Compare's Iron Mountain's actual documents with what their csvs say should be there.

count_csvs.rb

#!/usr/bin/env ruby -wKU

require 'faster_csv'

puts "Reading the Iron Mountain CSVs"
encounters = Hash.new
error_text = ''
enc_no = '' # Include information from a specific encounter
lines = 0
Dir.glob( '*.csv' ).each do |file|
  FasterCSV.foreach(file, :headers => :first_row) do |row|
    unless row['EncNo'].nil?
      lines += 1
      if encounters[row['EncNo']].nil?
        encounters[row['EncNo']] = { :docs  => 0,
                                     :doc_types => Array.new,
                                     :files => Array.new }
      end
      encounters[row['EncNo']][:docs] += 1
      encounters[row['EncNo']][:doc_types] << row['DocType']
      encounters[row['EncNo']][:files] << File.basename(file) unless encounters[row['EncNo']][:files].include? File.basename(file)
      if row['EncNo'] == '' and row['OrgId'] != ''
        error_text << "Empty encounter on line #{lines} in #{File.basename(file)}\n"
      end
    end
  end
end

puts "Reading the directories in input"
dirs = 0
dir_encounters = Hash.new
Dir.glob( './*' ).each do |file|
  if File.directory? file
    dirs += 1
    encounter = File.basename(file).split( '_' )[0]
    dir_encounters[encounter] = 0 if  dir_encounters[encounter].nil?
    dir_encounters[encounter] += 1
  elsif enc_no != '' and file.include? enc_no
    encounters[enc_no][:csv] = File.basename file
    encounters[enc_no][:idx_doc_types] = []
    page_num = ''
    index = File.open file, 'r'
    index.each_line do |line|
      if line.include? 'FILE'
        page_num = line.split(':')[1].chomp.strip
      end
      if line.include? 'DOCUMENT TYPE'
        doc_type = line.split(':')[1].chomp.strip
        encounters[enc_no][:idx_doc_types] << doc_type if (page_num == '1.tif')
      end
    end
  end
end

puts "Total Documents = #{lines} - #{dirs}"
encounters.each do |encounter, info|
  if info[:docs] != dir_encounters[encounter]
    puts "  #{encounter} - #{info[:docs]} - #{dir_encounters[encounter]}" 
    info[:files].each { |file| puts "    #{file}" }
  elsif encounter == enc_no
    puts "  #{encounter} - #{info[:docs]} - #{dir_encounters[encounter]}" 
    info[:files].each { |file| puts "    #{file}" }
    puts "    CSV Doc Types - #{info[:doc_types].count}:"
    info[:doc_types].sort.each { |doc_type| puts "      #{doc_type}" }
    puts "    Idx Doc Types - #{info[:idx_doc_types].count}:"
    info[:idx_doc_types].sort.each { |doc_type| puts "      #{doc_type}" }
    unmatched = info[:doc_types] - info[:idx_doc_types]
    puts "    Unmatched Doc Types = #{unmatched.count}"
    unmatched.each { |dt| puts "      #{dt}" }
  end
end