Created
May 25, 2016 18:16
-
-
Save maxcodes/df731d29cc9f8b35f0ce3e024e34c4ff to your computer and use it in GitHub Desktop.
This file contains 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
require 'fuzzystringmatch' | |
desc "This task eliminates books without ISBN, finds the duplicated books and merges them" | |
task find_duplicated_books: :environment do | |
jarow = FuzzyStringMatch::JaroWinkler.create(:native) | |
#Destroy books without isbn that have no shelf_books and progresses | |
Book.where(isbn: nil).where(shelf_books_count: 0, progresses_count: 0).destroy_all | |
books = Book.all # These are 30K books. | |
books.each do |book| | |
books.each do |otherbook| # <- this double loop is the one that concerns me the most. 30,000 * 30,000 = 900,000,000 loops. | |
next if same_book?(book, otherbook) | |
if books_are_duplicate(jarow, book, otherbook) | |
merge_books(book, otherbook) | |
end | |
end | |
end | |
end | |
def merge_books(book, otherbook) | |
sleep 2 # omitted for brevity. traversing several AR associations, some db calls, etc. | |
end | |
def same_book?(book_1, book_2) | |
book_1.id == book_2.id | |
end | |
def books_are_duplicate(jarow, book, otherbook) | |
title = book.title.parameterize(" ") | |
other_title = otherbook.title.parameterize(" ") | |
jarow.getDistance(title, other_title) > 0.99 # this is a really fast implementation of the Jaro-Winkler distance for strings. | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment