encoded_string 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6edf97129fcbe7bade9085842666d3b3c16eb38c
+  data.tar.gz: 2deb441cc137986c87c4fa0602afeb375a8b482f
+SHA512:
+  metadata.gz: bb64ed5b32b177a34fdfee13677e54a58a49972c67ad5129fe562c192f30e6a74c18efdf89df78bf6a9a356bc9fed0642e797c8b592a472cc26550937ce4a0a0
+  data.tar.gz: bc7503ec2ca60c355d7abe085606d6cade4439a0554638d48069bcc36d5b2f4973082c90817b7020d43143644da30c55c03f6a00c12dcf3b691f23182fdf9cbc

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.2.2
+before_install: gem install bundler -v 1.10.6

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,13 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, or religion.
+
+Examples of unacceptable behavior by participants include the use of sexual language or imagery, derogatory comments or personal attacks, trolling, public or private harassment, insults, or other unprofessional conduct.
+
+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. Project maintainers who do not follow the Code of Conduct may be removed from the project team.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
+
+This Code of Conduct is adapted from the [Contributor Covenant](http://contributor-covenant.org), version 1.0.0, available at [http://contributor-covenant.org/version/1/0/0/](http://contributor-covenant.org/version/1/0/0/)

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in encoded_string.gemspec
+gemspec

data/LICENSE.md

@@ -0,0 +1,23 @@
+The MIT License (MIT)
+====================
+
+* Copyright © 2013 David Chelimsky, Myron Marston, Jon Rowe, Sam Phippen, Xavier Shay, Bradley Schaefer
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+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 OR COPYRIGHT HOLDERS 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.

data/README.md

@@ -0,0 +1,99 @@
+# EncodedString
+
+EncodedString is a wrapper for a string and a given encoding that handles operations on
+strings with different encodings, invalid encodings, have no known conversion method,
+or are otherwise incompatible, all without raising excpetions
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'encoded_string'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install encoded_string
+
+## Usage
+
+```ruby
+EncodedString.pick_encoding(str1, str2)
+
+      def build_encoded_string(string, target_encoding = string.encoding)
+        EncodedString.new(string, target_encoding)
+      end
+str = "abc".encode('ASCII-8BIT')
+str = EncodedString.new(str, target_encoding = string.encoding)
+expect(str.source_encoding.to_s).to eq('ASCII-8BIT')
+str.split("\n")
+str << "123"
+str.to_s
+```
+
+## About
+
+Encoding Exceptions:
+
+```plain
+Raised by Encoding and String methods:
+  Encoding::UndefinedConversionError:
+    when a transcoding operation fails
+    if the String contains characters invalid for the target encoding
+    e.g. "\x80".encode('UTF-8','ASCII-8BIT')
+    vs "\x80".encode('UTF-8','ASCII-8BIT', undef: :replace, replace: '<undef>')
+    # => '<undef>'
+  Encoding::CompatibilityError
+    when Encoding.compatibile?(str1, str2) is nil
+    e.g. utf_16le_emoji_string.split("\n")
+    e.g. valid_unicode_string.encode(utf8_encoding) << ascii_string
+  Encoding::InvalidByteSequenceError:
+    when the string being transcoded contains a byte invalid for
+    either the source or target encoding
+    e.g. "\x80".encode('UTF-8','US-ASCII')
+    vs "\x80".encode('UTF-8','US-ASCII', invalid: :replace, replace: '<byte>')
+    # => '<byte>'
+  ArgumentError
+    when operating on a string with invalid bytes
+    e.g."\x80".split("\n")
+  TypeError
+    when a symbol is passed as an encoding
+    Encoding.find(:"UTF-8")
+    when calling force_encoding on an object
+    that doesn't respond to #to_str
+
+Raised by transcoding methods:
+  Encoding::ConverterNotFoundError:
+    when a named encoding does not correspond with a known converter
+    e.g. 'abc'.force_encoding('UTF-8').encode('foo')
+    or a converter path cannot be found
+    e.g. "\x80".force_encoding('ASCII-8BIT').encode('Emacs-Mule')
+
+Raised by byte <-> char conversions
+  RangeError: out of char range
+    e.g. the UTF-16LE emoji: 128169.chr
+```
+
+See [lib/encoded_string.rb](lib/encoded_string.rb) and
+[spec/encoded_string_spec.rb](spec/encoded_string_spec.rb) for more information.
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/bf4/encoded_string. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](contributor-covenant.org) code of conduct.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "encoded_string"
+
+# 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 "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/encoded_string.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'encoded_string/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "encoded_string"
+  spec.version       = EncodedString::VERSION
+  spec.authors       = ["Benjamin Fleischer"]
+  spec.email         = ["github@benjaminfleischer.com"]
+
+  spec.summary       = %q{Handle string operations without worrying about raising encoding exceptions.}
+  spec.description   = %q{Extracted from rspec-support. See https://github.com/rspec/rspec-support/issues/249.}
+  spec.homepage      = "https://github.com/bf4/encoded_string"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.10"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec"
+end

data/lib/encoded_string.rb

@@ -0,0 +1,150 @@
+class EncodedString
+  # Reduce allocations by storing constants.
+  UTF_8    = "UTF-8"
+  US_ASCII = "US-ASCII"
+  #
+  # In MRI 2.1 'invalid: :replace' changed to also replace an invalid byte sequence
+  # see https://github.com/ruby/ruby/blob/v2_1_0/NEWS#L176
+  # https://www.ruby-forum.com/topic/6861247
+  # https://twitter.com/nalsh/status/553413844685438976
+  #
+  # For example, given:
+  #   "\x80".force_encoding("Emacs-Mule").encode(:invalid => :replace).bytes.to_a
+  #
+  # On MRI 2.1 or above: 63  # '?'
+  # else               : 128 # "\x80"
+  #
+  # Ruby's default replacement string is:
+  #   U+FFFD ("\xEF\xBF\xBD"), for Unicode encoding forms, else
+  #   ?      ("\x3F")
+  REPLACE = "?"
+  ENCODE_UNCONVERTABLE_BYTES =  {
+    :invalid => :replace,
+    :undef   => :replace,
+    :replace => REPLACE
+  }
+  ENCODE_NO_CONVERTER = {
+    :invalid => :replace,
+    :replace => REPLACE
+  }
+
+  def initialize(string, encoding=nil)
+    @encoding = encoding
+    @source_encoding = detect_source_encoding(string)
+    @string = matching_encoding(string)
+  end
+  attr_reader :source_encoding
+
+  delegated_methods = String.instance_methods.map(&:to_s) & %w[eql? lines == encoding empty?]
+  delegated_methods.each do |name|
+    define_method(name) { |*args, &block| @string.__send__(name, *args, &block) }
+  end
+
+  def <<(string)
+    @string << matching_encoding(string)
+  end
+
+  def split(regex_or_string)
+    @string.split(matching_encoding(regex_or_string))
+  end
+
+  def to_s
+    @string
+  end
+  alias :to_str :to_s
+
+  if String.method_defined?(:encoding)
+
+    private
+
+    # Encoding Exceptions:
+    #
+    # Raised by Encoding and String methods:
+    #   Encoding::UndefinedConversionError:
+    #     when a transcoding operation fails
+    #     if the String contains characters invalid for the target encoding
+    #     e.g. "\x80".encode('UTF-8','ASCII-8BIT')
+    #     vs "\x80".encode('UTF-8','ASCII-8BIT', undef: :replace, replace: '<undef>')
+    #     # => '<undef>'
+    #   Encoding::CompatibilityError
+    #     when Encoding.compatibile?(str1, str2) is nil
+    #     e.g. utf_16le_emoji_string.split("\n")
+    #     e.g. valid_unicode_string.encode(utf8_encoding) << ascii_string
+    #   Encoding::InvalidByteSequenceError:
+    #     when the string being transcoded contains a byte invalid for
+    #     either the source or target encoding
+    #     e.g. "\x80".encode('UTF-8','US-ASCII')
+    #     vs "\x80".encode('UTF-8','US-ASCII', invalid: :replace, replace: '<byte>')
+    #     # => '<byte>'
+    #   ArgumentError
+    #     when operating on a string with invalid bytes
+    #     e.g."\x80".split("\n")
+    #   TypeError
+    #     when a symbol is passed as an encoding
+    #     Encoding.find(:"UTF-8")
+    #     when calling force_encoding on an object
+    #     that doesn't respond to #to_str
+    #
+    # Raised by transcoding methods:
+    #   Encoding::ConverterNotFoundError:
+    #     when a named encoding does not correspond with a known converter
+    #     e.g. 'abc'.force_encoding('UTF-8').encode('foo')
+    #     or a converter path cannot be found
+    #     e.g. "\x80".force_encoding('ASCII-8BIT').encode('Emacs-Mule')
+    #
+    # Raised by byte <-> char conversions
+    #   RangeError: out of char range
+    #     e.g. the UTF-16LE emoji: 128169.chr
+    def matching_encoding(string)
+      string = remove_invalid_bytes(string)
+      string.encode(@encoding)
+    rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
+      string.encode(@encoding, ENCODE_UNCONVERTABLE_BYTES)
+    rescue Encoding::ConverterNotFoundError
+      string.dup.force_encoding(@encoding).encode(ENCODE_NO_CONVERTER)
+    end
+
+    # Prevents raising ArgumentError
+    if String.method_defined?(:scrub)
+      # https://github.com/ruby/ruby/blob/eeb05e8c11/doc/NEWS-2.1.0#L120-L123
+      # https://github.com/ruby/ruby/blob/v2_1_0/string.c#L8242
+      # https://github.com/hsbt/string-scrub
+      # https://github.com/rubinius/rubinius/blob/v2.5.2/kernel/common/string.rb#L1913-L1972
+      def remove_invalid_bytes(string)
+        string.scrub(REPLACE)
+      end
+    else
+      # http://stackoverflow.com/a/8711118/879854
+      # Loop over chars in a string replacing chars
+      # with invalid encoding, which is a pretty good proxy
+      # for the invalid byte sequence that causes an ArgumentError
+      def remove_invalid_bytes(string)
+        string.chars.map do |char|
+          char.valid_encoding? ? char : REPLACE
+        end.join
+      end
+    end
+
+    def detect_source_encoding(string)
+      string.encoding
+    end
+
+    def self.pick_encoding(source_a, source_b)
+      Encoding.compatible?(source_a, source_b) || Encoding.default_external
+    end
+  else
+
+    def self.pick_encoding(_source_a, _source_b)
+    end
+
+    private
+
+    def matching_encoding(string)
+      string
+    end
+
+    def detect_source_encoding(_string)
+      US_ASCII
+    end
+  end
+end

data/lib/encoded_string/spec/string_matcher.rb

@@ -0,0 +1,46 @@
+require 'rspec/matchers'
+# Special matcher for comparing encoded strings so that
+# we don't run any expectation failures through the Differ,
+# which also relies on EncodedString. Instead, confirm the
+# strings have the same bytes.
+RSpec::Matchers.define :be_identical_string do |expected|
+
+  if String.method_defined?(:encoding)
+    match do
+      expected_encoding? &&
+        actual.bytes.to_a == expected.bytes.to_a
+    end
+
+    failure_message do
+      "expected\n#{actual.inspect} (#{actual.encoding.name}) to be identical to\n"\
+        "#{expected.inspect} (#{expected.encoding.name})\n"\
+        "The exact bytes are printed below for more detail:\n"\
+        "#{actual.bytes.to_a}\n"\
+        "#{expected.bytes.to_a}\n"\
+    end
+
+    # Depends on chaining :with_same_encoding for it to
+    # check for string encoding.
+    def expected_encoding?
+      if defined?(@expect_same_encoding) && @expect_same_encoding
+        actual.encoding == expected.encoding
+      else
+        true
+      end
+    end
+  else
+    match do
+      actual.split(//) == expected.split(//)
+    end
+
+    failure_message do
+      "expected\n#{actual.inspect} to be identical to\n#{expected.inspect}\n"
+    end
+  end
+
+  chain :with_same_encoding do
+    @expect_same_encoding ||= true
+  end
+end
+RSpec::Matchers.alias_matcher :a_string_identical_to, :be_identical_string
+RSpec::Matchers.alias_matcher :be_diffed_as, :be_identical_string

data/lib/encoded_string/version.rb

@@ -0,0 +1,3 @@
+class EncodedString
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,99 @@
+--- !ruby/object:Gem::Specification
+name: encoded_string
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Benjamin Fleischer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-10-26 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  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: Extracted from rspec-support. See https://github.com/rspec/rspec-support/issues/249.
+email:
+- github@benjaminfleischer.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.md
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- encoded_string.gemspec
+- lib/encoded_string.rb
+- lib/encoded_string/spec/string_matcher.rb
+- lib/encoded_string/version.rb
+homepage: https://github.com/bf4/encoded_string
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.6
+signing_key: 
+specification_version: 4
+summary: Handle string operations without worrying about raising encoding exceptions.
+test_files: []