From 31334b5caeba73765f1db590ebcf881b44a6f89c Mon Sep 17 00:00:00 2001
From: NAITOH Jun <naitoh@gmail.com>
Date: Fri, 5 Jan 2024 09:51:47 +0900
Subject: [PATCH] Add parse benchmark

---
 .github/workflows/benchmark.yml | 29 ++++++++++++++++++
 Rakefile                        | 39 ++++++++++++++++++++++++
 benchmark/parse.yaml            | 53 +++++++++++++++++++++++++++++++++
 rexml.gemspec                   |  1 +
 4 files changed, 122 insertions(+)
 create mode 100644 .github/workflows/benchmark.yml
 create mode 100644 benchmark/parse.yaml

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
new file mode 100644
index 00000000..52349b44
--- /dev/null
+++ b/.github/workflows/benchmark.yml
@@ -0,0 +1,29 @@
+name: Benchmark
+
+on:
+  - push
+  - pull_request
+
+jobs:
+  benchmark:
+    name: "Benchmark: Ruby ${{ matrix.ruby-version }}: ${{ matrix.runs-on }}"
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby-version:
+          - '3.3'
+        runs-on:
+          - ubuntu-latest
+    runs-on: ${{ matrix.runs-on }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby-version }}
+      - name: Install dependencies
+        run: |
+          bundle install
+          gem install rexml -v 3.2.6
+      - name: Benchmark
+        run: |
+          rake benchmark
diff --git a/Rakefile b/Rakefile
index 7143e754..ffdbccdb 100644
--- a/Rakefile
+++ b/Rakefile
@@ -28,3 +28,42 @@ RDoc::Task.new do |rdoc|
 end
 
 load "#{__dir__}/tasks/tocs.rake"
+
+benchmark_tasks = []
+namespace :benchmark do
+  Dir.glob("benchmark/*.yaml").sort.each do |yaml|
+    name = File.basename(yaml, ".*")
+    env = {
+      "RUBYLIB" => nil,
+      "BUNDLER_ORIG_RUBYLIB" => nil,
+    }
+    command_line = [
+      RbConfig.ruby, "-v", "-S", "benchmark-driver", File.expand_path(yaml),
+    ]
+
+    desc "Run #{name} benchmark"
+    task name do
+      puts("```")
+      sh(env, *command_line)
+      puts("```")
+    end
+    benchmark_tasks << "benchmark:#{name}"
+
+    case name
+    when /\Aparse/, "shift"
+      namespace name do
+        desc "Run #{name} benchmark: small"
+        task :small do
+          puts("```")
+          sh(env.merge("N_LINES" => "1000", "N_ATTRIBUTES" => "2"),
+             *command_line)
+          puts("```")
+        end
+        benchmark_tasks << "benchmark:#{name}:small"
+      end
+    end
+  end
+end
+
+desc "Run all benchmarks"
+task :benchmark => benchmark_tasks
diff --git a/benchmark/parse.yaml b/benchmark/parse.yaml
new file mode 100644
index 00000000..48c4fdcc
--- /dev/null
+++ b/benchmark/parse.yaml
@@ -0,0 +1,53 @@
+loop_count: 100
+contexts:
+  - gems:
+      rexml: 3.2.6
+    require: false
+    prelude: require 'rexml'
+  - name: 3.2.6(YJIT)
+    gems:
+      rexml: 3.2.6
+    require: false
+    prelude: |
+      require 'rexml'
+      RubyVM::YJIT.enable
+  - name: master
+    prelude: |
+      $LOAD_PATH.unshift(File.expand_path("lib"))
+      require 'rexml'
+  - name: master(YJIT)
+    prelude: |
+      $LOAD_PATH.unshift(File.expand_path("lib"))
+      require 'rexml'
+      RubyVM::YJIT.enable
+
+prelude: |
+  require 'rexml/document'
+  require 'rexml/parsers/sax2parser'
+  require 'rexml/parsers/pullparser'
+  require 'rexml/parsers/streamparser'
+  require 'rexml/streamlistener'
+
+  n_lines = Integer(ENV.fetch("N_LINES", "10000"), 10)
+  n_attributes = Integer(ENV.fetch("N_ATTRIBUTES", "10"), 10)
+
+  def build_xml(n_lines, n_attributes)
+    xml = '<?xml version="1.0"?><root>'
+    n_lines.times do |i|
+      xml << '<child '
+      n_attributes.times {|j| xml << "id#{j}=\"#{i}\" " }
+      xml << '/>'
+    end
+    xml << '</root>'
+  end
+  xml = build_xml(n_lines, n_attributes)
+
+  class Listener
+    include REXML::StreamListener
+  end
+
+benchmark:
+  'dom'        : REXML::Document.new(xml).elements.each("root/child") {|_|}
+  'sax'        : REXML::Parsers::SAX2Parser.new(xml).parse
+  'pull'       : p = REXML::Parsers::PullParser.new(xml); while p.has_next?; res = p.pull; end
+  'stream'     : REXML::Parsers::StreamParser.new(xml, Listener.new).parse
diff --git a/rexml.gemspec b/rexml.gemspec
index ceb77047..9a54609c 100644
--- a/rexml.gemspec
+++ b/rexml.gemspec
@@ -57,5 +57,6 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler"
   spec.add_development_dependency "rake"
+  spec.add_development_dependency "benchmark_driver"
   spec.add_development_dependency "test-unit"
 end