schleyfox-wikipedia-api 0.1.1

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2008 Ben Hughes
+
+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

@@ -0,0 +1 @@
+Utility for interacting with the mediawiki api

data/lib/mediawiki.rb

@@ -0,0 +1,158 @@
+# This file contains magical incantations to interface with the MediaWiki
+# API.  This is very much a work in progress so don't count on it not changing
+# (for the better).
+#
+# Check out the source on github http://github.com/schleyfox/wikipedia-api
+
+['hpricot', 'cgi', 'open-uri'].each {|f| require f}
+
+
+# The MediaWiki class allows one to interface with the MediaWiki API.
+# Everything about it is incomplete and I promise that it will eat your kids
+# and/or small furry woodland creatures.  These things happen.
+#
+# == Usage
+#
+# To use, you construct a MediaWiki object for the site
+# 
+#   require 'mediawiki'
+#   example_wiki = MediaWiki.new("http://example.com/w/api.php")
+#
+# From here you can query based on title or pageid for individual pages or
+# collections
+#
+#  # By pageid
+#  page = example_wiki.find(10)
+#  page.title #=> "foo"
+#
+#  # By title
+#  page = example_wiki.find_by_title("foo")
+#  page.pageid #=> 10
+#
+#  # a collection by pageids
+#  result = example_wiki.find_by_pageids(10,11)
+#  result.pages.collect(&:title) #=> ["foo", "bar"]
+#
+#  # a collection by titles
+#  result = example_wiki.find_by_titles("foo", "bar")
+#  result.pages.collect(&:pageid) #=> [10, 11]
+#
+class MediaWiki
+  PROPS = [:info, :revisions, :links, :langlinks, :images, :imageinfo,
+    :templates, :categories, :extlinks, :categoryinfo]
+  RVPROPS = [:ids, :flags, :timestamp, :user, :size, :comment, :content]
+
+
+  def initialize(url)
+    @url = url
+  end
+
+  # find by pageid
+  def find(*opts)
+    find_by_pageids(opts).pages.first
+  end
+
+  # find the articles identified by the Array page_ids
+  def find_by_pageids(*opts)
+    page_ids, opts_qs = handle_options(opts)
+    page_ids_qs = make_qs("pageids", page_ids)
+    MediaWikiBase.new(make_url(opts_qs.push(page_ids_qs)))
+  end
+
+  # Same as find_by_titles but returns a single page
+  def find_by_title(*opts)
+    find_by_titles(opts).pages.first
+  end
+
+  # find the articles identified by the Array titles
+  def find_by_titles(*opts)
+    titles, opts_qs = handle_options(opts)
+    titles_qs = make_qs("titles", titles)
+    MediaWikiBase.new(make_url(opts_qs.push(titles_qs)))
+  end
+
+  class MediaWikiBase
+  
+    attr_accessor :xml, :pages
+  
+    def initialize(url)
+      @xml = get_xml(url)
+      @pages = (@xml/:api/:query/:pages/:page).collect{|p| Page.new(p) }
+    end
+  
+    
+    # Page encapsulates the properties of wikipedia page.
+    class Page
+      attr_accessor *PROPS
+      attr_accessor :title, :pageid
+  
+      def initialize(page)
+        @title = page.attributes['title']
+        @pageid = page.attributes['pageid']
+        @links = (page/:links/:pl).collect{|pl| pl.attributes['title']}
+        @langlinks = (page/:langlinks/:ll).collect{|ll| ll.attributes['lang']}
+        @images = (page/:images/:im).collect{|im| im.attributes['title']}
+        @templates = (page/:templates/:tl).collect{|tl| tl.attributes['title']}
+        @extlinks = (page/:extlinks/:el).collect{|el| el.inner_html}
+        @revisions = (page/:revisions/:rev).collect{|rev| Revision.new(rev)}
+      end
+    end
+  
+    class Revision
+      attr_accessor *RVPROPS
+      attr_accessor :revid
+  
+      def initialize(rev)
+        @revid = rev.attributes['revid']
+        @user = rev.attributes['user']
+        @timestamp = Time.parse(rev.attributes['timestamp'])
+        @comment = rev.attributes['comment']
+        @content = rev.inner_html
+      end
+    end
+  
+    protected
+    def get_xml(url)
+      Hpricot.XML(open(url))
+    end
+  end
+
+
+  protected
+  def make_url(*opts)
+    @url + "?" + (["action=query", "format=xml"] + opts).join('&')
+  end
+
+  def handle_options(opts)
+    arr = opts.delete_if{|o| o.is_a? Hash}
+    hash = (opts - arr).first
+    [arr, handle_opts_hash(hash)]
+  end
+
+  def handle_opts_hash(opts)
+    opts ||= {}
+    res = []
+
+    opts[:prop] ||= PROPS
+    opts[:prop] = opts[:prop] & PROPS
+    res << make_qs("prop", opts[:prop])
+    
+    if opts[:revids]
+      res << make_qs("revids", opts[:revids])
+    end
+
+    if opts[:rvprop] 
+      opts[:rvprop] = opts[:rvprop] & RVPROPS
+      res << make_qs("rvprop", opts[:rvprop])
+    end
+
+    res
+  end
+
+  def make_qs(name, collection)
+    "#{name}=#{CGI.escape(collection.join('|'))}"
+  end
+
+end
+
+

data/lib/wikipedia.rb

@@ -0,0 +1,28 @@
+require 'mediawiki'
+
+# The Wikipedia constant allows the use of Wikipedia's Query API from Ruby
+# The wrapping is incomplete and the interface will be cleaned up as work is
+# done.
+#
+# == Usage
+#
+# The simplest case is just finding pages by title.  The Wikipedia API allows
+# requests to be on multiple titles or ids, so this wrapping returns an array of
+# pages
+#
+#   require 'wikipedia'
+#   page = Wikipedia.find_by_titles('Foo').pages.first
+#   page.title #=> "Foo"
+#
+# Pages can also be found based on pageid
+# 
+#   page = Wikipedia.find_by_pageids(10).pages.first
+#   page.title #=> "AccessibleComputing"
+#
+# Further API options can be specified in the optional second parameter to
+# find_by_*.  This can be used to limit the fetching of unnecessary data
+#
+#   page = Wikipedia.find_by_titles('Foo', :prop => [:langlinks]).pages.first
+#   page.langlinks #=> ["da", "fi", "it", "no", "sl", "vi"]
+#
+Wikipedia = MediaWiki.new("http://en.wikipedia.org/w/api.php") 

data/test/sample.xml

@@ -0,0 +1,85 @@
+<?xml version="1.0" encoding="utf-8"?>
+<api>
+  <query>
+    <pages>
+      <page lastrevid="208372148" touched="2008-04-29T06:15:08Z" title="Foo" ns="0" length="3945" counter="0" pageid="9132808">
+        <revisions>
+          <rev timestamp="2008-04-26T19:07:10Z" user="Andreas Kaufmann" revid="208372148" comment="Removed category &quot;Computer programming&quot;; Quick-adding category &quot;Variable (computer programming)&quot; (using [[WP:HOTCAT|HotCat]])" minor=""/>
+        </revisions>
+        <links>
+          <pl title="2007" ns="0"/>
+          <pl title="Abstract entity" ns="0"/>
+          <pl title="Abstraction (computer science)" ns="0"/>
+          <pl title="Algebra" ns="0"/>
+          <pl title="Apt:foo" ns="0"/>
+          <pl title="Backronym" ns="0"/>
+          <pl title="Bar (computer science)" ns="0"/>
+          <pl title="Bill Gates" ns="0"/>
+          <pl title="Canonical" ns="0"/>
+          <pl title="Commands" ns="0"/>
+          <pl title="Computer programming" ns="0"/>
+          <pl title="Computer science" ns="0"/>
+          <pl title="Cruft" ns="0"/>
+          <pl title="Data" ns="0"/>
+          <pl title="Eric S. Raymond" ns="0"/>
+          <pl title="FUBAR" ns="0"/>
+          <pl title="Foo Camp" ns="0"/>
+          <pl title="Foo Fighter" ns="0"/>
+          <pl title="Foo Fighters" ns="0"/>
+          <pl title="Foobar" ns="0"/>
+          <pl title="Functions" ns="0"/>
+          <pl title="Hacker convention" ns="0"/>
+          <pl title="Internet Engineering Task Force" ns="0"/>
+          <pl title="Kludge" ns="0"/>
+          <pl title="List of Daffy Duck cartoons" ns="0"/>
+          <pl title="MIT Press" ns="0"/>
+          <pl title="Metasyntactic variable" ns="0"/>
+          <pl title="Neologism" ns="0"/>
+          <pl title="November 5" ns="0"/>
+          <pl title="O'Reilly Media" ns="0"/>
+          <pl title="Perl" ns="0"/>
+          <pl title="Pogo (comics)" ns="0"/>
+          <pl title="Pseudocode" ns="0"/>
+          <pl title="Request for Comments" ns="0"/>
+          <pl title="Smokey Stover" ns="0"/>
+          <pl title="Subroutine" ns="0"/>
+          <pl title="United States v. Microsoft" ns="0"/>
+          <pl title="Variable" ns="0"/>
+          <pl title="Variables" ns="0"/>
+          <pl title="Web Services Interoperability" ns="0"/>
+          <pl title="Wiktionary" ns="0"/>
+        </links>
+        <langlinks>
+          <ll lang="da">Foo (data)</ll>
+          <ll lang="fi">Foo</ll>
+          <ll lang="it">Foo</ll>
+          <ll lang="no">Foo</ll>
+          <ll lang="sl">Foo</ll>
+          <ll lang="vi">Foo</ll>
+        </langlinks>
+        <images>
+          <im title="Image:Wiktionary-logo-en.svg" ns="6"/>
+        </images>
+        <templates>
+          <tl title="Template:Cite book" ns="10"/>
+          <tl title="Template:Cite web" ns="10"/>
+          <tl title="Template:De icon" ns="10"/>
+          <tl title="Template:Languageicon" ns="10"/>
+          <tl title="Template:Reflist" ns="10"/>
+          <tl title="Template:Wiktionary" ns="10"/>
+        </templates>
+        <categories>
+          <cl title="Category:Placeholder names" ns="14"/>
+          <cl title="Category:Variable (computer programming)" ns="14"/>
+        </categories>
+        <extlinks>
+          <el>http://books.google.com/books?id=POlUJW3Z9McC&amp;pg=PA5&amp;dq=foo+jargon&amp;ei=GnIvR8PwGJiSpgK1qIT6CQ&amp;ie=ISO-8859-1&amp;sig=hIE0I8TtPGKUbSU-wgDTm4hQ8ig#PPA4,M1</el>
+          <el>http://foo-magazin.de/</el>
+          <el>http://tools.ietf.org/html/rfc3092</el>
+          <el>http://www.ietf.org/rfc/rfc3092.txt</el>
+          <el>http://www.news.com/Microsoft-ploy-to-block-Sun-exposed/2100-1001_3-912906.html</el>
+        </extlinks>
+      </page>
+    </pages>
+  </query>
+</api>

data/test/test.rb

@@ -0,0 +1,34 @@
+require 'test/unit'
+require 'rubygems'
+require 'shoulda'
+require File.dirname(__FILE__) + '/../lib/mediawiki'
+
+class MediaWiki
+  class MediaWikiBase
+    def get_xml(url)
+      Hpricot.XML(open(File.dirname(__FILE__) + '/sample.xml'))
+    end
+  end
+end
+
+class MediaWikiTest < Test::Unit::TestCase
+  def setup
+    @mw = MediaWiki.new("http://mock.com/api.php")
+  end
+
+  context "MediaWiki interface" do
+    should("find article by id"){ assert @mw.find(10) }
+    should("find article by title"){ assert @mw.find_by_title("Foo") }
+    should("find articles by ids"){ assert @mw.find_by_pageids(10,11) }
+    should("find articles by titles"){ assert @mw.find_by_titles("Foo","Bar") }
+  end
+
+  context "MediaWiki base" do
+    should("have xml"){ assert @mw.find_by_titles("Foo").xml }
+    should("have pages"){ assert @mw.find_by_titles("Foo").pages }
+  end
+
+  context "MediaWiki pages" do
+  end
+end
+

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification 
+name: schleyfox-wikipedia-api
+version: !ruby/object:Gem::Version 
+  version: 0.1.1
+platform: ruby
+authors: 
+- Ben Hughes
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-05-06 00:00:00 -07:00
+default_executable: 
+dependencies: []
+
+description: 
+email: ben@pixelmachine.org
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- README
+- LICENSE
+- lib/mediawiki.rb
+- lib/wikipedia.rb
+- test/sample.xml
+- test/test.rb
+has_rdoc: true
+homepage: http://github.com/schleyfox/wikipedia-api/
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.0.1
+signing_key: 
+specification_version: 2
+summary: Wikipedia-API is a ruby wrapper for the MediaWiki API
+test_files: []
+