data_spork 0.0.3 → 0.0.4

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ZDBlMDM4OTU4ZDU2N2JjNDdiN2RkY2VjNDE3NDUyYmNkMzU5OTM3Nw==
+    OWE4Y2U5ODQyMzI2YmQzYmJhYTdkY2IxYTBjNGMxMjliZWQxYjVlMA==
   data.tar.gz: !binary |-
-    OTRjZDVhNTRlMzkzZjJhMjVlOWUwZTk5NzRlZTNhZWMyMzQxZThmYg==
+    YjgwOWVjMmQ4NjRhODk4ZTAxNWI1NDVlZDMyNmQ5YTY0YzU1MWVhNw==
 SHA512:
   metadata.gz: !binary |-
-    MDIyYTg1ZTkyNDg4MDA5OTJhM2NjOTViNjk3NWQwN2I5YzYxYTM0ZTRhMzcw
-    YWNhZTEyNjk0MWUzMGE0ZjQyY2U5NjRkN2Q1N2IwZTY4MWY1MTFiNmRlNWY3
-    ZDMwMWQ0Y2QwNDU5NGNhYzA0MGNmZDAyMTNlNmUzMzA0OGQ5ODA=
+    ZTZmOWRmYzY3ZTE2YWU3YjA0ZGM4ZDAyY2M5YzJiMzJiODg3NmE2ZjViZTM5
+    M2FmYjMwOGFmYTNiNTI4NGE0MzNiNmNjOThmYmU5N2E0NDI5YzQ3MjFlMDgx
+    ZWI3MjUwM2E0YTE3NjRhYmZiODYzMWM4NmRmZDBmOTQ1YjZiNmU=
   data.tar.gz: !binary |-
-    Zjc1MjcxNjc1MzhjZDhiNDI5ZGE0ZDJjNTQyYzRjNjkzZmY2YzU3Zjk3MDlk
-    ODI5ZTc2YmU4MzcxOTUyNjU4Y2IxMGM1MDA1YmYzZWExYmU4Njc3OTMwMDlk
-    YTU4NWI0YTgxNDE1N2E4YWJmZDdiNGYwZGU1NGYyMjAxYjZmZGI=
+    YzNjZTUzN2JjNWQzYTE4Y2Q2ZjY3YmI2ZWYzMTJmYmYyNGQ2OWQyN2ViY2Qy
+    MDY3ODBjNTIyZWE0MDI3N2Q5OWEzYzYzYmVkMzNkZWI4Yjg1NTA2MzgxMGM5
+    NTQyYzJkMzJkZGUyZjBkZGJjNjE3NDkzZGYyOWRkOWI1NTRmMDQ=

data/lib/data_spork/base_reader.rb

@@ -0,0 +1,30 @@
+require 'csv'
+
+module DataSpork
+  class BaseReader
+    attr_reader :owner
+    delegate :options, :input_pathname, :to => :owner
+
+    def initialize(owner)
+      @owner = owner
+    end
+  end
+
+  class CSV_Reader < BaseReader
+    def each(&block)
+      CSV.foreach(input_pathname) do |row|
+        block.call row
+      end
+    end
+  end
+
+  class XLSX_Reader < BaseReader
+    def each(&block)
+      excel = SimpleXlsxReader.open(input_pathname)
+      print_error "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
+  end
+end

data/lib/data_spork/google_spreadsheet.rb

@@ -0,0 +1,66 @@
+require 'google_drive'
+
+module DataSpork
+  class Importer::GoogleSpreadsheet < Importer
+
+    def init_options(options)
+      super
+      unless @options[:google].present?
+        @options[:google] = {
+          user: ENV['google_user'],
+          password: ENV['google_pwd']
+        }
+      end
+    end
+
+    def reader
+      if google?
+        Reader.new(self)
+      else
+        super
+      end
+    end
+
+    def google?
+      [ :google, :drive ].include?(input_type)
+    end
+
+    def google
+      options[:google]
+    end
+
+    def google_user
+      google[:user]
+    end
+
+    def google_password
+      google[:password]
+    end
+
+    def spreadsheet_title
+      google[:spreadsheet_title]
+    end
+
+    def worksheet_title
+      google[:worksheet_title]
+    end
+
+    class Reader < DataSpork::BaseReader
+      delegate :print, :print_error, :to => :owner
+      delegate :google_user, :google_password, :spreadsheet_title, :worksheet_title, :to => :owner
+
+      def each(&block)
+        google = GoogleDrive.login(google_user, google_password)
+        print_error "GoogleDrive #{google} login for #{google_user} #{google.present? ? 'succeeded' : 'failed'}."
+        print_error "GoogleDrive opening spreadsheet: #{spreadsheet_title}, worksheet: #{worksheet_title}."
+        spreadsheet = google.spreadsheet_by_title(spreadsheet_title)
+        sheet = spreadsheet.worksheet_by_title(worksheet_title)
+        print_error "GoogleDrive was opened and sheet name was found: #{sheet.title}"
+        sheet.rows.each do |row|
+          block.call(row.collect {|value| value })
+        end
+      end
+    end
+
+  end
+end

data/lib/data_spork/importer.rb

@@ -1,9 +1,13 @@
-require 'google_drive'
+require 'data_spork/base_reader'
+require 'data_spork/xml_writer'
+require 'data_spork/google_spreadsheet'
 
 module DataSpork
+
   class Importer
-    attr_reader :row_num, :row, :headers, :input_type
-    attr_reader :xml_tags, :root_tag, :row_tag, :options
+    attr_reader :headers, :input_type, :options, :writer
+    attr_reader :row_num, :row, :col_map
+    attr_reader :root_tag, :row_tag, :xml_tags
     attr_accessor :col_num, :setup_state, :blank_row
     attr_accessor :effective_date
 
@@ -12,21 +16,14 @@ module DataSpork
     # @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
+      self.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 = {}
+      @writer = XmlWriter.new(self)
     end
 
     def init_options(options)
@@ -38,8 +35,12 @@ module DataSpork
       /^[Ee]ffective [Dd]ate+/
     end
 
-    def map
-      {} # subclass should override
+    def print(str)
+      puts str
+    end
+
+    def print_error(str)
+      $stderr.puts str
     end
 
     def source_name
@@ -65,36 +66,16 @@ module DataSpork
       ''
     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
+    def reader
+      if csv?
+        CSV_Reader.new(self)
+      elsif xlsx?
+        XLSX_Reader.new(self)
       end
     end
 
     def each(&block)
-      if csv?
-        each_csv &block
-      elsif xlsx?
-        each_xlsx &block
-      elsif google?
-        each_google &block
-      end
+      reader.each &block
     end
 
     def csv?
@@ -117,9 +98,9 @@ module DataSpork
 
     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]
+        print_error "options: #{options}"
+        print_error "input_pathname: #{input_pathname}, exists: #{File.exist?(input_pathname)}"
+        print_error "output_filename: #{output_filename}" if options[:output_file]
       end
       if options[:output_file]
         output_pathname.mkpath
@@ -127,11 +108,11 @@ module DataSpork
       end
       @row_num = 0
       @headers = []
-      self.setup_state = :setup_xml
+      self.setup_state = :setup_writer
     end
 
     def finish
-      finish_xml
+      writer.finish
       finish_capture
     end
 
@@ -236,7 +217,7 @@ module DataSpork
 
     # 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 }
+      unless reject?.tap { |r| print "rejected #{row_num}: #{row}" if r and VERBOSE }
         if headers.empty?
           send setup_state
         else
@@ -261,8 +242,8 @@ module DataSpork
     end
 
     # Initializes the xml document and transfers setup_state to :setup
-    def setup_xml
-      start_xml
+    def setup_writer
+      writer.start
       self.setup_state = :setup
       send setup_state  # automatically transition to next state
     end
@@ -270,102 +251,39 @@ module DataSpork
     # Initializes the headers on the first row and optionally outputs them when VERBOSE=true.
     def setup
       row.each do |col|
-        headers << map[col]
+        headers << col_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
+      print "headers: #{row_num}: #{headers}" if VERBOSE
     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}")
+    # Answer the value for the current column of data, or for the specified index.
+    def col_value(index = nil)
+      row[index || col_num]
     end
 
-    def schema_uri
-      %q(xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance")
+    # Answer the header for the current column of data, or for the specified index.
+    def header(index = nil)
+      headers[index || col_num]
     end
 
-    # Close out the XML file.
-    def finish_xml
-      puts end_tag root_tag if started_xml?
+    # Answer true when the current column should be included in the output.
+    def output_column?
+      xml_tags.include? header
     end
 
     # Output the current row, one column at a time.
     def put_row
-      puts "#{indent}#{begin_row}"
+      writer.begin_put_row
       capture_row
       row.each_index do |index|
         self.col_num = index
         if output_column?
-          put_column
+          writer.put_column
           capture_column
         end
       end
-      puts "#{indent}#{end_row}"
+      writer.end_put_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

@@ -1,3 +1,3 @@
 module DataSpork
-  VERSION = "0.0.3"
+  VERSION = "0.0.4"
 end

data/lib/data_spork/xml_writer.rb

@@ -0,0 +1,93 @@
+class DataSpork::XmlWriter
+
+  attr_accessor :started
+  attr_reader :owner
+
+  delegate :print, :print_error, :to => :owner
+  delegate :effective_date, :xml_tags, :root_tag, :row_tag, :header, :col_value, :to => :owner
+
+  def initialize(owner)
+    @owner = owner
+    @started = false
+  end
+
+  # Output the XML preface.
+  def start
+    start_document
+    start_schema
+    self.started = true
+  end
+
+  # Output the XML document preface.
+  def start_document
+    print '<?xml version="1.0" encoding="UTF-8" standalone="yes" ?>'
+  end
+
+  # Output the schema with the root tag.
+  def start_schema
+    if owner.respond_to?(:xml_start_schema)
+      print owner.xml_start_schema(self)
+    else
+      print begin_tag %Q(#{root_tag} #{schema_uri} effective_date="#{effective_date}")
+    end
+  end
+
+  def schema_uri
+    %q(xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance")
+  end
+
+  def started?
+    started
+  end
+
+  # Close out the XML document.
+  def finish
+    print end_tag root_tag if started?
+  end
+
+  def begin_put_row
+    print "#{indent}#{begin_row}"
+  end
+
+  def end_put_row
+    print "#{indent}#{end_row}"
+  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)
+    print "#{indent 2}#{begin_tag tag}#{value || ''}#{end_tag tag}"
+  end
+
+  # Output the current column enclosing it with XML tags.
+  def put_column
+    print "#{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

data/lib/data_spork.rb

@@ -1,4 +1,3 @@
-require 'csv'
 require 'data_spork/version'
 
 module DataSpork

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: data_spork
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Brian Jackson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-05 00:00:00.000000000 Z
+date: 2014-02-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails
@@ -88,8 +88,11 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/data_spork.rb
+- lib/data_spork/base_reader.rb
+- lib/data_spork/google_spreadsheet.rb
 - lib/data_spork/importer.rb
 - lib/data_spork/version.rb
+- lib/data_spork/xml_writer.rb
 homepage: http://bitbucket.org/leadbaxter/data_spork
 licenses:
 - MIT