kebab 1.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 87bf31a3fd0eae739657da5215e01e9997814e36fac547bdad9a3b82b4a7cbb5
+  data.tar.gz: ba4be2bf8b9d9f531c2e89cc378fb77bb46c2bafd1238938750d6ca703fd8e72
+SHA512:
+  metadata.gz: fecfbf09cebc692a71693ccf8e1153135164f0dc353338dd262a2e1ce459fe706d95567bf1f7d65f9d0ef09d4c79df4c345c4c62572b2b4187686604ea5a39f0
+  data.tar.gz: 4ac136a1bdda3d4a7dfb986a75580c2b06882799aa8f6f7b20c8573ff3394e950c610ec9bafc0f8729b2b666bb4bda1cc5b73323730ccd57ef14fc3947e7b332

data/Changelog.md

@@ -0,0 +1,99 @@
+# Kebab Changelog
+
+## 1.0.2
+
+* Fix regression in ActiveSupport UTF8 proxy.
+
+## 1.0.1
+
+* Fix error with tidy_bytes on Rubinius.
+* Simplify Active Support UTF8 proxy.
+* Fix `allow_bangs` argument to to_ruby_method being silently ignored.
+* Raise error when generating an impossible Ruby method name.
+
+## 1.0.0
+
+* Adopt semantic versioning.
+* When using Active Support, require 3.2 or greater.
+* Require Ruby 2.0 or greater.
+* Fix Ruby warnings.
+* Improve support for Ukrainian.
+* Support some additional punctuation characters used by Chinese and others.
+* Add Polish spec.
+* Use native Unicode normalization on Ruby 2.2 in UTF8::DumbProxy.
+* Invoke Ruby-native upcase/downcase in UTF8::DumbProxy.
+* Proxy `tidy_bytes` method to Active Support when possible.
+* Remove SlugString constant.
+
+## 0.3.11
+
+*  Add support for Vietnamese.
+
+## 0.3.10
+
+*  Fix Macedonian "S/S". Don't `include JRuby` unnecessarily.
+
+## 0.3.9
+
+* Add missing Greek vowels with diaeresis.
+
+## 0.3.8
+
+* Correct and improve Macedonian support.
+
+## 0.3.7
+
+* Fix compatibility with Ruby 1.8.7.
+* Add Swedish support.
+
+## 0.3.6
+
+* Allow multiple transliterators.
+* Add Greek support.
+
+## 0.3.5
+
+* Don't strip underscores from identifiers.
+
+## 0.3.4
+
+* Add Romanian support.
+
+## 0.3.3
+
+* Add Norwegian support.
+
+## 0.3.2
+
+* Improve Macedonian support.
+
+## 0.3.1
+
+* Small fixes to Cyrillic.
+
+## 0.3.0
+
+* Cyrillic support.
+* Improve support for various Unicode spaces and dashes.
+
+## 0.2.2
+
+* Fix for "smart" quote handling.
+
+## 0.2.1
+
+* Implement #empty? for compatiblity with Active Support's #blank?.
+
+## 0.2.0
+
+* Add support for Danish.
+* Add method to generate Ruby identifiers.
+* Improve performance.
+
+## 0.1.1
+
+* Add support for Serbian.
+
+## 0.1.0
+
+* Initial extraction from FriendlyId.

data/MIT-LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2010 Norman Clarke
+
+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 +1,26 @@
+# Kebab
+
+The original is [here](http://github.com/norman/kebab). You should probably
+use that unless you hate monkey patching as much as I do.
+
+## Copyright
+
+Copyright (c) 2010-2013 Norman Clarke
+
+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/Rakefile

@@ -0,0 +1,34 @@
+require "rubygems"
+require "rake/testtask"
+require "rake/clean"
+require "rubygems/package_task"
+
+task :default => :spec
+task :test    => :spec
+
+CLEAN << "pkg" << "doc" << "coverage" << ".yardoc"
+
+begin
+  require "yard"
+  YARD::Rake::YardocTask.new do |t|
+    t.options = ["--output-dir=doc"]
+  end
+rescue LoadError
+end
+
+begin
+  desc "Run SimpleCov"
+  task :coverage do
+    ENV["COV"] = "true"
+    Rake::Task["spec"].execute
+  end
+rescue LoadError
+end
+
+gemspec = File.expand_path("../kebab.gemspec", __FILE__)
+if File.exist? gemspec
+  Gem::PackageTask.new(eval(File.read(gemspec))) { |pkg| }
+end
+
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec)

data/lib/kebab.rb

@@ -0,0 +1,18 @@
+module Kebab
+  def self.jruby15?
+    JRUBY_VERSION >= "1.5" rescue false
+  end
+
+  refine String do
+    def to_identifier
+      Kebab::Identifier.new self
+    end
+
+    alias to_slug to_identifier
+    alias skewer to_identifier
+  end
+end
+
+require "kebab/transliterator/base"
+require "kebab/utf8/proxy"
+require "kebab/identifier"

data/lib/kebab/identifier.rb

@@ -0,0 +1,294 @@
+# encoding: utf-8
+module Kebab
+
+  # Codepoints for characters that will be deleted by +#word_chars!+.
+  STRIPPABLE = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 14, 15, 16, 17, 18, 19,
+    20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39,
+    40, 41, 42, 43, 44, 45, 46, 47, 58, 59, 60, 61, 62, 63, 64, 91, 92, 93, 94,
+    96, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136,
+    137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151,
+    152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167,
+    168, 169, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 182, 183, 184,
+    185, 187, 188, 189, 190, 191, 215, 247, 8203, 8204, 8205, 8239, 65279]
+
+  # This class provides some string-manipulation methods specific to slugs.
+  #
+  # Note that this class includes many "bang methods" such as {#clean!} and
+  # {#normalize!} that perform actions on the string in-place. Each of these
+  # methods has a corresponding "bangless" method (i.e., +Identifier#clean!+
+  # and +Identifier#clean+) which does not appear in the documentation because
+  # it is generated dynamically.
+  #
+  # All of the bang methods return an instance of String, while the bangless
+  # versions return an instance of Kebab::Identifier, so that calls to methods
+  # specific to this class can be chained:
+  #
+  #   string = Identifier.new("hello world")
+  #   string.with_separators! # => "hello-world"
+  #   string.with_separators  # => <Kebab::Identifier:0x000001013e1590 @wrapped_string="hello-world">
+  #
+  # @see http://www.utf8-chartable.de/unicode-utf8-table.pl?utf8=dec Unicode character table
+  class Identifier
+    using Kebab
+
+    Error = Class.new(StandardError)
+
+    attr_reader :wrapped_string
+    alias to_s wrapped_string
+
+    @@utf8_proxy = if Kebab.jruby15?
+      UTF8::JavaProxy
+    elsif defined? Unicode::VERSION
+      UTF8::UnicodeProxy
+    elsif defined? ActiveSupport
+      UTF8::ActiveSupportProxy
+    else
+      UTF8::DumbProxy
+    end
+
+    # Return the proxy used for UTF-8 support.
+    # @see Kebab::UTF8::Proxy
+    def self.utf8_proxy
+      @@utf8_proxy
+    end
+
+    # Set a proxy object used for UTF-8 support.
+    # @see Kebab::UTF8::Proxy
+    def self.utf8_proxy=(obj)
+      @@utf8_proxy = obj
+    end
+
+    def method_missing(symbol, *args, &block)
+      @wrapped_string.__send__(symbol, *args, &block)
+    end
+
+    # @param string [#to_s] The string to use as the basis of the Identifier.
+    def initialize(string)
+      @wrapped_string = string.to_s
+      tidy_bytes!
+      normalize_utf8!
+    end
+
+    def ==(value)
+      @wrapped_string.to_s == value.to_s
+    end
+
+    def eql?(value)
+      @wrapped_string == value
+    end
+
+    def empty?
+      # included to make this class :respond_to? :empty for compatibility with Active Support's
+      # #blank?
+      @wrapped_string.empty?
+    end
+
+    # Approximate an ASCII string. This works only for Western strings using
+    # characters that are Roman-alphabet characters + diacritics. Non-letter
+    # characters are left unmodified.
+    #
+    #   string = Identifier.new "Łódź
+    #   string.transliterate                 # => "Lodz, Poland"
+    #   string = Identifier.new "日本"
+    #   string.transliterate                 # => "日本"
+    #
+    # You can pass any key(s) from +Characters.approximations+ as arguments. This allows
+    # for contextual approximations. Various languages are supported, you can see which ones
+    # by looking at the source of {Kebab::Transliterator::Base}.
+    #
+    #   string = Identifier.new "Jürgen Müller"
+    #   string.transliterate                 # => "Jurgen Muller"
+    #   string.transliterate :german         # => "Juergen Mueller"
+    #   string = Identifier.new "¡Feliz año!"
+    #   string.transliterate                 # => "¡Feliz ano!"
+    #   string.transliterate :spanish        # => "¡Feliz anio!"
+    #
+    # The approximations are an array, which you can modify if you choose:
+    #
+    #   # Make Spanish use "nh" rather than "nn"
+    #   Kebab::Transliterator::Spanish::APPROXIMATIONS["ñ"] = "nh"
+    #
+    # Notice that this method does not simply convert to ASCII; if you want
+    # to remove non-ASCII characters such as "¡" and "¿", use {#to_ascii!}:
+    #
+    #   string.transliterate!(:spanish)       # => "¡Feliz anio!"
+    #   string.transliterate!                 # => "¡Feliz anio!"
+    #
+    # @param *args <Symbol>
+    # @return String
+    def transliterate!(*kinds)
+      kinds.compact!
+      kinds = [:latin] if kinds.empty?
+      kinds.each do |kind|
+        transliterator = Transliterator.get(kind).instance
+        @wrapped_string = transliterator.transliterate(@wrapped_string)
+      end
+      @wrapped_string
+    end
+
+    # Converts dashes to spaces, removes leading and trailing spaces, and
+    # replaces multiple whitespace characters with a single space.
+    # @return String
+    def clean!
+      @wrapped_string = @wrapped_string.gsub("-", " ").squeeze(" ").strip
+    end
+
+    # Remove any non-word characters. For this library's purposes, this means
+    # anything other than letters, numbers, spaces, newlines and linefeeds.
+    # @return String
+    def word_chars!
+      @wrapped_string = (unpack("U*") - Kebab::STRIPPABLE).pack("U*")
+    end
+
+    # Normalize the string for use as a URL slug. Note that in this context,
+    # +normalize+ means, strip, remove non-letters/numbers, downcasing,
+    # truncating to 255 bytes and converting whitespace to dashes.
+    # @param Options
+    # @return String
+    def normalize!(options = nil)
+      options = default_normalize_options.merge(options || {})
+
+      if translit_option = options[:transliterate]
+        if translit_option != true
+          transliterate!(*translit_option)
+        else
+          transliterate!(*options[:transliterations])
+        end
+      end
+      to_ascii! if options[:to_ascii]
+      clean!
+      word_chars!
+      clean!
+      downcase!
+      truncate_bytes!(options[:max_length])
+      with_separators!(options[:separator])
+    end
+
+    # Normalize a string so that it can safely be used as a Ruby method name.
+    def to_ruby_method!(allow_bangs = true)
+      leader, trailer = @wrapped_string.strip.scan(/\A(.+)(.)\z/).flatten
+      leader          = leader.to_s
+      trailer         = trailer.to_s
+      if allow_bangs
+        trailer.downcase!
+        trailer.gsub!(/[^a-z0-9!=\\?]/, '')
+      else
+        trailer.downcase!
+        trailer.gsub!(/[^a-z0-9]/, '')
+      end
+      id = leader.to_identifier
+      id.transliterate!
+      id.to_ascii!
+      id.clean!
+      id.word_chars!
+      id.clean!
+      @wrapped_string = id.to_s + trailer
+      if @wrapped_string == ""
+        raise Error, "Input generates impossible Ruby method name"
+      end
+      with_separators!("_")
+    end
+
+    # Delete any non-ascii characters.
+    # @return String
+    def to_ascii!
+      @wrapped_string = @wrapped_string.gsub(/[^\x00-\x7f]/u, '')
+    end
+
+    # Truncate the string to +max+ characters.
+    # @example
+    #   "üéøá".to_identifier.truncate(3) #=> "üéø"
+    # @return String
+    def truncate!(max)
+      @wrapped_string = unpack("U*")[0...max].pack("U*")
+    end
+
+    # Truncate the string to +max+ bytes. This can be useful for ensuring that
+    # a UTF-8 string will always fit into a database column with a certain max
+    # byte length. The resulting string may be less than +max+ if the string must
+    # be truncated at a multibyte character boundary.
+    # @example
+    #   "üéøá".to_identifier.truncate_bytes(3) #=> "ü"
+    # @return String
+    def truncate_bytes!(max)
+      return @wrapped_string if @wrapped_string.bytesize <= max
+      curr = 0
+      new = []
+      unpack("U*").each do |char|
+        break if curr > max
+        char = [char].pack("U")
+        curr += char.bytesize
+        if curr <= max
+          new << char
+        end
+      end
+      @wrapped_string = new.join
+    end
+
+    # Replaces whitespace with dashes ("-").
+    # @return String
+    def with_separators!(char = "-")
+      @wrapped_string = @wrapped_string.gsub(/\s/u, char)
+    end
+
+    # Perform UTF-8 sensitive upcasing.
+    # @return String
+    def upcase!
+      @wrapped_string = @@utf8_proxy.upcase(@wrapped_string)
+    end
+
+    # Perform UTF-8 sensitive downcasing.
+    # @return String
+    def downcase!
+      @wrapped_string = @@utf8_proxy.downcase(@wrapped_string)
+    end
+
+    # Perform Unicode composition on the wrapped string.
+    # @return String
+    def normalize_utf8!
+      @wrapped_string = @@utf8_proxy.normalize_utf8(@wrapped_string)
+    end
+
+    # Attempt to convert characters encoded using CP1252 and IS0-8859-1 to
+    # UTF-8.
+    # @return String
+    def tidy_bytes!
+      @wrapped_string = @@utf8_proxy.tidy_bytes(@wrapped_string)
+    end
+
+    %w[transliterate clean downcase word_chars normalize normalize_utf8
+      tidy_bytes to_ascii to_ruby_method truncate truncate_bytes upcase
+      with_separators].each do |method|
+      class_eval(<<-EOM, __FILE__, __LINE__ + 1)
+        def #{method}(*args)
+          send_to_new_instance(:#{method}!, *args)
+        end
+      EOM
+    end
+
+    def to_identifier
+      self
+    end
+
+    # The default options for {#normalize!}. Override to set your own defaults.
+    def default_normalize_options
+      {:transliterate => true, :max_length => 255, :separator => "-"}
+    end
+
+    alias approximate_ascii transliterate
+    alias approximate_ascii! transliterate!
+    alias with_dashes with_separators
+    alias with_dashes! with_separators!
+    alias to_slug to_identifier
+
+    private
+
+    # Used as the basis of the bangless methods.
+    def send_to_new_instance(*args)
+      id = Identifier.allocate
+      id.instance_variable_set :@wrapped_string, to_s
+      id.send(*args)
+      id
+    end
+  end
+end