optic14n 2.0.1 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: faf613071e1b6009e6a97058aa8ccc17e537b88e
-  data.tar.gz: 87274484cb0115cae18914eb1ee8edeb070b1ca5
+SHA256:
+  metadata.gz: 7479db1ec2e377b50be0f54167958b1d7f6a49d45d662b26c19c840a61dfbb3f
+  data.tar.gz: ec11d6132aeec024bc68bcf85876645ddd2a4aff726b52468f2e367a119587b5
 SHA512:
-  metadata.gz: cde69422152d68439c35298f616876c82d6ed32ec8ae4efb92926326873a8c639f7fed718a7782c2a60b62b2e38f5b7b5585314988fb4863730b41bd41490b6b
-  data.tar.gz: aa2d3e22503736c3e0c86ebc243ddff0d85adf00d381a40fc7639fb9bb9a56dec0e43235c9cec2297479ae4e1d28ee01811ba6228e8ce6766d6e8c7e78d4e357
+  metadata.gz: a334df2fd339fbb0ce41554ae781f0fe24ff303116551e69a341ce4279f6239461d57565dcf285c7731328ddf597ae0536214e334251074f08ad02729543db49
+  data.tar.gz: 57c8eb1545b3d422c1ac53599928d41b0536ea445d3c7fc1567caebe58c7bc315266454124c946aa119e498c604a7342fa7ea7b97ecb4e8daeb0ba0660073889

data/.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: bundler
+    directory: /
+    schedule:
+      interval: daily
+  - package-ecosystem: "github-actions"
+    directory: /
+    schedule:
+      interval: daily

data/.github/pull_request_template.md

@@ -0,0 +1 @@
+This repo is owned by the publishing platform team. Please let us know in #govuk-publishing-platform when you raise any PRs.

data/.github/workflows/autorelease.yml

@@ -0,0 +1,10 @@
+on:
+  workflow_dispatch: {}
+  schedule:
+    - cron: '30 10 * * 1-5' # 10:30am UTC, Mon-Fri.
+
+jobs:
+  autorelease:
+    uses: alphagov/govuk-infrastructure/.github/workflows/autorelease-rubygem.yml@main
+    secrets:
+      GH_TOKEN: ${{ secrets.GOVUK_CI_GITHUB_API_TOKEN }}

data/.github/workflows/ci.yml

@@ -0,0 +1,45 @@
+on: [push, pull_request]
+
+jobs:
+  codeql-sast:
+    name: CodeQL SAST scan
+    uses: alphagov/govuk-infrastructure/.github/workflows/codeql-analysis.yml@main
+    permissions:
+      security-events: write
+
+  dependency-review:
+    name: Dependency Review scan
+    uses: alphagov/govuk-infrastructure/.github/workflows/dependency-review.yml@main
+  
+  # This matrix job runs the test suite against multiple Ruby versions
+  test_matrix:
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: [3.1, 3.2, 3.3]
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler-cache: true
+      - run: bundle exec rake
+
+  # Branch protection rules cannot directly depend on status checks from matrix jobs.
+  # So instead we define `test` as a dummy job which only runs after the preceding `test_matrix` checks have passed.
+  # Solution inspired by: https://github.community/t/status-check-for-a-matrix-jobs/127354/3
+  test:
+    needs: test_matrix
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "All matrix tests have passed 🚀"
+
+  publish:
+    needs: test
+    if: ${{ github.ref == 'refs/heads/main' }}
+    permissions:
+      contents: write
+    uses: alphagov/govuk-infrastructure/.github/workflows/publish-rubygem.yml@main
+    secrets:
+      GEM_HOST_API_KEY: ${{ secrets.ALPHAGOV_RUBYGEMS_API_KEY }}

data/.govuk_dependabot_merger.yml

@@ -0,0 +1,7 @@
+api_version: 2
+defaults:
+  allowed_semver_bumps:
+    - patch
+    - minor
+  auto_merge: true
+  update_external_dependencies: true

data/.rubocop.yml

@@ -0,0 +1,3 @@
+inherit_gem:
+  rubocop-govuk:
+    - config/default.yml

data/.ruby-version

@@ -1,2 +1 @@
-2.3.0
-
+3.1.4

data/CHANGELOG.md

@@ -0,0 +1,17 @@
+# Changelog
+
+- We use the [GOV.UK versioning guidelines](https://docs.publishing.service.gov.uk/manual/publishing-a-ruby-gem.html#versioning).
+- Mark breaking changes with `BREAKING:`. Be sure to include instructions on how applications should be upgraded.
+- Don't include changes that are purely internal. The CHANGELOG should be a
+  useful summary for people upgrading their application, not a replication
+  of the commit log.
+
+## Unreleased
+
+## 3.0.0
+
+[Full diff](https://github.com/alphagov/optic14n/compare/v2.1.0...v3.0.0)
+
+- BREAKING: Bump minimum Ruby version from 2.6.5 to 3.1.4
+- Add support for Ruby 3.3
+- BREAKING: Bump minimum rubocop-govuk version from 1.0.0 to 5.0.2

data/Gemfile

@@ -1,8 +1,4 @@
-source 'https://rubygems.org'
+source "https://rubygems.org"
 
 # Specify your gem's dependencies in optic14n.gemspec
 gemspec
-
-group :test do
-  gem 'rspec', '2.14.1'
-end

data/README.md

@@ -58,3 +58,7 @@ smaller than it would otherwise be. We do this aggressively by:
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create new Pull Request
+
+## Licence
+
+[MIT License](LICENCE)

data/Rakefile

@@ -1,19 +1,12 @@
-$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), "..", "lib"))
 
-require 'bundler/gem_tasks'
-require 'rspec/core/rake_task'
-require 'optic14n'
-Dir.glob('lib/tasks/*.rake').each { |r| import r }
-
-
-require 'gem_publisher'
-desc 'Publish gem to Rubygems'
-task :publish_gem do
-  gem = GemPublisher.publish_if_updated('optic14n.gemspec', :rubygems)
-  puts "Published #{gem}" if gem
-end
+require "rspec/core/rake_task"
+require "rubocop/rake_task"
+require "bundler/gem_tasks"
+require "optic14n"
+Dir.glob("lib/tasks/*.rake").each { |r| import r }
 
+RuboCop::RakeTask.new
 RSpec::Core::RakeTask.new(:spec)
 
-task default: :spec
-task test: :spec
+task default: %i[rubocop spec]

data/lib/optic14n/canonicalized_urls.rb

@@ -1,3 +1,5 @@
+require "set"
+
 module Optic14n
   ##
   # Canonicalizes a set of URLs
@@ -21,7 +23,7 @@ module Optic14n
       @urls.each do |url|
         begin
           @output_set.add(BLURI(url).canonicalize!(@options))
-        rescue Exception => e
+        rescue StandardError => e
           failures[url] = e
         end
         @seen += 1
@@ -29,7 +31,7 @@ module Optic14n
     end
 
     def write(filename)
-      File.open(filename, 'w') do |file|
+      File.open(filename, "w") do |file|
         @output_set.each do |url|
           file.puts url
         end
@@ -39,7 +41,7 @@ module Optic14n
     ##
     # Canonicalize given urls. +options+ will be passed to +BLURI.parse+
     def self.from_urls(urls, options = {})
-      CanonicalizedUrls.new(urls, options).tap { |c| c.canonicalize! }
+      CanonicalizedUrls.new(urls, options).tap(&:canonicalize!)
     end
   end
-end
+end

data/lib/optic14n/version.rb

@@ -1,3 +1,3 @@
 module Optic14n
-  VERSION = '2.0.1'
+  VERSION = "3.0.0".freeze
 end

data/lib/optic14n.rb

@@ -1,10 +1,10 @@
-require 'optic14n/version'
+require "optic14n/version"
 
-require 'uri'
-require 'addressable/uri'
-require 'cgi'
-require 'forwardable'
-require 'uri/query_hash'
-require 'uri/bluri'
+require "uri"
+require "addressable/uri"
+require "cgi"
+require "forwardable"
+require "uri/query_hash"
+require "uri/bluri"
 
-require 'optic14n/canonicalized_urls'
+require "optic14n/canonicalized_urls"

data/lib/tasks/measure_reduction.rake

@@ -1,7 +1,7 @@
-require 'set'
+require "set"
 
 namespace :opt do
-  desc 'Measure reduction from canonicalisation'
+  desc "Measure reduction from canonicalisation"
   task :measure, [:filename, :output_file] do |_, args|
     filename = args[:filename]
     output_file = args[:output_file]
@@ -12,4 +12,4 @@ namespace :opt do
       puts "#{urls.seen} urls seen, #{urls.size} after canonicalisation"
     end
   end
-end
+end

data/lib/uri/bluri.rb

@@ -1,39 +1,44 @@
-# encoding: utf-8
-
 module URI
   ##
   # A URI class with a bit extra for canonicalising query strings
   #
   class BLURI < URI::HTTP
     PATH_ESCAPE_MAPPINGS = {
-      '[' => '%5b',
-      ']' => '%5d',
-      ',' => '%2c',
-      '"' => '%22',
-      "'" => '%27',
-      '|' => '%7c',
-      '!' => '%21',
-      '£' => '%c2%a3'
-    }
+      "[" => "%5b",
+      "]" => "%5d",
+      "," => "%2c",
+      '"' => "%22",
+      "'" => "%27",
+      "|" => "%7c",
+      "!" => "%21",
+      "£" => "%c2%a3",
+    }.freeze
 
     PATH_UNESCAPE_MAPPINGS = {
-      '%7e' => '~',
-      '%21' => '!'
-    }
+      "%7e" => "~",
+      "%21" => "!",
+    }.freeze
 
-    REQUIRE_REGEX_ESCAPE = %w<. | ( ) [ ] { } + \ ^ $ * ?> & PATH_ESCAPE_MAPPINGS.keys
+    REQUIRE_REGEX_ESCAPE = [".", "|", "(", ")", "[", "]", "{", "}", "+", " ^", "$", "*", "?"] & PATH_ESCAPE_MAPPINGS.keys
 
     extend Forwardable
 
     def_delegators :@uri, :scheme, :path, :host, :host=, :query, :fragment, :to_s
 
-    def initialize(uri_str)
+    def initialize(uri_str) # rubocop:disable Lint/MissingSuper - This class seems a reimplementation rather than an ancestor
       @uri = ::Addressable::URI.parse(uri_str)
-      raise URI::InvalidURIError, "'#{uri_str}' not a valid URI" unless @uri
+
+      raise URI::InvalidURIError, "'#{uri_str}' not a valid URI" unless valid_uri?
+    end
+
+    def valid_uri?
+      return unless @uri
+
+      %w[http https mailto].include?(@uri.scheme)
     end
 
     def query_hash
-      @query_hash ||= CGI::parse(self.query || '').tap do |query_hash|
+      @query_hash ||= CGI.parse(query || "").tap do |query_hash|
         # By default, CGI::parse produces lots of arrays. Usually they have a single element
         # in them. That's correct but not terribly usable. Fix it here.
         query_hash.each_pair { |k, v| query_hash[k] = v[0] if v.length == 1 }
@@ -43,31 +48,31 @@ module URI
 
     def query_hash=(value)
       @query_hash = value
-      @uri.query = @query_hash.to_s == '' ? nil : @query_hash.to_s
+      @uri.query = @query_hash.to_s == "" ? nil : @query_hash.to_s
     end
 
     def query=(query_str)
       @query_hash = nil
-      @uri.query = query_str == '' ? nil : query_str
+      @uri.query = query_str == "" ? nil : query_str
     end
 
     def self.parse(uri_str)
       # Deal with known URI spec breaks - leading/trailing spaces and unencoded entities
       if uri_str.is_a? String
-        uri_str = uri_str.strip.downcase.gsub(' ', '%20')
-        uri_str.gsub!('&', '%26') if uri_str =~ /^mailto:.*&.*/
+        uri_str = uri_str.strip.downcase.gsub(" ", "%20")
+        uri_str.gsub!("&", "%26") if uri_str =~ /^mailto:.*&.*/
       end
       BLURI.new(uri_str)
     end
 
     def has_query?
-      %w(http https).include?(@uri.scheme) && query
+      %w[http https].include?(@uri.scheme) && query
     end
 
     def canonicalize!(options = {})
-      @uri.scheme = 'http' if @uri.scheme == 'https'
+      @uri.scheme = "http" if @uri.scheme == "https"
 
-      @uri.path = @uri.path.sub(/\/*$/, '') if @uri.path =~ /^*\/$/
+      @uri.path = @uri.path.sub(/\/*$/, "") if @uri.path =~ /^*\/$/
       @uri.path.gsub!(BLURI.path_escape_char_regex,   PATH_ESCAPE_MAPPINGS)
       @uri.path.gsub!(BLURI.path_unescape_code_regex, PATH_UNESCAPE_MAPPINGS)
 
@@ -82,7 +87,7 @@ module URI
       allowed_keys = [options[:allow_query]].flatten.compact.map(&:to_s) unless allow_all
 
       query_hash.keep_if do |k, _|
-        allow_all || (allowed_keys.include?(k.to_s))
+        allow_all || allowed_keys.include?(k.to_s)
       end
 
       self.query_hash = QueryHash[query_hash.sort_by { |k, _| k }]
@@ -91,26 +96,31 @@ module URI
     ##
     # Generate a regex which matches all characters in PATH_ESCAPE_MAPPINGS
     def self.path_escape_char_regex
-      @path_escape_char_regex ||=
-          Regexp.new('[' + PATH_ESCAPE_MAPPINGS.keys.map do |char|
-            REQUIRE_REGEX_ESCAPE.include?(char) ? "\\#{char}" : char
-          end.join + ']')
+      @path_escape_char_regex ||= begin
+        escaped_characters_for_regex = PATH_ESCAPE_MAPPINGS.keys.map do |char|
+          REQUIRE_REGEX_ESCAPE.include?(char) ? "\\#{char}" : char
+        end
+
+        Regexp.new("[#{escaped_characters_for_regex.join}]")
+      end
     end
 
     ##
     # Generate a regex which matches all escape sequences in PATH_UNESCAPE_MAPPINGS
     def self.path_unescape_code_regex
       @path_unescape_code_regex ||= Regexp.new(
-        PATH_UNESCAPE_MAPPINGS.keys.map { |code| "(?:#{code})" }.join('|')
+        PATH_UNESCAPE_MAPPINGS.keys.map { |code| "(?:#{code})" }.join("|"),
       )
     end
   end
 end
 
 module Kernel
+  # rubocop:disable Naming/MethodName
   def BLURI(uri_str)
     ::URI::BLURI.parse(uri_str)
   end
+  # rubocop:enable Naming/MethodName
 
   module_function :BLURI
 end

data/lib/uri/query_hash.rb

@@ -4,12 +4,12 @@ module URI
   module QueryHash
     def [](key)
       item = super key
-      item = super(key.to_s) if item.nil? || item.length == 0
-      item.class == Array && item.length == 0 ? nil : item
+      item = super(key.to_s) if item.nil? || item.empty?
+      item.instance_of?(Array) && item.empty? ? nil : item
     end
 
     def to_s
-      keys.map { |key| render_value(key, self[key]) }.join('&')
+      keys.map { |key| render_value(key, self[key]) }.join("&")
     end
 
     ##
@@ -20,13 +20,13 @@ module URI
       end
     end
 
-    private
+  private
 
     def render_value(key, value)
       case value
-        when nil   then key
-        when Array then value.map { |el| render_value(key, el) }.join('&')
-        else            URI.encode_www_form_component(key) << '=' << URI.encode_www_form_component(value)
+      when nil   then key
+      when Array then value.map { |el| render_value(key, el) }.join("&")
+      else URI.encode_www_form_component(key) << "=" << URI.encode_www_form_component(value)
       end
     end
   end

data/optic14n.gemspec

@@ -1,25 +1,28 @@
-# coding: utf-8
-lib = File.expand_path('../lib', __FILE__)
+require "English"
+lib = File.expand_path("lib", __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require 'optic14n/version'
+require "optic14n/version"
 
 Gem::Specification.new do |spec|
-  spec.name          = 'optic14n'
+  spec.name          = "optic14n"
   spec.version       = Optic14n::VERSION
-  spec.authors       = ['Russell Garner']
-  spec.email         = %w(rgarner@zephyros-systems.co.uk)
-  spec.description   = %q{Canonicalises URLs.}
-  spec.summary       = %q{Specifically, HTTP URLs, for a limited purpose}
-  spec.homepage      = ''
-  spec.license       = 'MIT'
+  spec.authors       = ["GOV.UK Dev"]
+  spec.email         = ["govuk-dev@digital.cabinet-office.gov.uk"]
+  spec.description   = "Canonicalises URLs."
+  spec.summary       = "Specifically, HTTP URLs, for a limited purpose"
+  spec.homepage      = "https://github.com/alphagov/optic14n"
+  spec.license       = "MIT"
 
-  spec.files         = `git ls-files`.split($/)
+  spec.required_ruby_version = ">= 3.1.4"
+
+  spec.files         = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
-  spec.require_paths = %w(lib)
+  spec.require_paths = %w[lib]
 
-  spec.add_dependency 'addressable', '~> 2.3'
+  spec.add_dependency "addressable", "~> 2.7"
 
-  spec.add_development_dependency 'rake'
-  spec.add_development_dependency 'gem_publisher', '~> 1.3.0'
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rubocop-govuk", "5.0.2"
 end

data/spec/bluri_spec.rb

@@ -1,88 +1,88 @@
-require 'spec_helper'
+require "spec_helper"
 
 describe URI::BLURI do
-  it 'should be an HTTP URI' do
-    bluri = BLURI('http://some.where.com')
-    bluri.should be_a URI::HTTP
+  it "should be an HTTP URI" do
+    bluri = BLURI("http://some.where.com")
+    expect(bluri).to be_a URI::HTTP
   end
 
-  it 'should not allow other schemes' do
-    lambda { BLURI('ftp://foo').should raise_error(ArgumentError) }
+  it "should not allow other schemes" do
+    expect { BLURI("ftp://foo") }.to raise_error(URI::InvalidURIError)
   end
 
-  it 'should not allow nil' do
-    lambda { BLURI(nil) }.should raise_error(URI::InvalidURIError)
+  it "should not allow nil" do
+    expect { BLURI(nil) }.to raise_error(URI::InvalidURIError)
   end
 
-  it 'supports scheme' do
-    BLURI('http://foo').scheme.should == 'http'
+  it "supports scheme" do
+    expect(BLURI("http://foo").scheme).to eq("http")
   end
-  it 'supports host' do
-    BLURI('http://foo').host.should == 'foo'
+  it "supports host" do
+    expect(BLURI("http://foo").host).to eq("foo")
   end
-  it 'supports path' do
-    BLURI('http://foo/a/path').path.should == '/a/path'
+  it "supports path" do
+    expect(BLURI("http://foo/a/path").path).to eq("/a/path")
   end
-  it 'supports query' do
-    BLURI('http://foo?to=you&you=foo').query.should == 'to=you&you=foo'
+  it "supports query" do
+    expect(BLURI("http://foo?to=you&you=foo").query).to eq("to=you&you=foo")
   end
-  it 'supports fragment' do
-    BLURI('http://foo#fragment').fragment.should == 'fragment'
+  it "supports fragment" do
+    expect(BLURI("http://foo#fragment").fragment).to eq("fragment")
   end
-  it 'supports mailto:someone@somewhere' do
-    BLURI('mailto:me@there.com').to_s.should == 'mailto:me@there.com'
+  it "supports mailto:someone@somewhere" do
+    expect(BLURI("mailto:me@there.com").to_s).to eq("mailto:me@there.com")
   end
-  it 'corrects unencoded ampersands ins mailto' do # http://www.faqs.org/rfcs/rfc2368.html
-    BLURI('mailto:fruit&veg.newcastle@rpa.gsi.gov.uk').to_s.should == 'mailto:fruit%26veg.newcastle@rpa.gsi.gov.uk'
+  it "corrects unencoded ampersands ins mailto" do # http://www.faqs.org/rfcs/rfc2368.html
+    expect(BLURI("mailto:fruit&veg.newcastle@rpa.gsi.gov.uk").to_s).to eq("mailto:fruit%26veg.newcastle@rpa.gsi.gov.uk")
   end
-  it 'corrects trailing spaces' do
-    BLURI('http://www.newspapersoc.org.uk ').to_s.should == 'http://www.newspapersoc.org.uk'
+  it "corrects trailing spaces" do
+    expect(BLURI("http://www.newspapersoc.org.uk ").to_s).to eq("http://www.newspapersoc.org.uk")
   end
-  it 'corrects leading spaces' do
-    BLURI('  http://www.newspapersoc.org.uk').to_s.should == 'http://www.newspapersoc.org.uk'
+  it "corrects leading spaces" do
+    expect(BLURI("  http://www.newspapersoc.org.uk").to_s).to eq("http://www.newspapersoc.org.uk")
   end
 
-  describe 'Query string parsing' do
-    context 'the query string is of HTML-encoded form k=v&q=p' do
+  describe "Query string parsing" do
+    context "the query string is of HTML-encoded form k=v&q=p" do
       before do
-        @bluri = BLURI('http://some.com/a/path?itemid=1&type=RESOURCE')
+        @bluri = BLURI("http://some.com/a/path?itemid=1&type=RESOURCE")
       end
 
-      it 'indexes the query string' do
-        @bluri.query_hash['itemid'].should == '1'
+      it "indexes the query string" do
+        expect(@bluri.query_hash["itemid"]).to eq("1")
       end
 
-      it 'allows indexing by symbol' do
-        @bluri.query_hash[:itemid].should == '1'
+      it "allows indexing by symbol" do
+        expect(@bluri.query_hash[:itemid]).to eq("1")
       end
 
-      it 'shows nil for absent items' do
-        @bluri.query_hash[:eerie_flash].should == nil
+      it "shows nil for absent items" do
+        expect(@bluri.query_hash[:eerie_flash]).to eq(nil)
       end
 
-      it 'indexes the second query string item' do
-        @bluri.query_hash['type'].should == 'resource'
+      it "indexes the second query string item" do
+        expect(@bluri.query_hash["type"]).to eq("resource")
       end
 
-      it 'allows setting of the query' do
-        @bluri.query = 'furry=really'
-        @bluri.to_s.should == 'http://some.com/a/path?furry=really'
+      it "allows setting of the query" do
+        @bluri.query = "furry=really"
+        expect(@bluri.to_s).to eq("http://some.com/a/path?furry=really")
       end
     end
 
-    context 'the querystring is not an HTML-encoded thing' do
+    context "the querystring is not an HTML-encoded thing" do
       before do
-        @bluri = BLURI('http://some.com/a/path?foo&bar')
+        @bluri = BLURI("http://some.com/a/path?foo&bar")
       end
 
-      it 'retains the query string' do
-        @bluri.query.should == 'foo&bar'
+      it "retains the query string" do
+        expect(@bluri.query).to eq("foo&bar")
       end
 
-      it 'has a query hash with empty elements' do
-        @bluri.query_hash['foo'].should == nil
-        @bluri.query_hash['foo'].should == nil
+      it "has a query hash with empty elements" do
+        expect(@bluri.query_hash["foo"]).to eq(nil)
+        expect(@bluri.query_hash["foo"]).to eq(nil)
       end
     end
   end
-end
+end