Last active
August 29, 2015 14:17
-
-
Save tonilin/393986d3588f6c1a00c1 to your computer and use it in GitHub Desktop.
pluck_in_batches.rb
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
# Reference: | |
# 1. https://gist.github.com/siannopollo/03d646eb7525f7fce678#file-pluck_in_batches-rb | |
# 2. https://github.com/rails/rails/blob/master/activerecord/lib/active_record/relation/batches.rb | |
class ActiveRecord::Relation | |
# pluck_in_batches: yields an array of *columns that is at least size | |
# batch_size to a block. | |
# | |
# Special case: if there is only one column selected than each batch | |
# will yield an array of columns like [:column, :column, ...] | |
# rather than [[:column], [:column], ...] | |
# Arguments | |
# columns -> an arbitrary selection of columns found on the table. | |
# batch_size -> How many items to pluck at a time | |
# &block -> A block that processes an array of returned columns. | |
# Array is, at most, size batch_size | |
# | |
# Returns | |
# nothing is returned from the function | |
def pluck_in_batches(*columns, batch_size: 1000, start: nil) | |
if columns.empty? | |
raise "There must be at least one column to pluck" | |
end | |
relation = self | |
select_columns = columns.dup | |
# Find index of :id in the array | |
remove_id_from_results = false | |
id_index = columns.index(:id) | |
# :id is still needed to calculate offsets | |
# add it to the front of the array and remove it when yielding | |
if id_index.nil? | |
id_index = 0 | |
select_columns.unshift(:id) | |
remove_id_from_results = true | |
end | |
unless block_given? | |
return to_enum(:pluck_in_batches, *select_columns, batch_size: batch_size, start: start) do | |
total = start ? where(table[primary_key].gteq(start)).size : size | |
(total - 1).div(batch_size) + 1 | |
end | |
end | |
if logger && (arel.orders.present? || arel.taken.present?) | |
logger.warn("Scoped order and limit are ignored, it's forced to be batch order and batch size") | |
end | |
relation = relation.reorder(batch_order).limit(batch_size) | |
items = start ? relation.where(table[primary_key].gteq(start)).pluck(*select_columns) : relation.pluck(*select_columns) | |
while items.any? | |
items_size = items.size | |
primary_key_offset = items.last[id_index] | |
# Remove :id column if not in *columns | |
items.map! { |row| row[1..-1] } if remove_id_from_results | |
# Only pluck one column return flatten array | |
items.flatten! if select_columns.length == 2 && remove_id_from_results | |
yield items | |
break if items_size < batch_size | |
items = relation.where(table[primary_key].gt(primary_key_offset)).pluck(*select_columns) | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment