sax-machine 0.2.1 → 0.3.0

data/lib/sax-machine/{sax_element_value_config.rb → config/sax_element_value.rb}

@@ -1,13 +1,12 @@
 module SAXMachine
   class SAXConfig
-
     class ElementValueConfig
       attr_reader :name, :setter
 
       def initialize(name, options)
-        @name = name.to_s
-        @as = options[:as]
-        @setter = "#{@as}="
+        @name     = name.to_s
+        @as       = options[:as]
+        @setter   = "#{@as}="
         @required = options[:required]
       end
 
@@ -16,9 +15,8 @@ module SAXMachine
       end
 
       def required?
-        @required
+        !!@required
       end
     end
-
   end
-end
+end

data/lib/sax-machine/{sax_handler.rb → handlers/sax_abstract_handler.rb}

@@ -1,8 +1,7 @@
-require "nokogiri"
-require "time"
+require 'time'
 
 module SAXMachine
-  class SAXHandler < Nokogiri::XML::SAX::Document
+  module SAXAbstractHandler
     NO_BUFFER = :no_buffer
 
     class StackNode < Struct.new(:object, :config, :buffer)
@@ -13,14 +12,14 @@ module SAXMachine
       end
     end
 
-    def initialize(object, on_error = nil, on_warning = nil)
+    def _initialize(object, on_error = nil, on_warning = nil)
       @stack = [ StackNode.new(object) ]
       @parsed_configs = {}
       @on_error = on_error
       @on_warning = on_warning
     end
 
-    def characters(data)
+    def _characters(data)
       node = stack.last
 
       if node.buffer == NO_BUFFER
@@ -29,10 +28,8 @@ module SAXMachine
         node.buffer << data
       end
     end
-    alias cdata_block characters
-
-    def start_element(name, attrs = [])
 
+    def _start_element(name, attrs = [])
       name   = normalize_name(name)
       node   = stack.last
       object = node.object
@@ -61,10 +58,10 @@ module SAXMachine
         if !collection_config && element_config = sax_config.element_config_for_tag(name, attrs)
           new_object =
             case element_config.data_class.to_s
-            when 'Integer' then 0
-            when 'Float'   then 0.0
-            when 'Time'    then Time.at(0)
-            when ''        then object
+            when "Integer" then 0
+            when "Float"   then 0.0
+            when "Time"    then Time.at(0)
+            when ""        then object
             else
               element_config.data_class.new
             end
@@ -76,7 +73,7 @@ module SAXMachine
       end
     end
 
-    def end_element(name)
+    def _end_element(name)
       name = normalize_name(name)
 
       start_tag = stack[-2]
@@ -107,13 +104,13 @@ module SAXMachine
         else
           value =
             case config.data_class.to_s
-            when 'String'  then value.to_s
-            when 'Integer' then value.to_i
-            when 'Float'   then value.to_f
+            when "String"  then value.to_s
+            when "Integer" then value.to_i
+            when "Float"   then value.to_f
             # Assumes that time elements will be string-based and are not
             # something else, e.g. seconds since epoch
-            when 'Time'    then Time.parse(value.to_s)
-            when ''        then value
+            when "Time"    then Time.parse(value.to_s)
+            when ""        then value
             else
               element
             end
@@ -134,30 +131,29 @@ module SAXMachine
       stack.pop
     end
 
-    private
-
-    def mark_as_parsed(object, element_config)
-      unless element_config.collection?
-        @parsed_configs[[object.object_id, element_config.object_id]] = true
+    def _error(string)
+      if @on_error
+        @on_error.call(string)
       end
     end
 
-    def parsed_config?(object, element_config)
-      @parsed_configs[[object.object_id, element_config.object_id]]
-    end
-
-    def warning(string)
+    def _warning(string)
       if @on_warning
         @on_warning.call(string)
       end
     end
 
-    def error(string)
-      if @on_error
-        @on_error.call(string)
+    private
+
+    def mark_as_parsed(object, element_config)
+      unless element_config.collection?
+        @parsed_configs[[object.object_id, element_config.object_id]] = true
       end
     end
 
+    def parsed_config?(object, element_config)
+      @parsed_configs[[object.object_id, element_config.object_id]]
+    end
 
     def sax_config_for(object)
       if object.class.respond_to?(:sax_config)
@@ -172,7 +168,7 @@ module SAXMachine
     end
 
     def normalize_name(name)
-      name.gsub(/\-/, '_')
+      name.gsub(/\-/, "_")
     end
 
     def set_attributes_on(object, attributes)

data/lib/sax-machine/handlers/sax_nokogiri_handler.rb

@@ -0,0 +1,16 @@
+require 'sax-machine/handlers/sax_abstract_handler'
+require 'nokogiri'
+
+module SAXMachine
+  class SAXNokogiriHandler < Nokogiri::XML::SAX::Document
+    include SAXAbstractHandler
+
+    alias_method :initialize, :_initialize
+    alias_method :characters, :_characters
+    alias_method :cdata_block, :_characters
+    alias_method :start_element, :_start_element
+    alias_method :end_element, :_end_element
+    alias_method :error, :_error
+    alias_method :warning, :_warning
+  end
+end

data/lib/sax-machine/handlers/sax_ox_handler.rb

@@ -0,0 +1,41 @@
+require 'sax-machine/handlers/sax_abstract_handler'
+require 'ox'
+
+module SAXMachine
+  class SAXOxHandler < Ox::Sax
+    include SAXAbstractHandler
+
+    def initialize(*args)
+      _initialize(*args)
+      _reset_element
+    end
+
+    def attr(name, str)
+      @attrs[name] = str
+    end
+
+    def attrs_done
+      _start_element(@element, @attrs)
+      _reset_element
+    end
+
+    def start_element(name)
+      @element = name
+    end
+
+    def error(message, line, column)
+      _error("#{message} on line #{line} column #{column}")
+    end
+
+    alias_method :text, :_characters
+    alias_method :cdata, :_characters
+    alias_method :end_element, :_end_element
+
+    private
+
+    def _reset_element
+      @attrs = {}
+      @element = ""
+    end
+  end
+end

data/lib/sax-machine/sax_config.rb

@@ -1,17 +1,16 @@
-require "sax-machine/sax_attribute_config"
-require "sax-machine/sax_element_value_config"
-require "sax-machine/sax_element_config"
-require "sax-machine/sax_collection_config"
-require "sax-machine/sax_ancestor_config"
+require "sax-machine/config/sax_attribute"
+require "sax-machine/config/sax_element_value"
+require "sax-machine/config/sax_element"
+require "sax-machine/config/sax_collection"
+require "sax-machine/config/sax_ancestor"
 
 module SAXMachine
   class SAXConfig
-
     attr_accessor :top_level_elements, :top_level_attributes, :top_level_element_value, :collection_elements, :ancestors
 
     def initialize
       # Default value is an empty array
-      @top_level_elements  = Hash.new { |hash, key| hash[key] = [] }
+      @top_level_elements = Hash.new { |hash, key| hash[key] = [] }
       @top_level_attributes  = []
       @top_level_element_value = []
       @collection_elements = Hash.new { |hash, key| hash[key] = [] }
@@ -19,11 +18,12 @@ module SAXMachine
     end
 
     def columns
-      @top_level_elements.map {|name, ecs| ecs }.flatten
+      @top_level_elements.map { |name, ecs| ecs }.flatten
     end
 
     def initialize_copy(sax_config)
       super
+
       @top_level_elements = sax_config.top_level_elements.clone
       @top_level_attributes = sax_config.top_level_attributes.clone
       @top_level_element_value = sax_config.top_level_element_value.clone
@@ -71,4 +71,4 @@ module SAXMachine
       @top_level_elements[name.to_s].detect { |ec| ec.attrs_match?(attrs) }
     end
   end
-end
+end

data/lib/sax-machine/sax_configure.rb

@@ -1,5 +1,4 @@
 module SAXMachine
-
   def self.configure(clazz)
     extended_clazz = Class.new(clazz)
     extended_clazz.send(:include, SAXMachine)
@@ -18,11 +17,9 @@ module SAXMachine
     (class << clazz;self;end).send(:define_method, :parse) do |xml_text|
       extended_clazz.parse(xml_text)
     end
-
   end
 
   module LightWeightSaxMachine
-
     attr_writer :sax_config
 
     def sax_config
@@ -32,7 +29,5 @@ module SAXMachine
     def inherited(subclass)
       subclass.sax_config.send(:initialize_copy, self.sax_config)
     end
-
   end
-
-end
+end

data/lib/sax-machine/sax_document.rb

@@ -1,18 +1,30 @@
 require "nokogiri"
 
 module SAXMachine
-
   def self.included(base)
     base.send(:include, InstanceMethods)
-    base.extend ClassMethods
+    base.extend(ClassMethods)
   end
 
   def parse(xml_text, on_error = nil, on_warning = nil)
-    sax_handler = SAXHandler.new(self, on_error, on_warning)
-    parser = Nokogiri::XML::SAX::Parser.new(sax_handler)
-    parser.parse(xml_text) do |ctx|
-      ctx.replace_entities = true
+    if SAXMachine.handler == :ox
+      Ox.sax_parse(
+        SAXOxHandler.new(self, on_error, on_warning),
+        StringIO.new(xml_text),
+        {
+          symbolize: false,
+          convert_special: true,
+          skip: :skip_return,
+        }
+      )
+    else
+      handler = SAXNokogiriHandler.new(self, on_error, on_warning)
+      parser = Nokogiri::XML::SAX::Parser.new(handler)
+      parser.parse(xml_text) do |ctx|
+        ctx.replace_entities = true
+      end
     end
+
     self
   end
 
@@ -25,13 +37,12 @@ module SAXMachine
   end
 
   module ClassMethods
-
     def inherited(subclass)
       subclass.sax_config.send(:initialize_copy, self.sax_config)
     end
 
-    def parse(xml_text, on_error = nil, on_warning = nil)
-      new.parse(xml_text, on_error, on_warning)
+    def parse(*args)
+      new.parse(*args)
     end
 
     def element(name, options = {})
@@ -42,13 +53,13 @@ module SAXMachine
 
     def attribute(name, options = {})
       real_name = (options[:as] ||= name).to_s
-      sax_config.add_top_level_attribute(self.class.to_s, options.merge(:name => name))
+      sax_config.add_top_level_attribute(self.class.to_s, options.merge(name: name))
       create_attr real_name
     end
 
     def value(name, options = {})
       real_name = (options[:as] ||= name).to_s
-      sax_config.add_top_level_element_value(self.class.to_s, options.merge(:name => name))
+      sax_config.add_top_level_element_value(self.class.to_s, options.merge(name: name))
       create_attr real_name
     end
 
@@ -80,6 +91,7 @@ module SAXMachine
 
     def elements(name, options = {})
       options[:as] ||= name
+
       if options[:class]
         sax_config.add_collection_element(name, options)
       else
@@ -88,7 +100,7 @@ module SAXMachine
             #{options[:as]} << value
           end
         SRC
-        sax_config.add_top_level_element(name, options.merge(:collection => true))
+        sax_config.add_top_level_element(name, options.merge(collection: true))
       end
 
       if !method_defined?(options[:as].to_s)
@@ -99,7 +111,7 @@ module SAXMachine
         SRC
       end
 
-      attr_writer options[:as] unless method_defined?("#{options[:as]}=")
+      attr_writer(options[:as]) unless method_defined?("#{options[:as]}=")
     end
 
     def sax_config
@@ -109,10 +121,9 @@ module SAXMachine
     # we only want to insert the getter and setter if they haven't defined it from elsewhere.
     # this is how we allow custom parsing behavior. So you could define the setter
     # and have it parse the string into a date or whatever.
-    def create_attr real_name
-      attr_reader real_name unless method_defined?(real_name)
-      attr_writer real_name unless method_defined?("#{real_name}=")
+    def create_attr(real_name)
+      attr_reader(real_name) unless method_defined?(real_name)
+      attr_writer(real_name) unless method_defined?("#{real_name}=")
     end
   end
-
 end

data/lib/sax-machine/version.rb

@@ -1,3 +1,3 @@
 module SAXMachine
-  VERSION = "0.2.1"
-end
+  VERSION = "0.3.0"
+end

data/sax-machine.gemspec

@@ -1,24 +1,21 @@
 # -*- encoding: utf-8 -*-
-require File.expand_path('../lib/sax-machine/version', __FILE__)
+require File.expand_path("../lib/sax-machine/version", __FILE__)
 
 Gem::Specification.new do |s|
-  s.name    = 'sax-machine'
-  s.version = SAXMachine::VERSION
+  s.name      = "sax-machine"
+  s.version   = SAXMachine::VERSION
 
-  s.authors   = ["Paul Dix", "Julien Kirch", "Ezekiel Templin"]
+  s.authors   = ["Paul Dix", "Julien Kirch", "Ezekiel Templin", "Dmitry Krasnoukhov"]
   s.email     = %q{paul@pauldix.net}
   s.homepage  = %q{http://github.com/pauldix/sax-machine}
-
-  s.summary   = %q{Declarative SAX Parsing with Nokogiri}
-
+  s.summary   = %q{Declarative SAX Parsing with Nokogiri or Ox}
   s.license   = %q{MIT}
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.require_paths = ["lib"]
+  s.platform      = Gem::Platform::RUBY
 
-  s.platform = Gem::Platform::RUBY
-
-  s.add_dependency 'nokogiri', "~> 1.6.0"
-  s.add_development_dependency "rspec", "~> 2.13.0"
+  s.add_dependency "nokogiri", "~> 1.6.0"
+  s.add_development_dependency "rspec", "~> 3.0"
 end

data/spec/fixtures/atom-content.html

@@ -0,0 +1,15 @@
+
+<div xmlns="http://www.w3.org/1999/xhtml"><p>In my previous <a href="http://www.pauldix.net/2008/08/serializing-dat.html">post about the speed of serializing data</a>, I concluded that Marshal was the quickest way to get things done. So I set about using Marshal to store some data in an ActiveRecord object. Things worked great at first, but on some test data I got this error: marshal data too short. Luckily, <a href="http://www.brynary.com/">Bryan Helmkamp</a> had helpfully pointed out that there were sometimes problems with storing marshaled data in the database. He said it was best to base64 encode the marshal dump before storing.</p>
+
+<p>I was curious why it was working on some things and not others. It turns out that some types of data being marshaled were causing the error to pop up. Here's the test data I used in my specs:</p>
+<pre>{ :foo =&gt; 3, :bar =&gt; 2 } # hash with symbols for keys and integer values<br />[3, 2.1, 4, 8]&nbsp; &nbsp;&nbsp; &nbsp;&nbsp; &nbsp;&nbsp; # array with integer and float values</pre>
+<p>Everything worked when I switched the array values to all integers so it seems that floats were causing the problem. However, in the interest of keeping everything working regardless of data types, I base64 encoded before going into the database and decoded on the way out.</p>
+
+<p>I also ran the benchmarks again to determine what impact this would have on speed. Here are the results for 100 iterations on a 10k element array and a 10k element hash with and without base64 encode/decode:</p>
+<pre>&nbsp; &nbsp;&nbsp; &nbsp;&nbsp; &nbsp;&nbsp; &nbsp;&nbsp; &nbsp; user&nbsp; &nbsp;&nbsp; &nbsp; system&nbsp; &nbsp;&nbsp; total&nbsp; &nbsp;&nbsp; &nbsp; real<br />array marshal&nbsp; 0.200000&nbsp; &nbsp;0.010000&nbsp; &nbsp;0.210000 (&nbsp; 0.214018) (without Base64)<br />array marshal&nbsp; 0.220000&nbsp; &nbsp;0.010000&nbsp; &nbsp;0.230000 (&nbsp; 0.250260)<br /><br />hash marshal&nbsp; &nbsp;1.830000&nbsp; &nbsp;0.040000&nbsp; &nbsp;1.870000 (&nbsp; 1.892874) (without Base64)<br />hash marshal&nbsp; &nbsp;2.040000&nbsp; &nbsp;0.100000&nbsp; &nbsp;2.140000 (&nbsp; 2.170405)</pre>
+<p>As you can see the difference in speed is pretty negligible. I assume that the error has to do with AR cleaning the stuff that gets inserted into the database, but I'm not really sure. In the end it's just easier to use Base64.encode64 when serializing data into a text field in ActiveRecord using Marshal.</p>
+
+<p>I've also read people posting about this error when using the database session store. I can only assume that it's because they were trying to store either way too much data in their session (too much for a regular text field) or they were storing float values or some other data type that would cause this to pop up. Hopefully this helps.</p></div>
+<div class="feedflare">
+<a href="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?a=rWfWO"><img src="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?i=rWfWO" border="0"></img></a> <a href="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?a=RaCqo"><img src="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?i=RaCqo" border="0"></img></a> <a href="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?a=1CBLo"><img src="http://feeds.feedburner.com/~f/PaulDixExplainsNothing?i=1CBLo" border="0"></img></a>
+</div><img src="http://feeds.feedburner.com/~r/PaulDixExplainsNothing/~4/383536354" height="1" width="1"/>