crowdflower 0.2.3

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,6 @@
+*.sw?
+.DS_Store
+coverage
+rdoc
+pkg
+tags

data/HISTORY.md

@@ -0,0 +1,18 @@
+## 0.2.2 (2010-02-03)
+* Simple Job#update addition
+
+## 0.2.1 (2010-01-24)
+* Added latest attribute to judgments
+* Fixed judgment class
+* Added judgment for a unit
+
+## 0.2.0 (2009-10-13)
+
+* Integration tests for CrowdFlower servers
+* No more API redirects
+* Webhook capability added
+
+## 0.1.0 (2009-09-14)
+
+* First release
+

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Dolores Labs
+
+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 +1,20 @@
+= ruby-crowdflower
+
+A toolkit for interacting with CrowdFlower via the REST API.
+
+This is alpha software. Have fun!
+
+== 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) 2009 Dolores Labs. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,46 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "crowdflower"
+    gem.summary = %Q{a toolkit for the CrowdFlower API}
+    gem.description = <<-EOF
+A toolkit for interacting with CrowdFlower via the REST API.
+
+This is alpha software. Have fun!
+
+EOF
+    gem.email = "brian@doloreslabs.com"
+    gem.homepage = "http://github.com/dolores/ruby-crowdflower"
+    gem.authors = ["Brian P O'Rourke", "Chris Van Pelt"]
+    gem.add_dependency 'httparty', '>= 0.4.3'
+  end
+
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+task :default => :build
+
+task :refresh_builder => [:build] do
+  cp "pkg/crowdflower-#{File.read("VERSION").strip}.gem", "../builder/gems/cache/"
+  rm_rf "../builder/gems/gems/crowdflower-#{File.read("VERSION").strip}/"
+  `cd ../builder && bin/thor merb:gem:redeploy`
+end
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "crowdflower #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.2.3

data/bindev/cl_skel.rb

@@ -0,0 +1,164 @@
+#!/usr/bin/env ruby 
+
+# == Synopsis 
+#   Use this command-line utility to create and update CrowdFlower jobs.
+#
+# == Examples
+#   Create a new job and populate it with data from a twitter feed.
+#     crowdflower -n -u 'http://search.twitter.com/search?q=milksteak'
+#
+#   Other examples:
+#     crowdflower -q bar.doc
+#     crowdflower --verbose foo.html
+#
+# == Usage 
+#   crowdflower [options] source_file
+#
+#   For help use: crowdflower -h
+#
+# == Options
+#   -h, --help          Displays help message
+#   -v, --version       Display the version, then exit
+#   -q, --quiet         Output as little as possible, overrides verbose
+#   -V, --verbose       Verbose output
+#   -n, --new           Create a new job
+#   -u, --uri           Accepts an RSS, Atom, XML, or JSON data feed
+#   -f, --file          Accepts .csv, .tsv, .xls, .xlsx, and .ods
+#   TO DO - add additional options
+#
+# == Author
+#   Mark Erdmann
+#
+# == Copyright
+#   Copyright (c) 2007 CrowdFlower. Licensed under the MIT License:
+#   http://www.opensource.org/licenses/mit-license.php
+
+
+# TO DO - update Synopsis, Examples, etc
+# TO DO - change license if necessary
+
+
+
+require 'optparse' 
+require 'rdoc/usage'
+require 'ostruct'
+require 'date'
+
+
+class App
+  VERSION = '0.0.1'
+  
+  attr_reader :options
+
+  def initialize(arguments, stdin)
+    @arguments = arguments
+    @stdin = stdin
+    
+    # Set defaults
+    @options = OpenStruct.new
+    @options.verbose = false
+    @options.quiet = false
+    # TO DO - add additional defaults
+  end
+
+  # Parse options, check arguments, then process the command
+  def run
+        
+    if parsed_options? && arguments_valid? 
+      
+      puts "Start at #{DateTime.now}\n\n" if @options.verbose
+      
+      output_options if @options.verbose # [Optional]
+            
+      process_arguments            
+      process_command
+      
+      puts "\nFinished at #{DateTime.now}" if @options.verbose
+      
+    else
+      output_usage
+    end
+      
+  end
+  
+  protected
+  
+    def parsed_options?
+      
+      # Specify options
+      opts = OptionParser.new 
+      opts.on('-v', '--version')    { output_version ; exit 0 }
+      opts.on('-h', '--help')       { output_help }
+      opts.on('-V', '--verbose')    { @options.verbose = true }  
+      opts.on('-q', '--quiet')      { @options.quiet = true }
+      opts.on('-n', '--new')        { @options.newjob = true }
+      opts.on('-u', '--uri')        { @options.uri = }
+      # TO DO - add additional options
+            
+      opts.parse!(@arguments) rescue return false
+      
+      process_options
+      true      
+    end
+
+    # Performs post-parse processing on options
+    def process_options
+      @options.verbose = false if @options.quiet
+    end
+    
+    def output_options
+      puts "Options:\n"
+      
+      @options.marshal_dump.each do |name, val|        
+        puts "  #{name} = #{val}"
+      end
+    end
+
+    # True if required arguments were provided
+    def arguments_valid?
+      # TO DO - implement your real logic here
+      true if @arguments.length == 1 
+    end
+    
+    # Setup the arguments
+    def process_arguments
+      # TO DO - place in local vars, etc
+    end
+    
+    def output_help
+      output_version
+      RDoc::usage() #exits app
+    end
+    
+    def output_usage
+      RDoc::usage('usage') # gets usage from comments above
+    end
+    
+    def output_version
+      puts "#{File.basename(__FILE__)} version #{VERSION}"
+    end
+    
+    def process_command
+      # TO DO - do whatever this app does
+      
+      #process_standard_input # [Optional]
+    end
+
+    def process_standard_input
+      input = @stdin.read      
+      # TO DO - process input
+      
+      # [Optional]
+      # @stdin.each do |line| 
+      #  # TO DO - process each line
+      #end
+    end
+end
+
+
+# TO DO - Add your Modules, Classes, etc
+
+
+# Create and run the application
+app = App.new(ARGV, STDIN)
+app.run

data/crowdflower.gemspec

@@ -0,0 +1,65 @@
+# 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{crowdflower}
+  s.version = "0.2.3"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Brian P O'Rourke", "Chris Van Pelt"]
+  s.date = %q{2010-02-22}
+  s.description = %q{A toolkit for interacting with CrowdFlower via the REST API.
+
+This is alpha software. Have fun!
+
+}
+  s.email = %q{brian@doloreslabs.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "HISTORY.md",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "bindev/cl_skel.rb",
+     "bindev/crowdflower.rb",
+     "crowdflower.gemspec",
+     "lib/crowdflower.rb",
+     "lib/crowdflower/base.rb",
+     "lib/crowdflower/job.rb",
+     "lib/crowdflower/judgment.rb",
+     "lib/crowdflower/order.rb",
+     "lib/crowdflower/unit.rb",
+     "test/integration_tests.rb",
+     "test/sample.csv"
+  ]
+  s.homepage = %q{http://github.com/dolores/ruby-crowdflower}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.6}
+  s.summary = %q{a toolkit for the CrowdFlower API}
+  s.test_files = [
+    "test/integration_tests.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_runtime_dependency(%q<httparty>, [">= 0.4.3"])
+    else
+      s.add_dependency(%q<httparty>, [">= 0.4.3"])
+    end
+  else
+    s.add_dependency(%q<httparty>, [">= 0.4.3"])
+  end
+end
+

data/lib/crowdflower/base.rb

@@ -0,0 +1,47 @@
+module CrowdFlower
+  @@key = nil
+  @@domain = nil
+
+  class UsageError < StandardError ; end
+
+  class APIError < StandardError
+    attr_reader :details
+
+    def initialize(hash)
+      @details = hash
+      super @details["message"]
+    end
+  end
+  
+  module Defaults
+    def self.included(base)
+      base.send :include, HTTParty
+      base.send :headers, "accept" => "application/json"
+      base.send :format, :json
+      base.extend ClassMethods
+    end
+
+    module ClassMethods
+      def connect
+        unless CrowdFlower.key
+          raise UsageError, "Please establish a connection using 'CrowdFlower.connect!'"
+        end
+        self.base_uri CrowdFlower.domain
+        self.default_params :key => CrowdFlower.key
+      end
+    end
+  end
+  
+  def self.connect!(key, development = false)
+    @@domain = development ? "http://api.tsujigiri.local:4000/v1" : "https://api.crowdflower.com/v1"
+    @@key = key
+  end
+
+  def self.key
+    @@key
+  end
+
+  def self.domain
+    @@domain
+  end
+end

data/lib/crowdflower/job.rb

@@ -0,0 +1,124 @@
+module CrowdFlower
+  class Job
+    include Defaults
+    attr_reader :id
+    
+    def initialize(job_id)
+      @id = job_id
+      Job.connect
+    end
+
+    def resource_uri
+      Job.resource_uri
+    end
+
+    def self.resource_uri
+      "/jobs"
+    end
+
+    def self.all
+      connect
+      get(resource_uri)
+    end
+    
+    def self.upload(file, content_type, job_id = nil)
+      connect
+      job_uri = job_id ? "/#{job_id}" : ""
+      res = post("#{resource_uri}/#{job_uri}/upload", 
+        :body => File.read(file), 
+        :headers => custom_content_type(content_type))
+      if res["error"]
+        raise CrowdFlower::APIError.new(res["error"])
+      end
+      Job.new(res["id"])
+    end
+
+    # Creates a new empty Job in CrowdFlower.
+    def self.create
+      connect
+      res = post("#{resource_uri}/upload", :query => {:job => {:without_data => "true" } } )
+      if res["error"]
+        raise CrowdFlower::APIError.new(res["error"])
+      end
+      Job.new(res["id"])
+    end
+ 
+    def get(id = nil)
+      Job.get("#{resource_uri}/#{@id || id}")
+    end
+
+    # Returns an accessor for all the Units associated with this job.
+    # This enables you to do things like:
+    #
+    # * job.units.all
+    # * job.units.get [id]
+    # * job.units.create [data]
+    def units
+      Unit.new(self)
+    end
+    
+    # Copies a job and optionally gold or all units.
+    # Parameters
+    #  opts: Hash
+    #    gold: when set to true copies gold units
+    #    all_units: when set to true copies all units
+    def copy(opts = {})
+      res = Job.get("#{resource_uri}/#{@id}/copy", {:query => opts})
+      if res["error"]
+        raise CrowdFlower::APIError.new(res["error"])
+      end
+      Job.new(res["id"])
+    end
+    
+    def status
+      Job.get("#{resource_uri}/#{@id}/ping")
+    end
+    
+    def upload(file, content_type)
+      Job.upload(file, content_type, @id)
+    end
+    
+    def legend
+      Job.get("#{resource_uri}/#{@id}/legend")
+    end
+    
+    def download_csv(full = true, filename = nil)
+      filename ||= "#{full ? "f" : "a"}#{@id}.csv"
+      res = Job.get("#{resource_uri}/#{@id}.csv", {:format => :csv, :query => {:full => full}})
+      puts "Status... #{res.code.inspect}"
+      if res.code == 202
+        puts "CSV Generating... Trying again in 10 seconds."
+        Kernel.sleep 10
+        download_csv(full, filename)
+      else
+        puts "CSV written to: #{File.expand_path(filename)}"
+        File.open(filename, "w") {|f| f.puts res.body }
+      end
+    end
+    
+    def pause
+      Job.get("#{resource_uri}/#{@id}/pause")
+    end
+    
+    def resume
+      Job.get("#{resource_uri}/#{@id}/resume")
+    end
+    
+    def cancel
+      Job.get("#{resource_uri}/#{@id}/cancel")
+    end
+
+    def update(data)
+      res = Job.put("#{resource_uri}/#{@id}.json", {:query => { :job => data }, :headers => { "Content-Length" => "0" } } )
+      if res["error"]
+        raise CrowdFlower::APIError.new(res["error"])
+      end
+    end
+
+    private
+    def self.custom_content_type(content_type)
+      #To preserve the accept header we are forced to merge the defaults back in...
+      Job.default_options[:headers].merge({"content-type" => content_type})
+    end
+  end
+end

data/lib/crowdflower/judgment.rb

@@ -0,0 +1,24 @@
+module CrowdFlower
+  class Judgment
+    include Defaults
+    attr_reader :job
+    
+    def initialize(job)
+      @job = job
+      Judgment.connect
+    end
+    
+    def resource_uri
+      "/jobs/#{@job.id}/judgments"
+    end
+    
+    #Pull every judgment
+    def all(page = 1, limit = 100, latest = true)#full = true
+      Judgment.get(resource_uri, {:query => {:limit => limit, :page => page, :latest => latest}})
+    end
+    
+    def get(id)
+      Judgment.get("/#{id}")
+    end
+  end
+end

data/lib/crowdflower/order.rb

@@ -0,0 +1,19 @@
+module CrowdFlower
+  class Order
+    include Defaults
+    attr_reader :job
+    
+    def initialize(job)
+      @job = job
+      Order.connect
+    end
+
+    def resource_uri
+      "/jobs/#{@job.id}/orders"
+    end
+    
+    def debit(percentage = 100, channels = ["amt"])
+      Order.post(resource_uri, {:body => {:percentage => percentage, :channels => channels}})
+    end
+  end
+end

data/lib/crowdflower/unit.rb

@@ -0,0 +1,39 @@
+module CrowdFlower
+  class Unit
+    include Defaults
+    attr_reader :job
+    
+    def initialize(job)
+      @job = job
+      Unit.connect
+    end
+
+    def resource_uri
+      "/jobs/#{@job.id}/units"
+    end
+    
+    def all(page = 1, limit = 1000)
+      Unit.get(resource_uri, {:query => {:limit => limit, :page => page}})
+    end
+    
+    def get(id)
+      Unit.get("#{resource_uri}/#{id}")
+    end
+    
+    def judgments(id)
+      Unit.get("#{resource_uri}/#{id}/judgments")
+    end
+    
+    def create(data, gold = nil)
+      Unit.post(resource_uri, {:query => {:unit => {:data => data.to_json, :golden => gold}}})
+    end
+    
+    def copy(unit_id, job_id, data = {})
+      Unit.get("#{resource_uri}/#{unit_id}/copy", {:query => {:unit => {:job_id => job_id, :data => data}}})
+    end
+    
+    def split(on, with = " ")
+      Unit.get("#{resource_uri}/split", {:query => {:on => on, :with => with}})
+    end
+  end
+end

data/lib/crowdflower.rb

@@ -0,0 +1,6 @@
+require 'httparty'
+require 'crowdflower/base'
+require 'crowdflower/job'
+require 'crowdflower/unit'
+require 'crowdflower/judgment'
+require 'crowdflower/order'

data/test/integration_tests.rb

@@ -0,0 +1,94 @@
+$: << File.dirname(__FILE__) + "/../lib"
+
+require 'rubygems'
+require 'ruby-crowdflower'
+require 'json'
+
+API_KEY   = ENV["API_KEY"]
+
+unless API_KEY && API_KEY.size > 5
+  puts <<EOF
+
+  These integration tests interact with api.crowdflower.com.
+  In order to run them, you will need to specify your API key.
+
+  This file is meant only as a reference - please understand
+  what you are doing before using the API - you are responsible
+  for your usage.
+
+EOF
+
+  exit 1
+end
+
+# If you turn this on, tasks will be posted on CrowdFlower and your
+# account will be charged. This is inadvisable for anyone other than
+# CrowdFlower employees.
+I_AM_RICH = ENV["CF_LIVE_TRANSACTIONS"] == "true"
+
+if I_AM_RICH
+  puts "*** LIVE TRANSACTIONS ENABLED - THIS TEST RUN WILL BE CHARGED ***"
+  puts
+end
+
+def wait_until
+  10.times do
+    if yield
+      return
+    end
+    sleep 1
+  end
+  raise "Condition not met in a reasonable time period"
+end
+
+def assert(truth)
+  unless truth
+    raise "Condition not met"
+  end
+end
+
+def say(msg)
+  $stdout.puts msg
+end
+
+say "Connecting to the API"
+CrowdFlower.connect! API_KEY, true
+
+say "Uploading a test CSV"
+job = CrowdFlower::Job.upload(File.dirname(__FILE__) + "/sample.csv", "text/csv")
+
+say "Trying to get all jobs"
+assert CrowdFlower::Job.all.first["id"] == job.id
+
+say "-- Waiting for CrowdFlower to process the data"
+wait_until { job.get["units_count"] == 4 }
+
+say "Adding some more data"
+job.upload(File.dirname(__FILE__) + "/sample.csv", "text/csv")
+
+say "-- Waiting for CrowdFlower to process the data"
+# You could also register a webhook to have CrowdFlower notify your
+# server.
+wait_until { job.get["units_count"] == 8 }
+
+say "Getting the units for this job."
+assert job.units.all.size == 8
+
+say "Copying the existing job to a new one."
+job2 = job.copy :all_units => true
+
+say "-- Waiting for CrowdFlower to finish copying the job."
+# You could also register a webhook to have CrowdFlower notify your
+# server.
+wait_until { job2.get["units_count"] == 8 }
+
+say "Checking the status of the job."
+assert job.status["tainted_judgments"] == 0
+
+say "Registering a webhook."
+job.update :webhook_uri => "http://localhost:8080/crowdflower"
+
+say "Webhook test needs to be written."
+#job.test_webhook
+
+say ">-< Tests complete. >-<"

data/test/sample.csv

@@ -0,0 +1,5 @@
+"created_at","from_user","text"
+"Sat, 10 Oct 2009 01:00:07 +0000","sogowave","CrowdFlower easily connects you with thousands of people online, around the clock. http://ow.ly/rpaT"
+"Sat, 10 Oct 2009 01:00:05 +0000","SogoPR","CrowdFlower easily connects you with thousands of people online, around the clock. http://ow.ly/rpaS"
+"Fri, 09 Oct 2009 15:00:07 +0000","SIIA_Software","...and don't forget: @CloudTrigger @businessobjects @longjump @CrowdFlower http://bit.ly/397y72"
+"Fri, 02 Oct 2009 19:49:50 +0000","julzie","RT @rev2 CrowdFlower - Labor as a Service in a New Concept | Rev2.org http://retwt.me/v80H - GO LaaS!!"

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification 
+name: crowdflower
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 2
+  - 3
+  version: 0.2.3
+platform: ruby
+authors: 
+- Brian P O'Rourke
+- Chris Van Pelt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-02-22 00:00:00 -08:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: httparty
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 4
+        - 3
+        version: 0.4.3
+  type: :runtime
+  version_requirements: *id001
+description: |+
+  A toolkit for interacting with CrowdFlower via the REST API.
+  
+  This is alpha software. Have fun!
+  
+email: brian@doloreslabs.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- HISTORY.md
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- bindev/cl_skel.rb
+- bindev/crowdflower.rb
+- crowdflower.gemspec
+- lib/crowdflower.rb
+- lib/crowdflower/base.rb
+- lib/crowdflower/job.rb
+- lib/crowdflower/judgment.rb
+- lib/crowdflower/order.rb
+- lib/crowdflower/unit.rb
+- test/integration_tests.rb
+- test/sample.csv
+has_rdoc: true
+homepage: http://github.com/dolores/ruby-crowdflower
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: a toolkit for the CrowdFlower API
+test_files: 
+- test/integration_tests.rb