Last active
August 29, 2015 14:12
-
-
Save jpterry/d9b0fb06699310f827b1 to your computer and use it in GitHub Desktop.
Pipe delimted file splitter
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 'csv' | |
class FileSplitter | |
SPLIT_COUNT = 250_000 | |
COPY_HEADERS = true | |
def initialize(filename) | |
@filename = filename | |
@header = nil | |
@file_count = 1 | |
@outfile = File.open("split_out_#{@file_count}.csv", 'wb') | |
end | |
def split | |
row_count = 0 | |
CSV.foreach(@filename, col_sep: '|') do |row| | |
row_count += 1 | |
@header ||= row | |
if (row_count % SPLIT_COUNT) == 0 | |
puts row_count | |
start_new_file | |
end | |
outfile << row.to_csv | |
end | |
end | |
def start_new_file | |
@outfile.close | |
@outfile = File.open("split_out_#{@file_count+=1}.csv", 'wb') | |
@outfile << @header.to_csv if COPY_HEADERS | |
end | |
def outfile | |
@outfile | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment