acts_as_tokenizable 0.1.0

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Splendeo
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,17 @@
+= acts_as_tokenizable
+
+Description goes here.
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 Splendeo. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,53 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "acts_as_tokenizable"
+    gem.summary = "Acts as tokenizable"
+    gem.description = "Make ActiveRecord models easily searchable via tokens."
+    gem.email = "github@splendeo.es"
+    gem.homepage = "http://github.com/splendeo/acts_as_tokenizable"
+    gem.authors = ["Enrique Garcia Cota", "Francisco de Juan"]
+    gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "acts_as_tokenizable #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/acts_as_tokenizable.gemspec

@@ -0,0 +1,58 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{acts_as_tokenizable}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Enrique Garcia Cota", "Francisco de Juan"]
+  s.date = %q{2010-01-12}
+  s.description = %q{Make ActiveRecord models easily searchable via tokens.}
+  s.email = %q{github@splendeo.es}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README",
+     "README.rdoc"
+  ]
+  s.files = [
+    "LICENSE",
+     "README",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "acts_as_tokenizable.gemspec",
+     "init.rb",
+     "lib/acts_as_tokenizable.rb",
+     "lib/acts_as_tokenizable/acts_as_tokenizable.rb",
+     "lib/acts_as_tokenizable/string_extensions.rb",
+     "lib/tasks/tokenizer.rake",
+     "test/helper.rb",
+     "test/test_acts_as_tokenizable.rb"
+  ]
+  s.homepage = %q{http://github.com/splendeo/acts_as_tokenizable}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Acts as tokenizable}
+  s.test_files = [
+    "test/helper.rb",
+     "test/test_acts_as_tokenizable.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 0"])
+    else
+      s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
+  end
+end
+

data/init.rb

@@ -0,0 +1 @@
+require 'acts_as_tokenizable'

data/lib/acts_as_tokenizable/acts_as_tokenizable.rb

@@ -0,0 +1,42 @@
+module ActsAsTokenizable
+  require 'acts_as_tokenizable/string_extensions'
+  
+  # default to_token method. needs to have a "name" property on the object.
+  # override for more complex token generation
+  def to_token
+    raise NoMethodError.new("You must redefine to_token in your model. Example: self.name.to_token()")
+  end
+  
+  #makes self.token=self.to_token, in a convoluted way
+  def tokenize
+    self.send("#{self.class.token_field_name}=", self.to_token)
+  end
+  
+  module ClassMethods
+    attr_accessor :token_field_name
+    
+    # search_token parameter is used by tokenized_by. This function allows for preparation
+    # before tokenized_by function is invoked. Usually this means removing
+    # stop words, replacing words.
+    # By default it tokenizes each word and removes duplicates.
+    def prepare_search_token(search_token)
+      search_token.words_to_token
+    end
+  end
+  
+  def self.included(base)
+    base.class_eval do
+      extend ClassMethods
+      
+      named_scope :tokenized_by, lambda {|search_token|
+        search_strings = []
+        search_values = []
+        prepare_search_token(search_token).words.each do |w|
+          search_strings.push("#{token_field_name} LIKE ?")
+          search_values.push("%#{w}%")
+        end
+        {:conditions => [search_strings.join(' AND '), *search_values]}
+      }
+    end
+  end
+end

data/lib/acts_as_tokenizable/string_extensions.rb

@@ -0,0 +1,66 @@
+String.class_eval do
+  
+  #converts accented letters into ascii equivalents (i.e. ñ becomes n)
+  def normalize
+    #this version is in the forums but didnt work for me
+    #string = string.chars.normalize(:kd).gsub!(/[^\x00-\x7F]/n,'').to_s
+    mb_chars.normalize(:d).gsub(/[^\x00-\x7F]/n,'').to_s
+  end
+  
+  #returns true if numeric, false, otherwise
+  def numeric?
+    true if Float(self) rescue
+    return false
+  end
+  
+  #returns an array of strings containing the words on this string. removes spaces, strange chars, etc
+  def words
+    gsub(/\W/, ' ').split
+  end
+  
+  #removes certain words from a string. 
+  # As a side-effect, all word-separators are converted to the separator char
+  def remove_words(words_array, separator = ' ')
+    (words - words_array).join separator
+  end
+  
+  # replaces certain words on a string. 
+  # As a side-effect, all word-separators are converted to the separator char
+  def replace_words(replacements, separator = ' ')
+    replaced_words = words
+    replacements.each do |candidates,replacement|
+      candidates.each do |candidate|
+        replaced_words=replaced_words.collect {|w| w==candidate ? replacement : w}
+      end
+    end
+    replaced_words.join separator
+  end
+  
+  # returns an array that contains, in order:
+  #   * the numeric parts, converted to numbers
+  #   * the non-numeric parts, as text
+  # this is useful for sorting alphanumerically. For example:
+  # ["A1", "A12", "A2"].sort_by{|x| x.alphanumerics} => ["A1", "A2", "A12"]
+  #
+  # inspired by : http://blog.labnotes.org/2007/12/13/rounded-corners-173-beautiful-code/
+  def alphanumerics
+    split(/(\d+)/).map { |v| v =~ /\d/ ? v.to_i : v }
+  end
+  
+  #convert into something that can be used as an indexation key
+  def to_token(max_length=255)
+    string = self.normalize.strip.downcase.gsub(/\W/, '') #remove all non-alphanumeric
+    string = string.squeeze unless string.numeric? #remove duplicates, except on pure numbers
+    return string[0..(max_length-1)]
+  end
+  
+  #convert into something that can be used on links
+  def to_slug(separator='-')
+    self.strip.downcase.normalize.words.join(separator)
+  end
+  
+  #tokenizes each word individually, and joins the word with the separator char.
+  def words_to_token(max_length=255, separator = ' ')
+    words.collect{|w| w.to_token}.uniq.join(separator)[0..(max_length-1)]
+  end
+end

data/lib/acts_as_tokenizable.rb

@@ -0,0 +1,9 @@
+require 'acts_as_tokenizable/acts_as_tokenizable'
+
+class ActiveRecord::Base
+  def self.acts_as_tokenizable(field_name=:token)
+    include ActsAsTokenizable
+    self.token_field_name = field_name
+    self.before_validation :tokenize
+  end
+end

data/lib/tasks/tokenizer.rake

@@ -0,0 +1,57 @@
+require 'config/environment'
+
+def array_of_active_record_models
+  Dir.glob(RAILS_ROOT + '/app/models/*.rb').each { |file| require file }
+
+  models_with_token = ActiveRecord::Base.send(:subclasses).select{|m| m.respond_to?(:tokenized_by)}
+end
+
+def tokenize_records(records)
+  total_count = records.size
+  
+  count = 0
+  
+  records.each do |record|
+    record.tokenize     #this generates tokens
+    record.save false   #this saves without checking validations
+    count += 1
+    print "\r#{count}/#{total_count}"
+    GC.start if count % 1000 == 0 #launch garbage collection each 1000 registers
+  end
+  puts ""
+end
+
+def tokenize_models(regenerate = false)
+  start = Time.now
+  puts "Start token generation"
+  puts "++++++++++++++++++++++++++++++++"
+  
+  array_of_active_record_models.each do |model|
+  puts "Generating new tokens for #{model.name.pluralize}"
+  
+  conditions = "#{model.token_field_name} IS NULL OR #{model.token_field_name} = ''" unless regenerate
+
+  records_without_token = model.all(:conditions => conditions)
+    if records_without_token.size > 0 
+      tokenize_records(records_without_token)
+    else
+      puts "There are no records without token"
+      puts "++++++++++++++++++++++++++++++++"
+    end
+  end
+  puts "Elapsed time " + (Time.now - start).seconds.to_s + " seconds"
+  
+end
+
+namespace :tokens do
+  desc "Generates the token for objects without tokens."
+  task :generate => :environment do
+    tokenize_models
+  end
+  
+  desc "Re-builds the token for all objects."
+  task :regenerate => :environment do
+    tokenize_models(true)
+  end
+  
+end

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'acts_as_tokenizable'
+
+class Test::Unit::TestCase
+end

data/test/test_acts_as_tokenizable.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestActsAsTokenizable < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,80 @@
+--- !ruby/object:Gem::Specification 
+name: acts_as_tokenizable
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Enrique Garcia Cota
+- Francisco de Juan
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-01-12 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: thoughtbot-shoulda
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+description: Make ActiveRecord models easily searchable via tokens.
+email: github@splendeo.es
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README
+- README.rdoc
+files: 
+- LICENSE
+- README
+- README.rdoc
+- Rakefile
+- VERSION
+- acts_as_tokenizable.gemspec
+- init.rb
+- lib/acts_as_tokenizable.rb
+- lib/acts_as_tokenizable/acts_as_tokenizable.rb
+- lib/acts_as_tokenizable/string_extensions.rb
+- lib/tasks/tokenizer.rake
+- test/helper.rb
+- test/test_acts_as_tokenizable.rb
+has_rdoc: true
+homepage: http://github.com/splendeo/acts_as_tokenizable
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Acts as tokenizable
+test_files: 
+- test/helper.rb
+- test/test_acts_as_tokenizable.rb