unicode-confusable 1.14.0 → 1.14.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9a846fb512f666162000fa09e91c189ca180a5da30687bfddfc326bcb30160f3
-  data.tar.gz: 4aab539e7de61de215b86077222cb684442b9d17db296a60d10a4611cff0cce0
+  metadata.gz: b6bc7e62b19cb936a3bc164d08264194866173ddacaff98354b3c2fc35705229
+  data.tar.gz: f5e4951ecc316d29c7c56a3355a330f9f7c9200efeb1aa6f04ee23ec96a75a15
 SHA512:
-  metadata.gz: 1d4987cf434226234b1e15df90484e809850e822ab528fdeb01677979e6c2b0e2e4dc82466f27cf1426d8bfcacff226ed11f5bdf45176b3b21477a5505b4f18e
-  data.tar.gz: f92279a9e7ceb667e0211eb77b16cc174500a16fadbda01d1ce770379df806fdc7dae3553ed6d8e43bfdd7ed799ca3303260972f578a6dfb3124cbb0d37b933c
+  metadata.gz: ce84aa52f44f53b94c062663ab53fbbdf7429ca00c43b32098d097996b558ecf21ac999ff9872be4b02c074285d0002f4f91193124a3b8176d19e52dfbf9b104
+  data.tar.gz: 79604e8f5dfae6d5e5a1abe1bc9757071e32ee5ff51b2e6d29df0e241e5867d831d976f67f9679656c15e47576ac54b2b47e617f5d6f9102b1e3e737efb73c4c

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## CHANGELOG
 
+### 1.14.1
+
+- Use regex to remove default ignorable codepoints, speeds up confusable check,
+  closes #2
+
 ### 1.14.0
 
 - Unicode 18.0

data/Gemfile.lock

@@ -2,39 +2,29 @@ PATH
   remote: .
   specs:
     unicode-confusable (1.14.0)
+      charcutter (>= 0.1.0, < 2.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    charcutter (0.1.0)
     drb (2.2.3)
-    erb (6.0.7)
-    io-console (0.9.4)
-    irb (1.18.0)
-      pp (>= 0.6.0)
-      prism (>= 1.3.0)
-      rdoc (>= 4.0.0)
-      reline (>= 0.4.2)
-    logger (1.7.0)
+    io-console (0.6.0)
+    irb (1.8.1)
+      rdoc
+      reline (>= 0.3.8)
     minitest (6.0.6)
       drb (~> 2.0)
       prism (~> 1.5)
-    pp (0.6.4)
-      prettyprint
-    prettyprint (0.2.0)
     prism (1.9.0)
-    rake (13.4.2)
-    rbs (4.2.0)
-      logger
-      prism (>= 1.6.0)
-      tsort
-    rdoc (8.0.0)
-      erb
-      prism (>= 1.6.0)
-      rbs (>= 4.0.0)
-      tsort
-    reline (0.7.0)
+    psych (5.1.0)
+      stringio
+    rake (13.0.6)
+    rdoc (6.5.0)
+      psych (>= 4.0.0)
+    reline (0.3.8)
       io-console (~> 0.5)
-    tsort (0.2.0)
+    stringio (3.0.8)
 
 PLATFORMS
   ruby
@@ -46,4 +36,4 @@ DEPENDENCIES
   unicode-confusable!
 
 BUNDLED WITH
-  4.1.0.beta1
+   2.5.17

data/lib/unicode/confusable/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module Confusable
-    VERSION = "1.14.0"
+    VERSION = "1.14.1"
     UNICODE_VERSION = "18.0.0"
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
     INDEX_FILENAME = (DATA_DIRECTORY + "/confusable.marshal.gz").freeze

data/lib/unicode/confusable.rb

@@ -1,11 +1,10 @@
 require_relative "confusable/constants"
 
 require 'unicode_normalize/normalize'
+require 'charcutter'
 
 module Unicode
   module Confusable
-    autoload :IGNORABLE, File.expand_path('confusable/ignorable', __dir__)
-
     def self.confusable?(string1, string2)
       skeleton(string1) == skeleton(string2)
     end
@@ -13,10 +12,10 @@ module Unicode
     def self.skeleton(string)
       require_relative 'confusable/index' unless defined? ::Unicode::Confusable::INDEX
       UnicodeNormalize.normalize(
-        UnicodeNormalize.normalize(string, :nfd).each_codepoint.map{ |codepoint|
-          unless IGNORABLE.include?(codepoint)
-            INDEX[:CONFUSABLE][codepoint] || codepoint
-          end
+        Charcutter[
+          UnicodeNormalize.normalize(string, :nfd)
+        ].deny(:ignorable).each_codepoint.map{ |codepoint|
+          INDEX[:CONFUSABLE][codepoint] || codepoint
         }.flatten.compact.pack("U*"), :nfd
       )
     end

data/scripts/benchmark.rb

@@ -0,0 +1,7 @@
+require 'benchmark'
+require 'unicode/confusable'
+
+test_str = "some long string" * 1000
+Benchmark.bm do |x|
+  x.report("skeleton") { 500.times { Unicode::Confusable.skeleton(test_str) } }
+end

data/unicode-confusable.gemspec

@@ -18,4 +18,5 @@ Gem::Specification.new do |gem|
   gem.metadata      = { "rubygems_mfa_required" => "true" }
 
   gem.required_ruby_version = ">= 2.2"
+  gem.add_dependency "charcutter", ">= 0.1.0", "< 2.0"
 end

metadata

@@ -1,14 +1,34 @@
 --- !ruby/object:Gem::Specification
 name: unicode-confusable
 version: !ruby/object:Gem::Version
-  version: 1.14.0
+  version: 1.14.1
 platform: ruby
 authors:
 - Jan Lelis
 bindir: bin
 cert_chain: []
 date: 1980-01-02 00:00:00.000000000 Z
-dependencies: []
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: charcutter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2.0'
 description: "[Unicode 18.0.0] Compares two strings if they are visually confusable
   as described in Unicode® Technical Standard #39: Both strings get transformed into
   a skeleton format before comparing them. The skeleton is generated by normalizing
@@ -33,6 +53,7 @@ files:
 - lib/unicode/confusable/ignorable.rb
 - lib/unicode/confusable/index.rb
 - lib/unicode/confusable/string_ext.rb
+- scripts/benchmark.rb
 - sig/unicode-confusable.rbs
 - spec/unicode_confusable_spec.rb
 - unicode-confusable.gemspec
@@ -55,7 +76,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.20
+rubygems_version: 4.0.10
 specification_version: 4
 summary: Detect characters that look visually similar.
 test_files: []