mike.daless.io/blog: Posts

The scene: Pivotal NYC · get familiar with it

# hello-world.rb
require 'rubygems'
puts 'hello world'

# run from cmdline
valgrind ruby hello-world.rb

valgrind --partial-loads-ok=yes --undef-value-errors=no ruby hello-world.rb

==15535== Memcheck, a memory error detector.
==15535== Copyright (C) 2002-2007, and GNU GPL'd, by Julian Seward et al.
==15535== Using LibVEX rev 1804, a library for dynamic binary translation.
==15535== Copyright (C) 2004-2007, and GNU GPL'd, by OpenWorks LLP.
==15535== Using valgrind-3.3.0-Debian, a dynamic binary instrumentation framework.
==15535== Copyright (C) 2000-2007, and GNU GPL'd, by Julian Seward et al.
==15535== For more details, rerun with: -v
==15535== 
hello world
==15535== 
==15535== ERROR SUMMARY: 0 errors from 0 contexts (suppressed: 0 from 0)
==15535== malloc/free: in use at exit: 10,403,440 bytes in 138,986 blocks.
==15535== malloc/free: 420,496 allocs, 281,510 frees, 155,680,688 bytes allocated.
==15535== For counts of detected errors, rerun with: -v
==15535== searching for pointers to 138,986 not-freed blocks.
==15535== checked 10,654,020 bytes.
==15535== 
==15535== LEAK SUMMARY:
==15535==    definitely lost: 21,280 bytes in 1,330 blocks.
==15535==      possibly lost: 27,368 bytes in 1,840 blocks.
==15535==    still reachable: 10,354,792 bytes in 135,816 blocks.
==15535==         suppressed: 0 bytes in 0 blocks.
==15535== Rerun with --leak-check=full to see details of leaked memory.

namespace :test do
  # partial-loads-ok and undef-value-errors necessary to ignore
  # spurious (and eminently ignorable) warnings from the ruby
  # interpreter
  VALGRIND_BASIC_OPTS = "--num-callers=50 --error-limit=no \
                         --partial-loads-ok=yes --undef-value-errors=no"

  desc "run test suite under valgrind with basic ruby options"
  task :valgrind =&gt; :compile do
    cmdline = "valgrind #{VALGRIND_BASIC_OPTS} ruby #{HOE.make_test_cmd}"
    puts cmdline
    system cmdline
  end
end

def test_suite_cmdline
  require 'find'
  files = []
  Find.find("test") do |f|
    files &lt;&lt; f if File.basename(f) =~ /.*test.*\.rb$/
  end
  cmdline = "#{RUBY} -w -I.:lib:ext:test -rtest/unit \
               -e '%w[#{files.join(' ')}].each {|f| require f}'"
end

namespace :test do
  # partial-loads-ok and undef-value-errors necessary to ignore
  # spurious (and eminently ignorable) warnings from the ruby
  # interpreter
  VALGRIND_BASIC_OPTS = "--num-callers=50 --error-limit=no \
                         --partial-loads-ok=yes --undef-value-errors=no"

  desc "run test suite under valgrind with basic ruby options"
  task :valgrind =&gt; :compile do
    cmdline = "valgrind #{VALGRIND_BASIC_OPTS} #{test_suite_cmdline}"
    puts cmdline
    system cmdline
  end
end

gdb --args ruby -S rake test

namespace :test do
  desc "run test suite under gdb"
  task :gdb =&gt; :compile do
    system "gdb --args ruby #{HOE.make_test_cmd}"
  end
end

if RUBY_VERSION &lt; "1.9"
 def ruby18
   yield
 end
else
 def ruby18
 end
end

test-in-memory:
  adapter: sqlite3
  database: ':memory:'

def in_memory_database?
  ENV["RAILS_ENV"] == "test" and 
    ENV["IN_MEMORY_DB"] and
    Rails::Configuration.new.database_configuration['test-in-memory']['database'] == ':memory:'
end

if in_memory_database?
  puts "connecting to in-memory database ..."
  ActiveRecord::Base.establish_connection&#40;Rails::Configuration.new.database_configuration['test-in-memory']&#41;
  puts "building in-memory database from db/schema.rb ..."
  load "#{Rails.root}/db/schema.rb" # use db agnostic schema by default
  #  ActiveRecord::Migrator.up&#40;'db/migrate'&#41; # use migrations
end

$ IN_MEMORY_DB=1 RAILS_ENV=test ./script/console 
Loading test environment &#40;Rails 2.3.2&#41;
connecting to in-memory database ...
building in-memory database from db/schema.rb ...
-- create_table&#40;"users", {:force=&gt;true}&#41;
   -&gt; 0.0065s
-- add_index&#40;"users", ["deleted_at"], {:name=&gt;"index_users_on_deleted_at"}&#41;
   -&gt; 0.0004s
-- add_index&#40;"users", ["id", "deleted_at"], {:name=&gt;"index_users_on_id_and_deleted_at"}&#41;
   -&gt; 0.0003s

...

&gt;&gt;

IN_MEMORY_DB=yes spec spec

#  spec/suite.rb

require "spec/spec_helper"

if ENV['IN_MEMORY_DB']
  N_PROCESSES = [ENV['IN_MEMORY_DB'].to_i, 1].max
  specs = &#40;Dir["spec/**/*_spec.rb"]&#41;.sort.in_groups_of&#40;N_PROCESSES&#41;
  processes = []

  interrupt_handler = lambda do
    STDERR.puts "caught keyboard interrupt, exiting gracefully ..."
    processes.each { |process| Process.kill "KILL", process }
    exit 1
  end

  Signal.trap 'SIGINT', interrupt_handler
  1.upto&#40;N_PROCESSES&#41; do |j|
    processes &lt;&lt; Process.fork {
      specs.each do |array|
        if array[j-1]
          require array[j-1]
        end
      end
    }
  end
  1.upto&#40;N_PROCESSES&#41; { Process.wait }

else
  &#40;Dir["spec/**/*_spec.rb"]&#41;.each do |file|
    require file
  end
end

#
#  To use this task, simply set the following variables:
#
#    set :pivotal_tracker_project_id, PROJECT_ID
#    set :pivotal_tracker_token, TOKEN
#
#  Then, inside the task for your demo platform, add
#
#    task :demo do
#      ...
#      after :deploy, 'pivotal_tracker:deliver_stories'
#    end
#
namespace :pivotal_tracker do
  desc "deliver your project's 'finished' stories"
  task :deliver_stories do
    require 'rubygems'
    require 'activeresource'

    class Story &lt; ActiveResource::Base
      self.site = "http://www.pivotaltracker.com/services/v2/projects/:project_id"
    end

    Story.headers['X-TrackerToken'] = pivotal_tracker_token
    puts "* delivering tracker stories ..."
    response = Story.put&#40;:deliver_all_finished, :project_id =&gt; pivotal_tracker_project_id&#41;

    begin
      require 'sax-machine'
      class Story
        include SAXMachine
        element :name
        element :story_type
        element :estimate
        element :description
      end
      class Stories
        include SAXMachine
        elements :story, :as =&gt; :stories, :class =&gt; Story
      end
      doc = Stories.parse&#40;response.body&#41;
      puts "* delivered #{doc.stories.length} stories"
      doc.stories.each do |story|
        puts "  - #{story.story_type}: #{story.name} &#40;#{story.estimate} points&#41;"
      end
    rescue LoadError =&gt; e
      puts "* stories delivered."
    end
  end
end

def spanify_links(text)
  text.gsub(/&lt;a\s+(.*)&gt;(.*)&lt;\/a&gt;/i, '&lt;a \1&gt;&lt;span&gt;\2&lt;/span&gt;&lt;/a&gt;')
end

&lt;a href='http://foo.com/'&gt; Foo! &lt;/a&gt;

&lt;a href='http://foo.com/'&gt; &lt;span&gt; Foo! &lt;/span&gt; &lt;/a&gt;

For an html snippet 2374 bytes long ...
                          user     system      total        real
regex * 1000          0.160000   0.010000   0.170000 (  0.182207)
hpricot * 1000        5.740000   0.650000   6.390000 (  6.401207)

it took an average of 0.0064 seconds for Hpricot to parse and operate on an HTML snippet 2374 bytes long

For an html snippet 97517 bytes long ...
                          user     system      total        real
regex * 10            0.100000   0.020000   0.120000 (  0.122117)
hpricot * 10          3.190000   0.300000   3.490000 (  3.502819)

it took an average of 0.3503 seconds for Hpricot to parse and operate on an HTML snippet 97517 bytes long

For an html snippet 2374 bytes long ...
                          user     system      total        real
regex * 1000          0.160000   0.010000   0.170000 (  0.182207)
nokogiri * 1000       1.440000   0.060000   1.500000 (  1.537546)
hpricot * 1000        5.740000   0.650000   6.390000 (  6.401207)

it took an average of 0.0015 seconds for Nokogiri to parse and operate on an HTML snippet 2374 bytes long
it took an average of 0.0064 seconds for Hpricot to parse and operate on an HTML snippet 2374 bytes long

For an html snippet 97517 bytes long ...
                          user     system      total        real
regex * 10            0.100000   0.020000   0.120000 (  0.122117)
nokogiri * 10         0.310000   0.020000   0.330000 (  0.322290)
hpricot * 10          3.190000   0.300000   3.490000 (  3.502819)

it took an average of 0.0322 seconds for Nokogiri to parse and operate on an HTML snippet 97517 bytes long
it took an average of 0.3503 seconds for Hpricot to parse and operate on an HTML snippet 97517 bytes long

html.gsub(/&lt;a\s+(.*)&gt;(.*)&lt;\/a&gt;/i, '&lt;a \1&gt;&lt;span&gt;\2&lt;/span&gt;&lt;/a&gt;') # broken regex
html.gsub(/&lt;(script|noscript|object|embed|style|frameset|frame|iframe)[&gt;\s\S]*&lt;\/\1&gt;/, '')

doc.search("a/text()").wrap("&lt;span&gt;&lt;/span&gt;")
doc.search("script","noscript","object","embed","style","frameset","frame","iframe").unlink

mike.daless.io/blog: Posts

Easily Valgrind & GDB your Ruby C Extensions

Basics

Rakified!

A Note for OS X Users

GDB FTW!

SOLID Object-Oriented Design (Sandi Metz)

Change

Design might save you.

Ignorable Rules

Testing Interlude

Important Rules

Summary

ROA with Waves (Dan Yoder)

A Brief History

Waves Introduction

Web as Services

REST and ROA

How Does Waves Help?

Ruby Guide to *nix Plumbing (Eleanor McHugh)

The Unix Way

System Calls with Ruby DL

Multicore

Where is Ruby Really Heading? (Gregory Brown)

Moving to 1.9

Ruby 1.8.7

Peanut Gallery

Writing Extensions

Oversimplified Explanations of Ruby Variations

Welcome to Goruco!

Parallelize Your RSpec Suite

Deliver Tracker Stories from Capistrano

Nokogiri, Your New Swiss Army Knife

Prologue

The Scene

The Problem

Why, God? Why?

Get On With It, Already

Where Else Can I Use Nokogiri?

Nokogiri: World's Finest (XML/HTML) Saw