textmaster-medium-regex-perfomance-benchmark
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 "benchmark/ips" | |
PART = <<TEXT | |
A text with 123,21231,231,23d a number: 12,212,234,12 | |
Other 12 43 123,21231,22,22,2,33d Some other 9012,123123 12 | |
TEXT | |
TEXT = PART * 100 | |
POSSESSIVE = /(\d++,?)++/ | |
LAZY = /(\d+?,?)+?/ | |
NORMAL = /(\d+,?)+/ | |
UNROLLING = /-?\d+(,\d+)*/ | |
def count(string, regex) | |
string.scan(regex).count | |
end | |
def compile_regex(regex) | |
/(?<=\s)(#{regex})(?=\s)/ | |
end | |
POSSESSIVE_WHOLE = compile_regex(POSSESSIVE) | |
LAZY_WHOLE = compile_regex(LAZY) | |
NORMAL_WHOLE = compile_regex(NORMAL) | |
UNROLLING_WHOLE = compile_regex(UNROLLING) | |
def measure(string, x) | |
x.report('possessive') { count(string, POSSESSIVE_WHOLE) } | |
x.report('lazy') { count(string, LAZY_WHOLE) } | |
x.report('greedy') { count(string, NORMAL_WHOLE) } | |
x.report('unrolling') { count(string, UNROLLING_WHOLE) } | |
x.compare! | |
end | |
def benchmark(string) | |
Benchmark.ips do |x| | |
measure(string, x) | |
end | |
end | |
benchmark(TEXT) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment