XML parsing benchmark

benchmark.exs

# Dependencies: {:saxy, "~> 1.2"}, {:sax_map, "~> 0.2"}, {:benchee, "~> 1.0"}

#
# Samples
#

simple = """
<?xml version="1.0"?>
<?xml-stylesheet href="catalog.xsl" type="text/xsl"?>
<catalog>
  <product description="Cardigan Sweater" product_image="cardigan.jpg">
    <catalog_item gender="Men's">
      <item_number>QWZ5671</item_number>
      <price>39.95</price>
      <!--Yet another comment-->
      <size description="Medium">
        <color_swatch image="red_cardigan.jpg">Red</color_swatch>
        <color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
      </size>
      <size description="Large">
        <color_swatch image="red_cardigan.jpg">Red</color_swatch>
        <color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
      </size>
    </catalog_item>
    <catalog_item gender="Women's">
      <item_number>RRX9856</item_number>
      <price>42.50</price>
      <?xml-stylesheet href="catalog.xsl" type="text/xsl"?>
      <size description="Small">
        <?xml-stylesheet href="catalog.xsl" type="text/xsl"?>
        <color_swatch image="red_cardigan.jpg">Red</color_swatch>
        <color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
        <color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
      </size>
      <size description="Medium">
        <color_swatch image="red_cardigan.jpg">Red</color_swatch>
        <color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
        <color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
        <color_swatch image="black_cardigan.jpg">Black</color_swatch>
      </size>
      <size description="Large">
        <color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
        <color_swatch image="black_cardigan.jpg">Black</color_swatch>
      </size>
      <size description="Extra Large">
        <color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
        <color_swatch image="black_cardigan.jpg">Black</color_swatch>
      </size>
    </catalog_item>
  </product>
</catalog>
"""

%{body: feed} = HTTPoison.get!("https://www.gamespot.com/feeds/mashup/")

%{body: complex} = HTTPoison.get!("http://aiweb.cs.washington.edu/research/projects/xmltk/xmldata/data/treebank/treebank_e.xml")

#
# Saxy.SimpleForm based implementation
#

defmodule Parser do

  def parse([{tag, attrs, children} | tail]) do
      %{}
      |> Map.put(tag, parse(children))
      |> Map.merge(parse(tail), fn 
        _k, v1, v2 when is_list(v2) -> [v1 | v2] 
        _k, v1, v2 -> [v1, v2] 
      end)      
  end

  def parse(["\n" <> _ | tail]), do: parse(tail)

  def parse([head | []]), do: head

  def parse([]), do: %{}

end

#
# Tests
#

Benchee.run(
  %{
    "SAXMap.from_string" => fn input -> 
      SAXMap.from_string(input)
    end,    
    "Parser.parse" => fn input -> 
      {:ok, result} = Saxy.SimpleForm.parse_string(input)
      Parser.parse([result]) 
    end   
  },
  time: 10,
  memory_time: 2,
  inputs: %{
    "SIMPLE XML" => simple,
    "FEED XML" => feed
  }
)

#
# Tests with complex files
#

# SAXMap.from_string can't process large files so I removed it from the tests.
# In my current hardware I've awaited over 15 minutes for tests to be completed without response.

Benchee.run(
  %{
    "Parser.parse" => fn input -> 
      {:ok, result} = Saxy.SimpleForm.parse_string(input)
      Parser.parse([result]) 
    end   
  },
  time: 10,
  memory_time: 2,
  inputs: %{
    "COMPLEX" => complex
  }
)