From: Joe Van Dyk <joevandyk@...>
Date: 2005-08-14T03:26:47+09:00
Subject: Re: no clue

On 8/13/05, Simon Kr�ger <SimonKroeger@gmx.de> wrote:
> Hi Joe,
> 
> as a more serious contribution to your problem:
> this is 10 times faster:
> 
> data.each{ |j, line|
>    k, v = -2, 0
>    while (v = line.index(58, k))
>      h5[j][line[(k+2)...v].intern] =
>        line[(v+2)...(k = line.index(44, v) || line.length)]
>    end
> }
> 
> i attached the whole test script, the output is:
> 
>                            user     system      total        real
> inject                4.640000   0.046000   4.686000 (  4.687000)
> scan                  5.204000   0.063000   5.267000 (  5.875000)
> eval                  6.078000   0.016000   6.094000 (  6.094000)
> tmp                   4.375000   0.000000   4.375000 (  4.391000)
> index                 0.312000   0.000000   0.312000 (  0.312000)
> true
> 
> cheers
> 
> Simon
> 
> 
> require 'benchmark'
> 
> a = []
> 100.times {|i| a << [i, "x_position: #{200+i}, y_position: #{400+i}, z_position: #{300+i}"]}
> 
> data = a
> iter = 1000
> h1 = h2 = h3 = h4 = h5 = {}
> 
> Benchmark.bm 20 do |bm|
>         bm.report("inject") do
>                 iter.times {
>                         data.each{|i, line| h1[i]={}; line.split(/\s*[:,]\s*/).inject(false){|a,b|
>                           if a then h1[i][a.to_sym]=b; a=false else a=b end }}
>                 }
>         end
> 
>         bm.report "scan" do
>                 iter.times {
>                 data.each{|i, line|h2[i]={}; line.scan(/(\w+)\s*:\s*([^, ]*)/) do |k, v|
>                   h2[i][k.to_sym] = v
>                 end
>                 } }
>         end
> 
>         bm.report "eval" do
>                 iter.times {
>                         h3 = eval('{' << ('~' << data.join('~')).
>                                 gsub!(/\s*([^:~]+):\s*([^,~]+),?/, ':\1=>\'\2\',').
>                                         gsub!(/~(\d+)~/, '},\1=>{')[2..-2] << '}}')
>                 }
>         end
> 
>         bm.report "tmp" do
>                 iter.times {
>                         data.each{ |j, line| h4[j]={};tmp = line.split(/\s*[:,]\s*/)
>                                 (0...tmp.size).step(2){ |i| h4[j][tmp[i].to_sym]=tmp[i+1] }
>                         }}
>         end
> 
>         bm.report "index" do
>                 iter.times {
>                         data.each{ |j, line|
>                                 k, v = -2, 0
>                                 while (v = line.index(58, k))
>                                         h5[j][line[(k+2)...v].intern] = line[(v+2)...(k = line.index(44, v) || line.length)]
>                                 end
>                         }
>                 }
>         end
> 
> end
> 
> p((h1 == h2) && (h1 == h3) && (h1 == h4) && (h1 == h5))


Thank you!  I must say that the logic in the 'index' one confuses me though.