utf8-cleaner 0.2.5 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 995c4ee0bf13ea4bb1df98a06293a397a9443394
-  data.tar.gz: cf98986f66466357bdcc87e8ef98e3c21e16fc2f
+SHA256:
+  metadata.gz: d7d130ec59597b9b6cb49ae8745fedf53d3cf10de189adef8240675193dc0f6c
+  data.tar.gz: 929e15585f3104054786be08e51141f1732876d3e9d562ee9ff2d84817a36183
 SHA512:
-  metadata.gz: ee8a133cae01cf22d10d27a7741de2be7eadd9a98b28259ac51198725022339d4c204362aee293a775fd21703f5036a1bde73aa1c5cce06fa748e3cb8cfc3da6
-  data.tar.gz: 5ec3a71bf8cd7e1606bc1e410f584581c018cc6dcb1ec7fd7a049ebe2a557a19768b752ba212cd4971af5640763c450e548eae27af74acd2dfcf8c6aadad5671
+  metadata.gz: f089a54246867ae6a438e68d45621e1ce56cfadd668a808079f46d8b9002650ceef35606e3a9cf49ca5a804fad8853db816963a31fc437c27e6d2cc974a9b741
+  data.tar.gz: 911a4922eb376f1d59d5e9404b6bc427feb138f1872bcdac02a0e0d45d9426eee164cf65c31b779dba59a020516336875589fbe444031594509efc84fc6a718d

data/.github/workflows/test.yml

@@ -0,0 +1,70 @@
+---
+name: Test
+
+'on':
+  - push
+  - pull_request
+
+jobs:
+  # rubocop:
+  #   runs-on: ubuntu-latest
+  #   env:
+  #     CI: true
+  #   steps:
+  #     - uses: actions/checkout@v3
+  #     - name: Set up Ruby 3.4
+  #       uses: ruby/setup-ruby@v1
+  #       with:
+  #         ruby-version: 3.4
+  #         bundler-cache: true
+  #     - name: Run RuboCop
+  #       run: bundle exec rubocop --parallel
+
+  test:
+    name: "${{matrix.ruby}} ${{matrix.os || 'ubuntu-latest'}}"
+    env:
+      CI: true
+    runs-on: ${{matrix.os || 'ubuntu-latest'}}
+    continue-on-error: "${{matrix.experimental || false}}"
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby:
+          - ruby-2.4
+          - ruby-2.5
+          - ruby-2.6
+          - ruby-2.7
+          - ruby-3.0
+          - ruby-3.1
+          - ruby-3.2
+          - ruby-3.3
+          - ruby-3.4
+          - jruby-9.4
+          - truffleruby
+        os:
+          - ubuntu-latest
+          - macos-latest
+          - windows-latest
+        exclude:
+          - ruby: ruby-2.4
+            os: macos-latest
+          - ruby: ruby-2.5
+            os: macos-latest
+          - ruby: jruby-9.4
+            os: windows-latest
+          - ruby: truffleruby
+            os: windows-latest
+
+    steps:
+      - name: repo checkout
+        uses: actions/checkout@v3
+      - name: load ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: "${{matrix.ruby}}"
+      - name: bundle
+        run: bundle install --jobs 4 --retry 3
+      - name: test
+        timeout-minutes: 60
+        continue-on-error: "${{matrix.experimental || false}}"
+        run: bundle exec rake spec

data/CHANGELOG.md

@@ -1,5 +1,18 @@
 # CHANGELOG
 
+## v2.0.0
+
+* Support Rack 3 and add Rack >= 3.0 as a dependency
+* Dropped support for Ruby < 2.4 to match Rack
+* Replace Travis CI with GitHub Actions
+* Add frozen_string_literal to all files
+* Remove guard gem
+
+## v1.0.0
+
+* Dropped support for Ruby < 2.3
+* Fixed deprecation warning in Ruby 2.7
+
 ## v0.2.5
 
 * MIT license specified in gemspec
@@ -31,4 +44,4 @@
 
 ## v0.1.0
 
-Broken.
+* Broken.

data/Gemfile

@@ -1,4 +1,5 @@
+# frozen_string_literal: true
+
 source 'https://rubygems.org'
 
-# Specify your gem's dependencies in utf8-cleaner.gemspec
 gemspec

data/README.md

@@ -1,28 +1,22 @@
 # UTF8Cleaner
 
-[![Build Status](https://secure.travis-ci.org/singlebrook/utf8-cleaner.png?branch=master)](http://travis-ci.org/singlebrook/utf8-cleaner)
-
-Removes invalid UTF-8 characters from the environment so that your app doesn't choke
-on them. This prevents errors like "invalid byte sequence in UTF-8".
+Rack middleware to remove invalid UTF-8 characters from the environment so that your
+app doesn't choke on them. Prevents errors like "invalid byte sequence in UTF-8".
 
 ## Installation
 
-Add this line to your application's Gemfile:
-
-    gem 'utf8-cleaner'
-
-And then execute:
+Add this line to your application's `Gemfile`:
 
-    $ bundle
+```ruby
+gem 'utf8-cleaner'
+```
 
-Or install it yourself as:
+If you're not running Rails, you'll have to add the middleware to your `config.ru`:
 
-    $ gem install utf8-cleaner
-
-If you're not running Rails, you'll have to add the middleware to your config.ru:
-
-    require 'utf8-cleaner'
-    use UTF8Cleaner::Middleware
+```ruby
+require 'utf8-cleaner'
+use UTF8Cleaner::Middleware
+```
 
 ## Usage
 
@@ -38,10 +32,10 @@ There's nothing to "use". It just works!
 
 ## Credits
 
-Original middleware author: @phoet - https://gist.github.com/phoet/1336754
-
+* Original middleware author: @phoet - https://gist.github.com/phoet/1336754
 * Ruby 1.9.3 compatibility: @pithyless - https://gist.github.com/pithyless/3639014
 * Code review and cleanup: @nextmat
 * POST body sanitization: @salrepe
 * Bug fixes: @cosine
 * Rails 5 deprecation fix: @benlovell
+* Rack 3 support: @johnnyshields

data/Rakefile

@@ -1,5 +1,8 @@
-require "bundler/gem_tasks"
+# frozen_string_literal: true
 
-task :default do
-  sh "rspec spec"
-end
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/lib/utf8-cleaner/middleware.rb

@@ -1,24 +1,25 @@
+# frozen_string_literal: true
+
 require 'active_support/multibyte/unicode'
 
 module UTF8Cleaner
   class Middleware
-
-    SANITIZE_ENV_KEYS = [
-     "HTTP_REFERER",
-     "HTTP_USER_AGENT",
-     "PATH_INFO",
-     "QUERY_STRING",
-     "REQUEST_PATH",
-     "REQUEST_URI",
-     "HTTP_COOKIE"
-    ]
+    SANITIZE_ENV_KEYS = %w[
+      HTTP_REFERER
+      HTTP_USER_AGENT
+      PATH_INFO
+      QUERY_STRING
+      REQUEST_PATH
+      REQUEST_URI
+      HTTP_COOKIE
+    ].freeze
 
     def initialize(app)
-     @app = app
+      @app = app
     end
 
     def call(env)
-     @app.call(sanitize_env(env))
+      @app.call(sanitize_env(env))
     end
 
     private
@@ -26,6 +27,7 @@ module UTF8Cleaner
     include ActiveSupport::Multibyte::Unicode
 
     def sanitize_env(env)
+      env = env.dup # Do not mutate the original
       sanitize_env_keys(env)
       sanitize_env_rack_input(env)
       env
@@ -33,34 +35,47 @@ module UTF8Cleaner
 
     def sanitize_env_keys(env)
       SANITIZE_ENV_KEYS.each do |key|
-        next unless value = env[key]
+        next unless (value = env[key])
         env[key] = cleaned_string(value)
       end
     end
 
     def sanitize_env_rack_input(env)
+      return unless env['rack.input']
+
       case env['CONTENT_TYPE']
-      when 'application/x-www-form-urlencoded'
+      when %r{\Aapplication/x-www-form-urlencoded}i
         # This data gets the full cleaning treatment
-        cleaned_value = cleaned_string(env['rack.input'].read)
-        env['rack.input'] = StringIO.new(cleaned_value) if cleaned_value
-        env['rack.input'].rewind
-      when 'application/json'
+        input_data = read_input(env['rack.input'])
+        return unless input_data
+
+        cleaned_value = cleaned_string(input_data)
+        env['rack.input'] = StringIO.new(cleaned_value)
+      when %r{\Aapplication/json}i
         # This data only gets cleaning of invalid UTF-8 (e.g. from another charset)
         # but we do not URI-decode it.
-        rack_input = env['rack.input'].read
-        if rack_input && !rack_input.ascii_only?
-          env['rack.input'] = StringIO.new(tidy_bytes(rack_input))
-        end
-        env['rack.input'].rewind
-      when 'multipart/form-data'
-        # Don't process the data since it may contain binary content
+        input_data = read_input(env['rack.input'])
+        return unless input_data && !input_data.ascii_only?
+
+        env['rack.input'] = StringIO.new(tidy_bytes(input_data))
       else
-        # Unknown content type. Leave it alone
+        # Do not process multipart/form-data since it may contain binary content.
+        # Leave all other unknown content types alone.
       end
     end
 
+    def read_input(input)
+      return nil unless input
+
+      data = input.read
+      input.rewind if input.respond_to?(:rewind)
+      data
+    end
+
     def cleaned_string(value)
+      return value if value.nil? || value.empty?
+
+      value = value.to_s
       value = tidy_bytes(value) unless value.ascii_only?
       value = URIString.new(value).cleaned if value.include?('%')
       value

data/lib/utf8-cleaner/railtie.rb

@@ -1,7 +1,9 @@
+# frozen_string_literal: true
+
 module UTF8Cleaner
   class Railtie < Rails::Railtie
-    initializer "utf8-cleaner.insert_middleware" do |app|
-      app.config.middleware.insert_before 0, UTF8Cleaner::Middleware
+    initializer('utf8-cleaner.insert_middleware') do |app|
+      app.config.middleware.insert_before(0, UTF8Cleaner::Middleware)
     end
   end
 end

data/lib/utf8-cleaner/uri_string.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module UTF8Cleaner
   # Cleans invalid %-encodings from URI-encoded strings.
   class URIString
@@ -32,7 +34,7 @@ module UTF8Cleaner
       char_array = []
       index = 0
 
-      while (index < data.length) do
+      while index < data.length do
         char = data[index]
 
         if char == '%'
@@ -87,7 +89,7 @@ module UTF8Cleaner
     end
 
     def valid_uri_encoded_utf8(string)
-      URI.decode(string).force_encoding('UTF-8').valid_encoding? &&
+      URI::DEFAULT_PARSER.unescape(string).force_encoding('UTF-8').valid_encoding? &&
         string !~ INVALID_PERCENT_ENCODING_REGEX
     rescue ArgumentError => e
       if e.message =~ /invalid byte sequence/
@@ -129,6 +131,5 @@ module UTF8Cleaner
         4
       end
     end
-
   end
 end

data/lib/utf8-cleaner/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module UTF8Cleaner
-  VERSION = "0.2.5"
+  VERSION = '2.0.0'
 end

data/lib/utf8-cleaner.rb

@@ -1,4 +1,6 @@
-require "utf8-cleaner/version"
-require "utf8-cleaner/middleware"
-require "utf8-cleaner/uri_string"
-require "utf8-cleaner/railtie" if defined? Rails
+# frozen_string_literal: true
+
+require 'utf8-cleaner/version'
+require 'utf8-cleaner/middleware'
+require 'utf8-cleaner/uri_string'
+require 'utf8-cleaner/railtie' if defined?(Rails)

data/spec/middleware_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'spec_helper'
 require 'rack/lint'
 
@@ -37,10 +39,8 @@ module UTF8Cleaner
       end
 
       describe "when rack.input is wrapped" do
-        # rack.input responds only to methods gets, each, rewind, read and close
-        # Rack::Lint::InputWrapper is the class which servers wrappers are based on
         it "removes invalid UTF-8 sequences" do
-          wrapped_rack_input = Rack::Lint::InputWrapper.new(StringIO.new("foo=%FFbar%F8"))
+          wrapped_rack_input = Rack::Lint::Wrapper::InputWrapper.new(StringIO.new("foo=%FFbar%F8"))
           env.merge!('rack.input' => wrapped_rack_input)
           new_env = Middleware.new(nil).send(:sanitize_env, env)
           expect(new_env['rack.input'].read).to eq('foo=bar')
@@ -99,7 +99,7 @@ module UTF8Cleaner
     # E.g. make sure Rack/Rails won't choke on them
     after do
       cleaned = new_env
-      env.keys.reject{|key| key == 'rack.input'}.each do |key|
+      env.keys.reject { |key| key == 'rack.input' }.each do |key|
         URI.decode_www_form_component(cleaned[key]) if cleaned[key]
       end
     end

data/spec/spec_helper.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'rubygems'
 require 'utf8-cleaner'
 require 'uri'

data/spec/uri_string_spec.rb

@@ -1,4 +1,5 @@
-# encoding: UTF-8
+# frozen_string_literal: true
+
 require 'spec_helper'
 
 module UTF8Cleaner
@@ -8,8 +9,10 @@ module UTF8Cleaner
     let(:ascii_string)     { URIString.new('foo') }
     let(:encoded_string)   { URIString.new('%26') }
     let(:multibyte_string) { URIString.new('%E2%9C%93') }
-    let(:complex_invalid_string) { URIString.new('foo/%FFbar%2e%2fbaz%26%3B%E2%9C%93%E2%9Cbaz') }
-                                                # foo/   bar.  /  baz&  ;  √              baz
+    let(:complex_invalid_string) do
+      # ------------ foo/   bar.  /  baz&  ;  √              baz
+      URIString.new('foo/%FFbar%2e%2fbaz%26%3B%E2%9C%93%E2%9Cbaz')
+    end
     let(:no_byte_at_all)      { URIString.new('%') }
     let(:not_even_hex_chars1) { URIString.new('%x') }
     let(:not_even_hex_chars2) { URIString.new('%0zhey') }
@@ -35,7 +38,6 @@ module UTF8Cleaner
       it { expect(ascii_string).to be_valid }
       it { expect(encoded_string).to be_valid }
       it { expect(multibyte_string).to be_valid }
-
       it { expect(invalid_string).to_not be_valid }
       it { expect(complex_invalid_string).to_not be_valid }
       it { expect(no_byte_at_all).to_not be_valid }
@@ -43,7 +45,5 @@ module UTF8Cleaner
       it { expect(not_even_hex_chars2).to_not be_valid }
       it { expect(mixed_encodings).to_not be_valid }
     end
-
   end
-
 end

data/utf8-cleaner.gemspec

@@ -1,29 +1,27 @@
-# -*- encoding: utf-8 -*-
-lib = File.expand_path('../lib', __FILE__)
-$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require 'utf8-cleaner/version'
+# frozen_string_literal: true
+
+require_relative 'lib/utf8-cleaner/version'
 
 Gem::Specification.new do |gem|
-  gem.name          = "utf8-cleaner"
+  gem.name          = 'utf8-cleaner'
   gem.version       = UTF8Cleaner::VERSION
-  gem.authors       = ["Leon Miller-Out"]
-  gem.email         = ["leon@singlebrook.com"]
-  gem.description   = %q{Removes invalid UTF8 characters from the URL and other env vars}
-  gem.summary       = %q{Prevent annoying error reports of "invalid byte sequence in UTF-8"}
-  gem.homepage      = "https://github.com/singlebrook/utf8-cleaner"
-  gem.license       = "MIT"
+  gem.authors       = ['Leon Miller-Out', 'Shane Cavanaugh']
+  gem.email         = ['leon@singlebrook.com', 'shane@shanecav.net']
+  gem.description   = %q{Rack middleware to remove invalid UTF8 characters from web requests.}
+  gem.summary       = %q{Prevent annoying 'invalid byte sequence in UTF-8' errors}
+  gem.homepage      = 'https://github.com/singlebrook/utf8-cleaner'
+  gem.license       = 'MIT'
 
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
-  gem.require_paths = ["lib"]
+  gem.require_paths = ['lib']
+
+  gem.required_ruby_version = '>= 2.4'
 
   gem.add_dependency 'activesupport'
+  gem.add_dependency 'rack', '~> 3.0'
 
-  gem.add_development_dependency "rake"
-  gem.add_development_dependency "listen", "3.0.8"
-  gem.add_development_dependency "guard"
-  gem.add_development_dependency "guard-rspec"
-  gem.add_development_dependency "rspec"
-  gem.add_development_dependency "rack"
+  gem.add_development_dependency 'rake'
+  gem.add_development_dependency 'rspec'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: utf8-cleaner
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 2.0.0
 platform: ruby
 authors:
 - Leon Miller-Out
-autorequire: 
+- Shane Cavanaugh
 bindir: bin
 cert_chain: []
-date: 2016-07-18 00:00:00.000000000 Z
+date: 2025-10-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -25,49 +25,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !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: listen
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 3.0.8
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 3.0.8
-- !ruby/object:Gem::Dependency
-  name: guard
+  name: rack
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
+        version: '3.0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: guard-rspec
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -94,32 +66,18 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rack
-  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'
-description: Removes invalid UTF8 characters from the URL and other env vars
+description: Rack middleware to remove invalid UTF8 characters from web requests.
 email:
 - leon@singlebrook.com
+- shane@shanecav.net
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/test.yml"
 - ".gitignore"
-- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
-- Guardfile
 - LICENSE.txt
 - README.md
 - Rakefile
@@ -136,7 +94,6 @@ homepage: https://github.com/singlebrook/utf8-cleaner
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -144,18 +101,16 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.4'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.4
-signing_key: 
+rubygems_version: 3.6.3
 specification_version: 4
-summary: Prevent annoying error reports of "invalid byte sequence in UTF-8"
+summary: Prevent annoying 'invalid byte sequence in UTF-8' errors
 test_files:
 - spec/middleware_spec.rb
 - spec/spec_helper.rb

data/.travis.yml

@@ -1,9 +0,0 @@
-before_install:
-  - gem install bundler
-language: ruby
-rvm:
-  - 1.9.3
-  - 2.0.0
-  - 2.1.8
-  - 2.2.5
-  - 2.3.1

data/Guardfile

@@ -1,9 +0,0 @@
-# A sample Guardfile
-# More info at https://github.com/guard/guard#readme
-
-guard :rspec, cmd: 'bundle exec rspec -b' do
-  watch(%r{^spec/.+_spec\.rb$})
-  watch(%r{^lib/utf8-cleaner/(.+)\.rb$}) { |m| "spec/#{m[1]}_spec.rb" }
-  watch('spec/spec_helper.rb') { "spec" }
-end
-