A ruby script for parsing the OmniClass excel file.

omni_parser.rb

require 'roo'
require 'pp'

xlsx = Roo::Excelx.new('./omni.xlsx')
# sheet = xlsx.default_sheet

ones = []
twos = []
threes = []
fours = []

current_one = ""
current_two = ""
current_three = ""
current_four = ""

xlsx.each do |row|
  n = {}
  n[:attributes] = {}
  n[:identifier] = row[0]
  if row[1] # ones
    current_one = row[0]
    n[:attributes][:name] = row[1]
    n[:attributes][:description] = row[5]
    ones << n
  elsif row[2]
    current_two = row[0]
    n[:attributes][:name] = row[2]
    n[:attributes][:description] = row[5]
    n[:parent] = "XXXConsumerClassification.find_by(identifier: \"#{current_one}\")XXX"
    twos << n
  elsif row[3]
    current_three = row[0]
    n[:attributes][:name] = row[3]
    n[:attributes][:description] = row[5]
    n[:parent] = "XXXConsumerClassification.find_by(identifier: \"#{current_two}\")XXX"
    threes << n
  elsif row[4]
    current_four = row[0]
    n[:attributes][:name] = row[4]
    n[:attributes][:description] = row[5]
    n[:parent] = "XXXConsumerClassification.find_by(identifier: \"#{current_three}\")XXX"
    fours << n
  end

end
pp fours