gistfile1.rb

#!/usr/bin/env ruby -wKU

puts "Begin Splitting - #{Time.now}"

header_line = "medical_record_number;encounter_number;encounter_start_date;patient_name;patient_birth_date;ip_op_indicator;encounter_type;doc_id;document_date;documnet_create_date;document_modify_date;doc_type_name;doc_type_description;page_number;signed;signatures;annotation_files;text_notes;file_path"
input = File.new('index.idx', 'r')
line_number = 0
line_limit = 930
file_count = 1
threshold = line_limit

output = File.new("index-#{file_count}.idx", 'w')
output << header_line

input.each_line do |line|
  line_number += 1
  document_page_number = line[line.length-10, 10].split("_")[1].split(".")[0].to_i
  output << line unless line_number == 1
  
  if line_number > threshold && document_page_number == 1
    output.close
    file_count += 1
    threshold += line_limit
    output = File.new("index-#{file_count}.idx", 'w')
    output << header_line
  end
end

output.close unless output.nil?

puts "  Created #{file_count} files, from #{line_number} lines."
puts "Done splitting - #{Time.now}"