opds 0.2.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Benoit Larroque
+
+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 +1,32 @@
+OPDS Parsing library
+====================
+
+This gem provides a parsing library for [OPDS Catalogs](http://opds-spec.org).
+
+It also has the ability to discover catalogs in html feeds.
+
+Installation
+------------
+
+	gem install opds
+
+
+Usage
+-----
+
+Parsing a feed is simply done. 
+
+	require "opds"
+	OPDS::Feed.parse_url("http://catalog.com/catalog.atom")
+
+This method will return an instance of the Feed or Entry classes. Each Atom element is accessible directly via a dedicated method (ex: `feed.title`). Entry also provides a method to directly access any embeded Dublin Core metadata (`dcmeta`). The `raw_doc` attribute gives access to the Nokogiri parsed source.
+
+### Complete atom entries ###
+
+Complete atom entries are available if detected as another instance of the Entry class. Just call `entry.complete` on the partial entry to access it.
+
+### Links ###
+
+Every links are automatically parsed in feeds and entries. They are made available in a collection called `links`. Relative links should be transformed in their absolute equivalent. On each link there is a `navigate` method which will proxy a call to OPDS::Feed.parse_url.
+
+

data/Rakefile

@@ -0,0 +1,46 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "opds"
+    gem.summary = %Q{ruby lib to read OPDS feeds}
+    gem.description = %Q{ruby lib to access OPDS feeds}
+    gem.email = "benoit dot larroque at feedbooks dot com"
+    gem.homepage = "http://github.com/zetaben/opds"
+    gem.authors = ["Benoit Larroque"]
+    gem.add_development_dependency "rspec", ">= 1.2.9"
+    gem.add_runtime_dependency "nokogiri"
+    # 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 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+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 = "opds #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.2.0

data/lib/opds.rb

@@ -0,0 +1,10 @@
+require 'opds/opds'
+require 'opds/support/logging'
+require 'opds/support/browser'
+require 'opds/support/linkset'
+require 'opds/parser'
+
+require 'opds/feed'
+require 'opds/entry'
+require 'opds/acquisition_feed'
+require 'opds/navigation_feed'

data/lib/opds/acquisition_feed.rb

@@ -0,0 +1,4 @@
+module OPDS
+	class AcquisitionFeed < Feed
+	end
+end

data/lib/opds/entry.rb

@@ -0,0 +1,138 @@
+module OPDS
+	class Entry
+		include Logging
+		attr_reader :raw_doc
+		attr_reader :title
+		attr_reader :id
+		attr_reader :updated
+		attr_reader :published
+		attr_reader :summary
+		attr_reader :authors
+		attr_reader :links
+		attr_reader :dcmetas
+		attr_reader :categories
+		attr_reader :content
+		attr_reader :rights
+		attr_reader :subtitle
+
+		def initialize(browser=nil)
+			@browser=browser
+			@browser||=OPDS::Support::Browser.new
+		end
+
+
+		def self.from_nokogiri(content,namespaces=nil, browser=nil)
+			z=self.new browser
+			z.instance_variable_set('@raw_doc',content)
+			z.instance_variable_set('@namespaces',namespaces)
+			z.serialize!
+			z
+		end
+
+
+		def serialize!
+			@namespaces=raw_doc.root.namespaces if @namespaces.nil?
+			@authors=[]
+			@raw_doc=raw_doc.at('./xmlns:entry',@namespaces) if raw_doc.at('./xmlns:entry',@namespaces)
+			@title=text(raw_doc.at('./xmlns:title',@namespaces))
+			@id=text(raw_doc.at('./xmlns:id',@namespaces))
+			@summary=text(raw_doc.at('./xmlns:summary',@namespaces))
+			d=text(raw_doc.at('./xmlns:updated',@namespaces))
+			@updated=DateTime.parse(d) unless d.nil?
+			d=text(raw_doc.at('./xmlns:published',@namespaces))
+			@published=DateTime.parse(d) unless d.nil?
+
+			@authors=raw_doc.xpath('./xmlns:author',@namespaces).collect do |auth|
+				{
+					:name => text(raw_doc.at('./xmlns:author/xmlns:name',@namespaces)),
+					:uri => text(raw_doc.at('./xmlns:author/xmlns:uri',@namespaces)),
+					:email => text(raw_doc.at('./xmlns:author/xmlns:email',@namespaces))
+				}
+			end
+
+			@links=OPDS::Support::LinkSet.new @browser
+			raw_doc.xpath('./xmlns:link',@namespaces).each do |n|
+				text=nil
+				text=n.attributes['title'].value unless n.attributes['title'].nil?
+				link=n.attributes['href'].value
+				type=n.attributes['type'].value unless n.attributes['type'].nil?
+				price=nil
+				currency=nil
+				@namespaces['opds']||='http://opds-spec.org/2010/catalog'
+				oprice=n.at('./opds:price',@namespaces)
+				if oprice
+					price=text(oprice)
+					currency=oprice.attributes['currencycode'].value unless oprice.attributes['currencycode'].nil?
+				end
+
+				unless n.attributes['rel'].nil?
+					n.attributes['rel'].value.split.each do |rel|
+						@links.push(rel,link,text,type,price,currency)
+					end
+				else
+					@links.push(nil,link,text,type,price,currency)
+				end
+			end
+			@dcmetas=Hash.new
+			prefs=@namespaces.reject{|_,v| !%W[http://purl.org/dc/terms/ http://purl.org/dc/elements/1.1/].include?v}
+			prefs.keys.map{|p| p.split(':').last}.each do |pref|
+				raw_doc.xpath('./'+pref+':*',@namespaces).each do |n|
+					@dcmetas[n.name]=[] unless  @dcmetas[n.name]
+					@dcmetas[n.name].push [n.text, n]
+				end
+			end
+
+			@categories=raw_doc.xpath('./xmlns:category',@namespaces).collect do |n|
+				[text(n.attributes['label']),text(n.attributes['term'])]
+			end
+
+			@content=raw_doc.at('./xmlns:content',@namespaces).to_s
+			
+			@contributors=raw_doc.xpath('./xmlns:contributor',@namespaces).collect do |auth|
+				{
+					:name => text(raw_doc.at('./xmlns:contributor/xmlns:name',@namespaces)),
+					:uri => text(raw_doc.at('./xmlns:contributor/xmlns:uri',@namespaces)),
+					:email => text(raw_doc.at('./xmlns:contributor/xmlns:email',@namespaces))
+				}
+			end
+
+			@rights=text(raw_doc.at('./xmlns:rights',@namespaces))
+			@subtitle=text(raw_doc.at('./xmlns:rights',@namespaces))
+
+		end
+
+
+		def author
+			authors.first
+		end
+
+		def partial?
+			links.by(:rel)['alternate'].any? do |l|
+				l[3]=='application/atom+xml'||l[3]=='application/atom+xml;type=entry'
+			end
+		end
+
+		def complete_url
+			links.by(:rel)['alternate'].find do |l|
+				l[3]=='application/atom+xml;type=entry'||l[3]=='application/atom+xml'
+			end unless !partial?
+		end
+
+		def acquisition_links
+			rel_start='http://opds-spec.org/acquisition'
+			[*links.by(:rel).reject do |k,_|
+				k[0,rel_start.size]!=rel_start unless k.nil?
+			end.values]
+		end
+		
+		def inspect
+			"#<#{self.class}:0x#{self.object_id.abs.to_s(16)} #{instance_variables.reject{|e| e=='@raw_doc' }.collect{|e| "#{e}=#{instance_variable_get(e).inspect}"}.join(' ')} >"
+		end
+
+		protected 
+		def text(t)
+			return t.text unless t.nil?
+			t
+		end
+	end
+end

data/lib/opds/feed.rb

@@ -0,0 +1,149 @@
+module OPDS
+	class Feed
+		include Logging
+		attr_reader :raw_doc
+		attr_reader :entries
+
+
+		def initialize(browser=nil)
+			@browser=browser
+			@browser||=OPDS::Support::Browser.new
+		end
+
+		# access root catalog
+		def root
+			return @root unless root?
+			self
+		end
+
+		# root catalog predicate
+		def root?
+		end
+
+		def self.parse_url(url,browser=nil,parser_opts={})
+			@browser=browser
+			@browser||=OPDS::Support::Browser.new
+			@browser.go_to(url)
+			if @browser.ok?
+				parsed = self.parse_raw(@browser.body,parser_opts,browser) 
+				if parsed.nil?
+					disco=@browser.discover(@browser.current_location)
+					if disco.size > 0
+						d=disco[nil]
+						d||=disco['related']
+						d||=disco
+						Logging.log("Discovered : #{d.first.url}")
+						return d.first.navigate
+					end
+					return false
+				else
+					return  parsed
+				end
+			else
+				return false
+			end
+		end
+
+		def self.parse_raw(txt,opts={},browser=nil)
+			parser=OPDSParser.new(opts)
+			pfeed=parser.parse(txt,browser)
+			type=parser.sniffed_type
+			return pfeed unless type.nil?
+			nil
+		end
+
+		def self.from_nokogiri(content,browser=nil)
+			z=self.new browser
+			z.instance_variable_set('@raw_doc',content)
+			z.serialize!
+			z
+		end
+
+		#read xml entries into entry struct
+		def serialize!
+			@entries=raw_doc.xpath('/xmlns:feed/xmlns:entry',raw_doc.root.namespaces).map do |el|
+				OPDS::Entry.from_nokogiri(el,raw_doc.root.namespaces,@browser)
+			end
+		end
+
+		def title
+			text(raw_doc.at('/xmlns:feed/xmlns:title',raw_doc.root.namespaces))
+		end
+
+		def icon
+			text(raw_doc.at('/xmlns:feed/xmlns:icon',raw_doc.root.namespaces))
+		end
+
+		def links
+			if !@links || @links.size ==0
+				@links=OPDS::Support::LinkSet.new @browser
+				raw_doc.xpath('/xmlns:feed/xmlns:link',raw_doc.root.namespaces).each do |n|
+					text=nil
+					text=n.attributes['title'].value unless n.attributes['title'].nil?
+					link=n.attributes['href'].value
+					unless n.attributes['rel'].nil?
+						n.attributes['rel'].value.split.each do |rel|
+							@links.push(rel,link,text)
+						end
+					else
+						@links.push(nil,link,text)
+					end
+				end
+
+			end
+			@links
+		end
+
+		def id
+			text(raw_doc.at('/xmlns:feed/xmlns:id',raw_doc.root.namespaces))
+		end
+
+		def author
+			{
+				:name => text(raw_doc.at('/xmlns:feed/xmlns:author/xmlns:name',raw_doc.root.namespaces)),
+				:uri => text(raw_doc.at('/xmlns:feed/xmlns:author/xmlns:uri',raw_doc.root.namespaces)),
+				:email => text(raw_doc.at('/xmlns:feed/xmlns:author/xmlns:email',raw_doc.root.namespaces))
+			}
+		end
+
+
+		def next_page_url
+			links.link_url(:rel => 'next')
+		end
+
+		def prev_page_url
+			links.link_url(:rel => 'prev')
+		end
+
+		def paginated?
+			!next_page_url.nil?||!prev_page_url.nil?
+		end
+
+		def first_page?
+			!prev_page_url if paginated?
+		end
+
+		def last_page?
+			!next_page_url if paginated?
+		end
+
+		def next_page
+			Feed.parse_url(next_page_url,@browser)
+		end
+
+		def prev_page
+			Feed.parse_url(prev_page_url,@browser)
+		end
+
+		def inspect
+			"#<#{self.class}:0x#{self.object_id.abs.to_s(16)} entries(count):#{@entries.size} #{instance_variables.reject{|e| e=='@raw_doc'||e=='@entries' }.collect{|e| "#{e}=#{instance_variable_get(e).inspect}"}.join(' ')} >"
+		end
+
+		protected
+		def text(t)
+			return t.text unless t.nil?
+			t
+		end
+
+	end
+end

data/lib/opds/navigation_feed.rb

@@ -0,0 +1,4 @@
+module OPDS
+	class NavigationFeed  < Feed
+	end
+end