pauldix-sax-machine 0.0.3

data/Rakefile

@@ -0,0 +1,14 @@
+require "spec"
+require "spec/rake/spectask"
+require 'lib/sax-machine.rb'
+
+Spec::Rake::SpecTask.new do |t|
+  t.spec_opts = ['--options', "\"#{File.dirname(__FILE__)}/spec/spec.opts\""]
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+task :install do
+  rm_rf "*.gem"
+  puts `gem build sax-machine.gemspec`
+  puts `sudo gem install sax-machine-#{SAXMachine::VERSION}.gem`
+end

data/lib/sax-machine.rb

@@ -0,0 +1,11 @@
+require "rubygems"
+
+$LOAD_PATH.unshift(File.expand_path(File.dirname(__FILE__))) unless $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
+
+require "sax-machine/sax_document"
+require "sax-machine/sax_handler"
+require "sax-machine/sax_config"
+
+module SAXMachine
+  VERSION = "0.0.3"
+end

data/lib/sax-machine/sax_config.rb

@@ -0,0 +1,38 @@
+require "sax-machine/sax_element_config"
+require "sax-machine/sax_collection_config"
+
+module SAXMachine
+  class SAXConfig
+    def initialize
+      @top_level_elements  = []
+      @collection_elements = []
+    end
+    
+    def add_top_level_element(name, options)
+      @top_level_elements << ElementConfig.new(name, options)
+    end
+    
+    def add_collection_element(name, options)
+      @collection_elements << CollectionConfig.new(name, options)
+    end
+    
+    def collection_config(name)
+      @collection_elements.detect { |ce| ce.name.to_s == name.to_s }
+    end
+
+    def element_config_for_attribute(name, attrs)
+      @top_level_elements.detect do |element_config|
+        element_config.name == name &&
+        element_config.has_value_and_attrs_match?(attrs)
+      end
+    end
+  
+    def element_config_for_tag(name, attrs)
+      @top_level_elements.detect do |element_config|
+        element_config.name == name &&
+        element_config.attrs_match?(attrs)
+      end
+    end
+    
+  end
+end

data/lib/sax-machine/sax_document.rb

@@ -0,0 +1,46 @@
+require "nokogiri"
+
+module SAXMachine
+  
+  def self.included(base)
+    base.extend ClassMethods
+  end
+  
+  def parse(xml_text)
+    sax_handler = SAXHandler.new(self)
+    parser = Nokogiri::XML::SAX::Parser.new(sax_handler)
+    parser.parse(xml_text)
+    self
+  end
+  
+  module ClassMethods
+
+    def parse(xml_text)
+      new.parse(xml_text)
+    end
+    
+    def element(name, options = {})
+      options[:as] ||= name
+      sax_config.add_top_level_element(name, options)
+      attr_accessor options[:as]
+    end
+    
+    def elements(name, options = {})
+      options[:as] ||= name
+      sax_config.add_collection_element(name, options)
+      
+      class_eval <<-SRC
+        def #{options[:as]}
+          @#{options[:as]} ||= []
+        end
+      SRC
+      
+      attr_writer options[:as]
+    end
+    
+    def sax_config
+      @sax_config ||= SAXConfig.new
+    end
+  end
+  
+end

data/lib/sax-machine/sax_handler.rb

@@ -0,0 +1,95 @@
+require "nokogiri"
+
+module SAXMachine
+  class SAXHandler < Nokogiri::XML::SAX::Document
+    attr_reader :object
+    
+    def initialize(object)
+      @object = object
+      @parsed_configs = {}
+    end
+    
+    def characters(string)
+      if parsing_collection?
+        @collection_handler.characters(string)
+      elsif @element_config
+        @value = string
+      end
+    end
+    
+    def start_element(name, attrs = [])
+      @name   = name
+      @attrs  = attrs
+      
+      if parsing_collection?
+        @collection_handler.start_element(@name, @attrs)
+        
+      elsif @collection_config = sax_config.collection_config(@name)
+        @collection_handler = @collection_config.handler
+        
+      elsif @element_config = sax_config.element_config_for_attribute(@name, @attrs)
+        parse_element_attribute
+        
+      else
+        @element_config = sax_config.element_config_for_tag(@name, @attrs)
+      end
+    end
+    
+    def end_element(name)
+      if parsing_collection? && @collection_config.name == name
+        @object.send(@collection_config.accessor) << @collection_handler.object
+        reset_current_collection
+        
+      elsif parsing_collection?
+        @collection_handler.end_element(name)
+        
+      elsif characaters_captured? && !parsed_config?
+        mark_as_parsed
+        @object.send(@element_config.setter, @value)
+      end
+      
+      reset_current_tag
+    end
+    
+    def characaters_captured?
+      !@value.nil?
+    end
+    
+    def parsing_collection?
+      !@collection_handler.nil?
+    end
+    
+    def parse_element_attribute
+      unless parsed_config?
+        mark_as_parsed
+        @object.send(@element_config.setter, @element_config.value_from_attrs(@attrs))
+      end
+      
+      @element_config = nil
+    end
+    
+    def mark_as_parsed
+      @parsed_configs[@element_config] = true
+    end
+    
+    def parsed_config?
+      @parsed_configs[@element_config]
+    end
+    
+    def reset_current_collection
+      @collection_handler = nil
+      @collection_config  = nil
+    end
+    
+    def reset_current_tag
+      @name   = nil
+      @attrs  = nil
+      @value  = nil
+      @element_config = nil
+    end
+    
+    def sax_config
+      @object.class.sax_config
+    end
+  end
+end

data/spec/sax-machine/sax_document_spec.rb

@@ -0,0 +1,286 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe "SAXMachine" do
+  describe "element" do
+    describe "when parsing a single element" do
+      before :each do
+        @klass = Class.new do
+          include SAXMachine
+          element :title
+        end
+      end
+
+      it "should provide an accessor" do
+        document = @klass.new
+        document.title = "Title"
+        document.title.should == "Title"
+      end
+
+      it "should not overwrite the accessor when the element is not present" do
+        document = @klass.new
+        document.title = "Title"
+        document.parse("<foo></foo>")
+        document.title.should == "Title"
+      end
+
+      it "should overwrite the accessor when the element is present" do
+        document = @klass.new
+        document.title = "Old title"
+        document.parse("<title>New title</title>")
+        document.title.should == "New title"
+      end
+
+      it "should save the element text into an accessor" do
+        document = @klass.parse("<title>My Title</title>")
+        document.title.should == "My Title"
+      end
+
+      it "should save the element text into an accessor when there are multiple elements" do
+        document = @klass.parse("<xml><title>My Title</title><foo>bar</foo></xml>")
+        document.title.should == "My Title"
+      end
+
+      it "should save the first element text when there are multiple of the same element" do
+        document = @klass.parse("<xml><title>My Title</title><title>bar</title></xml>")
+        document.title.should == "My Title"    
+      end
+    end
+
+    describe "when parsing multiple elements" do
+      before :each do
+        @klass = Class.new do
+          include SAXMachine
+          element :title
+          element :name
+        end
+      end
+
+      it "should save the element text for a second tag" do
+        document = @klass.parse("<xml><title>My Title</title><name>Paul</name></xml>")
+        document.name.should == "Paul"
+        document.title.should == "My Title"
+      end
+    end
+
+    describe "when using options for parsing elements" do
+      describe "using the 'as' option" do
+        before :each do
+          @klass = Class.new do
+            include SAXMachine
+            element :description, :as => :summary
+          end
+        end
+
+        it "should provide an accessor using the 'as' name" do
+          document = @klass.new
+          document.summary = "a small summary"
+          document.summary.should == "a small summary"
+        end
+
+        it "should save the element text into the 'as' accessor" do
+          document = @klass.parse("<description>here is a description</description>")
+          document.summary.should == "here is a description"
+        end
+      end
+      
+      describe "using the :with option" do
+        describe "and the :value option" do
+          before :each do
+            @klass = Class.new do
+              include SAXMachine
+              element :link, :value => :href, :with => {:foo => "bar"}
+            end
+          end
+          
+          it "should save the value of a matching element" do
+            document = @klass.parse("<link href='test' foo='bar'>asdf</link>")
+            document.link.should == "test"
+          end
+          
+          it "should save the value of the first matching element" do
+            document = @klass.parse("<xml><link href='first' foo='bar' /><link href='second' foo='bar' /></xml>")
+            document.link.should == "first"
+          end
+          
+          describe "and the :as option" do
+            before :each do
+              @klass = Class.new do
+                include SAXMachine
+                element :link, :value => :href, :as => :url, :with => {:foo => "bar"}
+                element :link, :value => :href, :as => :second_url, :with => {:asdf => "jkl"}
+              end
+            end
+            
+            it "should save the value of the first matching element" do
+              document = @klass.parse("<xml><link href='first' foo='bar' /><link href='second' asdf='jkl' /><link href='second' foo='bar' /></xml>")
+              document.url.should == "first"
+              document.second_url.should == "second"
+            end            
+          end
+        end
+        
+        describe "with only one element" do
+          before :each do
+            @klass = Class.new do
+              include SAXMachine
+              element :link, :with => {:foo => "bar"}
+            end
+          end
+
+          it "should save the text of an element that has matching attributes" do
+            document = @klass.parse("<link foo=\"bar\">match</link>")
+            document.link.should == "match"
+          end
+
+          it "should not save the text of an element that doesn't have matching attributes" do
+            document = @klass.parse("<link>no match</link>")
+            document.link.should be_nil
+          end
+
+          it "should save the text of an element that has matching attributes when it is the second of that type" do
+            document = @klass.parse("<xml><link>no match</link><link foo=\"bar\">match</link></xml>")
+            document.link.should == "match"          
+          end
+          
+          it "should save the text of an element that has matching attributes plus a few more" do
+            document = @klass.parse("<xml><link>no match</link><link asdf='jkl' foo='bar'>match</link>")
+            document.link.should == "match"
+          end
+        end
+        
+        describe "with multiple elements of same tag" do
+          before :each do
+            @klass = Class.new do
+              include SAXMachine
+              element :link, :as => :first, :with => {:foo => "bar"}
+              element :link, :as => :second, :with => {:asdf => "jkl"}
+            end
+          end
+          
+          it "should match the first element" do
+            document = @klass.parse("<xml><link>no match</link><link foo=\"bar\">first match</link><link>no match</link></xml>")
+            document.first.should == "first match"
+          end
+          
+          it "should match the second element" do
+            document = @klass.parse("<xml><link>no match</link><link foo='bar'>first match</link><link asdf='jkl'>second match</link><link>hi</link></xml>")
+            document.second.should == "second match"
+          end
+        end
+      end # using the 'with' option
+      
+      describe "using the 'value' option" do
+        before :each do
+          @klass = Class.new do
+            include SAXMachine
+            element :link, :value => :foo
+          end
+        end
+        
+        it "should save the attribute value" do
+          document = @klass.parse("<link foo='test'>hello</link>")
+          document.link.should == 'test'
+        end
+        
+        it "should save the attribute value when there is no text enclosed by the tag" do
+          document = @klass.parse("<link foo='test'></link>")
+          document.link.should == 'test'
+        end
+        
+        it "should save the attribute value when the tag close is in the open" do
+          document = @klass.parse("<link foo='test'/>")
+          document.link.should == 'test'
+        end
+      end
+    end
+  end
+  
+  describe "elements" do
+    # I took this stuff out because I'm not sure yet if this is something I want to bother supporting.
+    
+    # describe "when parsing multiple elements" do
+    #   before :each do
+    #     @klass = Class.new do
+    #       include SAXMachine
+    #       elements :entry, :as => :entries
+    #     end
+    #   end
+    #   
+    #   it "should provide a collection accessor" do
+    #     document = @klass.new
+    #     document.entries << :foo
+    #     document.entries.should == [:foo]
+    #   end
+    #   
+    #   it "should parse a single element" do
+    #     document = @klass.parse("<entry>hello</entry>")
+    #     document.entries.should == ["hello"]
+    #   end
+    #   
+    #   it "should parse multiple elements" do
+    #     document = @klass.parse("<xml><entry>hello</entry><entry>world</entry></xml>")
+    #     document.entries.should == ["hello", "world"]
+    #   end
+    # end
+    
+    describe "when using the class option" do
+      before :each do
+        class Foo
+          include SAXMachine
+          element :title
+        end
+        @klass = Class.new do
+          include SAXMachine
+          elements :entry, :as => :entries, :class => Foo
+        end
+      end
+      
+      it "should parse a single element with children" do
+        document = @klass.parse("<entry><title>a title</title></entry>")
+        document.entries.size.should == 1
+        document.entries.first.title.should == "a title"
+      end
+      
+      it "should parse multiple elements with children" do
+        document = @klass.parse("<xml><entry><title>title 1</title></entry><entry><title>title 2</title></entry></xml>")
+        document.entries.size.should == 2
+        document.entries.first.title.should == "title 1"
+        document.entries.last.title.should == "title 2"
+      end
+      
+      it "should not parse a top level element that is specified only in a child" do
+        document = @klass.parse("<xml><title>no parse</title><entry><title>correct title</title></entry></xml>")
+        document.entries.size.should == 1
+        document.entries.first.title.should == "correct title"
+      end
+    end    
+  end
+  
+  describe "full example" do
+    before :each do
+      @xml = File.read('spec/sax-machine/atom.xml')
+      class AtomEntry
+        include SAXMachine
+        element :title
+        element :name, :as => :author
+        element "feedburner:origLink", :as => :url
+        element :summary
+        element :content
+        element :published
+      end
+        
+      class Atom
+        include SAXMachine
+        element :title
+        element :link, :value => :href, :as => :url, :with => {:type => "text/html"}
+        element :link, :value => :href, :as => :feed_url, :with => {:type => "application/atom+xml"}
+        elements :entry, :as => :entries, :class => AtomEntry
+      end
+    end # before
+    
+    it "should parse the url" do
+      f = Atom.parse(@xml)
+      f.url.should == "http://www.pauldix.net/"
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--diff
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,13 @@
+require "rubygems"
+require "spec"
+
+# gem install redgreen for colored test output
+begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
+
+path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
+$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
+
+require "sax-machine"
+
+# Spec::Runner.configure do |config|
+# end

metadata

@@ -0,0 +1,69 @@
+--- !ruby/object:Gem::Specification 
+name: pauldix-sax-machine
+version: !ruby/object:Gem::Version 
+  version: 0.0.3
+platform: ruby
+authors: 
+- Paul Dix
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-01-13 00:00:00 -08:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+    version: 
+description: 
+email: paul@pauldix.net
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/sax-machine.rb
+- lib/sax-machine/sax_config.rb
+- lib/sax-machine/sax_document.rb
+- lib/sax-machine/sax_handler.rb
+- README.rdoc
+- Rakefile
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/sax-machine/sax_document_spec.rb
+has_rdoc: true
+homepage: http://github.com/pauldix/sax-machine
+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: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Declarative SAX Parsing with Nokogiri
+test_files: []
+