File: html_unescape.rb

package info (click to toggle)
ruby-escape-utils 1.2.1-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, forky, sid, trixie
  • size: 388 kB
  • sloc: ansic: 1,742; ruby: 1,079; sh: 7; makefile: 4
file content (35 lines) | stat: -rw-r--r-- 758 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
# encoding: utf-8

require 'rubygems'
require 'bundler/setup'
require 'benchmark/ips'

require 'cgi'
require 'haml'
require 'escape_utils'

module HamlBench
  extend Haml::Helpers
end

url = "https://en.wikipedia.org/wiki/Succession_to_the_British_throne"
html = `curl -s #{url}`
html = html.force_encoding('binary') if html.respond_to?(:force_encoding)
escaped_html = EscapeUtils.escape_html(html)
puts "Unescaping #{escaped_html.bytesize} bytes of escaped html, from #{url}"

Benchmark.ips do |x|
  x.report "CGI.unescapeHTML" do |times|
    times.times do
      CGI.unescapeHTML(escaped_html)
    end
  end

  x.report "EscapeUtils.unescape_html" do |times|
    times.times do
      EscapeUtils.unescape_html(escaped_html)
    end
  end

  x.compare!
end