Benchmark for lexer lines/second.

This benchmark uses a fixture file that is automatically downloaded.

.gitignore

@@ -5,3 +5,5 @@ Gemfile.lock
 
 lib/oga/xml/lexer.rb
 lib/oga/xml/parser.rb
+
+benchmark/fixtures/big.xml

Rakefile

@@ -8,7 +8,13 @@ GEMSPEC = Gem::Specification.load('oga.gemspec')
 LEXER_OUTPUT  = 'lib/oga/xml/lexer.rb'
 PARSER_OUTPUT = 'lib/oga/xml/parser.rb'
 
-GENERATED_FILES = ['coverage', 'yardoc', LEXER_OUTPUT, PARSER_OUTPUT]
+GENERATED_FILES = [
+  'coverage',
+  'yardoc',
+  LEXER_OUTPUT,
+  PARSER_OUTPUT,
+  'benchmark/fixtures/big.xml'
+]
 
 GENERATED_FILES.each do |file|
   CLEAN << file if File.exist?(file)

benchmark/lexer/bench_line_rate.rb

@@ -0,0 +1,25 @@
+require_relative '../../lib/oga'
+require 'benchmark'
+
+fixture = File.expand_path('../../fixtures/big.xml', __FILE__)
+
+unless File.file?(fixture)
+  system('rake fixtures')
+  puts
+end
+
+xml     = File.read(fixture)
+lines   = xml.lines.count
+lexer   = Oga::XML::Lexer.new(xml)
+timings = Benchmark.bm(20) do |bench|
+  bench.report("#{lines} lines") do
+    lexer.advance { |_| }
+    lexer.reset
+  end
+end
+
+time = timings[0].real
+rate = lines / time
+
+puts
+puts "Lines/second: #{rate.round(3)}"

task/fixtures.rake

@@ -0,0 +1,9 @@
+desc 'Generates large XML fixtures'
+task :fixtures do
+  dest = File.expand_path('../../benchmark/fixtures/big.xml.gz', __FILE__)
+
+  unless File.file?(dest)
+    sh "wget http://downloads.yorickpeterse.com/files/big_xml_file.xml.gz -O #{dest}"
+    sh "gunzip #{dest}"
+  end
+end