Script I was using to test regex to match urls

test_url_regex.rb

#!/usr/bin/env ruby

require 'awesome_print'

r = %r{ \A
        (?:(?<protocol>http)://)?
        (?<domain>(?:[a-z\d-]+\.)+[a-z\d]{2,})
        (?:
          /
          (?<path>(?:[a-z\d._\-+,%&()!'~&=:]+\/)*[a-z\d._\-+,%&()!'~&=:]+)
        )?
        /?
        (?:
          \?
          (?:
            (?<query>
              (?:[^=?#&]+(?:=[^#&]*)?&)*
              [^=?#&]+(?:=[^#&]*)?
            )
            &?
          )?
        )?
        (?:
          \#
          (?<fragment>
            [^=?#&]*
          )?
        )?
        \z
      }ix

path = ARGV[0] || "urls.txt"
begin STDERR.puts "File not found."; exit 1 end unless File.exists? path
lines = File.readlines(path).map(&:chomp).map(&:strip).reject(&:empty?).reject { |line| line.start_with? '#' }

x = lines.map { |s| s.match(r) || "No match for '#{s}'" }
x = x.map do |m|
  if m.is_a? String
    m
  else
    {
      original: m[0],
      domain:   "       " + m[:domain],
      path:     ("       " + m[:domain].gsub(/./, ' ') + " " + (m[:path]||"")).rstrip,
      query:    ("       " + m[:domain].gsub(/./, ' ') + " " + (m[:path]||"").gsub(/./, ' ') + " " + (m[:query]||"")).rstrip,
      fragment: ("       " + m[:domain].gsub(/./, ' ') + " " + (m[:path]||"").gsub(/./, ' ') + " " + (m[:query]||"").gsub(/./, ' ') + " " + (m[:fragment]||"")).rstrip
    }
  end
end

# ap x.select {|s| s.is_a? String } # Errors only
ap x