rdf-benchmark 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 11b9b218709e7c01b2d0c924c058b8d934e3ac7b
+  data.tar.gz: bb4859eb9b2075ccd9178d6ab7ffd6439121b3fb
+SHA512:
+  metadata.gz: 5d5c09fd5fd549d1d3f86f0bc933644b0afa455df95c3bf168cede0d6157d914e7a0bc41206aba5b3f752d1d7c561202be3666c52eade841d67df1b55312de50
+  data.tar.gz: c76b25a9f4137084d600688258ac8fc73757b1b7819997b69b89b4c2f61a1068bbb02c9347eb4dffa4eac4fc9b76ab995f6e78916ab7c8aac1ff951c48c67a93

data/AUTHORS

@@ -0,0 +1 @@
+* Tom Johnson <n0reply@uw.edu>

data/README.md

@@ -0,0 +1,31 @@
+RDF::Benchmark
+==============
+
+[![Build Status](https://travis-ci.org/ruby-rdf/rdf.png?branch=master)](http://travis-ci.org/ruby-rdf/rdf-benchmark)
+
+A benchmark framework for [RDF.rb](http://ruby-rdf.github.com/rdf).
+
+## Contributing
+
+This repository uses [Git Flow](https://github.com/nvie/gitflow) to mange development and release activity. All submissions _must_ be on a feature branch based on the _develop_ branch to ease staging and integration.
+
+* Do your best to adhere to the existing coding conventions and idioms.
+* Don't use hard tabs, and don't leave trailing whitespace on any line.
+  Before committing, run `git diff --check` to make sure of this.
+* Do document every method you add using [YARD][] annotations. Read the
+  [tutorial][YARD-GS] or just look at the existing code for examples.
+* Don't touch the `.gemspec` or `VERSION` files. If you need to change them,
+  do so on your private branch only.
+* Do feel free to add yourself to the `CREDITS` file and the
+  corresponding list in the the `README`. Alphabetical order applies.
+* Don't touch the `AUTHORS` file. If your contributions are significant
+  enough, be assured we will eventually add you in there.
+* Do note that in order for us to merge any non-trivial changes (as a rule
+  of thumb, additions larger than about 15 lines of code), we need an
+  explicit [public domain dedication][PDD] on record from you.
+
+## License
+
+This is free and unencumbered public domain software. For more information,
+see <http://unlicense.org/> or the accompanying {file:UNLICENSE} file.
+

data/UNLICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>

data/VERSION

@@ -0,0 +1 @@
+0.0.2

data/lib/rdf/benchmark/berlin_generator.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+require 'rdf/ntriples'
+
+module RDF::Benchmark
+  ##
+  # @see http://wifo5-03.informatik.uni-mannheim.de/bizer/berlinsparqlbenchmark/spec/BenchmarkRules/index.html#datagenerator
+  class BerlinGenerator
+    DEFAULT_FILENAME = 'dataset'.freeze
+    DEFAULT_FACTOR   = 2_000.freeze
+    DEFAULT_FORMAT   = 'nt'.freeze
+    DEFAULT_PATH     = './bsbmtools'.freeze
+
+    # @!attribute [rw] filename
+    # @!attribute [rw] product_factor
+    # @!attribute [rw] format
+    # @!attribute [rw] tool_path
+    attr_accessor :filename, :product_factor, :format, :tool_path
+    
+    ##
+    # @param filename [String]  (default: 'dataset')
+    # @param products [Integer] (default: 2000)
+    # @param format   [String]  (default: 'nt')
+    def initialize(filename:       DEFAULT_FILENAME, 
+                   product_factor: DEFAULT_FACTOR, 
+                   format:         DEFAULT_FORMAT, 
+                   tool_path:      DEFAULT_PATH)
+      self.filename       = filename
+      self.product_factor = product_factor
+      self.format         = format
+      self.tool_path      = tool_path
+    end
+    
+    ##
+    # @return [RDF::Reader] a stream of the requested data
+    def data(&block)
+      filepath = Pathname.new(tool_path) + "#{filename}.#{format}"
+      generate_data! unless File.exists?(filepath)
+      
+      RDF::Reader.open(filepath, &block)
+    end
+
+    ##
+    # Generates the data for this instance, writing it to disk.
+    #
+    # @return [Boolean] true if successful
+    #
+    # @note writes the output of the Berlin data generator to stdout
+    def generate_data!
+      start_dir = Dir.pwd
+      
+      Dir.chdir tool_path
+      system "./generate -pc #{product_factor} -fn #{filename} -fc"
+    ensure
+      Dir.chdir start_dir
+    end
+  end
+end

data/lib/rdf/benchmark/repository.rb

@@ -0,0 +1,58 @@
+# frozen_string_literal: true
+module RDF::Benchmark
+  class Repository
+    # @!attribute [rw] repository
+    #   @return [RDF::Repository] the repository to benchmark
+    attr_accessor :repository
+    
+    ##
+    # @param generator  [#data]
+    # @param repository [RDF::Repository] the repository to benchmark
+    def initialize(generator: , repository:)
+      @generator  = generator
+      @repository = repository
+    end
+
+    ##
+    # @return [RDF::Enumerator]
+    def statements
+      @generator.data.each_statement
+    end
+
+    ##
+    # @param name  [#to_s]
+    # @param count [Integer] number of statements to prime for insert
+    #
+    # @return [Benchmark::IPS::Report]
+    def insert!(name: 'insert', count: 100_000)
+      inserts = statements.lazy.take(count)
+      
+      report = RDF::Benchmark.benchmark_ips!(name: name) do
+        repository.insert(inserts.next)
+      end
+      
+      return report
+    ensure 
+      repository.clear
+    end
+
+    ##
+    # @param name  [#to_s]   the name to give the benchmark report
+    # @param count [Integer] number of statements to prime for delete
+    #
+    # @return [Benchmark::IPS::Report]
+    def delete!(name: 'delete', count: 100_000)
+      deletes = statements.lazy.take(count)
+
+      deletes.each { |st| repository.insert(st) }
+
+      report = RDF::Benchmark.benchmark_ips!(name: name) do
+        repository.delete(deletes.next)
+      end
+      
+      return report
+    ensure 
+      repository.clear
+    end
+  end
+end

data/lib/rdf/benchmark.rb

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+require 'rdf'
+require 'benchmark/ips'
+
+module RDF
+  module Benchmark
+    ##
+    # Benchmarks the given block, measuring iterations per second.
+    #
+    # @param name   [String]
+    # @param time   [Integer]
+    # @param warmup [Integer]
+    # @yield runs the block repeatedly as a Benchmark#ips report
+    #
+    # @return [Benchmark::IPS::Report]
+    # @see Benchmark#ips
+    def self.benchmark_ips!(name: , time: 5, warmup: 2, &block)
+      ::Benchmark.ips do |bm|
+        bm.config(:time => time, :warmup => warmup)
+        bm.report(name, &block)
+      end
+    end
+
+    ##
+    # Benchmarks a single run of the given block (with warmup).
+    #
+    # @param name [String]
+    # @yield runs the block as a Benchmark#bmbm report
+    #
+    # @return [Benchmark::Report]
+    # @see Benchmark#bmbm
+    def self.benchmark!(name:, &block)
+      ::Benchmark.bmbm do |bm|
+        bm.report(name, &block)
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,121 @@
+--- !ruby/object:Gem::Specification
+name: rdf-benchmark
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Tom Johnson
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-07-09 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rdf
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: benchmark-ips
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.8'
+description: Dataset Generation & Benchmarks for RDF.rb
+email: public-rdf-ruby@w3.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- AUTHORS
+- README.md
+- UNLICENSE
+- VERSION
+- lib/rdf/benchmark.rb
+- lib/rdf/benchmark/berlin_generator.rb
+- lib/rdf/benchmark/repository.rb
+homepage: http://ruby-rdf.github.com/rdf-benchmark
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Dataset Generation & Benchmarks for RDF.rb
+test_files: []
+has_rdoc: false