symbolify 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9e0fa391ee606b11f9c99f4f33e9656f08692534
-  data.tar.gz: df940cb466c10f7894ca7a582c1dd87c6998a8a7
+  metadata.gz: 86f1b09386497498d42a5bc13c1bd0eada8558e1
+  data.tar.gz: 40d18cd726a05c7b8374478dfef7fe1f0269b171
 SHA512:
-  metadata.gz: f970bd71fb817eb2205f45f46b65cfdb6dbead36e302eccc2e15f6f138da921192744ba0800c77fcb379d3e9b3972b3727b3dcb49f9a9930f733ae944f46c1fb
-  data.tar.gz: 73ca12130eafeab368588ea617a45c6cf4c1fc27a2d1a7f4439ab99bc8d1792f08175ae403a76c5304759cfd20e48a586eaf8ca506fe233266da9fa560ee99fa
+  metadata.gz: 5ad1e514f138cc49b80c4efb55d5fdfb1181d13a5f1c082f0b65eacdb980014f62c209d4cba852ee948cb75586638ed09e69664aad7f04f94090005c4783b825
+  data.tar.gz: 32296309c2cc61c305997c61cfc038a26f25c8d8480057ea6c9589adcb861bcefefe85e1685118c3d13f3509274c2767c99c6870f2479488025fdb631193e158

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 ## CHANGELOG
 
+### 1.1.0
+
+* Add special characters (U+FFF9 - U+FFFC)
+* Non-control separators return ⏎
+* Ensure that only first character/codepoint will be returned
+
 ### 1.0.0
 
 * Import from unibits gem

data/README.md

@@ -25,6 +25,8 @@ puts Symbolify.symbolify "\u{200F}"   # RLM
 puts Symbolify.symbolify "\u{2067}"   # RLI
 puts Symbolify.symbolify "\u{0300}"   # ◌̀
 puts Symbolify.symbolify " "   # ] [
+puts Symbolify.symbolify "\u{FFF9}"   # IAA
+puts Symbolify.symbolify "\u{FFFC}"   # OBJ
 puts Symbolify.symbolify "\u{E0020}"   # TAG ␠
 puts Symbolify.symbolify "\u{E01D7}"   # VS232
 puts Symbolify.symbolify "\u{E0000}"   # n/a

data/lib/symbolify.rb

@@ -96,6 +96,14 @@ module Symbolify
     0x2069 => "PDI",
   }.freeze
 
+  # no official aliases at the time of adding
+  SPECIALS = {
+    0xFFF9 => "IAA",
+    0xFFFA => "IAS",
+    0xFFFB => "IAT",
+    0xFFFC => "OBJ",
+  }.freeze
+
   TAG_NAMES = {
     0xE0001 => "LANG TAG",
     0xE0020 => "TAG ␠",
@@ -530,6 +538,7 @@ module Symbolify
 
     char = char.dup.encode("UTF-8")
     ord = char.ord
+    char = char[0]
 
     if char_info.delete?
       char = CONTROL_DELETE_SYMBOL
@@ -545,10 +554,14 @@ module Symbolify
       char = "◌" + char
     elsif char_info.category == "Me"
       char = " " + char
+    elsif char_info.separator?
+      char = "⏎"
     elsif char_info.blank?
       char = "]" + char + "["
     elsif TAG_NAMES.key?(ord)
       char = TAG_NAMES[ord]
+    elsif SPECIALS.key?(ord)
+      char = SPECIALS[ord]
     end
 
     char
@@ -559,6 +572,7 @@ module Symbolify
 
     ord = char.ord
     encoding = char_info.encoding
+    char = char[0]
     no_converter = !!(NO_UTF8_CONVERTER =~ encoding.name)
     treat_char_unconverted = false
 
@@ -588,6 +602,8 @@ module Symbolify
   end
 
   def self.ascii(char, char_info = AsciiCharacteristics.new(char))
+    char = char[0]
+
     if char_info.delete?
       char = CONTROL_DELETE_SYMBOL
     elsif char_info.c0?
@@ -600,10 +616,10 @@ module Symbolify
   end
 
   def self.binary(char, _ = nil)
-    dump(char)
+    dump(char[0])
   end
 
   def self.dump(char)
-    char.dump
+    char[0].dump
   end
 end

data/lib/symbolify/version.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module Symbolify
-  VERSION = "1.0.0".freeze
+  VERSION = "1.1.0".freeze
   UNICODE_VERSION = "9.0.0".freeze
 end
 

data/spec/symbolify_spec.rb

@@ -6,6 +6,10 @@ describe Symbolify do
     it "will show replacement character for invalid characters" do
       assert_equal "�", Symbolify.symbolify("\x80")
     end
+
+    it "will only return first character" do
+      assert_equal "a", Symbolify.symbolify("ab")
+    end
   end
 
   describe ".unicode" do
@@ -37,10 +41,24 @@ describe Symbolify do
       assert_equal " \u{20E3}", Symbolify.symbolify("\u{20E3}")
     end
 
+    it "replaces uncommon newline characters" do
+      assert_equal "⏎", Symbolify.symbolify("\u{2028}")
+      assert_equal "⏎", Symbolify.symbolify("\u{2029}")
+    end
+
     it "wraps blanks" do
       assert_equal "] [", Symbolify.symbolify(" ")
     end
 
+    it "replaces annotation characters" do
+      assert_equal "IAA", Symbolify.symbolify("\u{FFF9}")
+      assert_equal "IAS", Symbolify.symbolify("\u{FFFA}")
+    end
+
+    it "replaces object replacement character" do
+      assert_equal "OBJ", Symbolify.symbolify("\u{FFFC}")
+    end
+
     it "replaces tags" do
       assert_equal "TAG ␠", Symbolify.symbolify("\u{E0020}")
     end

data/symbolify.gemspec

@@ -18,5 +18,5 @@ Gem::Specification.new do |gem|
   gem.require_paths = ["lib"]
 
   gem.required_ruby_version = "~> 2.0"
-  gem.add_dependency "characteristics", "~> 0.5"
+  gem.add_dependency "characteristics", "~> 0.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: symbolify
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-03-25 00:00:00.000000000 Z
+date: 2017-03-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: characteristics
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.5'
+        version: '0.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.5'
+        version: '0.6'
 description: Safely print all codepoints from Unicode and single-byte encodings.
 email:
 - mail@janlelis.de