ecosystems-bibliothecary 14.3.0 → 15.0.0

data/.rubocop.yml

@@ -1,69 +0,0 @@
----
-
-# Without this, CI might pickup nested dep's rubocop files in vendor/
-inherit_mode:
-  merge:
-    - Exclude
-
-AllCops:
-  NewCops: enable
-  TargetRubyVersion: 4.0
-  Exclude:
-    - spec/fixtures/**/*
-    - vendor/bundle/**/* # This is actually needed for CI, not for biblio itself
-
-
-Metrics/BlockLength:
-  Max: 100
-  Exclude:
-    - config/routes.rb
-    - config/initializers/*
-    - spec/**/*_spec.rb
-    - spec/factories.rb
-    - lib/tasks/*.rake
-
-# metrics and documentation. code is complex as it needs to be,
-# and docs shouldn't be required. add them when needed.
-Metrics/AbcSize:
-  Enabled: false
-Layout/LineLength:
-  Enabled: false
-Metrics/ClassLength:
-  Enabled: false
-Metrics/MethodLength:
-  Enabled: false
-Metrics/ModuleLength:
-  Enabled: false
-Metrics/CyclomaticComplexity:
-  Enabled: false
-Metrics/PerceivedComplexity:
-  Enabled: false
-Metrics/ParameterLists:
-  Max: 7
-  CountKeywordArgs: false
-Style/Documentation:
-  Enabled: false
-
-# differences from standard ruby style guide.
-Style/RegexpLiteral:
-  Enabled: false
-Style/StringLiterals:
-  EnforcedStyle: double_quotes
-Style/TrailingCommaInArrayLiteral:
-  EnforcedStyleForMultiline: comma
-Style/TrailingCommaInHashLiteral:
-  EnforcedStyleForMultiline: comma
-Layout/FirstArrayElementIndentation:
-  Enabled: false
-Layout/MultilineMethodCallIndentation:
-  EnforcedStyle: indented
-Style/NumericPredicate:
-  Enabled: false
-Style/FormatStringToken:
-  Enabled: false
-Style/MultilineBlockChain:
-  Enabled: false
-Style/IfUnlessModifier:
-  Enabled: false
-Layout/BlockAlignment:
-  EnforcedStyleAlignWith: start_of_block

data/.ruby-version

@@ -1 +0,0 @@
-4.0.0

data/.tidelift

@@ -1 +0,0 @@
-TIDELIFT_EXCLUDED_MANIFESTS=spec/fixtures

data/CODE_OF_CONDUCT.md

@@ -1,74 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to making participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, gender identity and expression, level of experience,
-nationality, personal appearance, race, religion, or sexual identity and
-orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies both within project spaces and in public spaces
-when an individual is representing the project or its community. Examples of
-representing a project or community include using an official project e-mail
-address, posting via an official social media account, or acting as an appointed
-representative at an online or offline event. Representation of a project may be
-further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at andrew@libraries.io. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at [http://contributor-covenant.org/version/1/4][version]
-
-[homepage]: http://contributor-covenant.org
-[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -1,35 +0,0 @@
-# frozen_string_literal: true
-
-source "https://rubygems.org"
-
-# Temporarily pegging to HEAD until 0.2.1 is released: https://github.com/piotrmurach/strings-ansi/pull/2
-gem "strings-ansi", ref: "35d0c9430cf0a8022dc12bdab005bce296cb9f00", github: "piotrmurach/strings-ansi"
-
-# Ruby 3.4+ no longer includes these as default gems
-gem "base64"
-gem "benchmark"
-gem "bigdecimal"
-gem "csv"
-gem "logger"
-gem "ostruct"
-
-# Specify your gem's dependencies in bibliothecary.gemspec
-gemspec
-
-group :development do
-  gem "pry"
-end
-
-group :development, :test do
-  gem "rake", "~> 13.0"
-  gem "rubocop", "~> 1.71"
-  gem "rubocop-rails"
-  gem "rubocop-rake" # This is needed by packageurl-ruby, until it reclassifies it as a dev dependency.
-end
-
-group :test do
-  gem "rspec", "~> 3.0"
-  gem "simplecov"
-  gem "super_diff", "~> 0.18.0"
-  gem "webmock"
-end

data/Rakefile

@@ -1,18 +0,0 @@
-# frozen_string_literal: true
-
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
-
-RSpec::Core::RakeTask.new(:spec)
-
-task default: :spec
-
-desc "Run the linter"
-task :lint do
-  sh "bundle exec rubocop -P"
-end
-
-desc "Run the linter with autofix"
-task :fix do
-  sh "bundle exec rubocop -A"
-end

data/bin/benchmark

@@ -1,386 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-require "bundler/setup"
-require "bibliothecary"
-require "benchmark"
-require "optparse"
-
-class InfrastructureBenchmark
-  FIXTURES_DIR = File.expand_path("../spec/fixtures", __dir__)
-
-  def initialize(iterations: 100)
-    @iterations = iterations
-  end
-
-  def run
-    puts "Infrastructure Benchmark"
-    puts "=" * 60
-    puts "Iterations: #{@iterations}"
-    puts
-
-    # Prepare test data - mix of different file types
-    test_files = prepare_test_files
-    puts "Test files: #{test_files.length}"
-    puts
-
-    benchmark_package_managers
-    benchmark_matching_overhead
-    benchmark_load_file_info_list_from_contents(test_files)
-    benchmark_analyse_file(test_files)
-  end
-
-  def prepare_test_files
-    files = []
-    # Get a representative sample of fixtures
-    %w[package.json Gemfile.lock Cargo.toml pom.xml requirements.txt go.mod].each do |name|
-      path = Dir.glob("#{FIXTURES_DIR}/**/#{name}").first
-      next unless path
-
-      files << { file_path: path.sub("#{FIXTURES_DIR}/", ""), contents: File.read(path) }
-    end
-    files
-  end
-
-  def benchmark_package_managers
-    puts "package_managers method:"
-    puts "-" * 40
-
-    runner = Bibliothecary.runner
-
-    # Warm up
-    5.times { runner.package_managers }
-
-    time = Benchmark.measure do
-      @iterations.times { runner.package_managers }
-    end
-
-    printf "  %d calls: %.3f ms total, %.4f ms/call\n",
-           @iterations, time.real * 1000, (time.real / @iterations) * 1000
-    puts
-  end
-
-  def benchmark_load_file_info_list_from_contents(test_files)
-    puts "load_file_info_list_from_contents:"
-    puts "-" * 40
-
-    runner = Bibliothecary.runner
-
-    # Warm up
-    5.times { runner.load_file_info_list_from_contents(test_files) }
-
-    time = Benchmark.measure do
-      @iterations.times { runner.load_file_info_list_from_contents(test_files) }
-    end
-
-    total_files = test_files.length * @iterations
-    printf "  %d calls (%d files each): %.3f ms total\n",
-           @iterations, test_files.length, time.real * 1000
-    printf "  %.4f ms/call, %.4f ms/file\n",
-           (time.real / @iterations) * 1000,
-           (time.real / total_files) * 1000
-    puts
-  end
-
-  def benchmark_analyse_file(test_files)
-    puts "analyse_file (full pipeline):"
-    puts "-" * 40
-
-    runner = Bibliothecary.runner
-
-    test_files.each do |file|
-      # Warm up
-      3.times { runner.analyse_file(file[:file_path], file[:contents]) }
-
-      time = Benchmark.measure do
-        @iterations.times { runner.analyse_file(file[:file_path], file[:contents]) }
-      end
-
-      printf "  %-30s %.4f ms/call\n",
-             File.basename(file[:file_path]),
-             (time.real / @iterations) * 1000
-    end
-    puts
-  end
-
-  def benchmark_matching_overhead
-    puts "Matching overhead breakdown:"
-    puts "-" * 40
-
-    runner = Bibliothecary.runner
-    pms = runner.package_managers
-
-    # Test with a simple package.json
-    test_file = { file_path: "package.json", contents: '{"dependencies":{}}' }
-    info = Bibliothecary::FileInfo.new(nil, test_file[:file_path], test_file[:contents])
-
-    # Benchmark match_info? across all parsers
-    time = Benchmark.measure do
-      @iterations.times do
-        pms.each { |pm| pm.match_info?(info) }
-      end
-    end
-    printf "  match_info? x %d parsers: %.4f ms/file\n",
-           pms.length, (time.real / @iterations) * 1000
-
-    # Benchmark just the npm parser's match_info?
-    npm = pms.find { |pm| pm.platform_name == "npm" }
-    time = Benchmark.measure do
-      @iterations.times { npm.match_info?(info) }
-    end
-    printf "  npm.match_info? alone:    %.4f ms/call\n",
-           (time.real / @iterations) * 1000
-
-    # Benchmark first_matching_mapping_details (called multiple times per file)
-    time = Benchmark.measure do
-      @iterations.times do
-        npm.send(:first_matching_mapping_details, info)
-      end
-    end
-    printf "  first_matching_mapping_details: %.4f ms/call\n",
-           (time.real / @iterations) * 1000
-
-    puts
-  end
-end
-
-class ParserBenchmark
-  FIXTURES_DIR = File.expand_path("../spec/fixtures", __dir__)
-
-  # Parser methods that require remote services
-  REMOTE_PARSERS = {
-    "swiftpm" => [:parse_package_swift],
-    "hackage" => [:parse_cabal],
-    "hex" => [:parse_mix, :parse_mix_lock],
-    "carthage" => [:parse_cartfile, :parse_cartfile_private, :parse_cartfile_resolved],
-    "clojars" => [:parse_manifest],
-  }.freeze
-
-  # Multi-parser methods shared across many package managers
-  MULTI_PARSER_METHODS = %i[
-    parse_cyclonedx_json
-    parse_cyclonedx_xml
-    parse_spdx_json
-    parse_spdx_tag_value
-    parse_dependencies_csv
-  ].freeze
-
-  def initialize(options = {})
-    @iterations = options.fetch(:iterations, 100)
-    @parser_filter = options[:parser]
-    @verbose = options[:verbose]
-    @native_only = options[:native_only]
-    @results = {}
-  end
-
-  def run
-    puts "Bibliothecary Parser Benchmark"
-    puts "=" * 60
-    puts "Iterations per file: #{@iterations}"
-    puts "Fixtures directory: #{FIXTURES_DIR}"
-    puts
-
-    parsers = filtered_parsers
-    puts "Running benchmarks for #{parsers.length} parser(s)..."
-    puts
-
-    parsers.each do |parser|
-      benchmark_parser(parser)
-    end
-
-    print_summary
-  end
-
-  def filtered_parsers
-    all_parsers = Bibliothecary.package_managers
-    return all_parsers unless @parser_filter
-
-    matching = all_parsers.select do |pm|
-      pm.platform_name.downcase.include?(@parser_filter.downcase)
-    end
-
-    if matching.empty?
-      puts "No parser matching '#{@parser_filter}' found."
-      puts "Available parsers: #{all_parsers.map(&:platform_name).join(', ')}"
-      exit 1
-    end
-
-    matching
-  end
-
-  def benchmark_parser(parser)
-    platform = parser.platform_name
-    mapping = parser.mapping
-    fixtures = find_fixtures_for_parser(mapping, platform)
-
-    if fixtures.empty?
-      puts "#{platform}: no matching fixtures found"
-      puts if @verbose
-      return
-    end
-
-    puts "#{platform} (#{fixtures.length} files)"
-    puts "-" * 40
-
-    parser_total = 0
-    file_results = []
-
-    fixtures.each do |fixture_path, mapping_entry|
-      contents = File.read(fixture_path)
-      filename = File.basename(fixture_path)
-      relative = fixture_path.sub("#{FIXTURES_DIR}/", "")
-
-      begin
-        time = Benchmark.measure do
-          @iterations.times do
-            parser.send(mapping_entry[:parser], contents, options: { filename: filename })
-          end
-        end
-
-        avg_ms = (time.real / @iterations) * 1000
-        parser_total += time.real
-
-        file_results << {
-          file: relative,
-          total: time.real,
-          avg_ms: avg_ms,
-          kind: mapping_entry[:kind],
-        }
-
-        if @verbose
-          printf "  %-40s %8.3f ms/call (%s)\n", relative, avg_ms, mapping_entry[:kind]
-        end
-      rescue Bibliothecary::RemoteParsingError => e
-        puts "  #{relative}: skipped (remote parser unavailable)"
-      rescue => e
-        puts "  #{relative}: error - #{e.class}: #{e.message}"
-      end
-    end
-
-    unless @verbose
-      file_results.sort_by { |r| -r[:avg_ms] }.first(3).each do |r|
-        printf "  %-40s %8.3f ms/call\n", r[:file], r[:avg_ms]
-      end
-      puts "  ..." if file_results.length > 3
-    end
-
-    avg_total = (parser_total / fixtures.length / @iterations) * 1000
-    printf "  Total: %.3f ms avg per file\n", avg_total
-    puts
-
-    @results[platform] = {
-      files: fixtures.length,
-      total_time: parser_total,
-      avg_per_file: avg_total,
-      file_results: file_results,
-    }
-  end
-
-  def find_fixtures_for_parser(mapping, platform_name)
-    fixtures = []
-    remote_methods = REMOTE_PARSERS[platform_name] || []
-
-    all_fixtures.each do |fixture_path|
-      filename = File.basename(fixture_path)
-      relative_path = fixture_path.sub("#{FIXTURES_DIR}/", "")
-
-      mapping.each do |matcher, entry|
-        next unless entry[:parser]
-        next if remote_methods.include?(entry[:parser])
-        next if @native_only && MULTI_PARSER_METHODS.include?(entry[:parser])
-
-        if matcher_matches?(matcher, filename, fixture_path)
-          fixtures << [fixture_path, entry]
-          break
-        end
-      end
-    end
-
-    fixtures
-  end
-
-  def matcher_matches?(matcher, filename, full_path)
-    relative_path = full_path.sub("#{FIXTURES_DIR}/", "")
-
-    case matcher
-    when Regexp
-      filename.match?(matcher)
-    when String
-      filename == matcher
-    when Proc
-      matcher.call(relative_path)
-    else
-      false
-    end
-  end
-
-  def all_fixtures
-    @all_fixtures ||= Dir.glob("#{FIXTURES_DIR}/**/*")
-      .select { |f| File.file?(f) }
-      .reject { |f| f.include?("/broken/") }
-  end
-
-  def print_summary
-    return if @results.empty?
-
-    puts "=" * 60
-    puts "Summary (sorted by avg time per file)"
-    puts "=" * 60
-
-    sorted = @results.sort_by { |_, v| -v[:avg_per_file] }
-
-    printf "%-20s %10s %12s\n", "Parser", "Files", "Avg ms/file"
-    printf "%-20s %10s %12s\n", "-" * 20, "-" * 10, "-" * 12
-
-    sorted.each do |platform, data|
-      printf "%-20s %10d %12.3f\n", platform, data[:files], data[:avg_per_file]
-    end
-
-    puts
-    total_files = @results.values.sum { |v| v[:files] }
-    total_time = @results.values.sum { |v| v[:total_time] }
-    puts "Total: #{total_files} files, #{(total_time * 1000).round(1)} ms total time"
-  end
-end
-
-options = {
-  iterations: 100,
-  verbose: false,
-  mode: :parsers,
-}
-
-OptionParser.new do |opts|
-  opts.banner = "Usage: bin/benchmark [options]"
-
-  opts.on("-p", "--parser NAME", "Only benchmark parsers matching NAME") do |p|
-    options[:parser] = p
-  end
-
-  opts.on("-n", "--iterations N", Integer, "Number of iterations per file (default: 100)") do |n|
-    options[:iterations] = n
-  end
-
-  opts.on("-v", "--verbose", "Show all files, not just slowest") do
-    options[:verbose] = true
-  end
-
-  opts.on("--native-only", "Exclude shared multi-parsers (CycloneDX, SPDX, CSV)") do
-    options[:native_only] = true
-  end
-
-  opts.on("--infra", "Benchmark infrastructure (load_file_info_list, etc)") do
-    options[:mode] = :infra
-  end
-
-  opts.on("-h", "--help", "Show this help") do
-    puts opts
-    exit
-  end
-end.parse!
-
-case options[:mode]
-when :infra
-  InfrastructureBenchmark.new(iterations: options[:iterations]).run
-else
-  ParserBenchmark.new(options).run
-end

data/bin/console

@@ -1,15 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-require "bundler/setup"
-require "bibliothecary"
-
-# You can add fixtures and/or initialization code here to make experimenting
-# with your gem easier. You can also use a different console, if you like.
-
-# (If you use this, don't forget to add pry to your Gemfile!)
-# require "pry"
-# Pry.start
-
-require "pry"
-Pry.start

data/bin/setup

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install
-
-# Do any other automated setup that you need to do here

data/lib/bibliothecary/multi_parsers/bundler_like_manifest.rb

@@ -1,26 +0,0 @@
-# frozen_string_literal: true
-
-module Bibliothecary
-  module MultiParsers
-    module BundlerLikeManifest
-      # this takes parsed Bundler and Bundler-like (CocoaPods)
-      # manifests and turns them into a list of dependencies.
-      def parse_ruby_manifest(manifest, platform, source = nil)
-        manifest.dependencies.inject([]) do |deps, dep|
-          deps.push(Dependency.new(
-                      platform: platform,
-                      name: dep.name,
-                      requirement: dep
-                        .requirement
-                        .requirements
-                        .sort_by(&:last)
-                        .map { |op, version| "#{op} #{version}" }
-                        .join(", "),
-                      type: dep.type.to_s,
-                      source: source
-                    ))
-        end.uniq
-      end
-    end
-  end
-end