document_builder 0.1.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    NTc3MWYxYWFhYWQwOWI4MjUzOGRhMGE3MGRlNWI0MWExNzk0MDk4NA==
+  data.tar.gz: !binary |-
+    NDM3MGRkYzNiMWEzMmEyNDYxYjg5MmE5Y2ViZjMzN2Y0NGFiZmYyZQ==
+SHA512:
+  metadata.gz: !binary |-
+    YjJhZjQwYjk3ZWQ1NzQ3ZjY2ZTI5ZWUzOWQxYmE1YmVmNTQ4ODc1MDljOGJh
+    YzhmMTAwZTQ4MGUzMjI0MWRiZGUwZmU4ZjgyZDhiODkyNjM1NmVlODZjYWRl
+    MTZmZDU1NTNjY2NhMWZmNmM1MjFkMzBmNjliZTg2M2MzZDljNDM=
+  data.tar.gz: !binary |-
+    MzIyMTJlN2E1NjBhNDUyYjQ0MjdhY2YxYjljNzhmNTNkMWE5OWZmZjViMzcz
+    ODA5NDQ5N2FhNWE5Y2M1ZTA2YWU0ZTA4YzY2MmE5ZDM4Mjg0MjI4YjY5MGZh
+    YmM3ODNlZTZjYTk0YjI1YjJjNTY4M2IwNDhjYTRhZGU5MGY5Yjg=

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,11 @@
+language: ruby
+rvm:
+- 2.2.0
+deploy:
+  provider: rubygems
+  api_key:
+    secure: KLDtpoSEkumzNlaVuzyQUcrFdgMQcLSuGvG5F3yZptijDfFQ4dnQG3MkpdgPuJdxu7J5FZssaFaNDPfb9sgP5pYRcayW4iX3VzKJ5kfsSMYkoU/Yj8PENUGRyK0PjZjJIIeWOPwWg0ZgSBzW9f55Frvv3RBevLHH2c5flHAM0u0=
+  gem: document_builder
+  on:
+    tags: true
+    repo: bullfight/document_builder

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in document_builder.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 Patrick Schmitz
+
+MIT License
+
+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.md

@@ -0,0 +1,129 @@
+# DocumentBuilder
+
+[![Build Status](https://travis-ci.org/bullfight/document_builder.svg?branch=master)](https://travis-ci.org/bullfight/document_builder)
+
+This is a small set of modules for building up xpath based document attributes
+from a nokogir document object.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'document_builder'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install document_builder
+
+## Usage
+
+### Documents can be built using the Model and Collection modules as seen in the
+following example
+
+```ruby
+module Document
+  class Category
+    include DocumentBuilder::Model
+    xpath 'category'
+    attribute :domain, 'domain', DocumentBuilder::ElementAttribute
+    attribute :nicename, 'nicename', DocumentBuilder::ElementAttribute
+    attribute :body, nil, DocumentBuilder::ChildAttribute
+  end
+
+  class Postmeta
+    include DocumentBuilder::Model
+    xpath 'postmeta'
+    attribute :key, "wp:meta_key"
+    attribute :value, "wp:meta_value", DocumentBuilder::IntegerAttribute
+  end
+
+  class PostmetaCollection
+    include DocumentBuilder::Collection
+    xpath "item"
+    collection :postmeta, "//wp:postmeta", Postmeta
+  end
+
+  class Post
+    include DocumentBuilder::Model
+    xpath "item"
+    attribute :title
+    attribute :link
+    attribute :pub_date, "pubDate", DocumentBuilder::TimeAttribute
+    attribute :creator, "dc:creator"
+    attribute :content, "content:encoded"
+    attribute :excerpt, "excerpt:encoded"
+    attribute :id, "wp:post_id", DocumentBuilder::IntegerAttribute
+    attribute :published_at, 'wp:post_date_gmt', DocumentBuilder::TimeAttribute
+    attribute :comment_status, "wp:comment_status"
+    attribute :ping_status, "wp:ping_status"
+    attribute :name, 'wp:post_name'
+    attribute :status, "wp:status"
+    attribute :parent, "wp:post_parent", DocumentBuilder::IntegerAttribute
+    attribute :menu_order, "wp:menu_order", DocumentBuilder::IntegerAttribute
+    attribute :type, "wp:post_type"
+    attribute :is_sticky, "wp:is_sticky", DocumentBuilder::IntegerAttribute
+    attribute :category, "category", Category
+    attribute :postmetas, 'item', PostmetaCollection
+  end
+end
+
+### Using Model Objects
+```
+
+```ruby
+# Read an xml file
+url = "https://raw.githubusercontent.com/bullfight/wrxer/master/spec/fixtures/wrx.xml"
+uri = URI.parse(url)
+
+uri.open do |file|
+  document = Nokogiri::XML(file.read).xpath('//channel').at_xpath('item')}
+end
+
+post = Document::Post.call(document)
+
+=> #<Wrxer::Post:0x3fd4799693ac> Attributes: {
+  "title": "Welcome To Wrxer News.",
+  "link": "https://wrxernews.wordpress.com/2007/11/17/welcome-to-wrxer-news/",
+  "pub_date": "2007-11-17 21:30:51 +0000",
+  "creator": "wrxernews",
+  "content": "Welcome to <strong>Wrxer News</strong> - The most up-to-date and reliable source for Wrxer news.",
+  "excerpt": "Excerpt Text",
+  "id": 3,
+  "published_at": "2007-11-17 21:30:51 -0800",
+  "comment_status": "open",
+  "ping_status": "open",
+  "name": "welcome-to-wrxer-news",
+  "status": "publish",
+  "parent": 0,
+  "menu_order": 0,
+  "type": "post",
+  "is_sticky": 0,
+  "category": {
+    "domain": "category",
+    "nicename": "wrxer-news",
+    "body": "Wrxer News"
+  },
+  "postmetas": {
+    "data": "#<Enumerator::Lazy:0x007fa8f315a970>"
+  },
+  "comments": {
+    "data": "#<Enumerator::Lazy:0x007fa8f315a3f8>"
+  }
+}
+post.title
+=> "Welcome To Wrxer News."
+```
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/document_builder/fork )
+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 a new Pull Request

data/Rakefile

@@ -0,0 +1,7 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec
+

data/document_builder.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'document_builder/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "document_builder"
+  spec.version       = DocumentBuilder::VERSION
+  spec.authors       = ["Patrick Schmitz"]
+  spec.email         = ["p.schmitz@gmail.com"]
+  spec.summary       = %q{A document builder for nokogiri documents.}
+  spec.description   = %q{This is a small set of modules for building up xpath based document attributes from a nokogir document object.}
+  spec.homepage      = "https://github.com/bullfight/document_builder"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "nokogiri", "~> 1.6.6"
+  spec.add_development_dependency "rspec", "~> 3.2.0"
+  spec.add_development_dependency "pry"
+end

data/lib/document_builder/attribute.rb

@@ -0,0 +1,7 @@
+module DocumentBuilder
+  class Attribute < Struct.new(:name, :xpath, :coercion)
+    def call(document, params = {})
+      coercion.call(document, { xpath: xpath })
+    end
+  end
+end

data/lib/document_builder/coercion.rb

@@ -0,0 +1,71 @@
+module DocumentBuilder
+  module Coercion
+    module ClassMethods
+      def xpath(value)
+        @xpath = value
+      end
+
+      def call(document, params = {})
+        root = @xpath || params[:xpath]
+        unless document.name == root
+          document = document.at_xpath(root)
+        end
+
+        document.nil? ? nil : self.coerce(document)
+      end
+
+      def coerce(document)
+        self.new(document)
+      end
+    end
+
+    def self.included(base)
+      base.extend(ClassMethods)
+    end
+  end
+
+  class TextAttribute
+    include Coercion
+    def self.coerce(document)
+      document.text
+    end
+  end
+
+  class IntegerAttribute
+    include Coercion
+    def self.coerce(document)
+      Integer(document.text)
+    end
+  end
+
+  class TimeAttribute
+    include Coercion
+    def self.coerce(document)
+      Time.parse(document.text)
+    end
+  end
+
+  class ElementAttribute
+    include Coercion
+    def self.call(document, params = {})
+      element = document.attributes[params[:xpath].to_s]
+      element.nil? ? nil : self.coerce(element)
+    end
+
+    def self.coerce(document)
+      document.value
+    end
+  end
+
+  class ChildAttribute
+    include Coercion
+    def self.call(document, params = {})
+      child = document.children
+      child.empty? ? nil : self.coerce(child)
+    end
+
+    def self.coerce(document)
+      document.text
+    end
+  end
+end

data/lib/document_builder/collection.rb

@@ -0,0 +1,55 @@
+module DocumentBuilder
+  module Collection
+    module ClassMethods
+      def call(document, params = {})
+        root = @xpath || params[:xpath]
+        unless document.name == root
+          document = document.xpath(root)
+        end
+
+        document.nil? ? nil : self.coerce(document)
+      end
+
+      def collection(value, xpath, parser)
+        @collection = Attribute.new(value, xpath, parser)
+      end
+
+      def inherited(subclass)
+        subclass.instance_variable_set(:@collection, @collection)
+        super
+      end
+    end
+
+    def self.included(base)
+      base.extend(ClassMethods)
+      base.class_eval do
+        include Model
+        include Enumerable
+      end
+    end
+
+    def collection
+      self.class.instance_variable_get(:@collection)
+    end
+
+    def each(&block)
+      document.xpath(collection.xpath).each do |item|
+        block.call(
+          collection.call(item)
+        )
+      end
+    end
+
+    def data
+      lazy
+    end
+
+    def inspect
+      "#<#{self.class}:0x#{self.object_id.to_s(16)}> { data: #{data} } }"
+    end
+
+    def to_hash
+      { data: data }
+    end
+  end
+end

data/lib/document_builder/model.rb

@@ -0,0 +1,62 @@
+module DocumentBuilder
+  module Model
+    module ClassMethods
+      def attribute(name, xpath = nil, coercion = TextAttribute)
+        @attributes ||= []
+        @attributes << Attribute.new(name, xpath || name.to_s, coercion)
+      end
+
+      def inherited(subclass)
+        subclass.instance_variable_set(:@attributes, @attributes)
+        super
+      end
+    end
+
+    def self.included(base)
+      base.extend(ClassMethods)
+      base.class_eval do
+        include Coercion
+
+        attr_reader :document
+      end
+    end
+
+    def initialize(document)
+      @document = document
+    end
+
+    def attributes
+      self.class.instance_variable_get(:@attributes)
+    end
+
+    def [](key)
+      attributes.select { |item| item.name == key.to_sym}.first.call(document)
+    end
+
+    def method_missing(name, *args)
+      attributes.select { |item| item.name == name }.first.call(document)
+    rescue NoMethodError => e
+      raise NoMethodError.new("undefined method '#{name}' for #{self.class}")
+    end
+
+    def to_s(*args)
+      JSON.pretty_generate(to_hash)
+    end
+
+    def inspect
+      "#<#{self.class}:0x#{self.object_id.to_s(16)}> Attributes: " + JSON.pretty_generate(to_hash)
+    end
+
+    def to_json(*args)
+      JSON.generate(to_hash)
+    end
+
+    def to_hash
+      attributes.inject({}) do |acc, (key, value)|
+        value = key.call(document)
+        acc[key.name] = value.respond_to?(:to_hash) ? value.to_hash : value
+        acc
+      end
+    end
+  end
+end

data/lib/document_builder/version.rb

@@ -0,0 +1,3 @@
+module DocumentBuilder
+  VERSION = "0.1.1"
+end

data/lib/document_builder.rb

@@ -0,0 +1,12 @@
+require "document_builder/version"
+
+require 'time'
+require 'json'
+
+require 'document_builder/coercion'
+require 'document_builder/attribute'
+require 'document_builder/model'
+require 'document_builder/collection'
+
+module DocumentBuilder
+end

data/spec/document_builder_spec.rb

@@ -0,0 +1,7 @@
+require 'spec_helper'
+
+describe DocumentBuilder do
+  it 'has a version number' do
+    expect(DocumentBuilder::VERSION).not_to be nil
+  end
+end

data/spec/fixtures/document.rb

@@ -0,0 +1,45 @@
+module Document
+  class Category
+    include DocumentBuilder::Model
+    xpath 'category'
+    attribute :domain, 'domain', DocumentBuilder::ElementAttribute
+    attribute :nicename, 'nicename', DocumentBuilder::ElementAttribute
+    attribute :body, nil, DocumentBuilder::ChildAttribute
+  end
+
+  class Postmeta
+    include DocumentBuilder::Model
+    xpath 'postmeta'
+    attribute :key, "wp:meta_key"
+    attribute :value, "wp:meta_value", DocumentBuilder::IntegerAttribute
+  end
+
+  class PostmetaCollection
+    include DocumentBuilder::Collection
+    xpath "item"
+    collection :postmeta, "//wp:postmeta", Postmeta
+  end
+
+  class Post
+    include DocumentBuilder::Model
+    xpath "item"
+    attribute :title
+    attribute :link
+    attribute :pub_date, "pubDate", DocumentBuilder::TimeAttribute
+    attribute :creator, "dc:creator"
+    attribute :content, "content:encoded"
+    attribute :excerpt, "excerpt:encoded"
+    attribute :id, "wp:post_id", DocumentBuilder::IntegerAttribute
+    attribute :published_at, 'wp:post_date_gmt', DocumentBuilder::TimeAttribute
+    attribute :comment_status, "wp:comment_status"
+    attribute :ping_status, "wp:ping_status"
+    attribute :name, 'wp:post_name'
+    attribute :status, "wp:status"
+    attribute :parent, "wp:post_parent", DocumentBuilder::IntegerAttribute
+    attribute :menu_order, "wp:menu_order", DocumentBuilder::IntegerAttribute
+    attribute :type, "wp:post_type"
+    attribute :is_sticky, "wp:is_sticky", DocumentBuilder::IntegerAttribute
+    attribute :category, "category", Category
+    attribute :postmetas, 'item', PostmetaCollection
+  end
+end

data/spec/fixtures/missing_fields.xml

@@ -0,0 +1,155 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ This is a WordPress eXtended RSS file generated by WordPress as an export of your site.
+ It contains information about your site's posts, pages, comments, categories, and other content.
+ You may use this file to transfer that content from one site to another.
+ This file is not intended to serve as a complete backup of your site.
+
+ To import this information into a WordPress site follow these steps:
+ 1. Log in to that site as an administrator.
+ 2. Go to Tools: Import in the WordPress admin panel.
+ 3. Install the "WordPress" importer from the list.
+ 4. Activate & Run Importer.
+ 5. Upload this file using the form provided on that page.
+ 6. You will first be asked to map the authors in this export file to users
+    on the site. For each author, you may choose to map to an
+    existing user on the site or to create a new user.
+ 7. WordPress will then import each of the posts, pages, comments, categories, etc.
+    contained in this file into your site.
+-->
+<!-- generator="WordPress.com" created="2015-03-24 21:18"-->
+<rss version="2.0" xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:wp="http://wordpress.org/export/1.2/">
+  <channel>
+    <title>Wrxer News</title>
+    <link>https://wrxernews.wordpress.com</link>
+    <description>The Most Reliable Source For Wrxer News Since 2007.</description>
+    <pubDate>Tue, 24 Mar 2015 21:18:58 +0000</pubDate>
+    <language>en</language>
+    <wp:wxr_version>1.2</wp:wxr_version>
+    <wp:base_site_url>http://wordpress.com/</wp:base_site_url>
+    <wp:base_blog_url>https://wrxernews.wordpress.com</wp:base_blog_url>
+    <wp:author>
+      <wp:author_login>wrxernews</wp:author_login>
+      <wp:author_email>wrxernews@example.com</wp:author_email>
+      <wp:author_display_name><![CDATA[Wrx News]]></wp:author_display_name>
+      <wp:author_first_name><![CDATA[]]></wp:author_first_name>
+      <wp:author_last_name><![CDATA[]]></wp:author_last_name>
+    </wp:author>
+    <generator>http://wordpress.com/</generator>
+    <image>
+      <url>https://secure.gravatar.com/blavatar/foobar</url>
+      <title> &#187; Wrx News</title>
+      <link>https://wrxernews.wordpress.com</link>
+    </image>
+    <item>
+      <title>Missing post_id, post_name, post_date_gmt, and category</title>
+      <link>https://wrxernews.wordpress.com/2007/11/17/welcome-to-wrxer-news/</link>
+      <pubDate>Sat, 17 Nov 2007 21:30:51 +0000</pubDate>
+      <dc:creator>wrxernews</dc:creator>
+      <guid isPermaLink="false">http://wrxernews.wordpress.com/2007/11/17/welcome-to-wrxer-news/</guid>
+      <description/>
+      <content:encoded><![CDATA[Welcome to <strong>Wrx News</strong> - The most up-to-date and reliable source for Wrxer news.]]></content:encoded>
+      <excerpt:encoded><![CDATA[Excerpt Text]]></excerpt:encoded>
+      <wp:post_date>2007-11-17 15:30:51</wp:post_date>
+      <wp:comment_status>open</wp:comment_status>
+      <wp:ping_status>open</wp:ping_status>
+      <wp:status>publish</wp:status>
+      <wp:post_parent>0</wp:post_parent>
+      <wp:menu_order>0</wp:menu_order>
+      <wp:post_type>post</wp:post_type>
+      <wp:post_password/>
+      <wp:is_sticky>0</wp:is_sticky>
+      <category></category>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_4017882</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_47065</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>geo_public</wp:meta_key>
+        <wp:meta_value><![CDATA[0]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_edit_last</wp:meta_key>
+        <wp:meta_value><![CDATA[2223113]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:comment>
+        <wp:comment_id>2</wp:comment_id>
+        <wp:comment_author><![CDATA[Kid Vengeance]]></wp:comment_author>
+        <wp:comment_author_email>user@example.com</wp:comment_author_email>
+        <wp:comment_author_url>http://www.example.com/foobar</wp:comment_author_url>
+        <wp:comment_author_IP>69.245.96.185</wp:comment_author_IP>
+        <wp:comment_date>2007-11-18 11:45:26</wp:comment_date>
+        <wp:comment_date_gmt>2007-11-18 17:45:26</wp:comment_date_gmt>
+        <wp:comment_content><![CDATA[I feel this is going to be a great site! ]]></wp:comment_content>
+        <wp:comment_approved>1</wp:comment_approved>
+        <wp:comment_type/>
+        <wp:comment_parent>0</wp:comment_parent>
+        <wp:comment_user_id>0</wp:comment_user_id>
+        <wp:commentmeta>
+          <wp:meta_key>_elasticsearch_indexed_on</wp:meta_key>
+          <wp:meta_value>2007-11-18 17:45:26</wp:meta_value>
+        </wp:commentmeta>
+      </wp:comment>
+      <wp:comment>
+        <wp:comment_id>2900</wp:comment_id>
+        <wp:comment_author><![CDATA[iSyn4LiFe]]></wp:comment_author>
+        <wp:comment_author_email>user2@example.com</wp:comment_author_email>
+        <wp:comment_author_url/>
+        <wp:comment_author_IP>76.31.208.107</wp:comment_author_IP>
+        <wp:comment_date>2008-11-16 10:12:08</wp:comment_date>
+        <wp:comment_date_gmt>2008-11-16 17:12:08</wp:comment_date_gmt>
+        <wp:comment_content><![CDATA[I agree with Kid, that this is gonna be a great site so yeah good luck with it!!]]></wp:comment_content>
+        <wp:comment_approved>1</wp:comment_approved>
+        <wp:comment_type/>
+        <wp:comment_parent>0</wp:comment_parent>
+        <wp:comment_user_id>0</wp:comment_user_id>
+        <wp:commentmeta>
+          <wp:meta_key>_elasticsearch_indexed_on</wp:meta_key>
+          <wp:meta_value>2008-11-16 17:12:08</wp:meta_value>
+        </wp:commentmeta>
+      </wp:comment>
+    </item>
+    <item>
+      <title>Missing Category</title>
+      <link>https://wrxernews.wordpress.com/2007/11/17/wrxer-on-the-radio/</link>
+      <pubDate>Sat, 17 Nov 2007 21:33:08 +0000</pubDate>
+      <dc:creator>wrxernews</dc:creator>
+      <guid isPermaLink="false">http://wrxernews.wordpress.com/2007/11/17/wrxer-on-the-radio/</guid>
+      <description/>
+      <content:encoded><![CDATA[On November 19th, <a href="http://www.example.com/wrxer" target="_blank">wrxer</a> will be featured guests on the radio.]]></content:encoded>
+      <excerpt:encoded><![CDATA[]]></excerpt:encoded>
+      <wp:post_id>5</wp:post_id>
+      <wp:post_date>2007-11-17 15:33:08</wp:post_date>
+      <wp:post_date_gmt>2007-11-17 21:33:08</wp:post_date_gmt>
+      <wp:comment_status>open</wp:comment_status>
+      <wp:ping_status>open</wp:ping_status>
+      <wp:post_name>wrxer-on-the-radio</wp:post_name>
+      <wp:status>publish</wp:status>
+      <wp:post_parent>0</wp:post_parent>
+      <wp:menu_order>0</wp:menu_order>
+      <wp:post_type>post</wp:post_type>
+      <wp:post_password/>
+      <wp:is_sticky>0</wp:is_sticky>
+      <wp:postmeta>
+        <wp:meta_key>_edit_last</wp:meta_key>
+        <wp:meta_value><![CDATA[2223113]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>geo_public</wp:meta_key>
+        <wp:meta_value><![CDATA[0]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_4017882</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_47065</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+    </item>
+  </channel>
+</rss>

data/spec/fixtures/wrx.xml

@@ -0,0 +1,159 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ This is a WordPress eXtended RSS file generated by WordPress as an export of your site.
+ It contains information about your site's posts, pages, comments, categories, and other content.
+ You may use this file to transfer that content from one site to another.
+ This file is not intended to serve as a complete backup of your site.
+
+ To import this information into a WordPress site follow these steps:
+ 1. Log in to that site as an administrator.
+ 2. Go to Tools: Import in the WordPress admin panel.
+ 3. Install the "WordPress" importer from the list.
+ 4. Activate & Run Importer.
+ 5. Upload this file using the form provided on that page.
+ 6. You will first be asked to map the authors in this export file to users
+    on the site. For each author, you may choose to map to an
+    existing user on the site or to create a new user.
+ 7. WordPress will then import each of the posts, pages, comments, categories, etc.
+    contained in this file into your site.
+-->
+<!-- generator="WordPress.com" created="2015-03-24 21:18"-->
+<rss version="2.0" xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:wp="http://wordpress.org/export/1.2/">
+  <channel>
+    <title>Wrxer News</title>
+    <link>https://wrxernews.wordpress.com</link>
+    <description>The Most Reliable Source For Wrxer News Since 2007.</description>
+    <pubDate>Tue, 24 Mar 2015 21:18:58 +0000</pubDate>
+    <language>en</language>
+    <wp:wxr_version>1.2</wp:wxr_version>
+    <wp:base_site_url>http://wordpress.com/</wp:base_site_url>
+    <wp:base_blog_url>https://wrxernews.wordpress.com</wp:base_blog_url>
+    <wp:author>
+      <wp:author_login>wrxernews</wp:author_login>
+      <wp:author_email>wrxernews@example.com</wp:author_email>
+      <wp:author_display_name><![CDATA[Wrxer News]]></wp:author_display_name>
+      <wp:author_first_name><![CDATA[]]></wp:author_first_name>
+      <wp:author_last_name><![CDATA[]]></wp:author_last_name>
+    </wp:author>
+    <generator>http://wordpress.com/</generator>
+    <image>
+      <url>https://secure.gravatar.com/blavatar/foobar</url>
+      <title> &#187; Wrxer News</title>
+      <link>https://wrxernews.wordpress.com</link>
+    </image>
+    <item>
+      <title>Welcome To Wrxer News.</title>
+      <link>https://wrxernews.wordpress.com/2007/11/17/welcome-to-wrxer-news/</link>
+      <pubDate>Sat, 17 Nov 2007 21:30:51 +0000</pubDate>
+      <dc:creator>wrxernews</dc:creator>
+      <guid isPermaLink="false">http://wrxernews.wordpress.com/2007/11/17/welcome-to-wrxer-news/</guid>
+      <description/>
+      <content:encoded><![CDATA[Welcome to <strong>Wrxer News</strong> - The most up-to-date and reliable source for Wrxer news.]]></content:encoded>
+      <excerpt:encoded><![CDATA[Excerpt Text]]></excerpt:encoded>
+      <wp:post_id>3</wp:post_id>
+      <wp:post_date>2007-11-17 15:30:51</wp:post_date>
+      <wp:post_date_gmt>2007-11-17 21:30:51</wp:post_date_gmt>
+      <wp:comment_status>open</wp:comment_status>
+      <wp:ping_status>open</wp:ping_status>
+      <wp:post_name>welcome-to-wrxer-news</wp:post_name>
+      <wp:status>publish</wp:status>
+      <wp:post_parent>0</wp:post_parent>
+      <wp:menu_order>0</wp:menu_order>
+      <wp:post_type>post</wp:post_type>
+      <wp:post_password/>
+      <wp:is_sticky>0</wp:is_sticky>
+      <category domain="category" nicename="wrxer-news"><![CDATA[Wrxer News]]></category>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_4017882</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_47065</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>geo_public</wp:meta_key>
+        <wp:meta_value><![CDATA[0]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_edit_last</wp:meta_key>
+        <wp:meta_value><![CDATA[2223113]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:comment>
+        <wp:comment_id>2</wp:comment_id>
+        <wp:comment_author><![CDATA[Kid Vengeance]]></wp:comment_author>
+        <wp:comment_author_email>user@example.com</wp:comment_author_email>
+        <wp:comment_author_url>http://www.example.com/foobar</wp:comment_author_url>
+        <wp:comment_author_IP>69.245.96.185</wp:comment_author_IP>
+        <wp:comment_date>2007-11-18 11:45:26</wp:comment_date>
+        <wp:comment_date_gmt>2007-11-18 17:45:26</wp:comment_date_gmt>
+        <wp:comment_content><![CDATA[I feel this is going to be a great site! ]]></wp:comment_content>
+        <wp:comment_approved>1</wp:comment_approved>
+        <wp:comment_type/>
+        <wp:comment_parent>0</wp:comment_parent>
+        <wp:comment_user_id>0</wp:comment_user_id>
+        <wp:commentmeta>
+          <wp:meta_key>_elasticsearch_indexed_on</wp:meta_key>
+          <wp:meta_value>2007-11-18 17:45:26</wp:meta_value>
+        </wp:commentmeta>
+      </wp:comment>
+      <wp:comment>
+        <wp:comment_id>2900</wp:comment_id>
+        <wp:comment_author><![CDATA[iSyn4LiFe]]></wp:comment_author>
+        <wp:comment_author_email>user2@example.com</wp:comment_author_email>
+        <wp:comment_author_url/>
+        <wp:comment_author_IP>76.31.208.107</wp:comment_author_IP>
+        <wp:comment_date>2008-11-16 10:12:08</wp:comment_date>
+        <wp:comment_date_gmt>2008-11-16 17:12:08</wp:comment_date_gmt>
+        <wp:comment_content><![CDATA[I agree with Kid, that this is gonna be a great site so yeah good luck with it!!]]></wp:comment_content>
+        <wp:comment_approved>1</wp:comment_approved>
+        <wp:comment_type/>
+        <wp:comment_parent>0</wp:comment_parent>
+        <wp:comment_user_id>0</wp:comment_user_id>
+        <wp:commentmeta>
+          <wp:meta_key>_elasticsearch_indexed_on</wp:meta_key>
+          <wp:meta_value>2008-11-16 17:12:08</wp:meta_value>
+        </wp:commentmeta>
+      </wp:comment>
+    </item>
+    <item>
+      <title>Wrxer on the Radio</title>
+      <link>https://wrxernews.wordpress.com/2007/11/17/wrxer-on-the-radio/</link>
+      <pubDate>Sat, 17 Nov 2007 21:33:08 +0000</pubDate>
+      <dc:creator>wrxernews</dc:creator>
+      <guid isPermaLink="false">http://wrxernews.wordpress.com/2007/11/17/wrxer-on-the-radio/</guid>
+      <description/>
+      <content:encoded><![CDATA[On November 19th, <a href="http://www.example.com/wrxer" target="_blank">wrxer</a> will be featured guests on the radio.]]></content:encoded>
+      <excerpt:encoded><![CDATA[]]></excerpt:encoded>
+      <wp:post_id>5</wp:post_id>
+      <wp:post_date>2007-11-17 15:33:08</wp:post_date>
+      <wp:post_date_gmt>2007-11-17 21:33:08</wp:post_date_gmt>
+      <wp:comment_status>open</wp:comment_status>
+      <wp:ping_status>open</wp:ping_status>
+      <wp:post_name>wrxer-on-the-radio</wp:post_name>
+      <wp:status>publish</wp:status>
+      <wp:post_parent>0</wp:post_parent>
+      <wp:menu_order>0</wp:menu_order>
+      <wp:post_type>post</wp:post_type>
+      <wp:post_password/>
+      <wp:is_sticky>0</wp:is_sticky>
+      <category domain="category" nicename="radio"><![CDATA[Radio]]></category>
+      <wp:postmeta>
+        <wp:meta_key>_edit_last</wp:meta_key>
+        <wp:meta_value><![CDATA[2223113]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>geo_public</wp:meta_key>
+        <wp:meta_value><![CDATA[0]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_4017882</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+      <wp:postmeta>
+        <wp:meta_key>_wpas_skip_47065</wp:meta_key>
+        <wp:meta_value><![CDATA[1]]></wp:meta_value>
+      </wp:postmeta>
+    </item>
+  </channel>
+</rss>

data/spec/integration_spec.rb

@@ -0,0 +1,80 @@
+require 'spec_helper'
+require 'nokogiri'
+require 'fixtures/document'
+
+describe Document::Post do
+  context 'valid document' do
+    let(:filename) { fixture('wrx.xml') }
+    let(:document) { Nokogiri::XML(filename.read).xpath('//channel').at_xpath('item')}
+    subject { described_class.call(document) }
+
+    it 'has an id' do
+      expect(subject.id).to eq 3
+    end
+
+    it 'has a title' do
+      expect(subject.title).to eq "Welcome To Wrxer News."
+    end
+
+    it 'has a content' do
+      expect(subject.content).to match /Welcome to/
+    end
+
+    it 'has an excerpt' do
+      expect(subject.excerpt).to eq "Excerpt Text"
+    end
+
+    it 'has a slug' do
+      expect(subject.name).to eq "welcome-to-wrxer-news"
+    end
+
+    it 'has a post date' do
+      expect(subject.published_at).to eq Time.parse("2007-11-17 21:30:51")
+    end
+
+    it 'has a category' do
+      expect(subject.category).to be_a Document::Category
+    end
+
+    it 'has is_sticky' do
+      expect(subject.is_sticky).to eq 0
+    end
+
+    it 'has postmetas' do
+      expect(subject.postmetas.first).to be_a Document::Postmeta
+    end
+
+    it 'does not have a not foo' do
+      expect { subject.foo }.to raise_error(
+        NoMethodError, "undefined method 'foo' for Document::Post")
+    end
+  end
+
+  context "nil attribute case" do
+    let(:filename) { fixture('missing_fields.xml') }
+    let(:document) { Nokogiri::XML(filename.read).xpath('//channel').at_xpath('item')}
+    subject { described_class.call(document) }
+
+    it 'returns nil for nil integer' do
+      expect(subject.id).to eq nil
+    end
+
+    it 'returns nil for text' do
+      expect(subject.name).to eq nil
+    end
+
+    it 'returns nil for time' do
+      expect(subject.published_at).to eq nil
+    end
+  end
+
+  context "for missing node" do
+    let(:filename) { fixture('missing_fields.xml') }
+    let(:document) { Nokogiri::XML(filename.read).xpath('//channel').xpath('item')[1]}
+    subject { described_class.new(document) }
+
+    it 'returns nil for category' do
+      expect(subject.category).to eq nil
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,12 @@
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+require 'document_builder'
+require 'pry'
+
+def fixture_path
+  File.expand_path("../fixtures", __FILE__)
+end
+
+def fixture(file)
+  File.new(fixture_path + '/' + file)
+end
+

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: document_builder
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Patrick Schmitz
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-04-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.6
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.6
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This is a small set of modules for building up xpath based document attributes
+  from a nokogir document object.
+email:
+- p.schmitz@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- .travis.yml
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- document_builder.gemspec
+- lib/document_builder.rb
+- lib/document_builder/attribute.rb
+- lib/document_builder/coercion.rb
+- lib/document_builder/collection.rb
+- lib/document_builder/model.rb
+- lib/document_builder/version.rb
+- spec/document_builder_spec.rb
+- spec/fixtures/document.rb
+- spec/fixtures/missing_fields.xml
+- spec/fixtures/wrx.xml
+- spec/integration_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/bullfight/document_builder
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: A document builder for nokogiri documents.
+test_files:
+- spec/document_builder_spec.rb
+- spec/fixtures/document.rb
+- spec/fixtures/missing_fields.xml
+- spec/fixtures/wrx.xml
+- spec/integration_spec.rb
+- spec/spec_helper.rb