character_set 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: d2e4067480e00d5d03db2bbd1ee4f222f936e0f2
-  data.tar.gz: 0e4c0bc6cf393b1a81dc368ee86f94d0dea10a82
+SHA256:
+  metadata.gz: e44c152c023f9b427cf8cf28f78bd77b611ce0dea7d480683dc56a834d022ce7
+  data.tar.gz: d0c2416e610779e44f3d2f1e961c03f2315da6f141b200ddfc48ed34742d1c8b
 SHA512:
-  metadata.gz: d9150168393512190a496ed10af91a1eaa49eb2a01d3fb623de9586eb4fbd354dfea172bf6174ab180f6620ae6ca13a01f94ec26a95fbf118f48f611b4d7acd7
-  data.tar.gz: cb4b067fae5c8a550267a0dcef7708b30d36598b2ed18981711ad9b4a67b23cbf444270f7006d160e50f151ba32fe3402108429d415f7adbfb0be9160fedfda7
+  metadata.gz: 13aec8dd0c27b280382b75eec1f18998330fe92711c185af93d34d8414ef5585d5f231148371d7960c6b0646dc7a675afdc500f4c5bfab7aa88a88ec07741a1f
+  data.tar.gz: 39eaf06a7fe1c87ee4112693b157f8cea2b2130fa32c82259c3f1625b22807e3e3f3e1fe994055330fbf3a639bc64306b98c8031522e88d548217d08dabebb3b

data/CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
+and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
+
+## [1.1.0] - 2018-09-21
+
+### Added
+- added option to reference a predefined set via Symbol in `String` extension methods
+- added predefined sets `::ascii_alnum` and `::ascii_letters`
+
+## [1.0.0] - 2018-09-02
+Initial release.

data/README.md

@@ -13,6 +13,16 @@ Many parts can be used independently, e.g.:
 
 ## Usage
 
+### Usage examples
+
+```ruby
+CharacterSet.url_query.cover?('?a=(b$c;)') # => true
+
+CharacterSet.non_ascii.delete_in!(string)
+
+CharacterSet.emoji.sample(5) # => ["⛷", "👈", "🌞", "♑", "⛈"]
+```
+
 ### Parse/Initialize
 
 These all produce a `CharacterSet` containing `a`, `b` and `c`:
@@ -27,41 +37,25 @@ CharacterSet.parse('[a-c]')
 CharacterSet.parse('\U00000061-\U00000063')
 ```
 
-If the gems [`regexp_parser`](https://github.com/ammar/regexp_parser) and [`regexp_property_values`](https://github.com/janosch-x/regexp_property_values) are installed, `::of_regexp` and `::of_property` can also be used. `::of_regexp` can handle intersections, negations, and set nesting:
+If the gems [`regexp_parser`](https://github.com/ammar/regexp_parser) and [`regexp_property_values`](https://github.com/janosch-x/regexp_property_values) are installed, `::of_regexp` and `::of_property` can also be used. `::of_regexp` can handle intersections, negations, and set nesting.
 
 ```ruby
-# are there any non-digit ascii chars classified as emoji?
-set = CharacterSet.of_regexp(/[\D&&[:ascii:]&&\p{emoji}]/)
-
-# ... of course there are!
-set.to_a(stringify: true) # => ["#", "*"]
+CharacterSet.of_property('Thai') # => #<CharacterSet (size: 86)>
 
-# with the core extension:
 require 'character_set/core_ext/regexp_ext'
-/[a-e&&[^c]]/.character_set # => CharacterSet['a', 'b', 'd', 'e']
+
+/[\D&&[:ascii:]&&\p{emoji}]/.character_set.size # => 2
 ```
 
-### Common utility sets
+### Predefined utility sets
+
+`ascii`, `ascii_alnum`, `ascii_letters`, `bmp`, `crypt`, `emoji`, `newline`, `unicode`, `url_fragment`, `url_host`, `url_path`, `url_query`, `whitespace`
 
 ```ruby
-CharacterSet.ascii
-CharacterSet.bmp
-CharacterSet.crypt
-CharacterSet.emoji
-CharacterSet.newline
-CharacterSet.unicode
-CharacterSet.url_fragment
-CharacterSet.url_host
-CharacterSet.url_path
-CharacterSet.url_query
-CharacterSet.whitespace
-
-# e.g.
-CharacterSet.url_query.cover?('?a=(b$c;)') # => true
-CharacterSet.emoji.sample(5) # => ["⛷", "👈", "🌞", "♑", "⛈"]
+CharacterSet.ascii # => #<CharacterSet (size: 128)>
 
 # all can be prefixed with `non_`, e.g.
-CharacterSet.non_ascii.delete_in(string)
+CharacterSet.non_ascii
 ```
 
 ### Interact with Strings
@@ -95,9 +89,12 @@ There is also a core extension for String interaction.
 require 'character_set/core_ext/string_ext'
 
 "a\rb".character_set & CharacterSet.newline # => CharacterSet["\r"]
-"a\rb".uses_character_set?(CharacterSet.emoji) # => false
+"a\rb".uses_character_set?(CharacterSet['ä', 'ö', 'ü']) # => false
 "a\rb".covered_by_character_set?(CharacterSet.newline) # => false
-"a\rb".delete_character_set(CharacterSet.newline) # => 'ab'
+
+# predefined sets can also be referenced via Symbols
+"a\rb".covered_by_character_set?(:ascii) # => true
+"a\rb".delete_character_set(:newline) # => 'ab'
 # etc.
 ```
 

data/character_set.gemspec

@@ -28,7 +28,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'bundler', '~> 1.16'
   s.add_development_dependency 'rake', '~> 10.0'
   s.add_development_dependency 'rake-compiler', '~> 1.0'
-  s.add_development_dependency 'regexp_parser', '~> 1.0'
+  s.add_development_dependency 'regexp_parser', '~> 1.1'
   s.add_development_dependency 'regexp_property_values', '~> 0.3.2'
   s.add_development_dependency 'rspec', '~> 3.0'
 end

data/lib/character_set.rb

@@ -1,7 +1,7 @@
 require 'character_set/character'
-require 'character_set/common_sets'
 require 'character_set/expression_converter'
 require 'character_set/parser'
+require 'character_set/predefined_sets'
 require 'character_set/set_method_adapters'
 require 'character_set/shared_methods'
 require 'character_set/version'
@@ -17,5 +17,5 @@ class CharacterSet
   prepend SetMethodAdapters
   include Enumerable
   include SharedMethods
-  extend CommonSets
+  extend PredefinedSets
 end

data/lib/character_set/core_ext/string_ext.rb

@@ -5,28 +5,23 @@ class CharacterSet
         CharacterSet.of(self)
       end
 
-      def covered_by_character_set?(set)
-        set.cover?(self)
-      end
-
-      def uses_character_set?(set)
-        set.used_by?(self)
-      end
-
-      def delete_character_set(set)
-        set.delete_in(self)
-      end
-
-      def delete_character_set!(set)
-        set.delete_in!(self)
-      end
-
-      def keep_character_set(set)
-        set.keep_in(self)
-      end
-
-      def keep_character_set!(set)
-        set.keep_in!(self)
+      {
+        covered_by_character_set?: :cover?,
+        delete_character_set:      :delete_in,
+        delete_character_set!:     :delete_in!,
+        keep_character_set:        :keep_in,
+        keep_character_set!:       :keep_in!,
+        uses_character_set?:       :used_by?,
+      }.each do |string_method, set_method|
+        class_eval <<-RUBY, __FILE__, __LINE__ + 1
+          def #{string_method}(arg)
+            if arg.instance_of?(Symbol)
+              CharacterSet.__send__(arg).#{set_method}(self)
+            else
+              arg.#{set_method}(self)
+            end
+          end
+        RUBY
       end
     end
   end

data/lib/character_set/{common_sets.rb → predefined_sets.rb}

@@ -1,9 +1,17 @@
 class CharacterSet
-  module CommonSets
+  module PredefinedSets
     def ascii
       @ascii ||= from_ranges(0..0x7F).freeze
     end
 
+    def ascii_alnum
+      @ascii_alnum ||= from_ranges(0x30..0x39, 0x41..0x5A, 0x61..0x7A).freeze
+    end
+
+    def ascii_letters
+      @ascii_letters ||= from_ranges(0x41..0x5A, 0x61..0x7A).freeze
+    end
+
     # basic multilingual plane
     def bmp
       @bmp ||= from_ranges(0..0xD7FF, 0xE000..0xFFFF).freeze

data/lib/character_set/pure.rb

@@ -8,6 +8,6 @@ class CharacterSet
     prepend CharacterSet::RubyFallback
     prepend CharacterSet::SetMethodAdapters
     include CharacterSet::SharedMethods
-    extend CharacterSet::CommonSets
+    extend CharacterSet::PredefinedSets
   end
 end

data/lib/character_set/version.rb

@@ -1,3 +1,3 @@
 class CharacterSet
-  VERSION = '1.0.0'
+  VERSION = '1.1.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: character_set
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Janosch Müller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-09-02 00:00:00.000000000 Z
+date: 2018-09-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: range_compressor
@@ -86,14 +86,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '1.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: regexp_property_values
   requirement: !ruby/object:Gem::Requirement
@@ -134,6 +134,7 @@ files:
 - ".rspec"
 - ".travis.yml"
 - BENCHMARK.md
+- CHANGELOG.md
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -151,12 +152,12 @@ files:
 - ext/character_set/unicode_casefold_table.h
 - lib/character_set.rb
 - lib/character_set/character.rb
-- lib/character_set/common_sets.rb
 - lib/character_set/core_ext.rb
 - lib/character_set/core_ext/regexp_ext.rb
 - lib/character_set/core_ext/string_ext.rb
 - lib/character_set/expression_converter.rb
 - lib/character_set/parser.rb
+- lib/character_set/predefined_sets.rb
 - lib/character_set/pure.rb
 - lib/character_set/ruby_fallback.rb
 - lib/character_set/ruby_fallback/character_set_methods.rb
@@ -186,7 +187,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: Build, read, write and compare sets of Unicode codepoints.