wikipedia-client 1.0.0

data/.gitignore

@@ -0,0 +1,5 @@
+*.swp
+*.tmp
+*.log
+pkg/*
+

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2008 [name of plugin creator]
+
+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.textile

@@ -0,0 +1,81 @@
+h1. Wikipedia
+
+Allows you to get wikipedia content through their API. This uses the
+alpha API, not the deprecated query.php API type
+
+Wikipedia API reference: "http://en.wikipedia.org/w/api.php":http://en.wikipedia.org/w/api.php
+
+Adopted from: "http://code.google.com/p/wikipedia-client/":http://code.google.com/p/wikipedia-client/
+
+h2. Examples
+
+<pre><code>require 'wikipedia'
+page = Wikipedia.find( 'Getting Things Done' )
+
+=> #<Wikipedia:Page>
+
+page.title
+
+=> 'Getting Things Done'
+
+page.content
+
+=> # all the wiki markup appears here...
+
+page.categories
+
+=> [..., "Category:Self-help books", ...]
+
+page.links
+
+=> [..., "Business", "Cult following", ...]
+
+page.images
+
+=> ["File:Getting Things Done.jpg", ...]
+
+page.image_urls
+
+=> ["http://upload.wikimedia.org/wikipedia/en/e/e1/Getting_Things_Done.jpg", ...]]</code></pre>
+
+h2. Configuration
+
+This is by default configured like this:
+
+<pre><code>Wikipedia.Configure {
+  domain 'en.wikipedia.org'
+  path   'w/api.php'
+}</code></pre>
+
+h2. Advanced
+
+See the API spec at "http://en.wikipedia.org/w/api.php":http://en.wikipedia.org/w/api.php
+
+If you need data that is not already present, you can override
+parameters.
+
+For example, to retrieve only the page info:
+
+<pre><code>page = Wikipedia.find( 'Getting Things Done', :prop => "info" )
+
+page.title
+
+=> "Getting Things Done"
+
+page.raw_data
+
+=> {"query"=>{"pages"=>{"959928"=>{"pageid"=>959928, "ns"=>0,
+"title"=>"Getting Things Done", "touched"=>"2010-03-10T00:04:09Z",
+"lastrevid"=>348481810, "counter"=>0, "length"=>7891}}}}</code></pre>
+
+h2. Running specs
+
+if you have rspec >= 1.1.3 installed just type in
+
+rake spec
+
+h2. Thanks!
+
+Copyright (c) 2008 [Cyril David], released under the MIT license
+
+Adopted by Ken Pratt (ken@kenpratt.net) in 2010/03

data/Rakefile

@@ -0,0 +1,60 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "wikipedia-client"
+    gem.summary = %Q{Ruby client for the Wikipedia API}
+    gem.description = %Q{Ruby client for the Wikipedia API}
+    gem.email = "christian.hellsten@gmail.com"
+    gem.homepage = "http://github.com/christianhellsten/wikipedia-client"
+    gem.authors = ["Cyril David", "Ken Pratt"]
+    gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+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
+
+
+desc 'Test the wikipedia plugin.'
+task :spec do
+    spec_path = File.expand_path(File.dirname(__FILE__) + '/spec/**/*.rb')
+      system("spec -cfs #{spec_path}")
+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 :spec => :check_dependencies
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "wikipedia-client #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+1.0.0

data/init.rb

@@ -0,0 +1 @@
+require File.dirname(__FILE__) + '/lib/wikipedia'

data/install.rb

@@ -0,0 +1 @@
+puts File.read(File.dirname(__FILE__) + '/README')

data/lib/wikipedia.rb

@@ -0,0 +1,37 @@
+Dir[File.dirname(__FILE__) + '/wikipedia/**/*.rb'].each { |f| require f }
+
+require 'uri'
+
+module Wikipedia
+  # Examples : 
+  # page = Wikipedia.find('Rails') 
+  # => #<Wikipedia:0x123102>
+  # page.content
+  # => wiki content appears here
+  
+  # basically just a wrapper for doing 
+  # client = Wikipedia::Client.new
+  # client.find('Rails')
+  #
+  def self.find( page, options = {} )
+    client.find( page, options )
+  end
+  def self.find_image( title, options = {} )
+    client.find_image( title, options )
+  end
+  
+  def self.Configure(&block)
+    Configuration.instance.instance_eval(&block)
+  end
+  
+  Configure {
+    domain 'en.wikipedia.org'
+    path   'w/api.php'
+  }
+
+  private
+
+  def self.client
+    @client ||= Wikipedia::Client.new
+  end
+end

data/lib/wikipedia/client.rb

@@ -0,0 +1,91 @@
+module Wikipedia
+  class Client
+    # see http://en.wikipedia.org/w/api.php
+    BASE_URL = "http://:domain/:path?action=:action&format=json"
+
+    attr_accessor :follow_redirects
+
+    def initialize
+      self.follow_redirects = true
+    end
+
+    def find( title, options = {} )
+      title = Url.new(title).title rescue title
+      page = Page.new( request_page( title, options ) )
+      while follow_redirects and page.redirect?
+        page = Page.new( request_page( page.redirect_title, options ))
+      end
+      page
+    end
+
+    def find_image( title, options = {} )
+      title = Url.new(title).title rescue title
+      Page.new( request_image( title, options ) )
+    end
+
+    # http://en.wikipedia.org/w/api.php?action=query&format=json&prop=revisions%7Clinks%7Cimages%7Ccategories&rvprop=content&titles=Flower%20(video%20game)
+    def request_page( title, options = {} )
+      request( {
+                 :action => "query",
+                 :prop => %w{ revisions links images categories },
+                 :rvprop => "content",
+                 :titles => title
+               }.merge( options ) )
+    end
+
+    # http://en.wikipedia.org/w/api.php?action=query&format=json&prop=imageinfo&iiprop=url&titles=File:Flower.png
+    def request_image( title, options = {} )
+      request( {
+                 :action => "query",
+                 :prop => "imageinfo",
+                 :iiprop => "url",
+                 :titles => title
+               }.merge( options ) )
+    end
+
+    def request( options )
+      require 'open-uri'
+      URI.parse( url_for( options ) ).read( "User-Agent" => "Ruby/#{RUBY_VERSION}" )
+    end
+
+    protected
+      def configuration_options
+        {
+          :domain => Configuration[:domain],
+          :path   => Configuration[:path]
+        }
+      end
+
+      def url_for( options )
+        url = BASE_URL.dup
+        options = configuration_options.merge( options )
+        options.each do |key, val|
+          value = urlify_value( val )
+          if url.include?( ":#{key}" )
+            url.sub! ":#{key}", value
+          else
+            url << "&#{key}=#{value}"
+          end
+        end
+        url
+      end
+
+      def urlify_value( val )
+        case val
+        when Array
+          encode( val.flatten.join( '|' ) )
+        else
+          encode( val )
+        end
+      end
+
+      def encode( val )
+        case val
+        when String
+          URI.encode( val ).gsub( '&', '%26' )
+        else
+          val
+        end
+      end
+  end
+end

data/lib/wikipedia/configuration.rb

@@ -0,0 +1,25 @@
+require 'singleton'
+
+module Wikipedia
+  class Configuration
+    include Singleton
+
+    def self.directives(*directives)
+      directives.each do |directive|
+        define_method directive do |*args|
+          if args.empty?
+            return instance_variable_get("@#{directive}")
+          else
+            instance_variable_set("@#{directive}", args.first)
+          end
+        end
+      end
+    end
+    
+    def self.[](directive)
+      instance.send(directive)
+    end
+    
+    directives :domain, :path
+  end
+end

data/lib/wikipedia/page.rb

@@ -0,0 +1,109 @@
+module Wikipedia
+  class Page
+    def initialize(json)
+      require 'json'
+      @json = json
+      @data = JSON::load(json)
+    end
+
+    def page
+      @data['query']['pages'].values.first
+    end
+
+    def content
+      page['revisions'].first.values.first if page['revisions']
+    end
+
+    def sanitized_content
+      self.class.sanitize(content)
+    end
+
+    def redirect?
+      content && content.match(/\#REDIRECT\s+\[\[(.*?)\]\]/i)
+    end
+
+    def redirect_title
+      if matches = redirect?
+        matches[1]
+      end
+    end
+
+    def title
+      page['title']
+    end
+
+    def categories
+      page['categories'].map {|c| c['title'] } if page['categories']
+    end
+
+    def links
+      page['links'].map {|c| c['title'] } if page['links']
+    end
+
+    def images
+      page['images'].map {|c| c['title'] } if page['images']
+    end
+
+    def image_url
+      page['imageinfo'].first['url'] if page['imageinfo']
+    end
+
+    def image_urls
+      if list = images
+        filtered = list.select {|i| i =~ /^file:.+\.(jpg|jpeg|png|gif)$/i && !i.include?("LinkFA-star") }
+        filtered.map do |title|
+          Wikipedia.find_image( title ).image_url
+        end
+      end
+    end
+
+    def raw_data
+      @data
+    end
+
+    def json
+      @json
+    end
+
+    def self.sanitize( s )
+      if s
+        s = s.dup
+
+        # strip anything inside curly braces!
+        while s =~ /\{\{[^\{\}]+?\}\}/
+          s.gsub!(/\{\{[^\{\}]+?\}\}/, '')
+        end
+
+        # strip info box
+        s.sub!(/^\{\|[^\{\}]+?\n\|\}\n/, '')
+
+        # strip internal links
+        s.gsub!(/\[\[([^\]\|]+?)\|([^\]\|]+?)\]\]/, '\2')
+        s.gsub!(/\[\[([^\]\|]+?)\]\]/, '\1')
+
+        # strip images and file links
+        s.gsub!(/\[\[Image:[^\[\]]+?\]\]/, '')
+        s.gsub!(/\[\[File:[^\[\]]+?\]\]/, '')
+
+        # convert bold/italic to html
+        s.gsub!(/'''''(.+?)'''''/, '<b><i>\1</i></b>')
+        s.gsub!(/'''(.+?)'''/, '<b>\1</b>')
+        s.gsub!(/''(.+?)''/, '<i>\1</i>')
+
+        # misc
+        s.gsub!(/<ref[^<>]*>[\s\S]*?<\/ref>/, '')
+        s.gsub!(/<!--[^>]+?-->/, '')
+        s.gsub!('  ', ' ')
+        s.strip!
+
+        # create paragraphs
+        sections = s.split("\n\n")
+        if sections.size > 1
+          s = sections.map {|s| "<p>#{s.strip}</p>" }.join("\n")
+        end
+
+        s
+      end
+    end
+  end
+end