url_canonicalize 0.2.1 → 1.0.2

data/lib/url_canonicalize/uri.rb

@@ -4,22 +4,23 @@ module URLCanonicalize
   # Manage the URL into a URI with local exception handling
   class URI
     class << self
+      VALID_CLASSES = [::URI::HTTP, ::URI::HTTPS].freeze
+      COLON = ':'
+
       def parse(url)
         uri = ::URI.parse decorate(url)
-        uri if valid? uri
+        validate! uri
+        uri
       rescue ::URI::InvalidURIError => e
-        new_exception = URLCanonicalize::Exception::URI.new("#{e.class}: #{e.message}")
-        new_exception.set_backtrace e.backtrace
-        raise new_exception
+        raise URLCanonicalize::Exception::URI, "#{e.class}: #{e.message}" # the original error becomes the cause
       end
 
       private
 
-      def valid?(uri)
+      def validate!(uri)
         raise URLCanonicalize::Exception::URI, "#{uri} must be http or https" unless VALID_CLASSES.include?(uri.class)
         raise URLCanonicalize::Exception::URI, "Missing host name in #{uri}" unless uri.host
-
-        true
+        raise URLCanonicalize::Exception::URI, "Empty host name in #{uri}" if uri.host.empty?
       end
 
       def decorate(url)
@@ -27,9 +28,6 @@ module URLCanonicalize
 
         "http://#{url}" # Add protocol if we just receive a host name
       end
-
-      VALID_CLASSES = [::URI::HTTP, ::URI::HTTPS].freeze
-      COLON = ':'
     end
   end
 end

data/lib/url_canonicalize/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module URLCanonicalize
-  VERSION = '0.2.1'
+  VERSION = '1.0.2'
 end

data/lib/url_canonicalize.rb

@@ -4,25 +4,31 @@ require 'uri'
 require 'addressable/uri'
 require 'net/http'
 require 'nokogiri'
+require 'timeout'
 
 autoload :OpenSSL, 'openssl'
 
 # Core methods
 module URLCanonicalize
+  autoload :BoundedBody, 'url_canonicalize/bounded_body'
+  autoload :Destination, 'url_canonicalize/destination'
   autoload :Exception, 'url_canonicalize/exception'
   autoload :HTTP, 'url_canonicalize/http'
+  autoload :LinkHeader, 'url_canonicalize/link_header'
+  autoload :MediaType, 'url_canonicalize/media_type'
+  autoload :Options, 'url_canonicalize/options'
   autoload :Request, 'url_canonicalize/request'
   autoload :Response, 'url_canonicalize/response'
   autoload :URI, 'url_canonicalize/uri'
   autoload :VERSION, 'url_canonicalize/version'
 
   class << self
-    def canonicalize(url)
-      fetch(url).url
+    def canonicalize(url, **options)
+      fetch(url, **options).url
     end
 
-    def fetch(url)
-      URLCanonicalize::HTTP.new(url).fetch
+    def fetch(url, **options)
+      URLCanonicalize::HTTP.new(url, **options).fetch
     end
   end
 end
@@ -30,4 +36,3 @@ end
 require 'monkey_patches/uri'
 require 'monkey_patches/string'
 require 'monkey_patches/addressable/uri'
-require 'English' # Needed for $LAST_MATCH_INFO

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: url_canonicalize
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Dominic Sayers
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-02-01 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -46,38 +45,35 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".codeclimate.yml"
-- ".gitignore"
-- ".hound.yml"
-- ".rspec"
-- ".rubocop.yml"
-- ".ruby-gemset"
-- ".travis.yml"
 - CHANGELOG.md
-- Gemfile
-- Gemfile.lock
-- Guardfile
 - LICENSE
 - README.md
-- Rakefile
-- circle.yml
+- SECURITY.md
 - lib/monkey_patches/addressable/uri.rb
 - lib/monkey_patches/string.rb
 - lib/monkey_patches/uri.rb
 - lib/url_canonicalize.rb
+- lib/url_canonicalize/bounded_body.rb
+- lib/url_canonicalize/destination.rb
 - lib/url_canonicalize/exception.rb
 - lib/url_canonicalize/http.rb
+- lib/url_canonicalize/link_header.rb
+- lib/url_canonicalize/media_type.rb
+- lib/url_canonicalize/options.rb
 - lib/url_canonicalize/request.rb
 - lib/url_canonicalize/response.rb
 - lib/url_canonicalize/uri.rb
 - lib/url_canonicalize/version.rb
-- url_canonicalize.gemspec
 homepage: https://github.com/dominicsayers/url_canonicalize
 licenses:
 - MIT
 metadata:
+  bug_tracker_uri: https://github.com/dominicsayers/url_canonicalize/issues
+  changelog_uri: https://github.com/dominicsayers/url_canonicalize/blob/main/CHANGELOG.md
+  documentation_uri: https://www.rubydoc.info/gems/url_canonicalize
+  homepage_uri: https://github.com/dominicsayers/url_canonicalize
+  source_code_uri: https://github.com/dominicsayers/url_canonicalize
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -85,15 +81,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.6.0
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.6
-signing_key:
+rubygems_version: 4.0.16
 specification_version: 4
 summary: Finds the canonical version of a URL
 test_files: []

data/.codeclimate.yml

@@ -1,25 +0,0 @@
----
-engines:
-  duplication:
-    enabled: true
-    config:
-      languages:
-      - ruby
-      - javascript
-      - python
-      - php
-  fixme:
-    enabled: true
-  rubocop:
-    enabled: true
-ratings:
-  paths:
-  - "**.inc"
-  - "**.js"
-  - "**.jsx"
-  - "**.module"
-  - "**.php"
-  - "**.py"
-  - "**.rb"
-exclude_paths:
-  - spec/

data/.gitignore

@@ -1,51 +0,0 @@
-*.local
-*.gem
-*.rbc
-/.config
-/coverage/
-/InstalledFiles
-/pkg/
-/spec/reports/
-/spec/examples.txt
-/test/tmp/
-/test/version_tmp/
-/tmp/
-
-# Used by dotenv library to load environment variables.
-# .env
-
-## Specific to RubyMotion:
-.dat*
-.repl_history
-build/
-*.bridgesupport
-build-iPhoneOS/
-build-iPhoneSimulator/
-
-## Specific to RubyMotion (use of CocoaPods):
-#
-# We recommend against adding the Pods directory to your .gitignore. However
-# you should judge for yourself, the pros and cons are mentioned at:
-# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
-#
-# vendor/Pods/
-
-## Documentation cache and generated files:
-/.yardoc/
-/_yardoc/
-/doc/
-/rdoc/
-
-## Environment normalization:
-/.bundle/
-/vendor/bundle
-/lib/bundler/man/
-
-# for a library or gem, you might want to ignore these files since the code is
-# intended to run in multiple environments; otherwise, check them in:
-# Gemfile.lock
-.ruby-version
-.ruby-gemset
-
-# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
-.rvmrc

data/.hound.yml

@@ -1,4 +0,0 @@
----
-ruby:
-  enabled: true
-  config_file: .rubocop.yml

data/.rspec

@@ -1,5 +0,0 @@
---color
---require spec_helper
---profile
---format progress
---format RspecJunitFormatter --out <%= ENV.fetch('CIRCLE_TEST_REPORTS', 'tmp') %>/rspec/rspec.xml

data/.rubocop.yml

@@ -1,61 +0,0 @@
----
-AllCops:
-  DisplayStyleGuide: true
-  DisplayCopNames: true
-  TargetRubyVersion: 2.6
-  NewCops: enable
-
-Layout/DotPosition:
-  Description: 'Checks the position of the dot in multi-line method calls.'
-  EnforcedStyle: leading
-  Enabled: true
-
-Layout/ExtraSpacing:
-  Description: 'Do not use unnecessary spacing.'
-  Enabled: true
-
-Layout/LineLength:
-  Max: 120
-  Exclude:
-    - spec/**/*
-
-Lint/LiteralInInterpolation:
-  Description: 'Avoid interpolating literals in strings'
-  AutoCorrect: true
-
-Metrics/BlockLength:
-  Exclude:
-    - spec/**/*
-
-Metrics/ClassLength:
-  CountComments: false  # count full line comments?
-  Max: 200
-
-Metrics/MethodLength:
-  Max: 12
-
-Naming/FileName:
-  Description: 'Use snake_case for source file names.'
-  Enabled: true
-
-Style/ClassAndModuleChildren:
-  Description: 'Checks style of children classes and modules.'
-  EnforcedStyle: nested
-  Enabled: true
-
-Style/Documentation:
-  Description: 'Document classes and non-namespace modules.'
-  Enabled: false
-
-Style/StringLiterals:
-  EnforcedStyle: single_quotes
-  Enabled: true
-
-Style/SymbolArray:
-  Description: 'Use %i or %I for arrays of symbols.'
-  StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#percent-i'
-  Enabled: false # Only available in Ruby 2.0+
-
-Style/TrailingCommaInArguments:
-  EnforcedStyleForMultiline: no_comma
-  Enabled: true

data/.ruby-gemset

@@ -1 +0,0 @@
-url_canonicalize

data/.travis.yml

@@ -1,9 +0,0 @@
----
-language: ruby
-rvm:
-  - 2.6
-  - 2.7
-  - 3.0
-  - 3.1
-script:
-  - rspec

data/Gemfile

@@ -1,22 +0,0 @@
-# frozen_string_literal: true
-
-source 'https://rubygems.org'
-
-gemspec
-
-group :static_code_analysis do
-  gem 'rubocop', require: false
-  gem 'rubocop-rspec', require: false
-end
-
-group :test do
-  gem 'coveralls', require: false
-  gem 'rspec'
-  gem 'rspec_junit_formatter'
-  gem 'simplecov', '~> 0.13'
-  gem 'webmock'
-end
-
-group :build do
-  gem 'gem-release', require: false
-end

data/Gemfile.lock

@@ -1,102 +0,0 @@
-PATH
-  remote: .
-  specs:
-    url_canonicalize (0.2.1)
-      addressable (~> 2)
-      nokogiri (>= 1.13)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    addressable (2.8.0)
-      public_suffix (>= 2.0.2, < 5.0)
-    ast (2.4.2)
-    coveralls (0.7.2)
-      multi_json (~> 1.3)
-      rest-client (= 1.6.7)
-      simplecov (>= 0.7)
-      term-ansicolor (= 1.2.2)
-      thor (= 0.18.1)
-    crack (0.4.5)
-      rexml
-    diff-lcs (1.5.0)
-    docile (1.4.0)
-    gem-release (2.2.2)
-    hashdiff (1.0.1)
-    mime-types (3.4.1)
-      mime-types-data (~> 3.2015)
-    mime-types-data (3.2022.0105)
-    multi_json (1.15.0)
-    nokogiri (1.13.1-x86_64-linux)
-      racc (~> 1.4)
-    parallel (1.21.0)
-    parser (3.1.0.0)
-      ast (~> 2.4.1)
-    public_suffix (4.0.6)
-    racc (1.6.0)
-    rainbow (3.1.1)
-    regexp_parser (2.2.0)
-    rest-client (1.6.7)
-      mime-types (>= 1.16)
-    rexml (3.2.5)
-    rspec (3.10.0)
-      rspec-core (~> 3.10.0)
-      rspec-expectations (~> 3.10.0)
-      rspec-mocks (~> 3.10.0)
-    rspec-core (3.10.2)
-      rspec-support (~> 3.10.0)
-    rspec-expectations (3.10.2)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-mocks (3.10.3)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-support (3.10.3)
-    rspec_junit_formatter (0.5.1)
-      rspec-core (>= 2, < 4, != 2.12.0)
-    rubocop (1.25.0)
-      parallel (~> 1.10)
-      parser (>= 3.1.0.0)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.15.1, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.15.1)
-      parser (>= 3.0.1.1)
-    rubocop-rspec (2.8.0)
-      rubocop (~> 1.19)
-    ruby-progressbar (1.11.0)
-    simplecov (0.21.2)
-      docile (~> 1.1)
-      simplecov-html (~> 0.11)
-      simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
-    simplecov_json_formatter (0.1.3)
-    term-ansicolor (1.2.2)
-      tins (~> 0.8)
-    thor (0.18.1)
-    tins (0.13.2)
-    unicode-display_width (2.1.0)
-    webmock (3.14.0)
-      addressable (>= 2.8.0)
-      crack (>= 0.3.2)
-      hashdiff (>= 0.4.0, < 2.0.0)
-
-PLATFORMS
-  x86_64-linux
-
-DEPENDENCIES
-  coveralls
-  gem-release
-  rspec
-  rspec_junit_formatter
-  rubocop
-  rubocop-rspec
-  simplecov (~> 0.13)
-  url_canonicalize!
-  webmock
-
-BUNDLED WITH
-   2.3.6

data/Guardfile

@@ -1,18 +0,0 @@
-# frozen_string_literal: true
-
-guard :rubocop do
-  watch(/.+\.rb$/)
-  watch(%r{(?:.+/)?\.rubocop\.yml$}) { |m| File.dirname(m[0]) }
-end
-
-guard(
-  :rspec,
-  all_after_pass: false,
-  all_on_start: false,
-  cmd: 'NO_SIMPLECOV=true bundle exec rspec --fail-fast --format documentation'
-) do
-  watch(%r{spec/.+_spec\.rb$})
-  watch(%r{lib/(.+)\.rb$}) { |m| "spec/#{m[1]}_spec.rb" }
-  watch('spec/spec_helper.rb') { 'spec' }
-  watch(%r{^spec/support/.+\.rb$}) { 'spec' }
-end

data/Rakefile

@@ -1,3 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler/gem_tasks'

data/circle.yml

@@ -1,29 +0,0 @@
-version: 2.1
-orbs:
-  ruby: circleci/ruby@1.1
-jobs:
-  check_and_test:
-    parameters:
-      ruby-version:
-        type: string
-    docker:
-      - image: cimg/ruby:<< parameters.ruby-version >>
-    parallelism: 3
-    steps:
-      - checkout
-      - ruby/install-deps
-      - run:
-          name: Run static code analysis
-          command: bundle exec rubocop
-      - run:
-          name: Run tests
-          command: bundle exec rspec
-workflows:
-  version: 2
-  test:
-    jobs:
-      - check_and_test:
-          # cribbed from http://mikebian.co/running-tests-against-multiple-ruby-versions-using-circleci/
-          matrix:
-            parameters:
-              ruby-version: ["2.6", "2.7", "3.0", "3.1"]

data/url_canonicalize.gemspec

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-lib = File.expand_path('lib', __dir__)
-$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require 'url_canonicalize/version'
-
-Gem::Specification.new do |s|
-  s.name          = 'url_canonicalize'
-  s.version       = URLCanonicalize::VERSION
-  s.authors       = ['Dominic Sayers']
-  s.email         = ['dominic@sayers.cc']
-  s.summary       = 'Finds the canonical version of a URL'
-  s.description   = 'Rubygem that finds the canonical version of a URL by '\
-                    'providing #canonicalize methods for the String, URI::HTTP'\
-                    ', URI::HTTPS and Addressable::URI classes'
-  s.homepage      = 'https://github.com/dominicsayers/url_canonicalize'
-  s.license       = 'MIT'
-
-  s.required_ruby_version = '>= 2.6.0'
-
-  s.files = `git ls-files`.split($RS).grep_v(%r{^spec/})
-
-  s.test_files = []
-  s.executables   = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  s.require_paths = ['lib']
-
-  s.add_runtime_dependency 'addressable', '~> 2' # To normalize URLs
-  s.add_runtime_dependency 'nokogiri', '>= 1.13' # To look for <link rel="canonical" ...> in HTML
-  s.metadata['rubygems_mfa_required'] = 'true'
-end