pdf-service 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c68e174f54c08dcf6e7cb9717b0bb1f9c961016c
+  data.tar.gz: 6fc105d8bbce42a338d0dee58c9b23b67e7a4b53
+SHA512:
+  metadata.gz: 535afcffe1197183dc970bae0cbb709de93ca06e07bf3dbb3975851e81a59252f7edd2cac161695d3555c13207ff1da965be3154ea999d40a2f121c6678951f6
+  data.tar.gz: d25c8b21e997e1ca49de05a2575e79b46d5e61cd69d9527a1c585f7d609cc8594dd6bf18b41ea6c6c5bc5d1b97ed490bdd3e6dcfea964ecf5cacc27f5d74442e

data/lib/pdf_service.rb

@@ -0,0 +1,26 @@
+require 'pathname'
+require 'shellwords'
+require 'logger'
+require 'securerandom'
+require 'digest/sha2'
+require 'pdf_service/error'
+require 'pdf_service/config'
+require 'pdf_service/utils/tempfile_service'
+require 'pdf_service/utils/null_logger'
+require 'pdf_service/phantom_js_renderer'
+require 'pdf_service/service'
+
+
+module PDFService
+  ROOT_PATH = Pathname(__FILE__).dirname
+  DefaultConfiguration = Config.new
+
+
+  def self.with_config(config)
+    Service.new(Config[config])
+  end
+
+  def self.render(html)
+    with_config(DefaultConfiguration).render(html)
+  end
+end

data/lib/pdf_service/config.rb

@@ -0,0 +1,17 @@
+module PDFService
+  class Config
+    def initialize(logger: Logger.new(STDOUT), tmp_path: '.')
+      @logger = logger
+      @tmp_path = tmp_path
+    end
+    attr_reader :logger
+    attr_reader :tmp_path
+
+    class << self
+      def [](value)
+        return value if value.kind_of?(self)
+        new(value.to_h)
+      end
+    end
+  end
+end

data/lib/pdf_service/error.rb

@@ -0,0 +1,3 @@
+module PDFService
+  Error = Class.new(StandardError)
+end

data/lib/pdf_service/phantom_js_renderer.rb

@@ -0,0 +1,26 @@
+require 'pathname'
+module PDFService
+  class PhantomJSRenderer
+    RASTERIZE_SCRIPT_PATH = Pathname(__FILE__).dirname.join('phantomjs_rasterize.js').to_s.freeze
+
+    def initialize(script: RASTERIZE_SCRIPT_PATH, logger: NullLogger.new, binary: 'phantomjs')
+      @script = script.freeze
+      @logger = logger
+      @binary = binary.freeze
+      Kernel.warn("Warning! PhantomJS is not available in PATH #{@binary}") if `which #{binary}`.strip.empty?
+    end
+    attr_reader :logger
+
+    def rasterize(url, output, format: 'A4')
+      options = [url, output, format]
+      phantomjs(@script, url, options)
+    end
+
+    private
+    def phantomjs(script_path, _, options = [])
+      command = Shellwords.join([@binary, script_path, *options.map(&:to_s)])
+      logger.debug('pdf renderer command: ' << command)
+      system(command) || raise(::PDFService::Error.new("could not render PDF file. phantomjs exited with exit code = 0"))
+    end
+  end
+end

data/lib/pdf_service/phantomjs_rasterize.js

@@ -0,0 +1,48 @@
+var page = require('webpage').create(),
+  system = require('system'),
+  address, output, size;
+
+if (system.args.length < 3 || system.args.length > 5) {
+  console.log('Usage: rasterize.js URL filename [paperwidth*paperheight|paperformat] [zoom]');
+  console.log('  paper (pdf output) examples: "5in*7.5in", "10cm*20cm", "A4", "Letter"');
+  console.log('  image (png/jpg output) examples: "1920px" entire page, window width 1920px');
+  console.log('                                   "800px*600px" window, clipped to 800x600');
+  phantom.exit(1);
+} else {
+  address = system.args[1];
+  output = system.args[2];
+  page.viewportSize = { width: 600, height: 600 };
+  if (system.args.length > 3 && system.args[2].substr(-4) === ".pdf") {
+    size = system.args[3].split('*');
+    page.paperSize = size.length === 2 ? { width: size[0], height: size[1], margin: '0px' }
+      : { format: system.args[3], orientation: 'portrait', margin: '1cm' };
+  } else if (system.args.length > 3 && system.args[3].substr(-2) === "px") {
+    size = system.args[3].split('*');
+    if (size.length === 2) {
+      pageWidth = parseInt(size[0], 10);
+      pageHeight = parseInt(size[1], 10);
+      page.viewportSize = { width: pageWidth, height: pageHeight };
+      page.clipRect = { top: 0, left: 0, width: pageWidth, height: pageHeight };
+    } else {
+      console.log("size:", system.args[3]);
+      pageWidth = parseInt(system.args[3], 10);
+      pageHeight = parseInt(pageWidth * 3/4, 10); // it's as good an assumption as any
+      console.log ("pageHeight:",pageHeight);
+      page.viewportSize = { width: pageWidth, height: pageHeight };
+    }
+  }
+  if (system.args.length > 4) {
+    page.zoomFactor = system.args[4];
+  }
+  page.open(address, function (status) {
+    if (status !== 'success') {
+      console.log('Unable to load the address!');
+      phantom.exit();
+    } else {
+      window.setTimeout(function () {
+        page.render(output);
+        phantom.exit();
+      }, 200);
+    }
+  });
+}

data/lib/pdf_service/service.rb

@@ -0,0 +1,35 @@
+module PDFService
+  class Service
+    def initialize(config)
+      @tempfiles = Utils::TempfileService.new(root: config.tmp_path).freeze
+      @renderer = PhantomJSRenderer.new(logger: config.logger).freeze
+    end
+
+    attr_reader :tempfiles
+    attr_reader :renderer
+
+    def render(html)
+      tempfiles.use(extension: 'html') { |input_file|
+        input_file.write(html)
+        render_url("file://#{input_file.expand_path.to_s.strip}")
+      }
+    rescue Error => ex
+      raise ex
+    rescue => ex
+      raise Error.new(ex)
+    end
+
+    def render_url(url)
+      tempfiles.use(extension: 'pdf') { |output_file|
+
+        renderer.rasterize(url, output_file.expand_path.to_s)
+
+        return output_file.read
+      }
+    rescue Error => ex
+      raise ex
+    rescue => ex
+      raise Error.new(ex)
+    end
+  end
+end

data/lib/pdf_service/setup.rb

@@ -0,0 +1,11 @@
+require 'pdf_service/web_app'
+
+module PDFService
+  module Setup
+    def self.web_app
+      logger = Logger.new(STDOUT)
+      logger.level = Logger::INFO
+      PDFService::WebApp.new(pdf_service: PDFService.with_config(logger: logger))
+    end
+  end
+end

data/lib/pdf_service/utils/null_logger.rb

@@ -0,0 +1,17 @@
+require 'logger'
+
+module PDFService
+  module Utils
+    class NullLogger
+      def initialize(*args)
+        @level = Logger::WARN
+      end
+
+      attr_accessor :level
+
+      [:warn, :info, :error, :fatal, :debug].each do |level|
+        define_method("#{level}") { |*args|}
+      end
+    end
+  end
+end

data/lib/pdf_service/utils/tempfile_service.rb

@@ -0,0 +1,16 @@
+module PDFService
+  module Utils
+    class TempfileService
+      def initialize(root: Pathname('.'))
+        @root = Pathname(root)
+      end
+
+      def use(name: SecureRandom.hex, extension: 'tmp')
+        path = Pathname('.').expand_path.join("#{name}.#{extension}")
+        yield(path)
+      ensure
+        path.unlink if path.exist?
+      end
+    end
+  end
+end

data/lib/pdf_service/version.rb

@@ -0,0 +1,3 @@
+module PDFService
+  VERSION = '0.0.1'.freeze
+end

data/lib/pdf_service/web_app.rb

@@ -0,0 +1,43 @@
+require 'sinatra/base'
+require 'logger'
+require 'uri'
+
+module PDFService
+  class WebApp < Sinatra::Base
+    def initialize(pdf_service:)
+      super()
+      @pdf_service = pdf_service.freeze
+    end
+
+    attr_reader :pdf_service
+    VALID_SCHEMES = %w(http https).freeze
+
+    get '/' do
+      url = params[:url].to_s
+      begin
+        url = URI.parse(url.to_s)
+
+        unless VALID_SCHEMES.include?(url.scheme)
+          return ErrorResponse("Invalid url scheme #{url.scheme}://. Valid schemes is #{VALID_SCHEMES}")
+        end
+        PDFResponse(pdf_service.render_url(url))
+      rescue => ex
+        STDERR.puts(ex.inspect)
+        ErrorResponse('Internal Server Error')
+      end
+    end
+
+
+    post('/') {
+      PDFResponse(@pdf_service.render(request.body.read))
+    }
+
+    def ErrorResponse(message, status: 500)
+      [status, {'Content-Type' => 'text/plain'}, [message]]
+    end
+
+    def PDFResponse(pdf_data, status: 200)
+      [status, {'Content-Type' => 'application/pdf'}, [pdf_data]]
+    end
+  end
+end

metadata

@@ -0,0 +1,55 @@
+--- !ruby/object:Gem::Specification
+name: pdf-service
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Ruby Coder
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-10-30 00:00:00.000000000 Z
+dependencies: []
+description: Much longer explanation of the example!
+email:
+- rubycoder@example.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/pdf_service.rb
+- lib/pdf_service/config.rb
+- lib/pdf_service/error.rb
+- lib/pdf_service/phantom_js_renderer.rb
+- lib/pdf_service/phantomjs_rasterize.js
+- lib/pdf_service/service.rb
+- lib/pdf_service/setup.rb
+- lib/pdf_service/utils/null_logger.rb
+- lib/pdf_service/utils/tempfile_service.rb
+- lib/pdf_service/version.rb
+- lib/pdf_service/web_app.rb
+homepage: 
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5.1
+signing_key: 
+specification_version: 4
+summary: Small service the uses PhantomJS to turn HTML into PDF
+test_files: []