xmlhasher 0.0.5 → 0.0.6

data/README.md

@@ -1,16 +1,13 @@
 # XmlHasher
 
 [![Build Status](https://travis-ci.org/cloocher/xmlhasher.png)](https://travis-ci.org/cloocher/xmlhasher)
-[![Coverage Status](https://coveralls.io/repos/cloocher/xmlhasher/badge.png?branch=master)](https://coveralls.io/r/cloocher/xmlhasher)
 [![Gem Version](https://badge.fury.io/rb/xmlhasher.png)](http://badge.fury.io/rb/xmlhasher)
 
 Fast XML to Ruby Hash converter
 
 ## Installation
 
-## Installation
-
-Aggcat is available through [Rubygems](http://rubygems.org/gems/xmlhasher) and can be installed via:
+XmlHasher is available through [Rubygems](http://rubygems.org/gems/xmlhasher) and can be installed via:
 
 ```
 $ gem install xmlhasher
@@ -28,17 +25,27 @@ gem 'xmlhasher'
 require 'xmlhasher'
 
 # XmlHasher global configuration
+#
+# snakecase = true converts all keys to snake case notation
+# ignore_namespaces = true will remove XML namespace attributes
+# string_keys = true will convert all keys to Strings, otherwise they will be Symbols
+#
+# here is default configuration
 XmlHasher.configure do |config|
   config.snakecase = true
   config.ignore_namespaces = true
+  config.string_keys = false
 end
 
 # alternatively, specify configuration options when instantiating a Parser
 parser = XmlHasher::Parser.new(
   :snakecase => true,
   :ignore_namespaces => true
+  :string_keys => false
 )
 
+# by default, XmlHasher will convert all keys to symbols.  If you want all keys to be Strings, set :string_keys option to 'true'
+
 # parse XML file
 XmlHasher.parse(File.new('/path/to/my/file.xml'))
 
@@ -47,6 +54,33 @@ XmlHasher.parse("<tag1><tag2>content</tag2></tag1>")
 # => {:tag1=>{:tag2=>"content"}}
 
 ```
+## Benchmarks
+
+How fast is it?  Try it for yourself - [benchmark.rb](https://github.com/cloocher/xmlhasher/blob/master/benchmark/benchmark.rb)
+
+```
+Converting small xml from text to Hash:
+
+                            user     system      total        real
+activesupport(rexml)     0.380000   0.000000   0.380000 (  0.385326)
+activesupport(libxml)    0.060000   0.000000   0.060000 (  0.062008)
+activesupport(nokogiri)  0.090000   0.000000   0.090000 (  0.089466)
+xmlsimple                0.480000   0.010000   0.490000 (  0.490938)
+nori                     0.120000   0.000000   0.120000 (  0.123612)
+xmlhasher                0.010000   0.000000   0.010000 (  0.017366)
+
+Converting large xml from file to Hash:
+
+                            user     system      total        real
+activesupport(rexml)    57.230000   0.240000  57.470000 ( 57.460510)
+activesupport(libxml)   # Segmentation fault
+activesupport(nokogiri) 12.650000   0.250000  12.900000 ( 12.908073)
+xmlsimple               49.980000   0.160000  50.140000 ( 50.140775)
+nori                    15.590000   0.110000  15.700000 ( 15.697411)
+xmlhasher                4.290000   0.030000   4.320000 (  4.316379)
+```
+Note: benchmarks were generated on a Macbook Pro using Ruby 1.9.3p392
+
 ## Requirements
 
 * Ruby 1.8.7 or higher

data/benchmark/benchmark.rb

@@ -0,0 +1,95 @@
+$:.push File.expand_path('../../lib', __FILE__)
+
+require 'benchmark'
+require 'xmlhasher'
+begin
+  require 'nori'
+rescue
+  puts "nori gem in not installed, run 'gem install nori'"
+end
+begin
+  require 'active_support/core_ext/hash/conversions'
+rescue
+  puts "active_support gem in not installed, run 'gem install activesupport'"
+end
+begin
+  require 'xmlsimple'
+rescue
+  puts "xmlsimple gem in not installed, run 'gem install xml-simple'"
+end
+begin
+  require 'nokogiri'
+rescue
+  puts "nokogiri gem in not installed, run 'gem install nokogiri'"
+end
+begin
+  require 'libxml'
+rescue
+  puts "libxml gem in not installed, run 'gem install libxml-ruby'"
+end
+
+
+runs = 100
+xml = File.read(File.expand_path('../../test/fixtures/institution.xml', __FILE__))
+puts 'Converting small xml from text to Hash:'
+Benchmark.bm 10 do |x|
+  ActiveSupport::XmlMini.backend = ActiveSupport::XmlMini_REXML
+  x.report 'activesupport(rexml)   ' do
+    runs.times { Hash.from_xml(xml) }
+  end
+
+  ActiveSupport::XmlMini.backend = 'LibXML'
+  x.report 'activesupport(libxml)  ' do
+    runs.times { Hash.from_xml(xml) }
+  end
+
+  ActiveSupport::XmlMini.backend = 'Nokogiri'
+  x.report 'activesupport(nokogiri)' do
+    runs.times { Hash.from_xml(xml) }
+  end
+
+  x.report 'xmlsimple              ' do
+    runs.times { XmlSimple.xml_in(xml) }
+  end
+
+  x.report 'nori                   ' do
+    runs.times { Nori.new(:advanced_typecasting => false).parse(xml) }
+  end
+
+  x.report 'xmlhasher              ' do
+    runs.times { XmlHasher.parse(xml) }
+  end
+end
+
+puts
+runs = 5
+path = File.expand_path('../../test/fixtures/institutions.xml', __FILE__)
+puts 'Converting large xml from file to Hash:'
+Benchmark.bm 5 do |x|
+  ActiveSupport::XmlMini.backend = ActiveSupport::XmlMini_REXML
+  x.report 'activesupport(rexml)   ' do
+    runs.times { Hash.from_xml(File.new(path)) }
+  end
+
+  ActiveSupport::XmlMini.backend = 'LibXML'
+  x.report 'activesupport(libxml)  ' do
+    #runs.times { Hash.from_xml(File.new(path)) } # Segmentation fault
+  end
+
+  ActiveSupport::XmlMini.backend = 'Nokogiri'
+  x.report 'activesupport(nokogiri)' do
+    runs.times { Hash.from_xml(File.new(path)) }
+  end
+
+  x.report 'xmlsimple              ' do
+    runs.times { XmlSimple.xml_in(path) }
+  end
+
+  x.report 'nori                   ' do
+    runs.times { Nori.new(:advanced_typecasting => false).parse(File.new(path).read) } # Nori doesn't support reading from a stream, load the file in memory
+  end
+
+  x.report 'xmlhasher              ' do
+    runs.times { XmlHasher.parse(File.new(path)) }
+  end
+end

data/lib/xmlhasher/configurable.rb

@@ -1,9 +1,9 @@
 module XmlHasher
   module Configurable
 
-    attr_writer :snakecase, :ignore_namespaces
+    attr_writer :snakecase, :ignore_namespaces, :string_keys
 
-    KEYS = [:snakecase, :ignore_namespaces]
+    KEYS = [:snakecase, :ignore_namespaces, :string_keys]
 
     def configure
       yield self

data/lib/xmlhasher/handler.rb

@@ -40,6 +40,7 @@ module XmlHasher
     def transform(name)
       name = name.to_s.split(':').last if @options[:ignore_namespaces]
       name = Util.snakecase(name) if @options[:snakecase]
+      name = name.to_sym unless @options[:string_keys]
       name
     end
 

data/lib/xmlhasher/util.rb

@@ -1,7 +1,7 @@
 module XmlHasher
   module Util
     def self.snakecase(str)
-      str.to_s.gsub(/([A-Z]+)([A-Z][a-z])/, '\1_\2').gsub(/([a-z])([A-Z])/, '\1_\2').downcase.tr('-', '_').to_sym
+      str.to_s.gsub(/([A-Z]+)([A-Z][a-z])/, '\1_\2').gsub(/([a-z])([A-Z])/, '\1_\2').downcase.tr('-', '_')
     end
   end
 end

data/lib/xmlhasher/version.rb

@@ -1,3 +1,3 @@
 module XmlHasher
-  VERSION = '0.0.5'
+  VERSION = '0.0.6'
 end

data/test/test_helper.rb

@@ -9,7 +9,6 @@ SimpleCov.formatter = SimpleCov::Formatter::MultiFormatter[
   Coveralls::SimpleCov::Formatter
 ]
 SimpleCov.start
-Coveralls.wear!
 
 require 'test/unit'
 require 'xmlhasher'

data/test/xmlhasher/parser_test.rb

@@ -226,6 +226,16 @@ class XmlhasherTest < Test::Unit::TestCase
     assert_equal expected, XmlHasher::Parser.new(options).parse(xml)
   end
 
+  def test_snakecasing_string_elements
+    options = {
+        :snakecase => true,
+        :string_keys => true
+    }
+    xml = %[<my-tag><MyTag2>content</MyTag2></my-tag>]
+    expected = {'my_tag' => {'my_tag2' => 'content'}}
+    assert_equal expected, XmlHasher::Parser.new(options).parse(xml)
+  end
+
   def test_empty_tag
     xml = %[<tag></tag>]
     expected = {:tag => nil}

data/test/xmlhasher/xmlhasher_test.rb

@@ -6,18 +6,22 @@ class XmlhasherTest < Test::Unit::TestCase
     configurable = XmlHasher.configure do |config|
       config.snakecase = true
       config.ignore_namespaces = true
+      config.string_keys = true
     end
     assert_equal true, configurable.instance_variable_get(:'@snakecase')
     assert_equal true, configurable.instance_variable_get(:'@ignore_namespaces')
+    assert_equal true, configurable.instance_variable_get(:'@string_keys')
   end
 
   def test_configure_settings_all_off
     configurable = XmlHasher.configure do |config|
       config.snakecase = false
       config.ignore_namespaces = false
+      config.string_keys = false
     end
     assert_equal false, configurable.instance_variable_get(:'@snakecase')
     assert_equal false, configurable.instance_variable_get(:'@ignore_namespaces')
+    assert_equal false, configurable.instance_variable_get(:'@string_keys')
   end
 
   def test_parser

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xmlhasher
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-24 00:00:00.000000000 Z
+date: 2013-09-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ox
@@ -88,6 +88,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- benchmark/benchmark.rb
 - lib/xmlhasher.rb
 - lib/xmlhasher/configurable.rb
 - lib/xmlhasher/handler.rb