unicode-types 1.1.1 → 1.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0f30aed70893363dcf284d94fb14e78a7b97cc6e
-  data.tar.gz: 8c4d3ade7a56cd84bbe7e2637fd1a68477f2655a
+  metadata.gz: e9488ebcd84e5ca6243a189ba0424afa3793c565
+  data.tar.gz: 2df94931f98452e6d948f5bf9fe300d752ddc9a4
 SHA512:
-  metadata.gz: 293afcc57dfba9325c74d2cf85fd6bf164140712c47eb90224ff3d9ddd9fc14e5c0d92e197f82957356505756bcf710555235ab97e2a7a2680a10e43239483d6
-  data.tar.gz: c8984c80a34da22f5d4662961974a0616d5c814b7a4f01f8be18a07df892d59c5288fdc38d414d60b2f5db46ced53c4271c1791da4663c3accac91ed279ae7e0
+  metadata.gz: 2589173a6bbb02749b23c7f82fa136c7c7380a552095e08aebd4479ad0d07ff0e8aa92bdfa671960103ea359b9b1efa3a59637cf943588dbad2cd6bc102339b5
+  data.tar.gz: af68eea885a8bc4b22e6eff8863c5b9f2c93e888feda6dd352dfe895220ed31e8c27d96757aa6b8f580ae60b1b2f964b66a3d1ea99f3fc3e1fdf6f2f6c41887c

data/CHANGELOG.md

@@ -1,8 +1,13 @@
 ## CHANGELOG
 
+### 1.1.2
+
+* Fix that surrogates were detected in UTF-8 (regression of 1.1.1)
+* Fix bug in index compression scheme
+
 ### 1.1.1
 
-* Fix bug that prevented non-UTF-8 encodings from workin
+* Fix bug that prevented non-UTF-8 encodings from working
 
 ### 1.1.0
 

data/lib/unicode/types.rb

@@ -14,8 +14,7 @@ module Unicode
 
     def self.type(char)
       require_relative 'types/index' unless defined? ::Unicode::Types::INDEX
-      codepoint_depth_offset = char.ord or
-          raise(ArgumentError, "Unicode::Types.type must be given a valid char")
+      codepoint_depth_offset = get_codepoint_value(char)
       index_or_value = INDEX[:TYPES]
       [0x10000, 0x1000, 0x100, 0x10].each{ |depth|
         index_or_value         = index_or_value[codepoint_depth_offset / depth]
@@ -31,5 +30,28 @@ module Unicode
       require_relative 'types/index' unless defined? ::Unicode::Types::INDEX
       INDEX[:TYPE_NAMES].dup
     end
+
+    def self.get_codepoint_value(char)
+      ord = nil
+
+      if char.valid_encoding?
+        ord = char.ord
+      elsif char.encoding.name == "UTF-8"
+        begin
+          ord = char.unpack("U*")[0]
+        rescue ArgumentError
+        end
+      end
+
+      if ord
+        ord
+      else
+        raise(ArgumentError, "Unicode::Types.type must be given a valid char")
+      end
+    end
+
+    class << self
+      private :get_codepoint_value
+    end
   end
 end

data/lib/unicode/types/constants.rb

@@ -1,6 +1,6 @@
 module Unicode
   module Types
-    VERSION = "1.1.1".freeze
+    VERSION = "1.1.2".freeze
     UNICODE_VERSION = "9.0.0".freeze
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
     INDEX_FILENAME = (DATA_DIRECTORY + '/types.marshal.gz').freeze

data/spec/unicode_types_spec.rb

@@ -40,6 +40,10 @@ describe Unicode::Types do
       assert_equal "Reserved", Unicode::Types.type("\u{10c50}")
       assert_equal "Reserved", Unicode::Types.type("\u{c03a6}")
     end
+
+    it "will work with invalid surrogate values" do
+      assert_equal "Surrogate", Unicode::Types.type("\xED\xA0\x80")
+    end
   end
 
   describe ".names" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-types
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.1.2
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-03-08 00:00:00.000000000 Z
+date: 2017-03-19 00:00:00.000000000 Z
 dependencies: []
 description: "[Unicode 9.0.0] Determine the basic type of codepoints (Graphic, Format,
   Control, Private-use, Surrogate, Noncharacter, Reserved)"
@@ -31,6 +31,7 @@ files:
 - lib/unicode/types/constants.rb
 - lib/unicode/types/index.rb
 - lib/unicode/types/string_ext.rb
+- spec/.unicode_types_spec.rb.swp
 - spec/unicode_types_spec.rb
 - unicode-types.gemspec
 homepage: https://github.com/janlelis/unicode-types
@@ -58,4 +59,5 @@ signing_key:
 specification_version: 4
 summary: Determine the basic type of codepoints.
 test_files:
+- spec/.unicode_types_spec.rb.swp
 - spec/unicode_types_spec.rb