack/tidy/cleaner.rb
+- README.md
+has_rdoc: true
+homepage: http://github.com/customink/html5-rack-tidy
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.4.0
+signing_key: 
+specification_version: 3
+summary: Rack middleware for automatically cleaning markup using Tidy
+test_files: []
+