streambot 0.5.4 → 1.0.0.rc1

data/README.rdoc

@@ -7,7 +7,7 @@ to get streambot installed, you simply need to run
 
     gem install streambot
 
-== beta release
+== development release
 
     gem install streambot --pre
 
@@ -19,10 +19,10 @@ The full rdoc is available on rdoc.info[http://rdoc.info/projects/gr4y/streambot
 
     require 'streambot'
 
-    @params = { "oauth" => {"key" => "consumer key", "secret" => "consumer secret"},
-                "http" => {"username" => "username", "password" => "password"} }
-    @blacklist = ['mac_rt','apple_rt']
-    bot = StreamBot::Tracker.new(@params, @blacklist, 'apple','ipad','iphone os 4','steve jobs')
+	@params = { 'auth' => { 'username' => 'your username', 'password' => 'your password' },
+	 			'oauth' => { 'key' => 'your consumer key', 'secret' => 'your consumer secret' },
+	 			'keywords' => ['nowplaying'] }
+    bot = StreamBot::Tracker.new(@params)
     bot.start
 
 = Configuration
@@ -38,54 +38,54 @@ You need to register an application of the type desktop application on http://de
 *key*:: The consumer key Twitter provides you
 *secret*:: The consumer secret Twitter provides you
 
-=== http
+=== auth
 *username*:: Your login username
 *password*:: Your login password
 
-=== filters
-When a filter is matching on an status, then it won't be retweeted.
+=== keywords 
+:: the list of keywords as an array
 
-*key*:: this should just hold an description of your filter
-*type*:: the type,
-*value*:: a string, thats the content that should be filtered
-
-----
-These types are actually supported:
-
-*USER*:: The users screenname/nickname *NOT* realname
-*SOURCE*:: The client which the user is using
-*LANGUAGE*:: The language that's set in users profile
-*TIMEZONE*:: The timezone that's set in users profile
-*CONTENT*:: A word the status text could include
-----
+=== filters_config
+:: the path to the filters.yml file
 
 I wrote this stuff into my config.yml and load the params with 
 
 	require 'yaml'
 	@params = YAML.load_file('config.yml')
 
-== Callbacks
+= Callbacks
 
-Since version 0.5.0 streambot has an simple callback mechanism.
+*on_error*:: this callback is fired when an error occures
 
-*before_start*:: is fired before the tracker is running
-*before_match*:: is fired before we start the filtering
-*match_filter*:: is fired when an filter has matched
-*before_retweet*:: is fired before retweeting
+= Filters
 
-=== Examples
-==== before_match
+You need to configure the *filters_config* in the params and set the path to the YAML file. At the moment this needs to be an YAML file, cause the tracker is reading this file, every time a new status comes in via the client. I decided to read it on each status, cause I don't wanted to restart the Tracker every time I made a change to the filters.
 
-Before filtering we just want to print the status id to the console
+For example we want to filter all tweets with the source "web", we need to define the following line in our *filters.yml*
 
-    bot = StreamBot::Tracker.new(@params, nil,'nowplaying')
-    bot.before_match do
-        status = bot.instance_variable_get("@status")
-        puts status.id
-    end
-    bot.start
+	"source": "web"
+
+The Tracker checks if the field "source" of the incoming status *includes* OR *is equal* to "web". If you want to filter more than one source, you simply need to write it this way:
+
+	"source": ["web", "TweetDeck"]
+
+You can define all fields inside the status object. You want to filter tweets by me, so you need to define
 
-That's just an example. You can do anything you want to do here.
+	"user/screen_name": "gr4y"
+
+You can even filter all tweets of users with an evil background color.
+
+	"user/profile_background_color": "666666"
+
+= Example
+
+	@params = YAML.load_file('config.yml')
+	@client = StreamBot::Tracker.new(@params)
+	
+	@client.on_error do |msg, stacktrace|
+		puts msg
+		puts stacktrace
+	end
 
 = Contribution
 == Testing

data/Rakefile

@@ -10,47 +10,22 @@ begin
     gem.email = "swessel@gr4yweb.de"
     gem.homepage = "http://github.com/gr4y/streambot"
     gem.authors = ["Sascha Wessel"]
-    gem.post_install_message = File.exist?('USAGE.rdoc') ? File.read('USAGE.rdoc') : ""
     gem.require_path = 'lib'
     gem.files = %w(Rakefile) + Dir.glob("{lib}/**/*") + %w(VERSION)
-    
-    # Dependency for dealing with twitter streaming API
-    gem.add_dependency "tweetstream",">= 1.0.4"
-    gem.add_dependency "oauth",">= 0.4.0"
-    gem.add_development_dependency "webmock",">= 1.0.0"
-    gem.add_development_dependency "rcov",">= 0.9.8"
-    gem.add_development_dependency "reek",">= 1.2.8"
-    
-    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+    # the runtime dependencies
+    gem.add_runtime_dependency "twistream", "~> 0.2.3"
+    gem.add_runtime_dependency "oauth","~> 0.4.0"
+    # the development dependencies
+    gem.add_development_dependency "bundler", "~> 1.0.0"
+    gem.add_development_dependency "rspec", [">= 2.4.0"]
+    gem.add_development_dependency "webmock","~> 1.0.0"
+    gem.add_development_dependency "rcov","~> 0.9.8"
+    gem.add_development_dependency "reek","~> 1.2.8"
   end
 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 :build_gem => [:test,:rdoc,:build]
-task :install_gem => [:build_gem,:install]
-task :default => [:check_dependencies,:rcov,:reek,:build_gem]
-
 require 'rake/rdoctask'
 Rake::RDocTask.new do |rdoc|
   version = File.exist?('VERSION') ? File.read('VERSION') : ""
@@ -65,3 +40,9 @@ Reek::Rake::Task.new do |t|
   t.fail_on_error = false
   t.verbose = true
 end
+
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec)
+
+task :test => [:check_dependencies, :spec]
+task :default => [:test, :reek, :build]

data/VERSION

@@ -1 +1 @@
-0.5.4
+1.0.0.rc1

data/lib/streambot.rb

@@ -2,19 +2,21 @@ require 'rubygems'
 require 'open-uri'
 require 'net/http'
 require 'oauth'
-require 'tweetstream'
+require 'twistream'
 require 'logger'
 require 'yaml'
 
-require 'streambot/callbacks'
+require 'streambot/event'
+require 'streambot/event_handler'
 require 'streambot/retweet'
 require 'streambot/handler'
 require 'streambot/oauth'
+require 'streambot/array_path'
 require 'streambot/tracker'
 
-module StreamBot  
+module StreamBot
   LOG = Logger.new(STDOUT)
   LIBPATH = ::File.expand_path(::File.dirname(__FILE__)) + ::File::SEPARATOR
   PATH = ::File.dirname(LIBPATH) + ::File::SEPARATOR
-  VERSION = ::File.exist?(PATH + 'VERSION') ? ::File.read(PATH+'VERSION') : ""
+  VERSION = ::File.exist?('VERSION') ? ::File.read('VERSION') : ""
 end

data/lib/streambot/array_path.rb

@@ -0,0 +1,15 @@
+module StreamBot
+  # ArrayPath like XPath, but for Arrays
+  class ArrayPath
+    
+    def self.get_path(object, path)
+      # raise "#{object} is not an array" if !object.is_a?(Array) 
+      segments = path.chomp.split("/")
+      segments.each do |segment|
+        object = object[segment]
+      end
+      object
+    end
+        
+  end
+end

data/lib/streambot/event.rb

@@ -0,0 +1,19 @@
+module StreamBot
+  # event class
+  class Event
+    attr_reader :name
+
+    def initialize(name)
+      @name = name
+    end
+
+    def handle(method=nil, & block)
+      @handler = method if method
+      @handler = block if block
+    end
+
+    def trigger(* args)
+      @handler.call(* args) if !@handler.nil?
+    end
+  end
+end

data/lib/streambot/event_handler.rb

@@ -0,0 +1,32 @@
+module StreamBot
+  module EventHandler
+
+    # register an event with the given name
+    def event(name)
+      register_event(name)
+    end
+
+    # register several events with the given names
+    def events(* names)
+      names.each do |name|
+        event(name)
+      end
+    end
+
+    private
+    # the real event registration
+    def register_event(name)
+      class_eval do
+        variable =:"@#{name}"
+        define_method(name) do
+          event = instance_variable_get(variable)
+          if event == nil
+            event = StreamBot::Event.new(name)
+            instance_variable_set(variable, event)
+          end
+          event
+        end
+      end
+    end
+  end
+end

data/lib/streambot/retweet.rb

@@ -8,7 +8,7 @@ module StreamBot
 
     # retweets the status with given id
     def retweet(id)
-      @handler.post("/statuses/retweet/#{id}.json",nil)
+      @handler.post("/statuses/retweet/#{id}.json", nil)
     end
   end
 end

data/lib/streambot/tracker.rb

@@ -1,88 +1,79 @@
 module StreamBot
+
   # The Tracker class that provides a start and a stop method
   # This class has serveral callback methods
   class Tracker
-    extend StreamBot::Callbacks
-    callbacks :before_start, :before_match, :match_filter, :before_retweet
-    # the initialization method aka the constructor
-    def initialize(params, blacklist, * keywords)
-      LOG.debug("Tracker#initialize")
-      http_auth = params['http']
-      @stream = TweetStream::Client.new(http_auth['username'], http_auth['password'])
-      @stream.on_error do |message|
-        LOG.error "#{message}"
-        @stream.stop
-      end
-      # initializing retweet
-      @retweet = StreamBot::Retweet.new(params)
-      # get string with keywords comma separated keywords 
-      @keywords=keywords.join(',')
-      # set blacklist array if not nil
-      @blacklist=blacklist
-      if !@blacklist.nil?
-        warn "blacklisting is deprecated and will be removed with streambot 0.6.0"
+    extend StreamBot::EventHandler
+    events :on_error, :on_match
+    attr_accessor :auth, :params
+
+    # initializes the tracker
+    def initialize(params)
+      self.params = params
+      @retweet = StreamBot::Retweet.new(self.params)
+      @client = TwiStream::Client.new(authentication)
+      @client.on_error do |msg, trace|
+        on_error.trigger(msg, trace)
       end
-      @filters = params['filters']
     end
 
-    # start the bot
+    # start the tracker
     def start
-      before_start
-      LOG.debug("Tracker#start")
-      # starting to track the keywords via tweetstream
-      @stream.track(@keywords) do |status|
-        # make status an instance variable for callbacks
-        @status = status
-        username = status.user.screen_name
-        matched = false
-        # if status.user is NOT in blacklist or filters don't match then retweet it
-        before_match
-        if (@blacklist.nil? || !@blacklist.include?(username)) && !@filters.nil?
-          @filters.each do |key, value|
-            matched = match?(status, value)
-            if matched == true
-              match_filter
-              LOG.debug("Tracker#start - filter #{key} matched!")
-              break
-            end
+      keywords = self.params["keywords"]
+      @client.filter_by_keywords(keywords) do |status|
+        if retweet?(status)
+          # one thread per retweet, 
+          # cause it's much, much faster
+          @thread = Thread.new do
+            @retweet.retweet(status["id"])
           end
         end
-        if matched == false
-          retweet(status)
-        end
       end
     end
-
-    # retweet the status
-    def retweet(status)
-      before_retweet
-      id = status.id
-      LOG.debug("Tracker#retweet - retweet ##{id} from @#{status.user.screen_name}")
-      @retweet.retweet(id)
+    
+    # stop the tracker
+    def stop
+      @client.stop
     end
-
-    # returns true if an filter is matching
-    def match?(status, filter)
-      @type = filter["type"]
-      @value = filter["value"]
-      if @type == "USER" then
-        status.user.screen_name.eql?(@value)
-      elsif @type == "CONTENT" then
-        status.text.include?(@value)
-      elsif @type == "LANGUAGE" then
-        status.user.lang.eql?(@value)
-      elsif @type == "SOURCE" then
-        # just a thought at this point:
-        # why the heck is html markup in the source field?
-        status.source.include?(@value)
-      elsif @type == "TIMEZONE" then
-        status.user.time_zone.eql?(@value)
+    
+    private
+    # returns the authentication object
+    def authentication
+      auth = self.params["auth"]
+      {:user => auth["username"], :pass => auth["password"]}
+    end
+    
+    # load the YAML file that is specified in the params
+    def load_filters
+      filters_config = self.params["filters_config" ]
+      if !filters_config.nil? && File.exists?(filters_config)
+        begin
+          YAML::load_file(filters_config)
+        rescue 
+          on_error.trigger($!, $@)
+        end
       end
     end
 
-    # stop the bot
-    def stop
-      @stream.stop
+    # decide if the status is retweetable    
+    def retweet?(status)
+      filters = load_filters
+      retweet = true
+      if !filters.nil?
+        filters.each_pair do |path, value|
+          array = []
+          array << value
+          array.flatten.each do |aValue|
+            path_value = ArrayPath.get_path(status, path)
+            if path_value.eql?(aValue) || path_value.include?(aValue)
+              LOG.info "filter matched on #{path} with #{aValue} in status ##{status['id']}"
+              on_match.trigger(status)
+              retweet = false
+            end
+          end
+        end
+      end
+      retweet
     end
   end
 end

data/spec/retweet_spec.rb

@@ -0,0 +1,13 @@
+require 'spec_helper'
+
+describe StreamBot::Retweet do
+
+  before :all do 
+    params = YAML.load_file('spec/params.yml')
+    @retweet = StreamBot::Retweet.new(params)
+  end
+  
+  describe "#retweet" do
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,2 @@
+require 'streambot'
+require 'yaml'

data/spec/tracker_spec.rb

@@ -0,0 +1,34 @@
+require 'spec_helper'
+
+describe StreamBot::Tracker do
+  
+  before :all do
+    params = YAML.load_file('spec/params.yml')
+    @tracker = StreamBot::Tracker.new(params)
+    @tracker.on_error do |msg, trace|
+      puts "#{msg}: #{trace}"
+    end
+    @tracker.on_match do |status, filter_path, filter_value|
+      puts "filter matched on #{filter_path} with #{filter_value} in status ##{status['id']}"
+    end
+  end
+  
+  describe "#start" do
+    it "should start" do
+      @tracker.start
+    end
+  end
+  
+  describe "wait" do 
+    it "should sleep for 60 seconds" do 
+      sleep 60
+    end
+  end
+  
+  describe "#stop" do 
+    it "should stop" do 
+      @tracker.stop
+    end
+  end
+  
+end

metadata

@@ -1,12 +1,8 @@
 --- !ruby/object:Gem::Specification 
 name: streambot
 version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 5
-  - 4
-  version: 0.5.4
+  prerelease: 6
+  version: 1.0.0.rc1
 platform: ruby
 authors: 
 - Sascha Wessel
@@ -14,22 +10,18 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-09-09 00:00:00 +02:00
+date: 2011-02-07 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: tweetstream
+  name: twistream
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - ">="
+    - - ~>
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 0
-        - 4
-        version: 1.0.4
+        version: 0.2.3
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
@@ -38,60 +30,66 @@ dependencies:
   requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - ">="
+    - - ~>
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 4
-        - 0
         version: 0.4.0
   type: :runtime
   version_requirements: *id002
 - !ruby/object:Gem::Dependency 
-  name: webmock
+  name: bundler
   prerelease: false
   requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - ">="
+    - - ~>
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 0
-        - 0
         version: 1.0.0
   type: :development
   version_requirements: *id003
 - !ruby/object:Gem::Dependency 
-  name: rcov
+  name: rspec
   prerelease: false
   requirement: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 9
-        - 8
-        version: 0.9.8
+        version: 2.4.0
   type: :development
   version_requirements: *id004
 - !ruby/object:Gem::Dependency 
-  name: reek
+  name: webmock
   prerelease: false
   requirement: &id005 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - ">="
+    - - ~>
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 2
-        - 8
-        version: 1.2.8
+        version: 1.0.0
   type: :development
   version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  name: rcov
+  prerelease: false
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: 0.9.8
+  type: :development
+  version_requirements: *id006
+- !ruby/object:Gem::Dependency 
+  name: reek
+  prerelease: false
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: 1.2.8
+  type: :development
+  version_requirements: *id007
 description: a simple gem that tracks several keywords via twitter streaming api and re-publish it on twitter
 email: swessel@gr4yweb.de
 executables: []
@@ -105,26 +103,25 @@ files:
 - Rakefile
 - VERSION
 - lib/streambot.rb
-- lib/streambot/callbacks.rb
+- lib/streambot/array_path.rb
+- lib/streambot/event.rb
+- lib/streambot/event_handler.rb
 - lib/streambot/handler.rb
 - lib/streambot/oauth.rb
 - lib/streambot/retweet.rb
 - lib/streambot/tracker.rb
 - LICENSE
 - README.rdoc
-- test/streambot/base_test.rb
-- test/streambot/test_oauth.rb
-- test/streambot/test_retweet.rb
+- spec/retweet_spec.rb
+- spec/spec_helper.rb
+- spec/tracker_spec.rb
 has_rdoc: true
 homepage: http://github.com/gr4y/streambot
 licenses: []
 
-post_install_message: "=== You are upgrading from an earlier version?\n\n\
-  Then you maybe need to change your code.\n\
-  In version 0.4.0 oauth was introduced and I recommend you to read the README\n\n\
-  code is available on github[http://github.com/gr4y/streambot] "
-rdoc_options: 
-- --charset=UTF-8
+post_install_message: 
+rdoc_options: []
+
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
@@ -132,25 +129,21 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+      version: 1.3.1
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.5.0
 signing_key: 
 specification_version: 3
 summary: retweeting tweets with specified keywords on twitter
 test_files: 
-- test/streambot/base_test.rb
-- test/streambot/test_oauth.rb
-- test/streambot/test_retweet.rb
+- spec/retweet_spec.rb
+- spec/spec_helper.rb
+- spec/tracker_spec.rb

data/lib/streambot/callbacks.rb

@@ -1,29 +0,0 @@
-module StreamBot
-  module Callbacks    
-    def callback(name)
-      register_callback(name)
-    end
-
-    def callbacks(* names)
-      names.each do |name|
-        register_callback(name)
-      end
-    end
-
-    def is_registered?(name)      
-      @callbacks.include?(name)
-    end
-
-    def register_callback(name)
-      class_eval <<-EOF
-          def #{name} (*args,&block)
-            if block
-              @#{name} = block
-            elsif @#{name}
-              @#{name}.call(*args)
-            end
-          end
-      EOF
-    end
-  end
-end

data/test/streambot/base_test.rb

@@ -1,34 +0,0 @@
-require 'rubygems'
-require 'test/unit'
-require 'webmock'
-require 'yaml'
-include WebMock
-
-require 'streambot'
-
-module StreamBot
-  # The base of all tests in this projet
-  #
-  #   class TestName < StreamBot::BaseTest
-  #  
-  #     def setup 
-  #       super
-  #       # implementation goes here
-  #     end
-  #   end
-  class BaseTest < Test::Unit::TestCase
-
-    # reading config.yml and assign all keys to instance
-    def read_config
-      yml_config = YAML.load_file(File.dirname(__FILE__) + "/config.yml")
-      yml_config.each do |key, value|
-        instance_variable_set("@#{key}", value)
-      end
-    end
-
-    # :nodoc:
-    def setup
-      self.read_config
-    end
-  end
-end

data/test/streambot/test_oauth.rb

@@ -1,31 +0,0 @@
-require 'streambot/base_test'
-
-module StreamBot
-  # test for http wrapper class
-  class TestOAuth < StreamBot::BaseTest
-    # setup
-    def setup
-      super
-      WebMock.allow_net_connect!
-      @oauth = StreamBot::OAuth.new(@params['oauth'])
-      stub_request(:post,"http://api.twitter.com/statuses/update.json").to_return(:body=>"response")
-    end
-
-    def test_verify_credentials
-      json = @oauth.get('/account/verify_credentials.json')
-      assert_not_nil(json)
-    end
-
-    def test_post
-      WebMock.disable_net_connect!
-      json = @oauth.post('/statuses/update.json',{:status => 'test'})
-      assert_not_nil(json)
-      assert_equal("response",json)
-    end
-
-    # nil all variables
-    def teardown
-      @oauth = nil
-    end
-  end
-end

data/test/streambot/test_retweet.rb

@@ -1,34 +0,0 @@
-require 'streambot/base_test'
-
-module StreamBot
-  # the test for testing retweet functionality
-  class TestRetweet < StreamBot::BaseTest
-    # setup the test 
-    def setup
-      super
-      @retweet = StreamBot::Retweet.new(@params)
-      if @params['auth_type'] == "oauth"
-        stub_request(:post, "http://api.twitter.com/statuses/retweet/12355936428.json").to_return(:body => "response")
-      elsif @params['auth_type'] == "http"
-        stub_request(:post, "http://#{@params['http']['username']}:#{@params['http']['password']}@api.twitter.com/statuses/retweet/12355936428.json").to_return(:body => "response")
-      end
-    end
-
-    # retweet
-    def test_retweet
-      # no permission to access web!
-      WebMock.disable_net_connect!
-      # retweet the given id
-      response = @retweet.retweet(@id)
-      # assertion
-      assert_not_nil(response)
-      assert_equal("response", response)
-    end
-
-    # teardown the test
-    # nil all instance variables
-    def teardown
-      @id, @retweet = nil
-    end
-  end
-end