data_spork 0.0.3

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ZDBlMDM4OTU4ZDU2N2JjNDdiN2RkY2VjNDE3NDUyYmNkMzU5OTM3Nw==
+  data.tar.gz: !binary |-
+    OTRjZDVhNTRlMzkzZjJhMjVlOWUwZTk5NzRlZTNhZWMyMzQxZThmYg==
+SHA512:
+  metadata.gz: !binary |-
+    MDIyYTg1ZTkyNDg4MDA5OTJhM2NjOTViNjk3NWQwN2I5YzYxYTM0ZTRhMzcw
+    YWNhZTEyNjk0MWUzMGE0ZjQyY2U5NjRkN2Q1N2IwZTY4MWY1MTFiNmRlNWY3
+    ZDMwMWQ0Y2QwNDU5NGNhYzA0MGNmZDAyMTNlNmUzMzA0OGQ5ODA=
+  data.tar.gz: !binary |-
+    Zjc1MjcxNjc1MzhjZDhiNDI5ZGE0ZDJjNTQyYzRjNjkzZmY2YzU3Zjk3MDlk
+    ODI5ZTc2YmU4MzcxOTUyNjU4Y2IxMGM1MDA1YmYzZWExYmU4Njc3OTMwMDlk
+    YTU4NWI0YTgxNDE1N2E4YWJmZDdiNGYwZGU1NGYyMjAxYjZmZGI=

data/lib/data_spork/importer.rb

@@ -0,0 +1,371 @@
+require 'google_drive'
+
+module DataSpork
+  class Importer
+    attr_reader :row_num, :row, :headers, :input_type
+    attr_reader :xml_tags, :root_tag, :row_tag, :options
+    attr_accessor :col_num, :setup_state, :blank_row
+    attr_accessor :effective_date
+
+    # Entry point to convert the input menu and output it as a menu board.
+    #
+    # @param :input_type symbol indicating whether to output :xlsx or :csv
+    # @param :options hash with options to control the behavior of the conversion
+    def self.convert(input_type, options = nil)
+      new(input_type, options).convert
+    end
+
+    # Constructor
+    def initialize(input_type, options = nil)
+      @input_type = input_type
+      init_options options
+      @xml_tags = %w(menu_group_name name calories ingredients is_active trademarked is_good_cold )
+      @root_tag = 'MenuBoard'
+      @row_tag  = 'menu_choice'
+      @location_filters = {
+          default: nil
+      }
+      @started_xml = false
+      @menu_board = {}
+    end
+
+    def init_options(options)
+      @options = { source_path: '.' }.merge(options ||= {})
+      @options[:output_path] = @options[:source_path] if @options[:output_path].nil? and @options[:output_file]
+    end
+
+    def effective_date_pattern
+      /^[Ee]ffective [Dd]ate+/
+    end
+
+    def map
+      {} # subclass should override
+    end
+
+    def source_name
+      base = DEFAULT_INPUT_NAME
+      modifier = ''
+      "#{base}#{modifier}.#{input_type}"
+    end
+
+    def input_pathname
+      Pathname(options[:source_path]).join(source_name).to_s
+    end
+
+    def output_pathname
+      Pathname(options[:output_path]).join('output')
+    end
+
+    def output_filename
+      p = output_pathname.join(options[:output_file])
+      p.sub_ext "#{file_modifier}#{p.extname}"
+    end
+
+    def file_modifier
+      ''
+    end
+
+    def started_xml
+      @started_xml = true
+    end
+
+    def started_xml?
+      @started_xml
+    end
+
+    def each_csv(&block)
+      CSV.foreach(input_pathname) do |row|
+        block.call row
+      end
+    end
+
+    def each_xlsx(&block)
+      excel = SimpleXlsxReader.open(input_pathname)
+      $stderr.puts "Excel file was opened and sheet name was found: #{excel.sheets.first.name}"
+      excel.sheets.first.rows.each do |row|
+        block.call row
+      end
+    end
+
+    def each(&block)
+      if csv?
+        each_csv &block
+      elsif xlsx?
+        each_xlsx &block
+      elsif google?
+        each_google &block
+      end
+    end
+
+    def csv?
+      input_type == :csv
+    end
+
+    def xlsx?
+      [ :xlsx, :xls ].include? input_type
+    end
+
+    # Drives the conversion of the CSV input file to XML formatted output.
+    # @param :path_to_csv string path name of the CSV input file
+    def convert
+      start
+      each do |row|
+        append row
+      end
+      finish
+    end
+
+    def start
+      if VERBOSE_IO_OPTIONS
+        $stderr.puts "options: #{options}"
+        $stderr.puts "input_pathname: #{input_pathname}, exists: #{File.exist?(input_pathname)}"
+        $stderr.puts "output_filename: #{output_filename}" if options[:output_file]
+      end
+      if options[:output_file]
+        output_pathname.mkpath
+        $stdout = File.open("#{output_filename}", 'w')
+      end
+      @row_num = 0
+      @headers = []
+      self.setup_state = :setup_xml
+    end
+
+    def finish
+      finish_xml
+      finish_capture
+    end
+
+    # Appends the specified row to the output.
+    # @param :row Array of values parsed from the CSV input.
+    def append(row)
+      @row = row
+      @row_num += 1
+      sanitize
+      output
+    end
+
+    # Sanitize the current row of data. This is done in place, so not worried about a return value.
+    def sanitize
+      self.col_num = 0
+      self.blank_row = true
+      row.collect! do |utf_8|
+        value = (ENCODE_VALUES ? "#{utf_8}".encode('iso-8859-1', xml: :text) : utf_8)
+        self.blank_row = false if blank_row and !value.blank?
+        sanitize_value(value) if headers? and SANITIZE_VALUES
+        substitute_value(value).tap do
+          self.col_num += 1
+        end
+      end
+    end
+
+    # Substitute field-specific values based on their position in the row.
+    # The returned value is substituted for the passed value.
+    # This method does not process columns that are not included in the output.
+    #
+    # Subclasses should not override this method, but should override #get_substitute_value instead.
+    #
+    # @param :value the value to be substituted
+    def substitute_value(value)
+      if headers? and output_column?
+        get_substitute_value(value)
+      else
+        value
+      end
+    end
+
+    # Overridden by subclasses to substitute field-specific values based on their position in the row.
+    # The returned value is substituted for the passed value.
+    # This method expects only columns that are included in the output.
+    #
+    # @param :value the value to be substituted
+    def get_substitute_value(value)
+      value
+    end
+
+    # Sanitize field-specific values based on their position in the row.
+    # The values must be modified in place, so there is no need to return a value.
+    # This method does not sanitize columns that are not included in the output.
+    #
+    # @param :value the value to be sanitized
+    def sanitize_value(value)
+      if headers? and output_column?
+        case header
+          when nil?
+            0
+        end
+      end
+    end
+
+    # Answer true if the headers are already determined.
+    def headers?
+      !headers.empty?
+    end
+
+    def begin_menu_group(name)
+      self.menu_group_name = name
+      id = menu_board.size + 1
+      self.menu_group = { id: id, name: name, display_order: id, choices: [] }
+      menu_board[name] = menu_group
+    end
+
+    def capture_row
+      order = menu_group[:choices].size + 1
+      self.menu_choice = { id: row_num, display_order: order, menu_group_id: menu_group[:id], options: { } }
+      self.menu_group[:choices] << menu_choice
+    end
+
+    def capture_column
+      key = case header
+              when 'ingredients'
+                'description'
+              when 'trademarked'
+                'is_trademarked'
+              else
+                header
+            end
+      if %w(trademarked image_url).include?(key)
+        menu_choice[:options][key.to_sym] = col_value
+      else
+        menu_choice[key.to_sym] = col_value
+      end
+    end
+
+    def finish_capture
+      # empty - subclass should override
+    end
+
+    # Output the current row of data, which were parsed from the CSV input.
+    def output
+      unless reject?.tap { |r| puts "rejected #{row_num}: #{row}" if r and VERBOSE }
+        if headers.empty?
+          send setup_state
+        else
+          put_row #if location_filter?
+        end
+      end
+    end
+
+    # Answer true if rules dictate the current row should be discarded from processing.
+    def reject?
+      headers? and blank_row
+    end
+
+    # Answer true if the first_col value is the effective date header, and clip the effective date value.
+    def clip_effective_date?(first_col)
+      if first_col.match(effective_date_pattern)
+        self.effective_date = "#{row[1]}".strip
+        true
+      else
+        false
+      end
+    end
+
+    # Initializes the xml document and transfers setup_state to :setup
+    def setup_xml
+      start_xml
+      self.setup_state = :setup
+      send setup_state  # automatically transition to next state
+    end
+
+    # Initializes the headers on the first row and optionally outputs them when VERBOSE=true.
+    def setup
+      row.each do |col|
+        headers << map[col]
+      end
+      puts "headers: #{row_num}: #{headers}" if VERBOSE
+    end
+
+    # Output the XML preface.
+    def start_xml
+      start_xml_document
+      start_xml_schema
+      started_xml
+    end
+
+    # Output the XML document preface.
+    def start_xml_document
+      puts '<?xml version="1.0" encoding="UTF-8" standalone="yes" ?>'
+    end
+
+    # Output the schema with the root tag.
+    def start_xml_schema
+      puts begin_tag %Q(#{root_tag} #{schema_uri} effective_date="#{effective_date}")
+    end
+
+    def schema_uri
+      %q(xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance")
+    end
+
+    # Close out the XML file.
+    def finish_xml
+      puts end_tag root_tag if started_xml?
+    end
+
+    # Output the current row, one column at a time.
+    def put_row
+      puts "#{indent}#{begin_row}"
+      capture_row
+      row.each_index do |index|
+        self.col_num = index
+        if output_column?
+          put_column
+          capture_column
+        end
+      end
+      puts "#{indent}#{end_row}"
+    end
+
+    # Answer true when the current column should be included in the output.
+    def output_column?
+      xml_tags.include? header
+    end
+
+    # Answer the value for the current column of data, or for the specified index.
+    def col_value(index = nil)
+      row[index || col_num]
+    end
+
+    # Answer the header for the current column of data, or for the specified index.
+    def header(index = nil)
+      headers[index || col_num]
+    end
+
+    # Output the value enclosing it with the specified XML tag.
+    # @param :tag the xml tag name
+    # @param :value the value to output
+    def put_tag(tag, value)
+      puts "#{indent 2}#{begin_tag tag}#{value || ''}#{end_tag tag}"
+    end
+
+    # Output the current column enclosing it with XML tags.
+    def put_column
+      puts "#{indent 2}#{begin_tag}#{col_value}#{end_tag}"
+    end
+
+    # Answer a begin tag using the current header, or else override it with the sender's tag.
+    def begin_tag(h = nil)
+      "<#{h || header}>"
+    end
+
+    # Answer the end tag using the current header, or else override it with the sender's tag.
+    def end_tag(h = nil)
+      "</#{h || header}>"
+    end
+
+    # Answer the tag defining a row.
+    def begin_row
+      begin_tag(row_tag)
+    end
+
+    # Answer the closing tag for the current row.
+    def end_row
+      end_tag(row_tag)
+    end
+
+    # Answer a string prefix for the specified indent level.
+    # @param :level specifies the indent level; default is 1.
+    def indent(level = 1)
+      "\t" * level
+    end
+  end
+end

data/lib/data_spork/version.rb

@@ -0,0 +1,3 @@
+module DataSpork
+  VERSION = "0.0.3"
+end

data/lib/data_spork.rb

@@ -0,0 +1,13 @@
+require 'csv'
+require 'data_spork/version'
+
+module DataSpork
+  class Importer
+    VERBOSE = false
+    VERBOSE_IO_OPTIONS = ENV['VERBOSE'].eql?('true')
+    ENCODE_VALUES = false # skip encoding until a need is found
+    SANITIZE_VALUES = false # skip sanitizing until a need is found
+  end
+end
+
+require 'data_spork/importer'

metadata

@@ -0,0 +1,117 @@
+--- !ruby/object:Gem::Specification
+name: data_spork
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+- Brian Jackson
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-02-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: simple_xlsx_reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: google_drive
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.3'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.1'
+description: Importer of CSV and Spreadsheet data.
+email:
+- bjackson@leadbaxter.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/data_spork.rb
+- lib/data_spork/importer.rb
+- lib/data_spork/version.rb
+homepage: http://bitbucket.org/leadbaxter/data_spork
+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: 2.2.1
+signing_key: 
+specification_version: 4
+summary: Import CSV, Excel [.XLS, .XLSX] and Google Drive Spreadsheets.
+test_files: []