Created
October 9, 2019 22:28
-
-
Save marcotc/09db9af991b0ad3c435573836f86221e to your computer and use it in GitHub Desktop.
Fastest way to retrive all numbers from a string
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
# Code mostly adapted from original by Jesus: https://www.ruby-forum.com/t/extract-numbers-from-string/115434/5 | |
require 'benchmark' | |
n = 100_000 | |
header = 't=1570633834.463123' | |
Benchmark.bmbm do |x| | |
x.report('scan') do | |
n.times {header.scan(/\d/).join} | |
end | |
x.report('gsub') do | |
n.times {header.gsub(/[^\d]/,'')} | |
end | |
x.report('gsub2') do | |
n.times {header.gsub(/\D/, '')} | |
end | |
x.report('tr') do | |
n.times {header.tr('^0-9','')} | |
end | |
x.report('delete') do | |
n.times {header.delete('^0-9')} | |
end | |
x.report('split') do | |
n.times {header.split(/[^\d]/).join} | |
end | |
end; | |
# Memory benchmark using `benchmark-memory` gem: https://github.com/michaelherold/benchmark-memory | |
require 'benchmark/memory' | |
Benchmark.memory do |x| | |
x.report('scan') do | |
header.scan(/\d/).join | |
end | |
x.report('gsub') do | |
header.gsub(/[^\d]/,'') | |
end | |
x.report('gsub2') do | |
header.gsub(/\D/, '') | |
end | |
x.report('tr') do | |
header.tr('^0-9','') | |
end | |
x.report('delete') do | |
header.delete('^0-9') | |
end | |
x.report('split') do | |
header.split(/[^\d]/).join | |
end | |
x.compare! | |
end; | |
### OUTPUT ### | |
Rehearsal ------------------------------------------ | |
scan 0.501514 0.001129 0.502643 ( 0.503412) | |
gsub 0.212457 0.001135 0.213592 ( 0.213919) | |
gsub2 0.215123 0.001258 0.216381 ( 0.217076) | |
tr 0.039926 0.000275 0.040201 ( 0.040221) | |
delete 0.036174 0.000069 0.036243 ( 0.036440) | |
split 0.238501 0.001149 0.239650 ( 0.239973) | |
--------------------------------- total: 1.248710sec | |
user system total real | |
scan 0.476308 0.000484 0.476792 ( 0.477103) | |
gsub 0.210125 0.000944 0.211069 ( 0.211373) | |
gsub2 0.206936 0.001010 0.207946 ( 0.208079) | |
tr 0.037802 0.000043 0.037845 ( 0.037923) | |
delete 0.034158 0.000052 0.034210 ( 0.034314) | |
split 0.233673 0.001042 0.234715 ( 0.235123) | |
Calculating ------------------------------------- | |
scan 1.608k memsize ( 320.000 retained) | |
21.000 objects ( 2.000 retained) | |
11.000 strings ( 1.000 retained) | |
gsub 568.000 memsize ( 320.000 retained) | |
5.000 objects ( 2.000 retained) | |
3.000 strings ( 1.000 retained) | |
gsub2 568.000 memsize ( 320.000 retained) | |
5.000 objects ( 2.000 retained) | |
3.000 strings ( 1.000 retained) | |
tr 120.000 memsize ( 0.000 retained) | |
3.000 objects ( 0.000 retained) | |
3.000 strings ( 0.000 retained) | |
delete 80.000 memsize ( 0.000 retained) | |
2.000 objects ( 0.000 retained) | |
2.000 strings ( 0.000 retained) | |
split 648.000 memsize ( 0.000 retained) | |
9.000 objects ( 0.000 retained) | |
5.000 strings ( 0.000 retained) | |
Comparison: | |
delete: 80 allocated | |
tr: 120 allocated - 1.50x more | |
gsub: 568 allocated - 7.10x more | |
gsub2: 568 allocated - 7.10x more | |
split: 648 allocated - 8.10x more | |
scan: 1608 allocated - 20.10x more |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment