wkhtml 0.0.1

data/lib/wkhtml/to_pdf/global_settings.rb

@@ -0,0 +1,73 @@
+module WkHtml
+  module ToPdf
+    class GlobalSettings
+      include Settings
+      
+      KEYS = %w(
+        size.paperSize
+        size.width
+        size.height
+        orientation
+        colorMode
+        resolution
+        dpi
+        pageOffset
+        copies
+        collate
+        outline
+        outlineDepth
+        dumpOutline
+        out
+        documentTitle
+        useCompression
+        margin.top
+        margin.bottom
+        margin.left
+        margin.right
+        imageDPI
+        imageQuality
+        load.cookieJar
+      )
+      DEFAULTS = {}
+
+      self.settings = KEYS
+      self.default_settings = DEFAULTS
+
+      def out=(v)
+        v = CommonSettings::cleanup_path(v)
+        raise ArgumentError.new("#{v} is not writeable") unless CommonSettings::writable?(v)
+        self['out'] = v
+      end
+
+      def stdout=(v)
+        self.out = v ? CommonSettings::STDOUT : nil
+      end
+    end
+  end
+end
+
+
+__END__
+size.paperSize The paper size of the output document, e.g. "A4".
+size.width The with of the output document, e.g. "4cm".
+size.height The height of the output document, e.g. "12in".
+orientation The orientation of the output document, must be either "Landscape" or "Portrait".
+colorMode Should the output be printed in color or gray scale, must be either "Color" or "Grayscale"
+resolution Most likely has no effect.
+dpi What dpi should we use when printing, e.g. "80".
+pageOffset A number that is added to all page numbers when printing headers, footers and table of content.
+copies How many copies should we print?. e.g. "2".
+collate Should the copies be collated? Must be either "true" or "false".
+outline Should a outline (table of content in the sidebar) be generated and put into the PDF? Must be either "true" or false".
+outlineDepth The maximal depth of the outline, e.g. "4".
+dumpOutline If not set to the empty string a XML representation of the outline is dumped to this file.
+out The path of the output file, if "-" output is sent to stdout, if empty the output is stored in a buffer.
+documentTitle The title of the PDF document.
+useCompression Should we use loss less compression when creating the pdf file? Must be either "true" or "false".
+margin.top Size of the top margin, e.g. "2cm"
+margin.bottom Size of the bottom margin, e.g. "2cm"
+margin.left Size of the left margin, e.g. "2cm"
+margin.right Size of the right margin, e.g. "2cm"
+imageDPI The maximal DPI to use for images in the pdf document.
+imageQuality The jpeg compression factor to use when producing the pdf document, e.g. "92".
+load.cookieJar Path of file used to load and store cookies.

data/lib/wkhtml/to_pdf/object_settings.rb

@@ -0,0 +1,59 @@
+module WkHtml
+  module ToPdf
+    class ObjectSettings
+      include Settings
+
+      KEYS = %w(
+        toc.useDottedLines
+        toc.captionText
+        toc.forwardLinks
+        toc.backLinks
+        toc.indentation
+        toc.fontScale
+        page
+        useExternalLinks
+        useLocalLinks
+        replacements TODO
+        produceForms
+        includeInOutline
+        pagesCount
+        tocXsl
+      )
+      DEFAULTS = {}
+
+      self.settings = HeaderSettings::KEYS + WebSettings::KEYS + LoadSettings::KEYS + KEYS
+      self.default_settings = DEFAULTS
+
+      def page=(v)
+        v = CommonSettings::cleanup_path(v)
+        raise ArgumentError.new("#{v} is missing or not readable") unless CommonSettings::readable?(v)
+        self['page'] = v
+      end
+
+      def stdin=(v)
+        self.in = v ? CommonSettings::STDIN : ''
+      end
+    end
+  end
+end
+
+
+__END__
+toc.useDottedLines Should we use a dotted line when creating a table of content? Must be either "true" or "false".
+toc.captionText The caption to use when creating a table of content.
+toc.forwardLinks Should we create links from the table of content into the actual content? Must be either "true or "false.
+toc.backLinks Should we link back from the content to this table of content.
+toc.indentation The indentation used for every table of content level, e.g. "2em".
+toc.fontScale How much should we scale down the font for every toc level? E.g. "0.8"
+page The URL or path of the web page to convert, if "-" input is read from stdin.
+header.* Header specific settings see Header and footer settings.
+footer.* Footer specific settings see Header and footer settings.
+useExternalLinks Should external links in the HTML document be converted into external pdf links? Must be either "true" or "false.
+useLocalLinks Should internal links in the HTML document be converted into pdf references? Must be either "true" or "false"
+replacements TODO
+produceForms Should we turn HTML forms into PDF forms? Must be either "true" or file".
+load.* Page specific settings related to loading content, see Object Specific loading settings.
+web.* See Web page specific settings.
+includeInOutline Should the sections from this document be included in the outline and table of content?
+pagesCount Should we count the pages of this document, in the counter used for TOC, headers and footers?
+tocXsl If not empty this object is a table of content object, "page" is ignored and this xsl style sheet is used to convert the outline XML into a table of content.

data/lib/wkhtml/version.rb

@@ -0,0 +1,3 @@
+module WkHtml
+  VERSION = "0.0.1"
+end

data/lib/wkhtml/web_settings.rb

@@ -0,0 +1,28 @@
+module WkHtml
+  module WebSettings
+    PREFIX = 'web'
+    KEYS = %w(
+      background
+      loadImages
+      enableJavascript
+      enableIntelligentShrinking
+      minimumFontSize
+      printMediaType
+      defaultEncoding
+      userStyleSheet
+      enablePlugins
+    ).map!{|k| "#{PREFIX}.#{k}" }
+  end
+end
+
+
+__END__
+web.background Should we print the background? Must be either "true" or "false".
+web.loadImages Should we load images? Must be either "true" or "false".
+web.enableJavascript Should we enable javascript? Must be either "true" or "false".
+web.enableIntelligentShrinking Should we enable intelligent shrinkng to fit more content on one page? Must be either "true" or "false". Has no effect for wkhtmltoimage.
+web.minimumFontSize The minimum font size allowed. E.g. "9"
+web.printMediaType Should the content be printed using the print media type instead of the screen media type. Must be either "true" or "false". Has no effect for wkhtmltoimage.
+web.defaultEncoding What encoding should we guess content is using if they do not specify it properly? E.g. "utf-8"
+web.userStyleSheet Url er path to a user specified style sheet.
+web.enablePlugins Should we enable NS plugins, must be either "true" or "false". Enabling this will have limited success.

data/spec/spec_helper.rb

@@ -0,0 +1,98 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+require 'wkhtml'
+
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://rspec.info/blog/2012/06/rspecs-new-expectation-syntax/
+  #   - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://rspec.info/blog/2014/05/notable-changes-in-rspec-3/#zero-monkey-patching-mode
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end

data/spec/support/format.rb

@@ -0,0 +1,18 @@
+{
+  'jpg' => "\xFF\xD8\xFF\xE0",
+  'pdf' => '%PDF-',
+  'png' => "\x89\x50\x4E\x47\x0D\x0A\x1A\x0A",
+  'svg' => '<?xml',
+  'bmp' => "\x42\x4d"
+}.each do |format,magic|
+  magic.force_encoding(Encoding::BINARY)
+  
+  RSpec::Matchers.define :"be_#{format}" do
+    match do |output|
+      output = output.dup()
+      output.force_encoding(Encoding::BINARY)
+      output = output[0..magic.size]
+      output.start_with?(magic)
+    end
+  end
+end

data/spec/support/settings.rb

@@ -0,0 +1,65 @@
+require 'spec_helper'
+
+RSpec.shared_examples 'settings' do |boolean_setting|
+  let(:settings){ described_class.new() }
+  
+  describe '#initialize' do
+    it 'takes initial settings' do
+      obj = described_class.new({boolean_setting => 'true'})
+      expect(obj[boolean_setting]).to eql('true')
+    end
+    
+    it 'uses defaults' do
+      obj = Class.new(described_class) do
+        self.default_settings = {boolean_setting => 'true'}
+      end.new()
+      expect(obj[boolean_setting]).to eql('true')
+    end
+    
+    it 'will override defaults' do
+      obj = Class.new(described_class) do
+        self.default_settings = {boolean_setting => 'true'}
+      end.new({
+        boolean_setting => 'false'
+      })
+      expect(obj[boolean_setting]).to eql('false')
+    end
+  end
+  
+  describe '#to_hash' do
+    it 'contains setting' do
+      settings[boolean_setting] = 'true'
+      expect(settings.to_hash[boolean_setting]).to eql('true')
+    end
+    
+    it 'has an alias' do
+      expect{settings.to_h}.not_to raise_error
+    end
+  end
+  
+  describe '#settings=' do
+    let(:mock) do
+      Class.new(described_class) do
+        self.settings = ['blah']
+      end
+    end
+    
+    it 'defines method getter' do
+      expect(mock.instance_methods).to include(:blah)
+    end
+    
+    it 'defines method setter' do
+      expect(mock.instance_methods).to include(:blah=)
+    end
+    
+    it 'defined method can set' do
+      settings.__send__(:"#{boolean_setting}=", 'true')
+      expect(settings[boolean_setting]).to eql('true')
+    end
+    
+    it 'defined method can get' do
+      settings[boolean_setting] = 'true'
+      expect(settings.__send__(:"#{boolean_setting}")).to eql('true')
+    end
+  end
+end

data/spec/support/test.html

@@ -0,0 +1 @@
+<html><bod>My Test</body></html>

data/spec/support/to_x_settings.rb

@@ -0,0 +1,39 @@
+require 'spec_helper'
+
+RSpec.shared_examples 'to_x_settings' do |boolean_setting|
+  let(:settings){ described_class.new() }
+  
+  describe '#initialize' do
+    it 'can create' do
+      expect(settings).not_to be_nil
+    end
+  end
+  
+  describe '#[]' do
+    it 'can get' do
+      expect{ settings[boolean_setting] }.to_not raise_error
+    end
+    
+    it 'raises error when unknown' do
+      expect{ settings['blah'] }.to raise_error(ArgumentError)
+    end
+    
+    it 'can use a symbol' do
+      expect{ settings[boolean_setting.to_sym] }.to_not raise_error
+    end
+  end
+  
+  describe '#[]=' do
+    it 'can set' do
+      expect(settings[boolean_setting] = 'true').to eq('true')
+    end
+    
+    it 'raises error when unknown' do
+      expect{ settings['blah'] = '' }.to raise_error(ArgumentError)
+    end
+    
+    it 'can use a symbol' do
+      expect(settings[boolean_setting.to_sym] = 'true').to eq('true')
+    end
+  end
+end

data/spec/wkhtml/converter_spec.rb

@@ -0,0 +1,80 @@
+require 'spec_helper'
+require 'support/format'
+require 'tempfile'
+
+RSpec.describe WkHtml::Converter do
+  let(:html_content) {'<html><bod>My Test</body></html>'}
+  let(:html){ WkHtml::Converter.new(html_content) }
+  let(:uri){ WkHtml::Converter.new('http://example.com/') }
+  let(:file){ WkHtml::Converter.new(File.new(File.join(File.dirname(__FILE__), '..', 'support', 'test.html'))) }
+  
+  #Test a bunch of variations
+  ['jpg', 'pdf', 'png', 'bmp', 'svg'].each do |format|
+    ['internal', 'external'].each do |location|
+      context location do
+        describe '#to_image' do
+          it "returns a #{format}" do
+            convert = location == 'internal' ? html : uri
+            expect(convert.to_image(format)).to __send__(:"be_#{format}")
+          end
+        end
+        
+        describe "#to_#{format}" do
+          it "returns a #{format}" do
+            convert = location == 'internal' ? html : uri
+            expect(convert.to_image(format)).to __send__(:"be_#{format}")
+          end
+        end
+        
+        describe '#to_file' do
+          it "to write a #{format}" do
+            Tempfile.open('wkhtml') do |file|
+              convert = location == 'internal' ? html : uri
+              convert.to_file(file.path, format)
+              expect(IO.read(file)).to __send__(:"be_#{format}")
+            end
+          end
+        end
+      end
+    end
+  end
+  
+  describe '#initialize' do
+    it 'receives initial options' do
+      convert = WkHtml::Converter.new(html_content, {'documentTitle' => 'Here Is My Test'})
+      expect(convert.to_pdf().force_encoding(Encoding::BINARY)).to include("/Title (\xFE\xFF\x00H\x00e\x00r\x00e\x00 \x00I\x00s\x00 \x00M\x00y\x00 \x00T\x00e\x00s\x00t)".force_encoding(Encoding::BINARY))
+    end
+    
+    it 'can use a file' do
+      convert = file
+      expect(convert.to_pdf()).to be_pdf
+      expect(convert.to_jpg()).to be_jpg
+    end
+  end
+  
+  describe '#to_image' do
+    it 'raises when file is missing' do
+      temp = Tempfile.new('wkhtml')
+      file = File.new(temp.path)
+      temp.close()
+      temp.unlink()
+      convert = WkHtml::Converter.new(file)
+      expect{convert.to_image('pdf')}.to raise_error(ArgumentError)
+      expect{convert.to_image('jpg')}.to raise_error(ArgumentError)
+    end
+  end
+  
+  describe '#to_file' do
+    it 'creates when file is missing' do
+      temp = Tempfile.new('wkhtml')
+      file = File.new(temp.path)
+      temp.close()
+      temp.unlink()
+      convert = html
+      
+      expect(convert.to_file(file, 'pdf')).to eql(file.path)
+      expect(convert.to_file(file, 'jpg')).to eql(file.path)
+      expect(File.exists?(file.path)).to be true
+    end
+  end
+end