tax_generator 0.0.1

data/data/input/taxonomy.xml

@@ -0,0 +1,78 @@
+<?xml version="1.0" encoding="utf-8"?>
+<taxonomies>
+<taxonomy>
+<taxonomy_name>World</taxonomy_name>
+<node atlas_node_id = "355064" ethyl_content_object_id="82534" geo_id = "355064">
+<node_name>Africa</node_name>
+<node atlas_node_id = "355611" ethyl_content_object_id="3210" geo_id = "355611">
+<node_name>South Africa</node_name>
+<node atlas_node_id = "355612" ethyl_content_object_id="35474" geo_id = "355612">
+<node_name>Cape Town</node_name>
+<node atlas_node_id = "355613" ethyl_content_object_id="" geo_id = "355613">
+<node_name>Table Mountain National Park</node_name>
+</node>
+</node>
+<node atlas_node_id = "355614" ethyl_content_object_id="" geo_id = "355614">
+<node_name>Free State</node_name>
+<node atlas_node_id = "355615" ethyl_content_object_id="1000550692" geo_id = "355615">
+<node_name>Bloemfontein</node_name>
+</node>
+</node>
+<node atlas_node_id = "355616" ethyl_content_object_id="" geo_id = "355616">
+<node_name>Gauteng</node_name>
+<node atlas_node_id = "355617" ethyl_content_object_id="37710" geo_id = "355617">
+<node_name>Johannesburg</node_name>
+</node>
+<node atlas_node_id = "355618" ethyl_content_object_id="1000548256" geo_id = "355618">
+<node_name>Pretoria</node_name>
+</node>
+</node>
+<node atlas_node_id = "355619" ethyl_content_object_id="" geo_id = "355619">
+<node_name>KwaZulu-Natal</node_name>
+<node atlas_node_id = "355620" ethyl_content_object_id="43725" geo_id = "355620">
+<node_name>Durban</node_name>
+</node>
+<node atlas_node_id = "355621" ethyl_content_object_id="1000576780" geo_id = "355621">
+<node_name>Pietermaritzburg</node_name>
+</node>
+</node>
+<node atlas_node_id = "355622" ethyl_content_object_id="" geo_id = "355622">
+<node_name>Mpumalanga</node_name>
+<node atlas_node_id = "355623" ethyl_content_object_id="67561" geo_id = "355623">
+<node_name>Kruger National Park</node_name>
+</node>
+</node>
+<node atlas_node_id = "355624" ethyl_content_object_id="" geo_id = "355624">
+<node_name>The Drakensberg</node_name>
+<node atlas_node_id = "355625" ethyl_content_object_id="" geo_id = "355625">
+<node_name>Royal Natal National Park</node_name>
+</node>
+</node>
+<node atlas_node_id = "355626" ethyl_content_object_id="" geo_id = "355626">
+<node_name>The Garden Route</node_name>
+<node atlas_node_id = "355627" ethyl_content_object_id="" geo_id = "355627">
+<node_name>Oudtshoorn</node_name>
+</node>
+<node atlas_node_id = "355628" ethyl_content_object_id="" geo_id = "355628">
+<node_name>Tsitsikamma Coastal National Park</node_name>
+</node>
+</node>
+</node>
+<node atlas_node_id = "355629" ethyl_content_object_id="3263" geo_id = "355629">
+<node_name>Sudan</node_name>
+<node atlas_node_id = "355630" ethyl_content_object_id="" geo_id = "355630">
+<node_name>Eastern Sudan</node_name>
+<node atlas_node_id = "355631" ethyl_content_object_id="" geo_id = "355631">
+<node_name>Port Sudan</node_name>
+</node>
+</node>
+<node atlas_node_id = "355632" ethyl_content_object_id="" geo_id = "355632">
+<node_name>Khartoum</node_name>
+</node>
+</node>
+<node atlas_node_id = "355633" ethyl_content_object_id="3272" geo_id = "355633">
+<node_name>Swaziland</node_name>
+</node>
+</node>
+</taxonomy>
+</taxonomies>

data/data/output/.gitignore

@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore

data/init.rb

@@ -0,0 +1 @@
+require 'tax_generator'

data/lib/tax_generator/all.rb

@@ -0,0 +1,26 @@
+$stdin.sync = true # if $stdin.isatty
+$stdout.sync = true # if $stdout.isatty
+require 'rubygems'
+require 'bundler'
+require 'bundler/setup'
+require 'active_support/core_ext/object/blank'
+require 'active_support/core_ext/hash/keys'
+require 'active_support/core_ext/module/delegation'
+
+require 'slop'
+require 'nokogiri'
+require 'tree'
+require 'celluloid/autostart'
+require 'celluloid/pmap'
+
+require 'logger'
+require 'fileutils'
+require 'ostruct'
+require 'erb'
+require 'tilt'
+
+%w(classes helpers).each do |folder_name|
+  Gem.find_files("tax_generator/#{folder_name}/**/*.rb").each { |path| require path }
+end
+require_relative './application'
+require_relative './version'

data/lib/tax_generator/application.rb

@@ -0,0 +1,125 @@
+require_relative './helpers/application_helper'
+module TaxGenerator
+  # class used run the processsor
+  #
+  # @!attribute opts
+  #   @return [Slop::Options] the options that are used for command line access
+  #
+  class Application
+    include TaxGenerator::ApplicationHelper
+
+    attr_reader :opts
+
+    # method used to initialize the application, by initializing the options for command line
+    # access
+    #
+    #
+    # @return [void]
+    #
+    # @api public
+    def initialize
+      @opts = Slop::Options.new
+      @opts.banner = 'usage: tax_generator [options] ...'
+    end
+
+    #  receives a list of options that are used to determine the input files and output and input folders
+    #
+    # @param  [Hash]  options the options that are used for command line access
+    #
+    # @see #execute_with_rescue
+    # @see TaxGenerator::Processor#new
+    # @see TaxGenerator::Processor#work
+    #
+    # @return [void]
+    #
+    # @api public
+    def run(options = {})
+      execute_with_rescue do
+        options = options.present? ? options : parse_options
+        processor = TaxGenerator::Processor.new(options)
+        processor.work
+      end
+    end
+
+    #  returns the logger used to log messages and errors
+    #
+    # @return [Logger]
+    #
+    # @api public
+    def self.app_logger
+      @logger ||= Logger.new($stdout)
+    end
+
+    #  returns the options list as a hash after parsing command line arguments
+    #
+    # @return [Hash]
+    #
+    # @api public
+    def parse_options
+      setup_command_line_options
+      parser = Slop::Parser.new(@opts)
+      result = parser.parse(ARGV.dup)
+      result.to_hash
+    end
+
+    #  sets the directory options for command line access
+    #
+    # @return [void]
+    #
+    # @api public
+    def directory_options
+      @opts.separator ''
+      @opts.separator 'Directory options:'
+      @opts.string '-i', '--input_dir', 'The input directory ', default: "#{root}/data/input"
+      @opts.string '-o', '--output_dir', 'The ouput directory', default: "#{root}/data/output"
+    end
+
+    #  sets the file options for command line access
+    #
+    # @return [void]
+    #
+    # @api public
+    def file_options
+      @opts.separator ''
+      @opts.separator 'Extra options:'
+      @opts.string '-t', '--taxonomy_filename', 'The taxonomy file name', default: 'taxonomy.xml'
+      @opts.string '-d', '--destinations_filename', 'The destinations file name', default: 'destinations.xml'
+    end
+
+    #  sets the version of the gem available to be displayed from command line
+    #
+    # @return [void]
+    #
+    # @api public
+    def setup_version
+      @opts.on '--version', 'The destinations file name' do
+        puts TaxGenerator.gem_version
+        exit
+      end
+    end
+
+    #  sets the help menu for command line access
+    #
+    # @return [void]
+    #
+    # @api public
+    def setup_help
+      @opts.on '--help', 'print the help' do
+        puts @opts
+        exit
+      end
+    end
+
+    #  sets the command line options
+    #
+    # @return [void]
+    #
+    # @api public
+    def setup_command_line_options
+      directory_options
+      file_options
+      setup_version
+      setup_help
+    end
+  end
+end

data/lib/tax_generator/classes/destination.rb

@@ -0,0 +1,103 @@
+require_relative '../helpers/application_helper'
+module TaxGenerator
+  # class used to find xpaths from the destination node from xml
+  #
+  # @!attribute destination
+  #   @return [Nokogiri::Element] the element from the xml document that need to be parsed
+  class Destination
+    include TaxGenerator::ApplicationHelper
+
+    delegate :xpath,
+             to: :destination
+
+    attr_reader :destination
+
+    # receives destination node (xml element) that need to be parsed
+    #
+    # @param  [Nokogiri::Element] destination_node the element from the xml document that need to be parsed
+    #
+    # @return [void]
+    #
+    # @api public
+    def initialize(destination_node)
+      @destination = destination_node
+    end
+
+    # returns the information about the introduction
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def introduction
+      xpath('.//introductory/introduction/overview')
+    end
+
+    # returns the information about the history
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def history
+      xpath('./history/history/history')
+    end
+
+    # returns the information about the practical_information
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def practical_information
+      base = './/practical_information/health_and_safety'
+      xpath("#{base}/dangers_and_annoyances") + xpath("#{base}/while_youre_there") + \
+        xpath("#{base}/before_you_go") + xpath("#{base}/money_and_costs/money")
+    end
+
+    # returns the information about the transport
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def transport
+      xpath('.//transport/getting_around')
+    end
+
+    # returns the information about the weather
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def weather
+      xpath('.//weather')
+    end
+
+    # returns the information about the work_live_study
+    #
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def work_live_study
+      xpath('.//work_live_study')
+    end
+
+    # returns the a hash containing all the parsed information from the xml document
+    # and makes sure that only elements with content not blank will be returned
+    #
+    # @see #elements_with_content
+    # @return [Nokogiri::NodeSet]
+    #
+    # @api public
+    def to_hash
+      {
+        introduction: introduction,
+        history: history,
+        practical_information: practical_information,
+        transport:  transport,
+        weather: weather,
+        work_live_study: work_live_study
+      }.each_with_object({}) do |(key, value), hsh|
+        hsh[key] = elements_with_content(value)
+        hsh
+      end
+    end
+  end
+end

data/lib/tax_generator/classes/file_creator.rb

@@ -0,0 +1,100 @@
+require_relative '../helpers/application_helper'
+module TaxGenerator
+  # class used to create the files
+  #
+  # @!attribute processor
+  #   @return [TaxGenerator::Processor] the manager that manages the current actor
+  # @!attribute job
+  #   @return [Hash] the job that this actor received
+  # @!attribute job_id
+  #   @return [String] the id of the node from the taxonomy tree
+  # @!attribute destination
+  #   @return [Nokogiri::Element] the destination node from the xml document
+  # @!attribute taxonomy
+  #   @return [TaxGenerator::TaxonomyTree] the taxonomy tree holding all the nodes from the taxonomy xml document
+  # @!attribute output_folder
+  #   @return [String] the output folder where the new files will be created
+  class FileCreator
+    include Celluloid
+    include Celluloid::Logger
+    include TaxGenerator::ApplicationHelper
+
+    attr_reader :processor, :job, :job_id, :destination, :taxonomy, :output_folder
+
+    #  returns the template file path used for generating the files
+    #
+    # @return [void]
+    #
+    # @api public
+    def template_name
+      File.join(root, 'templates', 'template.html.erb')
+    end
+
+    #  processes the job received and registers itself inside the manager
+    # @see TaxGenerator::Processor#register_worker_for_job
+    # @see #process_job
+    #
+    # @param  [Hash] job the job that is passed to the current actor
+    # @param  [TaxGenerator::Processor] manager the manager that manages the actor
+    #
+    # @return [void]
+    #
+    # @api public
+    def work(job, manager)
+      job = job.stringify_keys
+      @job = job
+      @processor = manager
+      process_job(job)
+      @processor.register_worker_for_job(job, Actor.current)
+    end
+
+    #  processes the job information by retrieving keys from the hash
+    #
+    # @param  [Hash] job the job that is passed to the current actor
+    #
+    # @return [void]
+    #
+    # @api public
+    def process_job(job)
+      job = job.stringify_keys
+      @destination = job['destination']
+      @job_id = job['atlas_id']
+      @taxonomy = job['taxonomy']
+      @output_folder = job['output_folder']
+    end
+
+    #  renders the template and creates new file with the template html
+    #
+    # @return [void]
+    #
+    # @api public
+    def start_work
+      log_message "Generating html for destination #{@job_id}"
+      output = Tilt.new(template_name).render(Actor.current, fetch_atlas_details)
+      File.open(File.join(@output_folder, "#{@job_id}.html"), 'w') { |file| file << output }
+      mark_job_completed
+    end
+
+    #  marks the job as completed after file is generated
+    #
+    # @return [void]
+    #
+    # @api public
+    def mark_job_completed
+      @processor.jobs[@job_id]['status'] = 'finished'
+      @processor.condition.signal('completed') if @processor.alive? && @processor.all_workers_finished?
+    end
+
+    # fetches the details needed to be passed to the erb template
+    # @see TaxGenerator::Destination#new
+    #
+    # @return [void]
+    #
+    # @api public
+    def fetch_atlas_details
+      atlas_node = @taxonomy[@job_id]
+      content = @destination.present? ? TaxGenerator::Destination.new(@destination).to_hash : {}
+      content.merge(details: atlas_node, root: root)
+    end
+  end
+end