Last active
December 21, 2015 17:49
-
-
Save mikecarroll/6342821 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| desc "Normalize Uzbek file." | |
| task :uzbek => :environment do | |
| counter = 0 | |
| entry_counter = 0 | |
| previous = nil | |
| desc_array = [] | |
| new_file = File.open('~/fixed_UE.txt', 'w') | |
| CSV.foreach("~/UE.txt", { :col_sep => "|" }) do |row| | |
| if row.count > 2 | |
| row[1] = row[1] + row[2] | |
| row.pop | |
| end | |
| unless row.empty? | |
| entry = row[0].strip | |
| pos = entry.match(/\w*\.$/).to_s.strip | |
| entry = entry.gsub(/\w*\.$/, '').strip | |
| desc_array << [pos, row[1].strip] | |
| if previous.blank? || previous == entry | |
| previous = entry | |
| # p "#{previous} || #{entry}" | |
| else | |
| # p "#{previous} || #{entry}" | |
| new_entry = entry.dup | |
| hash = {} | |
| desc_array.each do |y| | |
| if hash[y[0]] | |
| hash[y[0]] = hash[y[0]] << ", #{y[1]}" | |
| else | |
| hash[y[0]] = y[1] | |
| end | |
| end | |
| hash.each_with_index do |(k, v), i| | |
| if i == 0 | |
| new_entry << " #{k} #{v}" | |
| else | |
| new_entry << "; #{k} #{v}" | |
| end | |
| end | |
| new_file << new_entry + "\n" | |
| # p new_entry.encoding.name | |
| desc_array = [] | |
| previous = entry | |
| entry_counter += 1 | |
| end | |
| counter += 1 | |
| if counter%1000 == 0 | |
| p counter | |
| end | |
| end | |
| end | |
| new_file.close | |
| p "Done! ENTRIES COUNT: #{entry_counter}" | |
| p "Done! TOTAL COUNT: #{counter}" | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment