chars 0.2.0 → 0.2.1

data/.yardopts

@@ -1 +1 @@
---markup markdown --title 'Chars Documentation' --protected --files ChangeLog.md,LICENSE.txt
+--markup markdown --title 'Chars Documentation' --protected --quiet --files ChangeLog.md,LICENSE.txt

data/ChangeLog.md

@@ -1,3 +1,12 @@
+### 0.2.1 / 2011-06-22
+
+* Added {Chars::CharSet.[]}
+* Added {Chars::CharSet#<<}.
+* Added {Chars::CharSet#byte_to_char}.
+* Added {Chars::CharSet#char_to_byte}.
+* Added a cache of characters of the bytes within {Chars::CharSet}.
+* Use `String#each_char` to distinguish Unicode from ASCII.
+
 ### 0.2.0 / 2010-10-27
 
 * Make sure all enumerable methods in {Chars::CharSet} return an

data/README.md

@@ -83,6 +83,10 @@ set of space characters:
     Chars.space.random_string(5..10)
     # => "\r\v\n\t\n\f"
 
+## Requirements
+
+* [ruby](http://www.ruby-lang.org/) >= 1.8.7
+
 ## Install
 
     $ sudo gem install chars

data/Rakefile

@@ -2,7 +2,7 @@ require 'rubygems'
 require 'rake'
 
 begin
-  gem 'ore-tasks', '~> 0.1.2'
+  gem 'ore-tasks', '~> 0.4'
   require 'ore/tasks'
 
   Ore::Tasks.new
@@ -12,7 +12,7 @@ rescue LoadError => e
 end
 
 begin
-  gem 'rspec', '~> 2.0.0'
+  gem 'rspec', '~> 2.4'
   require 'rspec/core/rake_task'
 
   RSpec::Core::RakeTask.new
@@ -21,6 +21,7 @@ rescue LoadError => e
     abort "Please run `gem install rspec` to install RSpec."
   end
 end
+task :test => :spec
 task :default => :spec
 
 begin

data/chars.gemspec

@@ -1,10 +1,127 @@
-# -*- encoding: utf-8 -*-
+# encoding: utf-8
 
-begin
-  Ore::Specification.new do |gemspec|
-    # custom logic here
+require 'yaml'
+
+Gem::Specification.new do |gemspec|
+  files = if File.directory?('.git')
+            `git ls-files`.split($/)
+          elsif File.directory?('.hg')
+            `hg manifest`.split($/)
+          elsif File.directory?('.svn')
+            `svn ls -R`.split($/).select { |path| File.file?(path) }
+          else
+            Dir['{**/}{.*,*}'].select { |path| File.file?(path) }
+          end
+
+  filter_files = lambda { |paths|
+    case paths
+    when Array
+      (files & paths)
+    when String
+      (files & Dir[paths])
+    end
+  }
+
+  version = {
+    :file => 'lib/chars/version.rb',
+    :constant => 'Chars::VERSION'
+  }
+
+  defaults = {
+    'name' => File.basename(File.dirname(__FILE__)),
+    'files' => files,
+    'executables' => filter_files['bin/*'].map { |path| File.basename(path) },
+    'test_files' => filter_files['{test/{**/}*_test.rb,spec/{**/}*_spec.rb}'],
+    'extra_doc_files' => filter_files['*.{txt,rdoc,md,markdown,tt,textile}'],
+  }
+
+  metadata = defaults.merge(YAML.load_file('gemspec.yml'))
+
+  gemspec.name = metadata.fetch('name',defaults[:name])
+  gemspec.version = if metadata['version']
+                      metadata['version']
+                    elsif File.file?(version[:file])
+                      require File.join('.',version[:file])
+                      eval(version[:constant])
+                    end
+
+  gemspec.summary = metadata.fetch('summary',metadata['description'])
+  gemspec.description = metadata.fetch('description',metadata['summary'])
+
+  case metadata['license']
+  when Array
+    gemspec.licenses = metadata['license']
+  when String
+    gemspec.license = metadata['license']
+  end
+
+  case metadata['authors']
+  when Array
+    gemspec.authors = metadata['authors']
+  when String
+    gemspec.author = metadata['authors']
+  end
+
+  gemspec.email = metadata['email']
+  gemspec.homepage = metadata['homepage']
+
+  case metadata['require_paths']
+  when Array
+    gemspec.require_paths = metadata['require_paths']
+  when String
+    gemspec.require_path = metadata['require_paths']
+  end
+
+  gemspec.files = filter_files[metadata['files']]
+
+  gemspec.executables = metadata['executables']
+  gemspec.extensions = metadata['extensions']
+
+  if Gem::VERSION < '1.7.'
+    gemspec.default_executable = gemspec.executables.first
+  end
+
+  gemspec.test_files = filter_files[metadata['test_files']]
+
+  unless gemspec.files.include?('.document')
+    gemspec.extra_rdoc_files = metadata['extra_doc_files']
+  end
+
+  gemspec.post_install_message = metadata['post_install_message']
+  gemspec.requirements = metadata['requirements']
+
+  if gemspec.respond_to?(:required_ruby_version=)
+    gemspec.required_ruby_version = metadata['required_ruby_version']
+  end
+
+  if gemspec.respond_to?(:required_rubygems_version=)
+    gemspec.required_rubygems_version = metadata['required_ruby_version']
+  end
+
+  parse_versions = lambda { |versions|
+    case versions
+    when Array
+      versions.map { |v| v.to_s }
+    when String
+      versions.split(/,\s*/)
+    end
+  }
+
+  if metadata['dependencies']
+    metadata['dependencies'].each do |name,versions|
+      gemspec.add_dependency(name,parse_versions[versions])  
+    end
+  end
+
+  if metadata['runtime_dependencies']
+    metadata['runtime_dependencies'].each do |name,versions|
+      gemspec.add_runtime_dependency(name,parse_versions[versions])  
+    end
+  end
+
+  if metadata['development_dependencies']
+    metadata['development_dependencies'].each do |name,versions|
+      gemspec.add_development_dependency(name,parse_versions[versions])  
+    end
   end
-rescue NameError
-  STDERR.puts "The 'chars.gemspec' file requires Ore."
-  STDERR.puts "Run `gem install ore` to install Ore."
 end

data/gemspec.yml

@@ -10,7 +10,9 @@ authors: Postmodern
 email: postmodern.mod3@gmail.com
 has_yard: true
 
+required_ruby_version: ">= 1.8.7"
+
 development_dependencies:
-  ore: ~> 0.2.0
-  ore-tasks: ~> 0.1.2
-  rspec: ~> 2.0.0
+  ore-tasks: ~> 0.4
+  rspec: ~> 2.4
+  yard: ~> 0.6.1

data/lib/chars/char_set.rb

@@ -6,23 +6,67 @@ module Chars
     #
     # Creates a new CharSet object.
     #
-    # @param [Array<String, Integer, Range>] chars
+    # @param [Array<String, Integer, Enumerable>] arguments
     #   The chars for the CharSet.
     #
-    def initialize(*chars)
+    def initialize(*arguments)
       super()
 
-      merge_chars = lambda { |element|
-        if element.kind_of?(String)
-          element.each_byte(&merge_chars)
-        elsif element.kind_of?(Integer)
-          self << element
-        elsif element.kind_of?(Enumerable)
-          element.each(&merge_chars)
+      @chars = Hash.new { |hash,key| hash[key] = byte_to_char(key) }
+
+      arguments.each do |subset|
+        case subset
+        when String, Integer
+          self << subset
+        when Enumerable
+          subset.each { |char| self << char }
+        else
+          raise(ArgumentError,"arguments must be a String, Integer or Enumerable")
+        end
+      end
+    end
+    
+    #
+    # Creates a new character set.
+    #
+    # @see #initialize
+    #
+    # @since 0.2.1
+    #
+    def self.[](*arguments)
+      new(*arguments)
+    end
+
+    #
+    # Adds a character to the set.
+    #
+    # @param [String, Integer] other
+    #   The character(s) or byte to add.
+    #
+    # @return [CharSet]
+    #   The modified character set.
+    #
+    # @raise [ArgumentError]
+    #   The argument was not a {String} or {Integer}.
+    #
+    # @since 0.2.1
+    #
+    def <<(other)
+      case other
+      when String
+        other.each_char do |char|
+          byte = char_to_byte(char)
+
+          @chars[byte] = char
+          super(byte)
         end
-      }
 
-      merge_chars.call(chars)
+        return self
+      when Integer
+        super(other)
+      else
+        raise(ArgumentError,"can only append Strings and Integers")
+      end
     end
 
     alias include_byte? include?
@@ -42,8 +86,8 @@ module Chars
     #   character set.
     #
     def include_char?(char)
-      if char.respond_to?(:each_byte)
-        char.each_byte.any? { |b| include?(b) }
+      unless char.empty?
+        @chars.has_value?(char) || include_byte?(char_to_byte(char))
       else
         false
       end
@@ -56,7 +100,7 @@ module Chars
     #   All the characters within the character set.
     #
     def chars
-      map { |b| b.chr }
+      map { |byte| @chars[byte] }
     end
 
     #
@@ -75,7 +119,7 @@ module Chars
     def each_char
       return enum_for(:each_char) unless block_given?
 
-      each { |b| yield b.chr }
+      each { |byte| yield @chars[byte] }
     end
 
     #
@@ -92,7 +136,7 @@ module Chars
     #   The selected characters from the character set.
     #
     def select_chars(&block)
-      chars.select(&block)
+      each_char.select(&block)
     end
 
     #
@@ -109,7 +153,7 @@ module Chars
     #   The mapped characters of the character set.
     #
     def map_chars(&block)
-      chars.map(&block)
+      each_char.map(&block)
     end
 
     #
@@ -125,7 +169,7 @@ module Chars
     #   A random char from the character set.
     #
     def random_char
-      random_byte.chr
+      @chars[random_byte]
     end
 
     #
@@ -168,7 +212,7 @@ module Chars
     def each_random_char(n,&block)
       return enum_for(:each_random_char,n) unless block_given?
 
-      each_random_byte(n) { |b| yield b.chr }
+      each_random_byte(n) { |byte| yield @chars[byte] }
     end
 
     #
@@ -215,7 +259,7 @@ module Chars
     #   The randomly selected characters.
     #
     def random_chars(length)
-      random_bytes(length).map { |b| b.chr }
+      random_bytes(length).map { |byte| @chars[byte] }
     end
 
     #
@@ -245,7 +289,7 @@ module Chars
     #   The randomly selected non-repeating characters.
     #
     def random_distinct_chars(length)
-      random_distinct_bytes(length).map { |b| b.chr }
+      random_distinct_bytes(length).map { |byte| @chars[byte] }
     end
 
     #
@@ -264,7 +308,6 @@ module Chars
       random_distinct_chars(length).join
     end
 
-
     #
     # Finds sub-strings within given data that are made of characters within
     # the character set.
@@ -284,7 +327,9 @@ module Chars
     #   sub-strings themselves.
     #
     def strings_in(data,options={})
-      min_length = (options[:length] || 4)
+      min_length = options.fetch(:length,4)
+
+      return found if data.length < min_length
 
       if options[:offsets]
         found = {}
@@ -298,15 +343,13 @@ module Chars
         }
       end
 
-      return found if data.length < min_length
-
       index = 0
 
       while index <= (data.length - min_length)
-        if self === data[index...(index + min_length)]
+        if self === data[index,min_length]
           sub_index = (index + min_length)
 
-          while self.include_char?(data[sub_index..sub_index])
+          while self.include_char?(data[sub_index,1])
             sub_index += 1
           end
 
@@ -324,14 +367,16 @@ module Chars
     # Creates a new CharSet object by unioning the character set with
     # another character set.
     #
-    # @param [CharSet, Array, Range] other_set
+    # @param [CharSet, Array, Range] set
     #   The other character set to union with.
     #
     # @return [CharSet]
     #   The unioned character sets.
     #
-    def |(other_set)
-      super(CharSet.new(other_set))
+    def |(set)
+      set = CharSet.new(set) unless set.kind_of?(CharSet)
+
+      return super(set)
     end
 
     alias + |
@@ -340,7 +385,7 @@ module Chars
     # Compares the bytes within a given string with the bytes of the
     # character set.
     #
-    # @param [String] string
+    # @param [String, Enumerable] string
     #   The string to compare with the character set.
     #
     # @return [Boolean]
@@ -351,9 +396,19 @@ module Chars
     #   Chars.alpha === "hello"
     #   # => true
     #
-    def ===(string)
-      if string.respond_to?(:each_byte)
-        string.each_byte.all? { |b| include?(b) }
+    def ===(other)
+      case other
+      when String
+        other.each_char.all? { |char| include_char?(char) }
+      when Enumerable
+        other.all? do |element|
+          case element
+          when String
+            include_char?(element)
+          when Integer
+            include_byte?(element)
+          end
+        end
       else
         false
       end
@@ -368,19 +423,83 @@ module Chars
     #   The inspected character set.
     #
     def inspect
-      "#<#{self.class.name}: {" + map { |b|
-        case b
+      "#<#{self.class.name}: {" + map { |byte|
+        case byte
         when (0x07..0x0d), (0x20..0x7e)
-          b.chr.dump
+          @chars[byte].dump
         when 0x00
           # sly hack to make char-sets more friendly
           # to us C programmers
           '"\0"'
         else
-          "0x%02x" % b
+          "0x%02x" % byte
         end
       }.join(', ') + "}>"
     end
 
+    protected
+
+    if RUBY_VERSION > '1.9.'
+      #
+      # Converts a byte to a character.
+      #
+      # @param [Integer] byte
+      #   The byte to convert.
+      #
+      # @return [String]
+      #   The character.
+      #
+      # @since 0.2.1
+      #
+      def byte_to_char(byte)
+        byte.chr(Encoding::UTF_8)
+      end
+
+      #
+      # Converts a character to a byte.
+      #
+      # @param [String] char
+      #   The character to convert.
+      #
+      # @return [Integer]
+      #   The byte.
+      #
+      # @since 0.2.1
+      #
+      def char_to_byte(char)
+        char.ord
+      end
+    else
+      #
+      # Converts a byte to a character.
+      #
+      # @param [Integer] byte
+      #   The byte to convert.
+      #
+      # @return [String]
+      #   The character.
+      #
+      # @since 0.2.1
+      #
+      def byte_to_char(byte)
+        byte.chr
+      end
+
+      #
+      # Converts a character to a byte.
+      #
+      # @param [String] char
+      #   The character to convert.
+      #
+      # @return [Integer]
+      #   The byte.
+      #
+      # @since 0.2.1
+      #
+      def char_to_byte(char)
+        char[0]
+      end
+    end
+
   end
 end