saxerator 0.0.2 → 0.0.3

data/README.md

@@ -1,7 +1,7 @@
 Saxerator
 =========
 
-Saxerator is a SAX-based xml parser designed for parsing very large files into manageable chunks. Rather than
+Saxerator is a SAX-based xml-to-hash parser designed for parsing very large files into manageable chunks. Rather than
 dealing directly with SAX callback methods, Saxerator gives you Enumerable access to chunks of an xml document.
 This approach is ideal for large xml files containing a collection of elements that you can process
 independently.
@@ -24,6 +24,18 @@ end
 puts "First title: #{parser.for_tag(:title).first}"
 ```
 
+```ruby
+# attributes are stored as a part of the Hash or String object they relate to
+
+# author behaves like a String here, but also responds to .attributes
+primary_authors = parser.for_tag(:author).select { |author| author.attributes['type'] == 'primary' }
+puts "Primary authors: #{primary_authors.join(", ")}"
+
+# item behaves like a Hash, but also responds to .attributes
+favorite_items = parser.for_tag(:item).select { |item| item.attributes['favorite'] }
+puts "First favorite title: #{favorite_items[0]['title']}"
+```
+
 Compatibility
 -------------
 Known compatible rubies:

data/Rakefile

@@ -1 +1,6 @@
 require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/lib/saxerator.rb

@@ -1,5 +1,9 @@
 require "saxerator/version"
 require 'saxerator/configuration'
+
+require 'saxerator/string_with_attributes'
+require 'saxerator/hash_with_attributes'
+
 require 'saxerator/xml_node'
 require 'saxerator/parser/nokogiri'
 

data/lib/saxerator/hash_with_attributes.rb

@@ -0,0 +1,5 @@
+module Saxerator
+  class HashWithAttributes < Hash
+    attr_accessor :attributes
+  end
+end

data/lib/saxerator/parser/nokogiri.rb

@@ -33,7 +33,7 @@ module Saxerator
 
         def start_element(name, attrs = [])
           if stack.size > 0 || name == @tag
-            stack.push Saxerator::XmlNode.new(@config, name, Hash[*attrs.flatten])
+            stack.push XmlNode.new(@config, name, Hash[*attrs.flatten])
           end
         end
 

data/lib/saxerator/string_with_attributes.rb

@@ -1,9 +1,5 @@
 module Saxerator
   class StringWithAttributes < String
     attr_accessor :attributes
-
-    def attribrutes
-      @attributes ||= {}
-    end
   end
 end

data/lib/saxerator/version.rb

@@ -1,3 +1,3 @@
 module Saxerator
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/saxerator/xml_node.rb

@@ -15,20 +15,29 @@ module Saxerator
       children << node
     end
 
+    def to_s
+      string = StringWithAttributes.new(@text ? children.join : children.to_s)
+      string.attributes = attributes
+      string
+    end
+
     def to_hash
       if @text
-        return children.join(' ')
+        to_s
       else
-        out = {}
+        out = HashWithAttributes.new
+        out.attributes = attributes
+
         @children.each do |child|
           name = child.name
+          element = child.to_hash
           if out[name]
             if !out[name].is_a?(Array)
               out[name] = [out[name]]
             end
-            out[name] << child.to_hash
+            out[name] << element
           else
-            out[name] = child.to_hash
+            out[name] = element
           end
         end
         out

data/saxerator.gemspec

@@ -9,9 +9,9 @@ Gem::Specification.new do |s|
   s.authors     = ['Bradley Schaefer']
   s.email       = ['bradley.schaefer@gmail.com']
   s.homepage    = 'https://github.com/soulcutter/saxerator'
-  s.summary     = 'A SAX-based XML parser for parsing large files into manageable chunks'
+  s.summary     = 'A SAX-based XML-to-hash parser for parsing large files into manageable chunks'
   s.description = <<-eos
-    Saxerator is a SAX-based xml parser designed for parsing very large files into manageable chunks. Rather than
+    Saxerator is a SAX-based xml-to-hash parser designed for parsing very large files into manageable chunks. Rather than
     dealing directly with SAX callback methods, Saxerator gives you Enumerable access to chunks of an xml document.
     This approach is ideal for large xml files containing a collection of elements that you can process
     independently.
@@ -28,7 +28,6 @@ Gem::Specification.new do |s|
     'spec/**/*.*',
     'benchmark/**/*.rb',
     'Gemfile',
-    'Guardfile',
     'Rakefile',
     '.rvmrc',
     '.gitignore'
@@ -41,9 +40,6 @@ Gem::Specification.new do |s|
 
   s.add_development_dependency 'rake'
   s.add_development_dependency 'rspec'
-  s.add_development_dependency 'guard'
-  s.add_development_dependency 'guard-bundler'
-  s.add_development_dependency 'guard-rspec'
   s.add_development_dependency 'simplecov'
   s.add_development_dependency 'ipsum'
 end

data/spec/fixtures/nested_elements.xml

@@ -11,15 +11,12 @@
     <updated>2012-01-01T16:17:00-06:00</updated>
     <link type="text/html" href="https://example.com/blog/how-to-eat-an-airplane" rel="alternate"/>
     <title>How to eat an airplane</title>
-    <content type="html">&lt;p&gt;Airplanes are very large, which can present difficulty in digestion.&lt;/p&gt;
-
-      &lt;p&gt;The key is to break it down into bite-sized portions and go slowly.&lt;/p&gt;
-    </content>
+    <content type="html">&lt;p&gt;Airplanes are very large &#8212; this can present difficulty in digestion.&lt;/p&gt;</content>
     <media:thumbnail url="http://www.gravatar.com/avatar/a9eb6ba22e482b71b266daadf9c9a080?s=80"/>
     <author>
       <name>Soulcutter</name>
     </author>
-    <contributor>
+    <contributor type="primary">
       <name>Jane Doe</name>
     </contributor>
     <contributor>

data/spec/lib/saxerator_spec.rb

@@ -1,3 +1,5 @@
+# encoding: utf-8
+
 require 'spec_helper'
 
 describe Saxerator do
@@ -55,6 +57,10 @@ describe Saxerator do
       specify { subject['title'].should == 'How to eat an airplane' }
       specify { subject['author'].should == {'name' => 'Soulcutter'} }
       specify { subject['contributor'].should == [{'name' => 'Jane Doe'}, {'name' => 'Leviticus Alabaster'}] }
+      specify { subject['content'].should == "<p>Airplanes are very large — this can present difficulty in digestion.</p>"}
+      specify { subject['content'].attributes['type'].should == 'html' }
+      specify { subject['contributor'][0].attributes['type'].should == 'primary' }
+      specify { subject['contributor'][0]['name'].should == 'Jane Doe' }
     end
   end
 end

data/spec/spec_helper.rb

@@ -1,6 +1,8 @@
-require 'simplecov'
-SimpleCov.start do
-  add_filter "spec/"
+if ENV['COVERAGE']
+  require 'simplecov'
+  SimpleCov.start do
+    add_filter "spec/"
+  end
 end
 
 require 'saxerator'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: saxerator
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-08 00:00:00.000000000 Z
+date: 2012-04-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -59,54 +59,6 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: guard
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: guard-bundler
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: guard-rspec
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
@@ -139,11 +91,11 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: ! "    Saxerator is a SAX-based xml parser designed for parsing very
-  large files into manageable chunks. Rather than\n    dealing directly with SAX callback
-  methods, Saxerator gives you Enumerable access to chunks of an xml document.\n    This
-  approach is ideal for large xml files containing a collection of elements that you
-  can process\n    independently.\n"
+description: ! "    Saxerator is a SAX-based xml-to-hash parser designed for parsing
+  very large files into manageable chunks. Rather than\n    dealing directly with
+  SAX callback methods, Saxerator gives you Enumerable access to chunks of an xml
+  document.\n    This approach is ideal for large xml files containing a collection
+  of elements that you can process\n    independently.\n"
 email:
 - bradley.schaefer@gmail.com
 executables: []
@@ -154,6 +106,7 @@ files:
 - README.md
 - saxerator.gemspec
 - lib/saxerator/configuration.rb
+- lib/saxerator/hash_with_attributes.rb
 - lib/saxerator/parser/nokogiri.rb
 - lib/saxerator/string_with_attributes.rb
 - lib/saxerator/version.rb
@@ -166,7 +119,6 @@ files:
 - benchmark/benchmark.rb
 - benchmark/generate_sample_file.rb
 - Gemfile
-- Guardfile
 - Rakefile
 - .rvmrc
 - .gitignore
@@ -194,7 +146,7 @@ rubyforge_project: saxerator
 rubygems_version: 1.8.21
 signing_key: 
 specification_version: 3
-summary: A SAX-based XML parser for parsing large files into manageable chunks
+summary: A SAX-based XML-to-hash parser for parsing large files into manageable chunks
 test_files:
 - spec/fixtures/flat_blurbs.xml
 - spec/fixtures/nested_elements.xml

data/Guardfile

@@ -1,13 +0,0 @@
-# More info at https://github.com/guard/guard#readme
-
-guard :bundler do
-  watch('Gemfile')
-  watch(/^saxerator\.gemspec$/)
-end
-
-guard :rspec, :cli => '--color' do
-  watch(%r{^spec/.+_spec\.rb$})
-  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
-  watch(%r{^spec/fixtures/.+\.xml$}) { :spec }
-  watch('spec/spec_helper.rb')  { :spec }
-end