pdfkit 0.4.6 → 0.5.2

data/.gitignore

@@ -20,3 +20,4 @@ pkg
 
 ## PROJECT::SPECIFIC
 .bundle
+spec/custom_wkhtmltopdf_path.rb

data/Gemfile

@@ -1,9 +1,3 @@
-source :rubygems
+source :gemcutter
 
-group :development do
-  gem "rspec", "~> 2.0.0.beta.8"
-  gem "rspec-core", "~> 2.0.0.beta.8"
-  gem "mocha"
-  gem "jeweler"
-  gem "rack"
-end
+gemspec

data/Gemfile.lock

@@ -1,35 +1,32 @@
+PATH
+  remote: .
+  specs:
+    pdfkit (0.5.2)
+
 GEM
   remote: http://rubygems.org/
   specs:
+    activesupport (3.0.9)
     diff-lcs (1.1.2)
-    gemcutter (0.6.1)
-    git (1.2.5)
-    jeweler (1.4.0)
-      gemcutter (>= 0.1.0)
-      git (>= 1.2.5)
-      rubyforge (>= 2.0.0)
-    json_pure (1.4.3)
-    mocha (0.9.8)
-      rake
-    rack (1.2.1)
-    rake (0.8.7)
-    rspec (2.0.0.beta.19)
-      rspec-core (= 2.0.0.beta.19)
-      rspec-expectations (= 2.0.0.beta.19)
-      rspec-mocks (= 2.0.0.beta.19)
-    rspec-core (2.0.0.beta.19)
-    rspec-expectations (2.0.0.beta.19)
-      diff-lcs (>= 1.1.2)
-    rspec-mocks (2.0.0.beta.19)
-    rubyforge (2.0.4)
-      json_pure (>= 1.1.7)
+    mocha (0.9.12)
+    rack (1.3.0)
+    rack-test (0.6.0)
+      rack (>= 1.0)
+    rspec (2.2.0)
+      rspec-core (~> 2.2)
+      rspec-expectations (~> 2.2)
+      rspec-mocks (~> 2.2)
+    rspec-core (2.6.4)
+    rspec-expectations (2.6.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.6.0)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  jeweler
-  mocha
-  rack
-  rspec (~> 2.0.0.beta.8)
-  rspec-core (~> 2.0.0.beta.8)
+  activesupport (>= 3.0.8)
+  mocha (>= 0.9.10)
+  pdfkit!
+  rack-test (>= 0.5.6)
+  rspec (~> 2.2.0)

data/History.md

@@ -0,0 +1,26 @@
+2011-07-02
+==================
+  * Bump to 0.5.2
+  * Fix of dealing with ActiveSupport::SafeBuffer >= 3.0.8.
+  * Fix for meta tag options getting dropped in REE 1.8.7.
+  * Fix on bundler environment detection.
+
+2011-06-17
+==================
+  * Bump to 0.5.1
+  * Fix for response body coming through as an array.
+  * Added root_url configuration for setup where a host my not know its own name.
+  * Awareness of Bundler when looking for the wkhtmltopdf executable.
+  * Fix for file data getting truncated in Ruby 1.8.6
+  * Fix for 0.5.0 release getting stuck rendering all requests as PDFs.
+  * More robust meta tag detection.
+
+2010-12-27
+==================
+  * Bump to 0.5.0
+  * Switched to popen - adds support for JRuby and Windows
+  * Pulled in support for pdf rendering conditions in middleware via Rémy Coutable
+  * Use `which` to try and determine path to wkhtmltopdf
+  * Removed wkhtmltopdf auto installer
+  * Changed :disable\_smart\_shrinking to false for default options.
+  * Added History.md

data/POST_INSTALL

@@ -1,8 +1,14 @@
 ******************************************************************
 
-Now install wkhtmltopdf binaries:
-Global: sudo `which pdfkit` --install-wkhtmltopdf
-or inside RVM folder: export TO=`which pdfkit | sed 's:/pdfkit:/wkhtmltopdf:'` && pdfkit --install-wkhtmltopdf
-(run pdfkit --help to see more options)
+Install wkhtmltopdf:
 
-******************************************************************
+1. Install by hand (recomended):
+
+        https://github.com/jdpace/PDFKit/wiki/Installing-WKHTMLTOPDF
+
+2. Try using the wkhtmltopdf-binary gem (mac + linux i386)
+
+        gem install wkhtmltopdf-binary
+
+
+******************************************************************

data/README.md

@@ -1,6 +1,6 @@
 # PDFKit
 
-Create PDFs using plain old HTML+CSS. Uses [wkhtmltopdf](http://github.com/antialize/wkhtmltopdf) on the backend which renders HTML using Webkit.
+Create PDFs using plain old HTML+CSS. Uses [wkhtmltopdf](http://github.com/antialize/wkhtmltopdf) on the back-end which renders HTML using Webkit.
 
 ## Install
 
@@ -9,24 +9,30 @@ Create PDFs using plain old HTML+CSS. Uses [wkhtmltopdf](http://github.com/antia
     gem install pdfkit
 
 ### wkhtmltopdf
- * **Automatic**: `sudo pdfkit --install-wkhtmltopdf`  
- install latest version into /usr/local/bin  
- (overwrite defaults with e.g. ARCHITECTURE=amd64 TO=/home/foo/bin)
- * By hand: http://code.google.com/p/wkhtmltopdf/downloads/list
+
+1. Install by hand (recommended):
+
+    <https://github.com/jdpace/PDFKit/wiki/Installing-WKHTMLTOPDF>
+
+2.  Try using the wkhtmltopdf-binary gem (mac + linux i386)
+
+        gem install wkhtmltopdf-binary
+
+*Note:* The automated installer has been removed.
 
 ## Usage
-    
+
     # PDFKit.new takes the HTML and any options for wkhtmltopdf
     # run `wkhtmltopdf --extended-help` for a full list of options
     kit = PDFKit.new(html, :page_size => 'Letter')
     kit.stylesheets << '/path/to/css/file'
-    
+
     # Git an inline PDF
     pdf = kit.to_pdf
-    
+
     # Save the PDF to a file
     file = kit.to_file('/path/to/save/pdf')
-    
+
     # PDFKit.new can optionally accept a URL or a File.
     # Stylesheets can not be added when source is provided as a URL of File.
     kit = PDFKit.new('http://google.com')
@@ -34,18 +40,19 @@ Create PDFs using plain old HTML+CSS. Uses [wkhtmltopdf](http://github.com/antia
 
     # Add any kind of option through meta tags
     PDFKit.new('<html><head><meta name="pdfkit-page_size" content="Letter")
-    
+
 ## Configuration
 
 If you're on Windows or you installed wkhtmltopdf by hand to a location other than /usr/local/bin you will need to tell PDFKit where the binary is. You can configure PDFKit like so:
 
     # config/initializers/pdfkit.rb
     PDFKit.configure do |config|
-      config.wkhtmltopdf = '/path/to/wkhtmltopdf'
-      config.default_options = {
-        :page_size => 'Legal',
-        :print_media_type => true
-      }
+      # config.wkhtmltopdf = '/path/to/wkhtmltopdf'
+      # config.default_options = {
+      #   :page_size => 'Legal',
+      #   :print_media_type => true
+      # }
+      # config.root_url = "http://localhost" # Use only if your external hostname is unavailable on the server.
     end
 
 ## Middleware
@@ -55,27 +62,61 @@ PDFKit comes with a middleware that allows users to get a PDF view of any page o
 ### Middleware Setup
 
 **Non-Rails Rack apps**
-   
+
     # in config.ru
     require 'pdfkit'
     use PDFKit::Middleware
-    
+
 **Rails apps**
 
     # in application.rb(Rails3) or environment.rb(Rails2)
     require 'pdfkit'
     config.middleware.use PDFKit::Middleware
-    
+
 **With PDFKit options**
 
     # options will be passed to PDFKit.new
     config.middleware.use PDFKit::Middleware, :print_media_type => true
 
+**With conditions to limit routes that can be generated in pdf**
+
+    # conditions can be regexps (either one or an array)
+    config.middleware.use PDFKit::Middleware, {}, :only => %r[^/public]
+    config.middleware.use PDFKit::Middleware, {}, :only => [%r[^/invoice], %r[^/public]]
+
+    # conditions can be strings (either one or an array)
+    config.middleware.use PDFKit::Middleware, {}, :only => '/public'
+    config.middleware.use PDFKit::Middleware, {}, :only => ['/invoice', '/public']
+
+## Troubleshooting
+
+*  **Single thread issue:** In development environments it is common to run a
+   single server process. This can cause issues when rendering your pdf
+   requires wkhtmltopdf to hit your server again (for images, js, css).
+   This is because the resource requests will get blocked by the initial
+   request and the initial request will be waiting on the resource
+   requests causing a deadlock.
+
+   This is usually not an issue in a production environment. To get
+   around this issue you may want to run a server with multiple workers
+   like Passenger or try to embed your resources within your HTML to
+   avoid extra HTTP requests.
+
+*  **Resources aren't included in the PDF:** Images, CSS, or JavaScript
+   does not seem to be downloading correctly in the PDF. This is due
+   to the fact that wkhtmltopdf does not know where to find those files.
+   Make sure you are using absolute paths (start with forward slash) to
+   your resources. If you are using PDFKit to generate PDFs from a raw
+   HTML source make sure you use complete paths (either file paths or
+   urls including the domain). In restrictive server environments the
+   root_url configuration may be what you are looking for change your
+   asset host.
+
 ## TODO
  - add amd64 support in --install-wkhtmltopdf
 
 ## Note on Patches/Pull Requests
- 
+
 * Fork the project.
 * Setup your development environment with: gem install bundler; bundle install
 * Make your feature addition or bug fix.

data/Rakefile

@@ -1,26 +1,7 @@
 require 'rubygems'
 require 'rake'
 require 'bundler'
-Bundler.require(:development)
-
-begin
-  require 'jeweler'
-  Jeweler::Tasks.new do |gem|
-    gem.name = "pdfkit"
-    gem.summary = %Q{HTML+CSS -> PDF}
-    gem.description = %Q{Uses wkhtmltopdf to create PDFs using HTML}
-    gem.email = "jared@codewordstudios.com"
-    gem.homepage = "http://github.com/jdpace/PDFKit"
-    gem.authors = ["jdpace"]
-    gem.add_development_dependency "rspec", "~> 2.0.0.beta.8"
-    gem.add_development_dependency "rspec-core", "~> 2.0.0.beta.8"
-    gem.add_development_dependency 'mocha'
-    gem.post_install_message = File.read('POST_INSTALL')
-  end
-  Jeweler::GemcutterTasks.new
-rescue LoadError
-  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
-end
+Bundler::GemHelper.install_tasks
 
 require 'rspec/core/rake_task'
 RSpec::Core::RakeTask.new(:spec) do |spec|
@@ -30,8 +11,6 @@ RSpec::Core::RakeTask.new(:rcov) do |spec|
   spec.rcov = true
 end
 
-task :spec => :check_dependencies
-
 task :default => :spec
 
 require 'rake/rdoctask'

data/lib/pdfkit/configuration.rb

@@ -1,12 +1,12 @@
 class PDFKit
   class Configuration
-    attr_accessor :meta_tag_prefix, :wkhtmltopdf, :default_options
+    attr_accessor :meta_tag_prefix, :default_options, :root_url
+    attr_writer :wkhtmltopdf
 
     def initialize
       @meta_tag_prefix = 'pdfkit-'
-      @wkhtmltopdf = '/usr/local/bin/wkhtmltopdf'
       @default_options = {
-        :disable_smart_shrinking => true,
+        :disable_smart_shrinking => false,
         :page_size => 'Letter',
         :margin_top => '0.75in',
         :margin_right => '0.75in',
@@ -15,6 +15,10 @@ class PDFKit
         :encoding => "UTF-8"
       }
     end
+
+    def wkhtmltopdf
+      @wkhtmltopdf ||= (defined?(Bundler::GemfileError) ? `bundle exec which wkhtmltopdf` : `which wkhtmltopdf`).chomp
+    end
   end
 
   class << self
@@ -28,14 +32,12 @@ class PDFKit
   #   PDFKit.configure do |config|
   #     config.wkhtmltopdf = '/usr/bin/wkhtmltopdf'
   #   end
-  
+
   def self.configuration
     @configuration ||= Configuration.new
   end
-  
-  
+
   def self.configure
-    self.configuration 
     yield(configuration)
   end
-end
+end

data/lib/pdfkit/middleware.rb

@@ -1,61 +1,79 @@
 class PDFKit
-  
+
   class Middleware
-    
-    def initialize(app, options = {})
-      @app = app
-      @options = options
+
+    def initialize(app, options = {}, conditions = {})
+      @app        = app
+      @options    = options
+      @conditions = conditions
     end
-        
+
     def call(env)
+      @request    = Rack::Request.new(env)
       @render_pdf = false
-      set_request_to_render_as_pdf(env) if env['PATH_INFO'].match(/\.pdf$/)
-      
+
+      set_request_to_render_as_pdf(env) if render_as_pdf?
       status, headers, response = @app.call(env)
-      
-      request = Rack::Request.new(env)
-      if @render_pdf && headers['Content-Type'] =~ /text\/html|application\/xhtml\+xml/
-        body = response.body
-        
-        body = translate_paths(body, env)
-        
-        pdf = PDFKit.new(body, @options)
-        body = pdf.to_pdf
-        
+
+      if rendering_pdf? && headers['Content-Type'] =~ /text\/html|application\/xhtml\+xml/
+        body = response.respond_to?(:body) ? response.body : response.join
+        body = body.join if body.is_a?(Array)
+        body = PDFKit.new(translate_paths(body, env), @options).to_pdf
+        response = [body]
+
         # Do not cache PDFs
         headers.delete('ETag')
         headers.delete('Cache-Control')
-        
-        headers["Content-Length"] = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
-        headers["Content-Type"] = "application/pdf"
-        
-        response = [body]
+
+        headers["Content-Length"]         = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
+        headers["Content-Type"]           = "application/pdf"
       end
-      
+
       [status, headers, response]
     end
-    
+
     private
-    
-      # Change relative paths to absolute
-      def translate_paths(body, env)
-        # Host with protocol
-        root = env['rack.url_scheme'] + "://" + env['HTTP_HOST'] + "/"
-        
-        body.gsub(/(href|src)=(['"])\/([^\"']*|[^"']*)['"]/,'\1=\2'+root+'\3\2')        
-      end
-    
-      def set_request_to_render_as_pdf(env)
-        @render_pdf = true
 
-        path = Pathname(env['PATH_INFO'])
-        ['PATH_INFO','REQUEST_URI'].each { |e| env[e] = path.to_s.sub(/#{path.extname}$/,'')  } if path.extname == '.pdf'
-        env['HTTP_ACCEPT'] = concat(env['HTTP_ACCEPT'], Rack::Mime.mime_type('.html'))
-      end
-      
-      def concat(accepts, type)
-        (accepts || '').split(',').unshift(type).compact.join(',')
+    # Change relative paths to absolute
+    def translate_paths(body, env)
+      # Host with protocol
+      root = PDFKit.configuration.root_url || "#{env['rack.url_scheme']}://#{env['HTTP_HOST']}/"
+
+      body.gsub(/(href|src)=(['"])\/([^\"']*|[^"']*)['"]/, '\1=\2' + root + '\3\2')
+    end
+
+    def rendering_pdf?
+      @render_pdf
+    end
+
+    def render_as_pdf?
+      request_path_is_pdf = @request.path.match(%r{\.pdf$})
+
+      if request_path_is_pdf && @conditions[:only]
+        rules = [@conditions[:only]].flatten
+        rules.any? do |pattern|
+          if pattern.is_a?(Regexp)
+            @request.path =~ pattern
+          else
+            @request.path[0, pattern.length] == pattern
+          end
+        end
+      else
+        request_path_is_pdf
       end
-  
+    end
+
+    def set_request_to_render_as_pdf(env)
+      @render_pdf = true
+      path = @request.path.sub(%r{\.pdf$}, '')
+      %w[PATH_INFO REQUEST_URI].each { |e| env[e] = path }
+      env['HTTP_ACCEPT'] = concat(env['HTTP_ACCEPT'], Rack::Mime.mime_type('.html'))
+      env["Rack-Middleware-PDFKit"] = "true"
+    end
+
+    def concat(accepts, type)
+      (accepts || '').split(',').unshift(type).compact.join(',')
+    end
+
   end
 end

data/lib/pdfkit/pdfkit.rb

@@ -3,45 +3,46 @@ class PDFKit
   class NoExecutableError < StandardError
     def initialize
       msg  = "No wkhtmltopdf executable found at #{PDFKit.configuration.wkhtmltopdf}\n"
-      msg << ">> Install wkhtmltopdf by hand or try running `pdfkit --install-wkhtmltopdf`"
+      msg << ">> Please install wkhtmltopdf - https://github.com/jdpace/PDFKit/wiki/Installing-WKHTMLTOPDF"
       super(msg)
     end
   end
-  
+
   class ImproperSourceError < StandardError
     def initialize(msg)
       super("Improper Source: #{msg}")
     end
   end
-  
+
   attr_accessor :source, :stylesheets
   attr_reader :options
-  
+
   def initialize(url_file_or_html, options = {})
     @source = Source.new(url_file_or_html)
-    
+
     @stylesheets = []
 
     @options = PDFKit.configuration.default_options.merge(options)
     @options.merge! find_options_in_meta(url_file_or_html) unless source.url?
     @options = normalize_options(@options)
-    
+
     raise NoExecutableError.new unless File.exists?(PDFKit.configuration.wkhtmltopdf)
   end
-  
-  def command
+
+  def command(path = nil)
     args = [executable]
     args += @options.to_a.flatten.compact
     args << '--quiet'
-    
+
     if @source.html?
       args << '-' # Get HTML from stdin
     else
       args << @source.to_s
     end
-    
-    args << '-' # Read PDF from stdout
-    args
+
+    args << (path || '-') # Write to file or stdout
+
+    args.map {|arg| %Q{"#{arg.gsub('"', '\"')}"}}
   end
 
   def executable
@@ -53,62 +54,62 @@ class PDFKit
       default.split('/').last
     end
   end
-  
-  def to_pdf
+
+  def to_pdf(path=nil)
     append_stylesheets
-    
-    pdf = Kernel.open('|-', "w+")
-    exec(*command) if pdf.nil?
-    pdf.puts(@source.to_s) if @source.html?
-    pdf.close_write
-    result = pdf.gets(nil)
-    pdf.close_read
-
-    raise "command failed: #{command.join(' ')}" if result.to_s.strip.empty?
+
+    args = command(path)
+    invoke = args.join(' ')
+
+    result = IO.popen(invoke, "wb+") do |pdf|
+      pdf.puts(@source.to_s) if @source.html?
+      pdf.close_write
+      pdf.gets(nil)
+    end
+    result = File.read(path) if path
+
+    raise "command failed: #{invoke}" if result.to_s.strip.empty?
     return result
   end
-  
+
   def to_file(path)
-    File.open(path,'w') {|file| file << self.to_pdf}
+    self.to_pdf(path)
+    File.new(path)
   end
-  
+
   protected
 
-    def find_options_in_meta(body)
-      pdfkit_meta_tags(body).inject({}) do |found, tag|
-        name = tag.attributes["name"].sub(/^#{PDFKit.configuration.meta_tag_prefix}/, '').to_sym
-        found.merge(name => tag.attributes["content"])
-      end
-    end
+    def find_options_in_meta(content)
+      # Read file if content is a File
+      content = content.read if content.is_a?(File)
 
-    def pdfkit_meta_tags(body)
-      require 'rexml/document'
-      xml_body = REXML::Document.new(body)
-      found = []
-      xml_body.elements.each("html/head/meta") do |tag|
-        found << tag if tag.attributes['name'].to_s =~ /^#{PDFKit.configuration.meta_tag_prefix}/
+      found = {}
+      content.scan(/<meta [^>]*>/) do |meta|
+        if meta.match(/name=["']#{PDFKit.configuration.meta_tag_prefix}/)
+          name = meta.scan(/name=["']#{PDFKit.configuration.meta_tag_prefix}([^"']*)/)[0][0]
+          found[name.to_sym] = meta.scan(/content=["']([^"']*)/)[0][0]
+        end
       end
+
       found
-    rescue # rexml random crash on invalid xml
-      []
     end
-  
+
     def style_tag_for(stylesheet)
       "<style>#{File.read(stylesheet)}</style>"
     end
-    
+
     def append_stylesheets
       raise ImproperSourceError.new('Stylesheets may only be added to an HTML source') if stylesheets.any? && !@source.html?
-      
+
       stylesheets.each do |stylesheet|
         if @source.to_s.match(/<\/head>/)
-          @source.to_s.gsub!(/(<\/head>)/, style_tag_for(stylesheet)+'\1')
+          @source = Source.new(@source.to_s.gsub(/(<\/head>)/, style_tag_for(stylesheet)+'\1'))
         else
           @source.to_s.insert(0, style_tag_for(stylesheet))
         end
       end
     end
-  
+
     def normalize_options(options)
       normalized_options = {}
 
@@ -119,11 +120,11 @@ class PDFKit
       end
       normalized_options
     end
-    
+
     def normalize_arg(arg)
       arg.to_s.downcase.gsub(/[^a-z0-9]/,'-')
     end
-    
+
     def normalize_value(value)
       case value
       when TrueClass
@@ -132,5 +133,5 @@ class PDFKit
         value.to_s
       end
     end
-  
-end
+
+end

data/lib/pdfkit/source.rb

@@ -1,13 +1,11 @@
 class PDFKit
-  
   class Source
-        
     def initialize(url_file_or_html)
       @source = url_file_or_html
     end
     
     def url?
-      @source.is_a?(String) && @source.match(/^http/)
+      @source.is_a?(String) && @source.match(/\Ahttp/)
     end
     
     def file?
@@ -21,7 +19,5 @@ class PDFKit
     def to_s
       file? ? @source.path : @source
     end
-    
   end
-  
-end
+end

data/lib/pdfkit/version.rb

@@ -0,0 +1,3 @@
+class PDFKit
+  VERSION = "0.5.2"
+end