Last active
July 22, 2021 20:32
-
-
Save thegorgon/5430b4149e51e06ecaab109fadfeec56 to your computer and use it in GitHub Desktop.
CSV Chunker in Ruby
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
#! /usr/bin/env ruby | |
require 'fileutils' | |
require 'optparse' | |
require 'csv' | |
chunks = [[]] | |
options = { input: nil, output: nil, size: 1000 } | |
OptionParser.new do |parser| | |
parser.banner = 'Usage: csv-chunker [options]' | |
parser.on('-i', '--input INPUT', 'Read CSV from INPUT') do |input| | |
options[:input] = input | |
end | |
parser.on('-o', '--output OUTPUT', 'Output chunks into directory OUTPUT') do |output| | |
options[:output] = output | |
end | |
parser.on('-n', '--size SIZE', Integer, 'Chunk Size') do |size| | |
options[:size] = size | |
end | |
end.parse! | |
raise 'Input and output are both required' unless options[:input] and options[:output] | |
extname = File.extname(options[:input]) | |
basename = File.basename(options[:input]).gsub(/#{extname}$/, '') | |
CSV.read(options[:input], headers: true).each do |row| | |
if chunks.last.count > options[:size] - 1 | |
chunks << [row] | |
else | |
chunks.last << row | |
end | |
end | |
FileUtils.mkdir_p(options[:output]) | |
chunks.each.with_index do |chunk, index| | |
CSV.open("#{options[:output]}/#{basename}--chunk-#{index}.csv", 'wb', headers: true) do |csv| | |
csv << chunk.first.headers | |
chunk.each do |chunk_row| | |
csv << chunk_row | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment