unbreakable 0.0.1 → 0.0.2

data/lib/unbreakable.rb

@@ -14,7 +14,7 @@ require 'dragonfly'
 #     require 'unbreakable'
 #
 #     class MyScraper < Unbreakable::Scraper
-#       def retrieve
+#       def retrieve(*args)
 #         # download all the documents
 #       end
 #       def processable
@@ -23,10 +23,10 @@ require 'dragonfly'
 #     end
 #
 #     class MyProcessor < Unbreakable::Processors::Transform
-#       def perform(temp_object)
+#       def perform
 #         # return the transformed record as a hash, array, etc.
 #       end
-#       def persist(temp_object, arg)
+#       def persist(arg)
 #         # store the hash/array/etc. in Mongo, MySQL, YAML, etc.
 #       end
 #     end

data/lib/unbreakable/processors/transform.rb

@@ -5,12 +5,12 @@ module Unbreakable
     #     require 'nokogiri'
     #     class MyProcessor < Unbreakable::Processors::Transform
     #       # Extracts the page title from an HTML page.
-    #       def perform(temp_object)
+    #       def perform
     #         Nokogiri::HTML(temp_object.data).at_css('title')
     #       end
     #
     #       # Saves the page title to an external database.
-    #       def persist(temp_object, arg)
+    #       def persist(arg)
     #         MyModel.create(:title => arg)
     #       end
     #     end
@@ -27,14 +27,18 @@ module Unbreakable
       include Dragonfly::Configurable
       include Dragonfly::Loggable
 
+      attr_reader :temp_object, :opts
+
       # +#transform+ must be defined on the subclass for Dragonfly to see it.
       # @param [Class] subclass a subclass
       def self.inherited(subclass)
         subclass.class_eval do
           # @param [Dragonfly::TempObject] temp_object
+          # @param [Hash] opts
           # @return [Dragonfly::TempObject] the same object
-          def transform(temp_object)
-            persist temp_object, perform(temp_object)
+          def transform(temp_object, opts = {})
+            @temp_object, @opts = temp_object, opts
+            persist perform
             temp_object
           end
         end
@@ -43,16 +47,14 @@ module Unbreakable
     private
 
       # Transforms a record.
-      # @param [Dragonfly::TempObject] temp_object
       # @return [Hash] the transformed record
-      def perform(temp_object)
+      def perform
         raise NotImplementedError
       end
 
       # Persists a transformed record.
-      # @param [Dragonfly::TempObject] temp_object
       # @param arg a transformed record
-      def persist(temp_object, arg)
+      def persist(arg)
         raise NotImplementedError
       end
     end

data/lib/unbreakable/scraper.rb

@@ -10,12 +10,12 @@ module Unbreakable
   #     require 'open-uri'
   #     class MyScraper < Unbreakable::Scraper
   #       # Stores the contents of +http://www.example.com/+ in +index.html+.
-  #       def retrieve
+  #       def retrieve(*args)
   #         store(:path => 'index.html'){ open('http://www.example.com/').read }
   #       end
   #
   #       # Processes +index.html+.
-  #       def process
+  #       def process(*args)
   #         fetch('index.html').process(:transform).apply
   #       end
   #
@@ -96,9 +96,9 @@ The most commonly used commands are:
       command = args.shift
       case command
       when 'retrieve'
-        retrieve
+        retrieve(*args)
       when 'process'
-        process
+        process(*args)
       when 'config'
         print_configuration @app
       when nil
@@ -148,14 +148,16 @@ The most commonly used commands are:
     end
 
     # Caches remote files to the datastore for later processing.
-    def retrieve
+    # @param [Array] args splat of command-line arguments
+    def retrieve(*args)
       raise NotImplementedError
     end
 
     # Processes cached files into machine-readable data.
-    def process
+    # @param [Array] args splat of command-line arguments
+    def process(*args)
       processable.each do |record|
-        fetch(record).process(:transform).apply
+        fetch(record).process(:transform, :args => args).apply
       end
     end
 

data/lib/unbreakable/version.rb

@@ -1,3 +1,3 @@
 module Unbreakable
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unbreakable
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-07 00:00:00.000000000Z
+date: 2011-09-08 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
-  requirement: &70281322437780 !ruby/object:Gem::Requirement
+  requirement: &70289593588560 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: 3.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *70281322437780
+  version_requirements: *70289593588560
 - !ruby/object:Gem::Dependency
   name: dragonfly
-  requirement: &70281322437140 !ruby/object:Gem::Requirement
+  requirement: &70289593588040 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: 0.9.5
   type: :runtime
   prerelease: false
-  version_requirements: *70281322437140
+  version_requirements: *70289593588040
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70281322436620 !ruby/object:Gem::Requirement
+  requirement: &70289593587560 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,7 +43,7 @@ dependencies:
         version: 2.6.0
   type: :development
   prerelease: false
-  version_requirements: *70281322436620
+  version_requirements: *70289593587560
 description: Abstracts and bulletproofs common scraping tasks.
 email:
 - info@opennorth.ca