mida 0.3.3 → 0.3.6

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6d01fe436dfe46a4496213212df9720593e13754
+  data.tar.gz: 5320742776ee4fb1ca0a171b76ccd72471681c54
+SHA512:
+  metadata.gz: 4637578b6ff945acf8adc05a8d464502664870b422f13a2d7fc87c120471df8d46b7bf7232362aced30133db5bccc0162ea2ec0da9708896e99e6c46cc5d49cd
+  data.tar.gz: e2b442573d64d3d601c536d4b18bd9638247022b4962947c5bca8328f91c6266af409d77b8e0be0667f4c8e5ded59ba2830ad23a1c190a073d7d98cb6464fc38

data/.gitignore

@@ -0,0 +1,21 @@
+# vi swap files
+*.swp
+
+# Gem pkg directory
+pkg/
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.DS_Store

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,8 @@
+language: ruby
+rvm:
+  - 1.9.2
+  - 1.9.3
+  - 2.0.0
+branches:
+  only:
+    - master

data/CHANGELOG.rdoc

@@ -1,3 +1,13 @@
+== 0.3.6 (22nd September 2013)
+* Corrects Gemfile.lock to work properly with bundler
+
+== 0.3.5 (22nd September 2013)
+* Corrects Gemfile.lock to work properly with bundler
+
+== 0.3.4 (22nd September 2013)
+* Ensure works on Ruby v1.9.3 and v2.0
+* Display exception error message from parse_source()
+
 == 0.3.3 (31st July 2011)
 * Removed validation from +new+ for +Item+ and +Document+
 * Created <tt>vocabularies/</tt> to put the vocabularies in

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,33 @@
+PATH
+  remote: .
+  specs:
+    mida (0.3.6)
+      blankslate (= 2.1.2.4)
+      nokogiri (>= 1.5)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    blankslate (2.1.2.4)
+    diff-lcs (1.1.3)
+    mini_portile (0.5.1)
+    nokogiri (1.6.0)
+      mini_portile (~> 0.5.0)
+    rake (10.1.0)
+    rspec (2.10.0)
+      rspec-core (~> 2.10.0)
+      rspec-expectations (~> 2.10.0)
+      rspec-mocks (~> 2.10.0)
+    rspec-core (2.10.1)
+    rspec-expectations (2.10.0)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.10.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.3)
+  mida!
+  rake
+  rspec (~> 2.10.0)

data/LICENCE.rdoc

@@ -1,6 +1,6 @@
 = The MIT Licence
 
-Copyright (c) 2011 Lawrence Woodman
+Copyright (c) 2011-2013 Lawrence Woodman <lwoodman@vlifesystems.com>
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.rdoc

@@ -1,6 +1,6 @@
 = Mida
 
-* {Mida Project Page}[http://lawrencewoodman.github.com/mida]
+* {Mida Project Page}[http://lawrencewoodman.github.io/mida]
 * {Mida Github Repository}[https://github.com/LawrenceWoodman/mida]
 * {Mida Bug Tracker}[https://github.com/LawrenceWoodman/mida/issues]
 
@@ -22,11 +22,11 @@ Mida keeps RubyGems[http://rubygems.org/gems/mida] up-to-date with its latest ve
 
 To use the command line tool, supply it with the urls or filenames that you
 would like to be parsed (by default each item is output as yaml):
-  mida http://lawrencewoodman.github.com/mida/news/
+  mida http://lawrencewoodman.github.io/mida/news/
 
 If you want to search for specific types you can use the <tt>-t</tt> switch
 followed by a Regular Expression:
-  mida -t /person/i http://lawrencewoodman.github.com/mida/news/
+  mida -t /person/i http://lawrencewoodman.github.io/mida/news/
 
 For more information look at <tt>mida</tt>'s help:
   mida -h
@@ -132,5 +132,5 @@ Mida project's {issues tracker}[https://github.com/LawrenceWoodman/mida/issues]
 on github.
 
 == Licence
-Copyright (c) 2011 Lawrence Woodman.
+Copyright (c) 2011-2013 Lawrence Woodman <lwoodman@vlifesystems.com>.
 This software is licensed under the MIT Licence.  Please see the file, LICENCE.rdoc, for details.

data/Rakefile

@@ -1,28 +1,6 @@
-task :default => :spec
-
-desc "Create Gem"
-require 'rubygems/package_task'
-spec = Gem::Specification.new do |s|
-  s.name        = "mida"
-  s.summary     = "A Microdata parser/extractor library"
-  s.description = "A Microdata parser and extractor library which includes support for the schema.org vocabularies"
-  s.version     = "0.3.3"
-  s.author      = "Lawrence Woodman"
-  s.email       = "lwoodman@vlifesystems.com"
-  s.homepage    = %q{http://lawrencewoodman.github.com/mida/}
-  s.platform    = Gem::Platform::RUBY
-  s.required_ruby_version = '>=1.9'
-  s.files       = Dir['lib/**/*.rb'] + Dir['spec/**/*.rb'] + Dir['*.rdoc'] + Dir['Rakefile']
-  s.executables = ['mida']
-  s.extra_rdoc_files = ['README.rdoc', 'LICENCE.rdoc', 'CHANGELOG.rdoc']
-  s.rdoc_options << '--main' << 'README.rdoc'
-  s.add_dependency('nokogiri', '>= 1.5')
-  s.add_dependency('blankslate')
-  s.add_development_dependency('rspec', '>= 2.0' )
-  s.add_development_dependency('bundler')
-end
-Gem::PackageTask.new(spec).define
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
 
-desc "Run Specs"
-require 'rspec/core/rake_task'
 RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/mida

@@ -92,29 +92,28 @@ end
 
 def parse_source(source, options)
   url = get_url  
-  begin
-    open(source) do |f|
-      doc = Mida::Document.new(f, url)
-      items = if options[:type]
-        doc.search(options[:type])
-      else
-        doc.items
-      end
+  open(source) do |f|
+    doc = Mida::Document.new(f, url)
+    items = if options[:type]
+      doc.search(options[:type])
+    else
+      doc.items
+    end
 
-      if items.empty?
-        puts "No microdata found in this document."; exit
+    if items.empty?
+      puts "No microdata found in this document."; exit
+    else
+      if options.include?(:count)
+        display_count(items)
       else
-        if options.include?(:count)
-          display_count(items)
-        else
-          display_items(items)
-        end
+        display_items(items)
       end
     end
-  rescue
-    puts "Failed to parse: #{source}"
-    exit
   end
+rescue => e
+  puts "Failed to parse: #{source}"
+  puts "Error: #{e.to_s}"
+  exit
 end
 
 ARGV.each do |source|

data/lib/mida.rb

@@ -1,4 +1,4 @@
-$LOAD_PATH.unshift File.dirname(__FILE__)
+require "mida/version"
 Dir[File.dirname(__FILE__) + '/mida/*.rb'].each { |f| require f }
 
 # Mida is a Microdata parser and extractor.

data/lib/mida/datatype/iso8601date.rb

@@ -11,6 +11,8 @@ module Mida
       # Raises +ArgumentError+ if value not valid
       def initialize(value)
         @parsedValue = ::DateTime.iso8601(value)
+      rescue => e
+        raise ArgumentError, e
       end
 
       def to_s

data/lib/mida/version.rb

@@ -0,0 +1,3 @@
+module Mida
+  VERSION = "0.3.6"
+end

data/lib/mida/vocabularies/schemaorg.rb

@@ -1 +1 @@
-Dir.glob(File.dirname(__FILE__) + '/schemaorg/*.rb') {|file| require file}
+Dir.glob(File.dirname(__FILE__) + '/schemaorg/*.rb').reverse {|file| require file}

data/mida.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'mida/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "mida"
+  spec.version       = Mida::VERSION
+  spec.author      = "Lawrence Woodman"
+  spec.email       = "lwoodman@vlifesystems.com"
+  spec.description = "A Microdata parser and extractor library which includes support for the schema.org vocabularies"
+  spec.summary     = "A Microdata parser/extractor library"
+  spec.homepage    = %q{http://lawrencewoodman.github.io/mida/}
+  spec.license       = "MIT"
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = ['mida']
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+  spec.extra_rdoc_files = ['README.rdoc', 'LICENCE.rdoc', 'CHANGELOG.rdoc']
+  spec.rdoc_options << '--main' << 'README.rdoc'
+  spec.add_dependency('blankslate', '2.1.2.4')
+  spec.add_dependency('nokogiri', '>= 1.5')
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec", "~> 2.10.0"
+end

data/resources/schema.org/generate.rb

@@ -0,0 +1,191 @@
+#!/usr/bin/env ruby
+# Creates the vocabulary and enumeration classes for schema.org from
+# vocabularies.json which is held at:
+#   https://github.com/LawrenceWoodman/schema.org_schemas
+# The classes are created in vocabularies/
+require 'erb'
+require 'json'
+require 'set'
+
+ENUMERATION_TEMPLATE = <<-EOB
+require 'mida/datatype'
+
+module Mida
+  module SchemaOrg
+
+    # <%= type.description %>
+    class <%= type.name %> < Mida::DataType::Enumeration
+      VALID_VALUES = [
+% num_instances = type.instances.size
+% type.instances.first(num_instances-1).each do |instance|
+        [::Mida::DataType::URL, %r{http://schema.org/<%= instance %>}i],
+% end
+        [::Mida::DataType::URL, %r{http://schema.org/<%= type.instances.last %>}i]
+      ]
+    end
+
+  end
+end
+EOB
+
+VOCABULARY_TEMPLATE = <<-EOB
+require 'mida/vocabulary'
+
+module Mida
+  module SchemaOrg
+
+% type.types_used.each do |klass|
+    autoload :<%= klass %>, 'mida/vocabularies/schemaorg/<%= klass.downcase %>'
+% end
+
+    # <%= type.description %>
+    class <%= type.name %> < Mida::Vocabulary
+      itemtype %r{http://schema.org/<%= type.name %>}i
+% type.vocabularies.each do |include_vocabulary|
+      include_vocabulary Mida::SchemaOrg::<%= include_vocabulary %>
+% end
+% type.properties.each do |property|
+
+      # <%= property.description %>
+%   if property.types.size == 1 && property.types[0].name == 'Text'
+      has_many '<%= property.name %>'
+%   else
+      has_many '<%= property.name %>' do
+%     property.types.each do |prop_type|
+        extract <%= prop_type.full_name %>
+%     end
+      end
+%   end
+% end
+    end
+
+  end
+end
+EOB
+
+DATATYPES = [
+  {'name' => 'Boolean', 'full_name' => 'Mida::DataType::Boolean'},
+  {'name' => 'Date', 'full_name' => 'Mida::DataType::ISO8601Date'},
+  {'name' => 'Float', 'full_name' => 'Mida::DataType::Float'},
+  {'name' => 'Integer', 'full_name' => 'Mida::DataType::Integer'},
+  {'name' => 'Number', 'full_name' => 'Mida::DataType::Number'},
+  {'name' => 'URL', 'full_name' => 'Mida::DataType::URL'},
+  {'name' => 'Text', 'full_name' => 'Mida::DataType::Text'},
+]
+
+class Property
+  
+  attr_reader :name, :description, :types
+
+  def initialize(name, description, types)
+    @name = name
+    @description = description
+    @types = (types || []).collect {|type| Type.find(type)}.sort
+    add_text_type(@types)
+  end
+
+  def add_text_type(types)
+    if types.any? {|type| type.vocabulary?} &&
+       types.none? {|type| type.name == 'Text'}
+      @types << Type.find('Text')
+    end
+  end
+
+end
+
+class Type
+  include Comparable
+
+  attr_reader :name, :full_name, :description, :vocabularies, :properties
+  attr_reader :instances
+
+  def initialize(definition)
+    @name = definition['name']
+    @ancestors = definition['ancestors'] || []
+    @description = definition['description']
+    @vocabularies = definition['vocabularies'] || []
+    @properties = definition['properties'] || []
+    @instances = definition['instances'] || []
+    @full_name = definition['full_name'] || "Mida::SchemaOrg::#{@name}"
+    (@@types ||= []) << self
+  end
+
+  # Returns the found type or nil of not found
+  def self.find(name)
+    found_types = @@types.find_all {|type| type.name == name}
+    found_types.any? ? found_types[0] : nil
+  end
+
+  def process_properties
+    @properties = @properties.collect do |property|
+      Property.new(property['name'], property['description'], property['types'])
+    end
+  end
+
+  def types_used
+    types = Set.new
+    @vocabularies.each do |vocabulary|
+      types << vocabulary
+    end
+
+    @properties.each do |property|
+      property.types .each do |type|
+        unless type.datatype?
+          types << type.name
+        end
+      end
+    end
+    types
+  end
+
+  def get_requires(vocabulary)
+    types = types_used(vocabulary)
+    types.collect do |type|
+      "mida/vocabularies/schemaorg/#{type.name.downcase}"
+    end
+  end
+
+  def enumeration?
+    @ancestors.include?('Enumeration')
+  end
+
+  def datatype?
+    full_name =~ /^Mida::DataType::/
+  end
+
+  def vocabulary?
+    !enumeration? && !datatype?
+  end
+
+  def <=>(other)
+    if full_name =~ /^Mida::DataType::Text/ &&
+       other.full_name !=~/^Mida::DataType::Text/
+      1
+    elsif other.full_name =~ /^Mida::DataType::Text/ &&
+           full_name !=~/^Mida::DataType::Text/
+      -1
+    else
+      full_name <=> other.full_name
+    end
+  end
+end
+
+types = JSON.parse(File.read('vocabularies.json'))
+types = types.collect {|type| Type.new(type)}
+datatypes = DATATYPES.collect {|type| Type.new(type)}
+types.each {|type| type.process_properties}
+
+Dir.mkdir('enumerations') unless File.directory?('enumerations')
+Dir.mkdir('vocabularies') unless File.directory?('vocabularies')
+
+types.each do |type|
+  if type.enumeration?
+    File.open("enumerations/#{type.name.downcase}.rb", 'w') do |file|
+      file.puts ERB.new(ENUMERATION_TEMPLATE, 0, '%').result(binding)
+    end
+  elsif type.vocabulary?
+    File.open("vocabularies/#{type.name.downcase}.rb", 'w') do |file|
+      file.puts ERB.new(VOCABULARY_TEMPLATE, 0, '%').result(binding)
+    end
+  end
+end