craft 0.0.1 → 0.0.2

data/README.md

@@ -1,29 +1,37 @@
 # Craft
 
-TODO: Write a gem description
+Craft XML and HTML into objects.
 
-## Installation
+## Examples
+```ruby
+require 'craft'
+require 'open-uri'
 
-Add this line to your application's Gemfile:
+class Page < Craft
+  # Use CSS selectors
+  one   :title,   'title'
 
-    gem 'craft'
+  # Use XPath
+  many  :links,   'a/@href'
 
-And then execute:
+  # Perform transforms on returned nodes
+  many  :images,  'img', lambda { |img| img.attr('src').upcase }
+end
 
-    $ bundle
+page = Page.parse open('http://www.google.com')
 
-Or install it yourself as:
+page.title #=> 'Google'
+page.links #=> ['http://www.google.com/imghp?hl=en&tab=wi', ...]
+page.images #=> ['/LOGOS/2012/MOBY_DICK12-HP.JPG']
 
-    $ gem install craft
+class Script < Craft
+  one :body, 'text()'
+end
 
-## Usage
+class Page < Craft
+  many :scripts, 'script', Script
+end
 
-TODO: Write usage instructions here
-
-## Contributing
-
-1. Fork it
-2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Commit your changes (`git commit -am 'Add some feature'`)
-4. Push to the branch (`git push origin my-new-feature`)
-5. Create new Pull Request
+page = Page.parse open('http://www.google.com')
+page.scripts[0].body #=> 'window.google=...'
+```

data/Rakefile

@@ -1 +1,8 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+    t.pattern = "spec/*_spec.rb"
+end
+
+task :default => :test

data/craft.gemspec

@@ -4,16 +4,19 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'craft/version'
 
 Gem::Specification.new do |gem|
-  gem.name          = "craft"
+  gem.name          = 'craft'
   gem.version       = Craft::VERSION
-  gem.authors       = ["Ezekiel Templin", "Hakan Ensari"]
-  gem.email         = ["code@papercavalier.com"]
-  gem.description   = %q{Data extraction tool}
-  gem.summary       = %q{Data extraction tool}
-  gem.homepage      = "https://github.com/papercavalier/craft"
+  gem.authors       = ['Ezekiel Templin', 'Hakan Ensari']
+  gem.email         = ['code@papercavalier.com']
+  gem.description   = %q{Craft XML into objects}
+  gem.summary       = %q{Craft is a data extraction tool that crafts objects
+                         out of HTML and XML.}
+  gem.homepage      = 'http://papercavalier.com/craft/'
 
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
-  gem.require_paths = ["lib"]
+  gem.require_paths = ['lib']
+
+  gem.add_dependency 'nokogiri', '~> 1.5'
 end

data/lib/craft.rb

@@ -1,5 +1,91 @@
-require "craft/version"
+require 'craft/version'
+require 'nokogiri'
 
-module Craft
-  # Your code goes here...
+# Craft objects out of HTML and XML.
+#
+# Examples
+#
+#   module Transformations
+#     IntegerTransform = lambda { |n| Integer n.text }
+#   end
+#
+#   class Person < Craft
+#     include Transformations
+#
+#     one :name, 'div.name'
+#     one :age, 'div.age', IntegerTransform
+#     many :friends, 'li.friend', Person
+#   end
+#
+class Craft
+  class << self
+    # We alias call to new so that crafted objects may nest themselves or other
+    # crafted objects as transformations.
+    alias call new
+
+    # Define a method that extracts a collection of values from a parsed
+    # document.
+    #
+    # name  - The Symbol name of the method.
+    # paths - One or more String XPath of CSS queries. An optional Proc
+    #         transformation on the extracted value may be appended. If none is
+    #         appended, the default transformation returns the stripped String
+    #         value of the node.
+    #
+    # Returns an Array.
+    def many(name, *paths)
+      transform = pop_transformation paths
+
+      define_method name do
+        @node.search(*paths).map { |node| transform.call node }
+      end
+    end
+
+    # Define a method that extracts a single value from a parsed document.
+    #
+    # name  - The Symbol name of the method.
+    # paths - One or more String XPath of CSS queries. An optional Proc
+    #         transformation on the extracted value may be appended. If none is
+    #         appended, the default transformation returns the stripped String
+    #         value of the node.
+    #
+    # Returns an Object.
+    def one(name, *paths)
+      transform = pop_transformation paths
+
+      define_method name do
+        transform.call @node.at(*paths)
+      end
+    end
+
+    # Parse a document.
+    #
+    # body - A String HTML or XML document.
+    #
+    # Returns an instance of its self.
+    def parse(body)
+      new Nokogiri body
+    end
+
+    private
+
+    def pop_transformation(array)
+      if array.last.respond_to? :call
+        array.pop
+      else
+        Module.new do
+          def self.call(node)
+            node.text.strip if node
+          end
+        end
+      end
+    end
+  end
+
+  # Craft a new object.
+  #
+  # node - A Nokogiri::XML::Node.
+  def initialize(node)
+    @node = node
+  end
 end

data/lib/craft/version.rb

@@ -1,3 +1,3 @@
-module Craft
-  VERSION = "0.0.1"
+class Craft
+  VERSION = '0.0.2'
 end

data/spec/craft_spec.rb

@@ -0,0 +1,58 @@
+require 'bundler/setup'
+require 'minitest/autorun'
+require 'craft'
+
+describe Craft do
+  let :html do
+    '<html><ul><li>1</li><li>2</li>'
+  end
+
+  let :klass do
+    Class.new Craft
+  end
+
+  let :instance do
+    klass.parse html
+  end
+
+  describe '.many' do
+    it 'extracts nodes' do
+      klass.many 'foo', 'li'
+      instance.foo.must_equal %w(1 2)
+    end
+
+    it 'transforms' do
+      klass.many 'foo', 'li', ->(node) { node.text.to_i }
+      instance.foo.must_equal [1, 2]
+    end
+  end
+
+  describe '.one' do
+    it 'extracts a node' do
+      klass.one 'foo', 'li'
+      instance.foo.must_equal '1'
+    end
+
+    it 'transforms' do
+      klass.one 'foo', 'li', ->(node) { node.text.to_i }
+      instance.foo.must_equal 1
+    end
+
+    describe 'given no matches' do
+      before do
+        klass.one 'foo', 'foo'
+      end
+
+      it 'returns nil' do
+        instance.foo.must_be_nil
+      end
+    end
+  end
+
+  it 'nests' do
+    nest = Class.new Craft
+    nest.many 'foo', 'li'
+    klass.one 'foo', 'ul', nest
+    instance.foo.foo.must_equal %w(1 2)
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: craft
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -10,9 +10,25 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-12 00:00:00.000000000 Z
-dependencies: []
-description: Data extraction tool
+date: 2012-10-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+description: Craft XML into objects
 email:
 - code@papercavalier.com
 executables: []
@@ -27,7 +43,8 @@ files:
 - craft.gemspec
 - lib/craft.rb
 - lib/craft/version.rb
-homepage: https://github.com/papercavalier/craft
+- spec/craft_spec.rb
+homepage: http://papercavalier.com/craft/
 licenses: []
 post_install_message: 
 rdoc_options: []
@@ -39,17 +56,23 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -3848600058118697198
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -3848600058118697198
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
-summary: Data extraction tool
-test_files: []
-has_rdoc: 
+summary: Craft is a data extraction tool that crafts objects out of HTML and XML.
+test_files:
+- spec/craft_spec.rb